《IMT：2025具身智能（Embodied AI）概念、核心要素及未來進展：趨勢與挑戰研究報告（英文版）（25頁）.pdf》由會員分享，可在線閱讀，更多相關《IMT：2025具身智能（Embodied AI）概念、核心要素及未來進展：趨勢與挑戰研究報告（英文版）（25頁）.pdf（25頁珍藏版）》請在三個皮匠報告上搜索。

1、Embodied Artificial Intelligence:Trends and Challenges Rolf Pfeifer and Fumiya Iida Artificial Intelligence Laboratory,Department of Informatics,University of Zurich Andreasstrasse 15,CH-8050 Zurich,Switzerland pfeifer,iidaifi.unizh.ch Abstract.The field of Artificial Intelligence,which started roug

2、hly half a cen-tury ago,has a turbulent history.In the 1980s there has been a major paradigm shift towards embodiment.While embodied artificial intelligence is still highly diverse,changing,and far from“theoretically stable”,a certain consensus about the important issues and methods has been achieve

3、d or is rapidly emerging.In this non-technical paper we briefly characterize the field,summarize its achievements,and identify important issues for future research.One of the fun-damental unresolved problems has been and still is how thinking emerges from an embodied system.Provocatively speaking,th

4、e central issue could be cap-tured by the question“How does walking relate to thinking?”1.Introduction This conference and this paper are about embodied artificial intelligence.If you search for“embodied artificial intelligence”or“embodied cognition”on the Internet using your favorite search engine,

5、you will find a radically smaller number of entries than if you search for“artificial intelligence”or“cognition”.Trying to answer this question of why this might be the case,reveals a lot about the structure of this research field and uncovering its organization is one of the goals of this paper.Ove

6、r the last 50 years Artificial Intelligence(AI)has changed dramatically from a computational discipline into a highly transdisciplinary one that incorporates many different areas.Embodied AI,because of its very nature of being about embodied systems in the real physical and social world,must deal wi

7、th many issues that are entirely alien to a computational perspective:as we will discuss later,physical organ-isms in the real world,whether biological or artificial,are highly complex and their investigation requires the cooperation of many different areas.The implications of this change in perspec

8、tive are far-reaching and can hardly be overestimated.In this paper,we will try to outline some of them.With the fundamental paradigm shift from a computational to an embodied per-spective,the kinds of research topics,the theoretical and engineering issues,and the disciplines involved have undergone

9、 dramatic changes,or stated differently,the“landscape”has been completely transformed.In the first part of the paper we try to characterize these changes.In the second part,we will identify the grand challenges in the field and discuss how far researchers have come towards achieving them.Given the e

10、normous diversity,as discussed in the first part,this will necessarily be abstract,somewhat selective and reflect the authors personal opinion,but we do hope that many people will agree with the our description of how the field is now structured.We conclude with some general comments on the future o

11、f the field and applications.2.The“landscape”The landscape of artificial intelligence has always been rugged but it has become even more so over the last two decades.When the field started initially,roughly half a century ago,intelligence was essentially viewed as a computational process.Research to

12、pics included abstract problem solving and reasoning,knowledge representation,theorem proving,formal games like chess,search techniques,and written natural language,topics normal associated with higher level intelligence.It should be mentioned however,that in the 60s there was a considerable amount

13、of research on robotics in artificial intelligence at MIT,SRI,and CMU.But later on the artificial intelligence research community has not paid much attention to this line of work.Successes of the classical approach By the mid 1980s,the classical,computational or cognitivistic approach,had grown into

14、 a large discipline with many facets and has brought forward many successes in terms of computer and engineering applications.If you start your favorite search en-gine on the Internet,you are,among many others,employing clever machine learning algorithms.Text processing system utilizes matching algo

15、rithms,or algorithms that try to infer users intentions from the context of what have been done earlier.Controls for appliances using fuzzy logic,embedded systems(as they are employed in fuel injec-tion systems,breaking systems,air conditioners,etc.),control systems for elevators,and trains,natural

16、language interfaces to directory information systems,translation support software,etc.,are also among the successes of the classical approach.More recently,data mining systems have been developed that heavily rely on machine learn-ing techniques,and chess programs have been realized that beat 99.99

17、percent of all humans on earth,a considerable achievement indeed!The development of these kinds of systems,although they have their origin in artificial intelligence,have now become indistinguishable from applied informatics in general:they have become a firm con-stituent of any computer science dep

18、artment.Problems of the classical approach However,the original intention of artificial intelligence was not only to develop clever algorithms,but also to understand natural forms of intelligence that have as argued here more to do with the interaction with the real world.Alas,as is now generally ag

19、reed,the classical approach has not contributed significantly to our understanding of,for example,perception,locomotion,manipulation,everyday speech and conversation,social interaction in general,common sense,emotion,and so on.Classical approaches to computer vision,for example,have been successful

20、in fac-tory environments,where there are constant lighting conditions,the geometry of the situation is precisely known(i.e.the camera is always in the same place,the objects appear on the conveyer belt always in the same position),and the types of potential objects are known and can therefore be mod

21、eled.However,when these conditions do not hold and in the real world,they are never given,i.e.the distance of objects from the eyes always changes,which is one of the many consequences of moving around,and lighting conditions and orientation also vary continuously these algorithms can no longer be u

22、sed.Moreover,objects are often entirely or partially occluded,they move(e.g.cars,people),and they appear against very different and changing back-grounds.Artificial vision systems with capacities similar to human or animal vision,are far from being realized artificially.A further example where the c

23、lassical approach could not provide adequate an-swers is object manipulation.Indeed,animals and humans are enormously skilled at manipulating objects;even very simple animals like insects are masters at manipula-tion.Or watch a dog chew on a bone,how he controls it with his paws,mouth and tongue:unb

24、elievable.Although there are specialized machines for virtually any kind of manipulation(driving a screw,picking up objects for packaging in production lines,lifting heavy objects in construction sites),the general purpose manipulation abilities of natural systems are to date unparalleled.Locomotion

25、 is another case in point.Animals and humans move with an uncanny flexibility and elegance.We can walk with a bag in one hand,an arm around a friend,up and down the stairs,while looking around,something none of the existing robots can do.And building a running robot is still considered one of the gr

26、eat challenges.In the classical approach,common sense has been treated at the level of“semantic content”and has been taken to include knowledge such as“cars cannot become preg-nant”,“objects(normally)dont fly”,“people have biological needs”(they get hungry and thirsty),etc.Building systems with this

27、 type of common-sense knowledge has been the goal of many classical natural language and problem solving systems like CYC(e.g.Lenat et al.,1986).But there is an important additional aspect of common-sense knowledge,which is to do with bodily sensations and feelings,and this aspect has its origin lar

28、gely in our embodiment.Take,for example,the word“drinking”and freely associate what comes to mind.Perhaps being thirsty,liquid,cool drink,beer,hot sunshine,the feeling of wetness in your mouth,on the lips,and on your tongue when you are drinking,and the feeling of thirst disappearing as you drink,et

29、c.It is this kind of common sense knowledge and common experience that everyone shares and that forms the basis of robust natural language communication,and it is firmly grounded in our own specific embodiment.And to our knowledge,there are currently no artificial systems,capable of dealing with thi

30、s kind of knowledge in a flexible and adaptive way.The last point that we would like to mention here concerns speech systems.While in restricted areas,speech systems can be used,e.g.as an interface to directory infor-mation systems,or systems where single word commands can be used(e.g.for robot cont

31、rol,or name databases for mobile phones),in most areas they have only been used with limited success.Speech to text systems have to be tuned to the speakers voice,and because of the high error rate,typically a lot of post-editing needs to be done on the text produced by the software.This may be one

32、of the reasons why speech systems have not really taken off so far,even though the idea of not having to type any more,of producing text rapidly,is highly appealing.Although some of the systems may have a relatively impressive performance,the fact of the matter remains that there are to date no gene

33、ral purpose natural language systems whose performance even remotely resembles the one of humans in a free format everyday conversation.Finally,it is interesting to note,It is interesting to note that these more natural kinds of activities(perception,manipulation,speech)are all activities that have,

34、in some very essential ways,to do with complex,“high bandwidth”interaction with the real world.We will come back to this point later on.Embodied Artificial Intelligence These failures,largely due to the lack of rich system-environment interaction,have lead some researchers to pursue a different aven

35、ue,the one of embodiment.With this change of orientation,the nature of the research questions also began to change.Rod-ney Brooks,one of the first promoters of embodied intelligence(e.g.Brooks,1991),started studying insect-like locomotion,building,for example,the six-legged walking robot“Ghengis”.So

36、,walking and locomotion in general became important research areas,topics typically associated with low-level sensory-motor intelligence.This is,of course,a fundamental change from studying chess,theorem proving,and abstract problem solving,and it is far from obvious how the two relate to one anothe

37、r,an issue that we will elaborate in detail later.Other subjects that people started investigating have been orientation behavior(i.e.finding ones way in only partially known and changing environments),path-finding,and elementary behaviors such as wall follow-ing,and obstacle avoidance.The perspecti

38、ve of embodiment requires working with real world physical systems,i.e.robots.A crucial aspect of embodiment is that it requires working with real world physical systems,i.e.robots.Computers and robots are an entirely different ball game:computers are neat and clean,they have clearly defined inputs

39、and outputs,and any-body can use them,can program them,and can perform simulations.Computers also have for the better part only very limited types of interaction with the outside world:input is via keyboard or mouse click,and output is via display panel.In other words,the“bandwidth”of communication

40、with the environment is extremely low.Also com-puters follow clearly defined“input processing”output scheme that has,by the way,shaped the we think about intelligent systems and has become the guiding metaphor of the classical cognitivistic approach.Robots,by contrast,have a much wider sensory-motor

41、 repertoire that enables a tight coupling with the outside world and the computer metaphor of input-processing-output can no longer be directly applied.Building robots requires engineering expertise,which is typically not present in computer science laboratories,let alone psychology departments.So,w

42、ith the advent of embodiment the nature of the field,artificial intelligence,changed dramatically.While in the traditional approach,because of the interest in high-level intelligence,the relation to psychology,in particular cognitive psychology was very prominent,the attention,at least in the early

43、days of the approach of embodied intelligence,shifted more towards non-human biological systems,such as insects,but other kinds of animals as well.Also,at this point,the meaning of the term“artificial intelligence”started to change,or rather started to adopt two meanings.One meaning stands for GOFAI

44、(Good Old-Fashioned Artificial Intelligence),the traditional algorithmic approach.The other one designates the embodied approach,a paradigm that employs the synthetic methodol-ogy which has three goals:(1)understanding biological systems,(2)abstracting gen-eral principles of intelligent behavior,and

45、(3)the application of this knowledge to build artificial systems such as robots or intelligent devices in general.As a result,the modern,embodied approach started to move out of computer science laboratories more into robotics and engineering or biology labs.It is also of interest to look at the rol

46、e of neuroscience in this context.In the 1970s and early 1980s,as researchers in artificial intelligence started to realize the problems with the traditional symbol processing approach,the field of artificial neural networks,an area that had been around since the 1950s,started to take off new hope f

47、or AI researchers who had been struggling with the fundamental problems of the symbol processing paradigm.Inspiration was drawn from the brain,but only at a very abstract level.In the embodied approach,there was a renewed and much stronger interest in neuroscience because researchers realized that n

48、atural neural systems are extremely robust and efficient at controlling the interaction with the real world.As mentioned above,animals can move and manipulate objects with great ease,and they are con-trolled by natural neural networks.In addition,they can move very elegantly,with great speed and wit

49、h little energy consumption.These impressive kinds of behaviors can only be achieved if the dynamical properties of the neural networks are exploited.This is quite in contrast to the traditional AI approach where mostly static feedforward networks were employed.Diversification So,in terms of researc

50、h disciplines participating in the AI adventure,we see that in the classical approach it was mainly computer science,psychology,philosophy,and lin-guistics,whereas in the embodied approach,it is computer science and philosophy as before,but also engineering,robotics,biology,and neuroscience(with a f

51、ocus on dynamics),whereas psychology and linguistics have lost their role as core disciplines.So we see somewhat of a shift from high-level(psychology,linguistics)to more low-level sensory-motor processes,with the neurosciences covering both aspects,sensory-motor and cognitive levels.With this shift

52、,the terms used for describing the research area shifted:researchers working in the embodied approach no longer referred to themselves as working in artificial intelligence but more in robotics,engineering of adaptive systems,artificial life,adaptive locomotion,bio-inspired systems,and neuro-informa

53、tics.But more than that,not only have researchers in artificial intelligence moved into neighboring fields,but researchers that have their origins in these other fields started in natural ways to contribute to artificial intelligence.This way,the field on the one hand significantly expanded,but on t

54、he other,its boundaries became even more fuzzy and ill-defined than before.These considerations also provide a partial answer to the question of why we dont get many entries when we type“embodied intelligence”or“embodied artificial intel-ligence”into one of the search engines:Because the communities

55、 started to split and researchers in embodied intelligence started attending other kinds of conferences,e.g.“Intelligent Autonomous Systems,IAS”,“Simulation of Adaptive Behavior From Animals to Animats,SAB”,“International Conference on Intelligent Robotics and Systems,IROS”,“Adaptive Motion in Anima

56、ls and Machines,AMAM”,“European Conference on Artificial Life,ECAL”,“Artificial Life Conference,ALIFE”,“Artifi-cial Life and Robotics,AROB”,“Evolutionary Robotics,ER”,or the various IEEE conferences(International Society of Electrical&Electronics Engineering),etc.An-ecdotally speaking,I(Rolf Pfeifer

57、)remember that initially,in the early 90s,when I tried to convince people at AI conferences such as International Joint Conference on Artificial Intelligence(IJCAI),the European Conference on Artificial Intelligence,ECAI,or the German annual AI Conference,that embodiment is not only interesting but

58、essential to understanding intelligence,I mostly got very negative reactions and no real discussion was possible.So,together with many colleagues we turned to other conferences where people were more receptive to these new ideas.More recently,perhaps because of the stagnation in the field of classic

59、al AI in terms of tackling the big problems about the nature of intelligence,there has been a growing interest in embodiment and now AI conferences,at least some of them,have started workshops on issues in embodiment.But by and large,the two communities,the classical and the embodied one,are pretty

60、much separate,and will probably remain so for a while.Biorobotics There are a number of additional interesting developments worth mentioning here.One is,in the field of embodiment,a renewed interest in high-level cognition.Rodney Brooks,at the time,had forcefully argued that getting insects to walk

61、from scratch took evolution much longer than getting from insects to humans.This implies that creating insects was the really hard problem and after that,moving towards human level intelligence was relatively easy.Thus,so his conclusion,one should first work on insects rather than humans,one should

62、do“biorobotics”.Many people started doing biorobotics and began cooperations with biology laboratories.An excellent example is the work by Dimitrios Lambrinos at the Artificial Intelligence Laboratory in Zurich,who started to cooperate with the world champion in ant navigation,Ruediger Wehner of the

63、 University of Zurich.Jointly,they built a series of robots,the Sahabot-Series that mimic long-and short-term navigation behavior of the desert ant Cataglyphis(e.g.Lambrinos et al.,2000).Rodney Brooks cooperated with the famous biologist Holk Cruse of the University of Bielefeld in Germany,who had b

64、een studying insect walking for many years and who had found that there is no central control for leg coordination in walking in ants.Brooks implemented Cruses ideas on an MIT ant-like robot and termed the controller“cru(i)se”control,in honor of the designer,Holk Cruse.There are many examples of suc

65、h cooperation which have all been very productive(for an excellent collection of which have all been very productive(for an excellent collection of papers on biorobot-ics,see(Webb and Consi,2000).Developmental robotics However,after a few years of working on insect like behavior,Brooks started chang

66、-ing research topics.He argued that we have to“think big”and should work towards human level intelligence,and the project“Cog”for the development of a humanoid robot,was born(Brooks and Stein,1993).He neatly mapped out the necessary steps and stages for achieving human-level intelligence,but due to

67、many problems,after less than 10 years,changed topics again.But the Cog project generated a lot of ex-citement and many researchers were attracted by the idea of moving towards human-level intelligence,which had also been the target of classical artificial intelligence,and the field of developmental

68、 robotics emerged.The term developmental robotics desig-nates the attempt to model aspects of human or primate development using real robots.Its pertinent conferences come under many labels,“Emergence and Development of Embodied Cognition,EDEC”,“Epigenetic robotics”,“Development of Embodied Cognitio

69、n,DECO”,“International Conference on Development and Learning”,etc.This was,of course,a happy turn for those who might have been slightly sad or disap-pointed by the direction the field took insects simply are not as sexy as humans!And human intelligence happens to be the most fascinating type of in

70、telligence that we know.But once again,this strand of conferences is separate from the traditional ones in artificial intelligence,and they do not contain the term“embodied intelligence”.Ubiquitous computing Another line of development that should be introduced here is the one of ubiquitous computin

71、g(Weiser 1993).Computer science has undergone dramatic changes as well.Computing as such,software engineering,the development of algorithms,operating systems,the virtual machine,etc.are topics that we now understand relatively well and it is not clear whether there will be big innovations in these a

72、reas in the near fu-ture.Rather,it seems that the new challenges are seen in the interaction with the real world.Initially,the field was characterized by the idea of putting sensors everywhere,into rooms(mostly cameras,motion detectors),floors(e.g.pressure sensors to detect the position of individua

73、ls)objects such as cars,chairs,beds,but also cups,or any kind of devices such as mobile telephones,clothes(e.g.t-shirts,shoes)to measure physiological data of the individual wearing them for sports or medical reasons(the list is in fact endless).More recently,ubiquitous computing has also been inves

74、tigat-ing actuation,i.e.ways in which systems can influence their environments:control systems for buildings for temperature,humidity,windows,and blinds;cars that auto-matically apply their breaks when the distance to the car in front gets too small,or in the medical domain systems that monitor phys

75、iological variables(pulse rate,skin resistance,level of dehydration)and send a message to a physician if necessary.The field of ubiquitous computing is closely related to user interfaces or generally to hu-man-machine interaction.Even though user interfaces have always been an important topic in com

76、puters,the problem,in contrast to robotics,has been the low“bandwidth of communication”,as pointed out earlier.In order to increase this“bandwidth”,there has been a lot of work on speech,spoken language,to interact with computers,but these efforts,for various reasons,have only been met with very lim

77、ited success(see our discussion above).Just recently have there been projects for developing more interesting and richer interfaces using,for example,touch,and to some extent vision.There is also work on smell but that has although very exciting not yet advanced significantly.The research on wearabl

78、es should be pointed out here as well.What is interesting about these“move-ments”,human-machine interface,wearables,ubiquitous computing,is that now virtu-ally all computer science departments start moving into the real world.They are not doing robotics per se,but many have started hiring engineers

79、and establishing me-chanical and electronics workshops where they can build hardware,because now real-world devices with certain sensory-motor abilities need to be constructed,devices that could be called“robotic devices”.So far as we can tell,there has been little theory development,but there is a

80、lot of creative experimentation going on.We feel that the set of design principles that we have developed for embodied systems will be ex-tremely useful in designing such systems(e.g.Pfeifer and Scheier,1999).For example,the principle of sensory-motor coordination which states that through the activ

81、e interaction with the environment,patterns of sensory stimulation are induced that are correlated across sensory modalities,is an important guiding principle,but has,to date,not been applied.We might also say that computer science has now come full circle,from disembodied algorithm to embodied real

82、-world computing,or rather real-world interaction,with embodied artificial intelligence as the fore-runner.Artificial life and multi-agent systems Another interesting line of development has its origins in the field of Artificial Life,also called Alife for short.The classical perspective of artifici

83、al intelligence had a strong focus on the individual,just as psychology,and psychology was the major discipline with which artificial intelligence researchers cooperated at the time.ALife research which has strong roots in biology rather than psychology has been focus-ing on emergence of behavior in

84、 large populations of agents,in other words it is inter-ested in what some call multi-agent systems.We deliberately say“that some call multi-agent systems”because normally,in Alife research,the term complex dynamical system is preferred,as it encompasses also physical systems where the individual co

85、mponents only have limited“agent character”,e.g.the molecules in the famous Bnard experiment.An agent typically has certain sensory-motor abilities,i.e.it can perceive aspects of the environment,and depending on this information and its own state,performs a particular behavior.Molecules,rocks,or oth

86、er“dead”physical ob-jects do not have this ability.One point of interest has been the emergence of complex global behavior from simple rules and local interactions.(Langton,1995)Modular robotics,a research area that has drawn inspiration from artificial life re-search,also relates to multi-agent sys

87、tems,where the individual agents are robotic modules capable of configuring into different morphologies(see the volume by Hara and Pfeifer(2003)for examples of modular robotic systems).One of the goals of this research is to design systems capable of self-repair,a property that all living systems ha

88、ve to some extent.Self-assembly and self-reconfiguration are fascinating topics that will become increasingly important as systems have to operate over extended periods of time in remote,hostile environments.The seminal work by Murata and his co-workers(Murata et al.,2004)demonstrates,how self-recon

89、figuration can be achieved not only in simulation but with real robotic systems.It should be mentioned,however,that to date,much of the research on self-repair and self-reconfiguration is tightly controlled,rather than being emergent from local interactions.Evolutionary systems are another example o

90、f“population thinking”,where the adaptivity of entire populations is studied rather than that of individuals.Because of its close relation to biology,economics has also taken inspiration from multi-agent systems and created the discipline of agent-based economics(e.g.Epstein and Axtell,1996).Work on

91、 self-organization in insect societies,for example,by Jean-Louis Deneubourg of the Universit libre de Bruxelles,has attracted many researchers from different fields:“ant intelligence”was one of their slogans(e.g.Bonabeau et al.,1999).Interestingly,the term multi-agent systems has quickly been adopte

92、d by researchers in classical artificial intelligence.However,rather than looking for emergence,they endowed their individual agents with the same types of centralized control that they used for individuals(e.g.Ferber,1999).As a consequence they could not study emer-gent phenomena,and a look into th

93、e journal“Autonomous Agents and Multi-Agent Systems”shows that the research under the heading“multi-agent systems”typically has different goals and does not focus on emergence.For the better part,the research is geared towards internet applications using software agents.In robotics there has also be

94、en an interest in multi-agent systems.There the prob-lem has been that often only relatively few robots have been available so that it has proved difficult to investigate emergence phenomena in populations.This is illustrated by the rapidly growing“Robocup”or robot soccer community.Initially the rob

95、ots,for the better part,were programmed directly by the designers in order to win the game.More recently there has been growing interest and significant results in producing scientifically compelling and elegant solutions by incorporating ideas of emergence,but this still remains a big challenge.One

96、 of the important research problems and limitations so far has been the achievement of higher levels of intelligence by the multi-agent community:typically,as in the work of ethologist and Alife researcher Charlotte Hemelrijk,the interest is in emergent hierarchies,group size formation,or migration

97、patterns.Thinking,reasoning,or language,have typically not been topics of interest here.An exception is the work of the group of researchers interested in evolution of communication and evolution of language.An excellent example of this type of research that tries to combine popula-tion thinking or

98、multi-agent systems with higher-level processes such as language is the“Talking Heads”experiment by Luc Steels(e.g.Steels,2001,2003).In an ingen-ious experiment he could demonstrate how,for example,a common vocabulary emerges through interaction of agents with their environment and with other agents

99、 via a language game.He has also been working on emergence of syntax,but in these experiments many assumptions have to be made to bootstrap the process.In this re-search strand,many insights have been gained into how communication systems estab-lish themselves and how something like grammar could em

100、erge.Although fascinating and highly promising,the jury is still out on whether this approach will indeed lead to something resembling human natural language.Because of the fundamental differences in goals,the distributed agents community artificial life style,and the artificial intelligence and rob

101、otics community,individual style,have to date remained largely separate.Summary In summary,we can see that the landscape has changed significantly:while originally artificial intelligence was clearly a computational discipline,dominated by computer science,cognitive psychology,linguistics,and philos

102、ophy,it has turned into a multid-isciplinary field requiring the cooperation and talents of many other fields such as biology,neuroscience,engineering(electronic and mechanical),robotics,biomechan-ics,material sciences,and dynamical systems.And this exciting new transdisciplinary community is now ca

103、lled“embodied artificial intelligence.”While for some time,psychology and linguistics have not been at center stage,with the rise of developmen-tal robotics,there has been renewed interest in these disciplines.The ultimate quest to understand and build systems capable of high-level thinking and natu

104、ral language,and ultimately consciousness,has remained unchanged.Only the path on how to get there is fundamentally different.Although the emergence of ideas of embodiment can be traced back to pre-Socratic thinking and can be found throughout the history of phi-losophy,the recent developments in ar

105、tificial intelligence that enable not only the analysis but also the construction of embodied systems,are supplying ample novel intellectual fodder for philosophers.As we will show later,these developments sig-nificantly change the image we have of ourselves and our society.In spite of the multiface

106、ted nature,there is a unifying principle and that is the actual agent to be designed in the context of the synthetic methodology,be it physical in the real world,or simulated in a realistic physics-based simulation.Such agents have a highly integrating function by bringing together results from all

107、these different areas,and allowing concrete testing in an objective way.Moreover,they serve as excellent platforms for transdisciplinary research and communication.3.State-of-the-art and challenges Given the diversity of embodied artificial intelligence and the ruggedness of the land-scape it will b

108、e next to impossible to come up with a set of challenges and a charac-terization of the state-of-the-art that everybody will agree on.In characterizing the state-of-the-art we will start from the overall challenges that we will organize according to the three time scales(“here and now”,ontogenetic,p

109、hylogenetic)(see Table 1).These time scales,although clearly identifiable,have important interactions,a point that we will also take into account.Moreover,we will divide our discussion into two parts,theoretical/conceptual,and engineering.In iden-tifying the challenges and research issues we tried t

110、o do a comprehensive survey of the literature and we,in particular,consulted the papers in this volume in order to assess the important trends.By the very nature of this endeavor of identifying challenges,this will be rather subjective and mirrors the personal research interests of the authors.Table

111、 1.Time scales for understanding and designing agents time scale designer commitments state-oriented”here and now”“hand design”learning and development”ontogenetic”initial conditions;learning and developmental processes evolutionary”phylogenetic”evolutionary algorithms;morphogenetic processes Howeve

112、r,we do believe that they reflect,one way or other,the important directions in the field.Nevertheless,we do not expect everyone to agree.We propose the following“grand challenges”for future research,theoretical under-standing of behavior;achieving higher level intelligence;automated design methods(a

113、rtificial evolution and morphogenesis),and“moving into the real world”.Theoretical understanding of behavior By theoretical understanding of behavior we mean an understanding of how particular behaviors in the real world can be achieved in artificial agents.This may also shed light on how particular

114、 behaviors that we observe in nature come about,which is also one of the goals of artificial intelligence research.This goal is mainly to do with the“here and now”time scale,i.e.with the question of the mechanisms underlying behav-ior.Although a vast body of knowledge has been accumulated this still

115、 remains one of the big conundrums.As outlined in the previous section,many research areas and a host of studies have contributed to this understanding.However,we still dont have,for example,general purpose perceptual systems human or primate vision is still unparalleled,and we still have an insuffi

116、cient understanding of motor control,e.g.how we can achieve rapid legged locomotion.For example,there has been a lot of progress in research on humanoid walking robots,especially in Japan(e.g.Sonys QRIO,Hondas Asimo,Kawadas HRP,the University of Tokyos H-7,to mention but a few).However,al-though mos

117、t of these robots show impressive performance,they still walk slower than humans,their walking style looks somewhat unnatural,and research on running is still in its infancy.One of the issues,and this is one of the challenges,is the fact that most of the re-search has been focused on control,which h

118、as been,and still is,the standard perspec-tive in robotics.Recent work in the area of biomechanics seems to suggest that mate-rial and morphological properties,i.e.the intrinsic dynamical properties of the muscle-tendon systems and the specific shapes and material properties of the limbs and the bod

119、y play an essential role in locomotion(e.g.Blickhan et al.,2003;Kubow and Full,1999),but also in behavior in general,e.g.object manipulation,posture control,ges-turing,etc.These ideas are captured in the theoretical principle of“ecological bal-ance”,as outlined by Pfeifer et al.,(in press),Hara and

120、Pfeifer(2000),Ishiguro et al.,(2003)and earlier in Pfeifer and Scheier(1999),which states that there is a balance or task distribution between morphology,materials,control,and interaction with the environment:Some tasks,e.g.the elastic movement of the knee joint when the foot hits the ground in runn

121、ing,can be taken over by the elastic materials,and their trajectories do not need to be explicitly controlled.By morphology we mean the form and structure of an organism and its parts,including the physical nature of the sensors and their distribution.We discuss materials separately,as they play an

122、extraordinary role in agent design.There is another aspect of ecological balance,namely that there should be a match in the complexity of the sensory,motor and(neural)control systems.Many robotic systems are“unbalanced”in the sense that they are built of hard materials and electri-cal motors,and thu

123、s the control requires an enormous amount of computation.Robot vision systems are also often unbalanced as they are largely algorithmic and do not exploit morphological properties.For example,natural systems dont have cameras but retinas that perform some kind of morphological computation by their n

124、on-homogeneous arrangement of the light-sensitive cells.Moreover,generally speaking retinas perform an enormous amount of computation right at the periphery so that the signals that are passed on,are already highly processed.Artificial retinas have been around since the mid-80s(e.g.Mead,1989),but th

125、ey are still not widely used in the field.Moreover,vision or perception in general is not a matter of mapping inputs to internal representation,but of sensory-motor coordination,requiring a complex motor system as well.While initially it might seem that taking the motor system into account as well i

126、n perception would make the problem harder,when viewed in an ecological context,many problems might in fact be simplified,as demonstrated by the field of active vision or animate vision(e.g.Ballard,1991).In animate vision,the ability of the agent(the vision system)to move is exploited to make the vi

127、sion task easier.The development of vision systems,which includes the development of retinas,remains a big challenge.And these vision systems must not be developed in isolation,but in the context of multi-modal systems(see also below,achieving higher level intelligence).Recently,it has been demonstr

128、ated that by exploiting the intrinsic dynamics of an agent,the complexity of the control system can be substantially reduced(e.g.Collins et al.,2001;Iida and Pfeifer,2004a,b;Wisse and Frankenhuyzen,2003;Yamamoto and Kuniyoshi,2001),as articulated in the principle of ecological balance.Thus,in order

129、to achieve rapid locomotion,but also motion in general,material properties must be exploited.In order to achieve real progress,artificial muscles,tendons,and flexible joints must be developed which represents a big engineering challenge.Big strides in this direction have been made by Rudolf Bannasch

130、 and his colleagues(Boblan et al.,2004).Behavior in general requires sensory-motor coordination that again,in natural sys-tems,is achieved by a subtle interplay of morphology(of the sensory and motor sys-tems),materials,control,and interaction with the environment.While the design prin-ciples of Pfe

131、ifer et al.(in press)do provide intuitions,they are only qualitative in nature.What is needed now,and this is a big challenge,is a more quantitative ap-proach.While it is relatively straightforward to quantify sensory data and to estimate the amount of computation in a controller,little research has

132、 been done on quantifying morphology and materials in computational terms.Finding a common currency which is required for a theoretical and quantitative understanding,is an important research issue as it will connect the computational effort(or control)with the contributions of physical,i.e.non-comp

133、utational aspects of the system(for quantitative research in the field of sensory-motor coordination that will be relevant for these issues using meth-ods from information theory and statistics,see,e.g.Sporns and Pegors,2004;te Boek-horst et al.,2003)(Lungarella and Pfeifer,2001).Lichtensteiger(2004

134、),for example,demonstrated how the pre-processing function performed by the morphological arrangement of facets in an insect(or robot)eye,can be measured quantitatively and how a particular arrangement influences learning speed.In general,there is a definite need for more quantitative methods in ord

135、er to turn the field into a true scientific discipline.Gaussier et al.,for example(Gaussier,et al.,2004)developed a formalism in the form of an algebra for cognitive processes based on the idea of perception-action coupling in autonomous agents.They apply the for-malism to demonstrate how facial exp

136、ressions can be learned and that there is no need to postulate innate mechanisms.Other examples of quantification will be discussed in the section on development.While we must move towards more quantative methods,there is a certain danger involved:Because of the limitations of formal description,the

137、re tends to be a focus on isolated,well-formalizable areas,as we know it from the field of classical robotics and control theory.For example,there is a lot of formal work on path planning and inverse kinematics which lends itself more readily to a formal treatment than,for example,locomotion of comp

138、lex systems involving materials with different kinds of properties and many degrees of freedom.Formalizing the latter represents a big challenge.From an engineering perspective,in addition to the materials of the motor system,there are challenges concerning the various sensory modalities:haptics for

139、 example,is a very fundamental and rich modality in natural organisms.But the technology is,compared to natural systems,very underdeveloped:low resolution,hard,non-bendable materials,pressure only.However,there are exciting developments towards overcoming these limitations,as illustrated by the soft

140、 robotic fingertip with randomly distributed sensors for measuring slip and texture by Hosoda(2004).The development of skin-sensors by which the entire body can be covered represents a big challenge,not so much for artificial intelligence,but for the material sciences,similar to the issue of artific

141、ial muscles.At the moment,this is a significant bottleneck:better materials would almost certainly entail a quantum leap in artificial intelligence.Achieving higher level intelligence The term“higher level”intelligence is used to designate behavior that is not purely sensory-motor,such as problem so

142、lving and reasoning,or generally thinking,natural language,emotion,and consciousness.Note that there is a frame-of-reference issue here:when we say“not purely sensory-motor”it is not really clear whether we are referring to behavior or mechanism.Inspection of the mechanisms underlying so-called non-

143、sensory motor or cognitive behavior yields that almost universally the sensory and motor systems will be involved since in natural systems brains are intrin-sically intertwined with embodiment and cannot clearly separated(e.g.Thelen and Smith,1994).While it is possible in principle to“hand design”ag

144、ents(see Table 1)endowed with higher level intelligence,all efforts to date have been met with only very limited success.One of the big unresolved issues to date is the one of symbol processing:How is it possible that humans have the capability for symbol processing?More precisely we would have to a

145、sk how it is possible that humans can behave in ways that it makes sense to describe their behavior as“symbolic”,irrespective of the underlying mechanisms,which might involve explicit symbol processing or not.The question is very broad and of general importance:it is about how organisms can ac-quire

146、 meaning,how they can learn about the real world,and how they can combine what they have learned to generate symbolic behavior,a problem known as the“sym-bol grounding problem.”.There is general agreement that learning will make substan-tial contributions towards a solution.However,learning alone wi

147、ll not suffice em-bodiment must be taken into account as well.Drawing inspiration from nature,a consensus has emerged that a productive ap-proach might be to mimic at some level of abstraction a developmental process.De-velopment,in contrast to learning,also incorporates growth and maturation of the

148、 organism.There is a vast literature on machine learning that might be potentially rele-vant here for solving the symbol grounding problem,but also for development in general.The book“Re-thinking innateness”has been viewed as a kind of landmark publication,employing a connectionist modeling approach

149、(Elman et al.,1996).While a lot of ideas can be taken from this book,the approach does not deal with embodi-ment.This is the case with most of the machine learning literature.As indicated earlier,the impact of taking embodiment into account can hardly be over-estimated.For example,there is the big c

150、hallenge of general perception in the real world:How come we can recognize objects or faces under large variations of distance,orientation,partial occlusion,and lighting conditions?Again,many people seem to agree that a developmental approach might be useful.One of the basic issues is the fact that

151、agents in the real world do not receive neatly structured input vectors as is assumed in most simulation studies but there is a continuously changing stream of sensory stimulation which strongly depends on the agents current behavior.One way to deal with this issue is by exploiting the embodied inte

152、raction with the real world:Through the physical interaction with the environment,the agent induces or generates sensory stimulation(e.g.Pfeifer and Scheier,1999).The thus generated stimulation will typically be more structured,and will contain correlations within and between sensory channels that g

153、reatly facilitate the problem of focusing on the rele-vant stimulation and is in fact the enabler for learning(Lungarella and Pfeifer,2001;Sporns and Pegors,2004).A very simple example is grasping and centering which stabilizes and normalizes the visual stimulation of an object on the retina,and at

154、the same time produces correlated haptic and proprioceptive stimulation.This issue is covered in the principle of sensory-motor coordination which may be an important constituent in bootstrapping perception.Achieving general purpose,flexible and adap-tive perception in the real world is certainly on

155、e of the very grand challenges.This is one of the big research topics in the field of“developmental robotics”or“cognitive robotics”that has recently picked up a lot of momentum.It has been suggested that the principle of sensory-motor coordination should be called more generally the prin-ciple of in

156、formation self-structuring because the agent himself(or itself)interacts in particular ways with the environment to generate proper sensory stimulation.Now the goal of this new field is not only perception,but development in general.An important direction is and has been imitation learning that seem

157、s to play a key role.This research has been inspired by the discovery of mirror neurons in the 1990s(e.g.Dipellegrino et al.,1992;Fadiga et al.,2000;Gallese et al.,1996)which demonstrated that motor and sensory systems are very closely intertwined in the brain.Designing and building a system capable

158、 of a wide range of imitation behaviors is certainly an-other one of the big challenges.Important first steps have demonstrated the in-principle feasibility of this approach(e.g.Kuniyoshi et al.,2004;Jansen et al.,2004;Yoshikawa et al.,2004).Robots will no longer have to be programmed,but the skills

159、 they should acquire can simply be demonstrated.While this ability will certainly im-prove the sensory-motor behavior of agents,the hope is that it will also contribute to the development of social behavior,and language and communication abilities.For a review of the research in developmental roboti

160、cs,see Lungarella et al.(2004).One of the challenges for the research on imitation is that direct copying is not possible,be-cause the caregiver has a morphology that considerably differs from the one of the baby,i.e.certain perceptual generalizations will have to be made by the baby in order to int

161、erpret the caregivers action.Over the last few years,there has been increasing consensus that joint attention plays a key role in learning and social development,a topic now being studied in developmental robotics(e.g.Nagai et al.,2003).Let us briefly discuss a few additional grand challenges in dev

162、elopment,acquisition of natural language,consciousness,emotion,and motivation.First steps toward acqui-sition of natural language,acquisition of a joint vocabulary,has been demonstrated in Luc Steelss ingenious“Talking Heads”experiment.Steels also did some preliminary work on acquisition of syntax,b

163、ut there is a long way to the final goal of complete natural language development.Consciousness has always been considered as something like the ultimate criterion for true intelligence.An elusive and fascinating topic that has attracted quite a bit of attention in the field of embodied artificial i

164、ntelligence.Owen Holland is also having a stab at the future of embodied artificial intelligence and asks the question of whether we will be able to achieve machine consciousness(Holland,2004).A topic often discussed in investigating consciousness and in building machine consciousness,are the so-cal

165、led qualia.Qualia are the subjective sensory qualities like the redness of red that accompany our perception.Qualia symbolize the explanatory gap that exists between the subjective qualities of our perception and the physical brain-body system whose states can,in principle,be measured objectively.In

166、 our terminology,qualia are closely related to embodiment,to the physical,material,and morphological structure of the sensory systems.Emotions,another highly controversial topic,also relate to the issue of conscious-ness and the development of emotional machines is also a topic of interest(for a par

167、-tial review of an embodied perspective,see e.g.Pfeifer,2000).Last but not least,a topic that anyone interested in intelligence and especially development will have to deal with is why an agent does anything in the first place?Why should it learn new things?This question is especially relevant if th

168、ere are rich task environments with many behavioral possibilities.A chess computer only has one task,i.e.to make the next move,whereas in the real world there are always a host of possibilities at least for those agents that we are potentially interested in(not for Braitenberg Type 1 vehi-cles).It i

169、s the entire issue of motivation,a topic with an enormous history.Luc Steels and Frederic Kaplan in this volume present two simple but powerful and highly plau-sible general solutions(Steels,2004;Kaplan and Oudeyer,2004).These are all fun-damental questions of cognitive science.In order to make deve

170、lopment work,a number of engineering challenges must be resolved.From developmental studies it is known that sensory-motor coordination underlies much of concept development.This requires on the one hand the develop-ment of proper actuators:upper torso with head/neck,and arms with hands.Many researc

171、hers work with torsos only,but given the importance of locomotion for cogni-tive development,it would be desirable to have complete agents capable of walking freely in their environments.To date most robots are specialized,either for walking or other kinds of locomotion purposes,or for sensory-motor

172、 manipulation,but rarely are they skilled at performing a wide spectrum of tasks.This is due to conceptual and engineering limitations.Actuator technology is a major problem as today mostly elec-trical motors are employed,whereas as argued earlier artificial muscles would be more desirable.Skin sens

173、ors for the fingertips,but also for covering the entire body,would be essential for building up something like a body image,and ultimately to bootstrap cognition.Huge transdisciplinary efforts between engineering,biomechanics,and material science will be required to make progress here.Note that alth

174、ough most people in developmental or cognitive robotics are inter-ested in humanoids,this is by no means the only path.A developmental perspective can be beneficial for all kinds of animal studies.High-level intelligence cannot only be achieved using a developmental approach,but also,at least theore

175、tically,by means of evolutionary methods.We will discuss them in the subsequent paragraph,but given the state-of-the-art in artificial evolution,we will have to resort to more direct methods such as hand design or developmental approaches for the time being.Automated design methods(artificial evolut

176、ion and morphogenesis)Using artificial evolution for design has a tradition in the field of evolutionary robotics(e.g.Nolfi and Floreano,2001).The standard approach is to take a particular robot and use an evolutionary algorithm to evolve a controller for a particular task.However,if we want to expl

177、ore morphological issues,and if we want to design entire agents rather than controllers only,we have to devise powerful methods capable of handling these issues.Floreano et al.(2004)provide an excellent overview of the field with many illustrations and experiments.Because of the many parameters and

178、design considerations involved,automated methods must be employed because humans will no longer be able to“hand design”all aspects of such systems.There is the morphology of the body,the materials,the neural control,the interaction with the environment,and there is the possibility of having several

179、agents,perhaps simpler ones,perform the task collectively.For indi-vidual organisms,there have been some initial successful attempts at designing sys-tems by evolutionary means,the main approaches being the parameterization with recursive encoding(e.g.Sims,1994;Lipson and Pollack,2000),and those whe

180、re ontogenetic development is based on abstract models of genetic regulatory networks using cell-to-cell signaling mechanisms(Eggenberger,1997,1999;Bongard,2002,2003;Bongard and Pfeifer,2001;Banzhaf,2004).The advantage of genetic regula-tory networks is that they incorporate less of a designer bias

181、and that they allow for incorporation of interaction with the environment during ontogenetic development,developmental plasticity(Bongard,2003).Moreover,because they encode growth processes,they also,in some sense,contain the mechanisms for self-repair,an essen-tial property of natural systems.There

182、 are a number of challenges,here.First,it is the further development of mod-els genetic regulatory networks to grow creatures of arbitrary complexity and to make the evolution open-ended in the sense that not only the parameters of the genetic regu-latory networks can be manipulated,but that the mec

183、hanisms themselves are under evolutionary control.Moreover,understanding and controlling the highly involved complex dynamics of genetic regulatory networks will require a lot of research(see Bongard,2003;Eggenberger,1999;and Banzhaf,2004,for some preliminary perti-nent research).An important aspect

184、 will be the understanding of the emergence of hierarchical structures and modularity of the phenotypes(see also Floreano et al.,2004).Second,the physics-based simulation models need to be augmented to allow for more sophisticated agent-environment interactions.Also,deformable,flexible materials,add

185、itional sensors such as“skins”for covering the entire body,or olfaction,as well artificial muscles should be accounted for.Third,along these lines,the task environments must be made much more complex in order to put these design methods to a real test.In this way,we might be able to observe and bett

186、er understand phenom-ena of centralization of neural substrate,i.e.the formation of brains.Eventually we might be able to see not only exploitation of physical interaction constraints,but also social ones.Whether the mechanisms of simulated genetic regulatory networks will in fact scale to very comp

187、lex organisms capable of sophisticated social interaction,is an open question.The grand challenge remains to evolve truly complex creatures capable of communication,language,high-level cognition,and perhaps consciousness.Several orders of magnitude of scale will have to be bridged in the process,fro

188、m molecules to macroscopic organisms.To what extent physically realistic simulations will be sufficient for this purpose,or whether evolution actually must happen in the real world with its indefinite richness,is a deep and currently unanswered issue.This evolutionary level,designing the evolutionar

189、y mechanisms as well as the de-velopmental processes based on genetic regulatory networks,might in fact provide a proper level of formalization of ecological balance.While it is indeed hard to find a common currency for trading computation for materials and morphology,it might turn out to be much ea

190、sier to formally specify the developmental processes as encoded in the genome.This is because,at this stage,it is still undecided how the tasks will be distributed to control,materials,and morphology for a particular task-environment.Moving into the real world The last grand challenge that we would

191、like to discuss here concerns very generally speaking the“move into the real world.”The first significant step in this direction has been the introduction of the notion of embodiment and the insight that true intelli-gence always requires the interaction with the real world.Embodied artificial intel

192、li-gence is based on this idea.Building intelligent robots,i.e.robots capable of perform-ing a wide range of tasks,is,as we have argued throughout this paper,hard enough,and the robots we currently are capable of building are not to our satisfaction,and so building robots per se remains a grand chal

193、lenge in the field.In designing higher-level intelligence we identified developmental approaches as a potentially suitable method.Development requires growth processes that we can cur-rently only simulate.But there are some tricks that can be applied to make develop-ment somewhat more realistic vis-

194、vis the real world.One possibility is to start with high-resolution,high-precision systems with many degrees of freedom.Growth,at least in some respects,can then be“simulated”by constraining the systems initially,freezing degrees of freedom,and simulating low resolution,for example,of the vision sen

195、sor in software by applying certain kinds of filters.These constraints can succes-sively be released which in some sense reflects an organisms maturational processes(Gmez et al.,2004).However,biological organisms actually do grow in the real world by means of cell division and cell differentiation,a

196、 process that may in fact be essential for the emer-gence of cognition.Developing growing structures in the real world is one of the great engineering challenges that will require the cooperation of material scientists,engi-neers,molecular and developmental biologists,and nanotechnology experts.Thes

197、e are,by the way,all disciplines that are not normally associated with artificial intelligence.If artificial evolutionary processes are not only to be simulated in a computer but performed in the real world,we will need growth processes as well.As mentioned earlier,it is not clear to what extent phy

198、sics-based simulations will be sufficient for scalable artificial evolution,and to what extent evolution has to rely on processes in the real world.First steps in performing artificial evolution in the real world have been taken already in the 1960s by Ingo Rechenberg who evolved optimal shapes of f

199、uel pipes by actually configuring the physical system“designed”by the evolutionary algorithm(an evolution strategy)and measuring the performance on the real fuel pipe system(Rechenberg,1973).Another example is the work by Adrian Thompson at the University of Sussex who used FPGAs to test the circuit

200、s evolved using a genetic algorithm(Thompson,1996).FPGAs,in contrast to microprocessors,rather than making a digital simulation of a circuit,actually configure a physical circuit.The results achieved are truly amazing and provides a glimpse at the power of evolution in the real world.A major step is

201、 taken by researchers in the EU-funded PACE(Programmable Arti-ficial Cell Evolution)project by John McCaskill of the Ruhr University Bochum,in Germany,where the goal is to evolve an artificial cell in a chemical laboratory.Using micro-fluidic arrays,carefully controlled chemical reactions can be ind

202、uced so that cells can be formed and their metabolisms influenced in precise ways.Part of the evolution will be performed in simulation and part in the real world.The goal is to evolve self-replicating cells in the laboratory,an enormous challenge.If successful,this would enable us to perform artifi

203、cial evolution in the real world and thus we could generate any kind of structure required for performing a particular task.Because the cells can divide we would have actual growth processes in the real world.Some peo-ple like Ray Kurzweil believe that nanotechnology will be the key to engineer grow

204、th in the real world.Whether this will materialize we will only know in the future.Cyborgs could also be viewed as a way to“move into the real world”:rather than constraining the neural substrate to function in a dish in isolation,it is connected to either a simulation or to a robot that behaves in

205、the real world and sends its sensory signals back to the neural tissue in the dish(Bakkum et al.,2004).Coupling biological neural tissue to a real world artifact opens up entirely new avenues in man-machine interaction.This research in itself bears many great challenges,the general issue of coupling

206、 biological and technical substrate.On the one hand,we can expect to learn something about neural functioning,and on the other we might,in the future,be able to better understand how to control robots by observing the natural neurons.Medical applications in prosthetics(e.g.Yokoi et al.,2004),are of

207、course obvious candidates for practical applications.Finally,coming back to the research on self-repair,self-assembly,and self-reconfiguration discussed in the“Landscape”section,a big challenge,conceptually and from an engineering perspective,is the development of such systems in the real world.Agai

208、n,while simulation of processes of self-repair,for example,represents a challenge and is far from being straight-forward,the ultimate challenge will be the transfer to the real world.Murata and his collaborators(2004)have demonstrated first ideas using modular robotic systems.4.Conclusions,the futur

209、e,and applications The challenges outlined are big challenges and we must not expect to reach them in the near future.However,it is important to keep the long-term visions in mind when thinking about the next steps.The difficulty of research in any field,but in particular in artificial intelligence,

210、is to map the big visions and challenges onto concrete,doable steps.We have also tried to outline what researchers in the field are currently attempt-ing to do and what they are planning for the near future.And the papers presented in this volume provide an excellent starting point.Let us now return

211、 to the initial question of what thinking has to do with walking the symbol grounding problem and reflect on how the challenges outlined in the paper will contribute to this question which metaphorically summarizes the goals of embodied artificial intelligence.In the early phases of embodied artific

212、ial intelligence,many people were working on navigation and orientation out of a conviction that locomotion and orientation are somehow the underlying driving forces in the devel-opment of cognition,in the evolution of the brain.This is corroborated by the question asked by the famous Oxford neurosc

213、ientist Daniel Wolpert“Why dont plants have brains?”.And he suggested that the answer might actually be quite simple:“Plants dont have to move!”Because of the“embodied turn”,researchers started working with robots,and because they were readily available and easy to use,wheeled robots were the tools

214、of choice.Navigation in the real world is a challenging problem and there has been much exciting research in robotics in general(e.g.Bellot et al.,2004,who introduce the new method of Bayesian Programming)and in biologically inspired approaches in particular(e.g.Hafner,2004).While there was a lot of

215、 progress re-searchers were forced to deal with the intricacies of the interaction with the real world,such as noise,imprecisions,change,unpredictability there were also some intrinsic problems with the approach.Remember that one of the aspects of the principle of ecological balance is the match in

216、complexity of sensory,motor,and neural systems.Because it is easy to put a high-resolution camera on a robot,and because wheeled robots only have few degrees of freedom of actuation,many experimental designs were“unbalanced”:complex sensory systems,very simple motor systems.As a result of these unba

217、lanced designs,these systems had a relatively uninteresting physical dynamics.One implication is that the algorithms used for control were largely arbi-trary:Even though they were mostly biologically inspired,they were arbitrary with respect to the robots own dynamics;one algorithm can be exchanged

218、by another,achieving essentially the same behavior.Something was missing and many suspected that this is a complex sensory-motor level with an interesting and rich dynamics.As a consequence a number of researchers started working on complex body dy-namics(e.g.Kuniyoshi et al,2004;Iida and Pfeifer,20

219、04a;Proc.of the Int.Workshop on Adaptive Motion in Animals and Machines,AMAM-2003).This shift was inter-preted by critics but also by people sympathetic to these developments,as a move away from the goal of understanding and building cognitive systems.However,and this is one of the big insights from

220、 embodied artificial intelligence,the exact opposite was the case:It turned out that a rich complex body dynamics is the foundation,the prerequisite for something like symbol processing to develop(see,e.g.Okada et al.,2003;Iida and Pfeifer,2004b;Kuniyoshi et al.,2004).So what happened is that what s

221、eemed like a deviation from the road to cognition,turned out to be necessary.This view is also compatible with Nez(2004)who argues that even very abstract mathe-matical concepts have their origins,are grounded,in our embodiment which provides the basis for metaphors.Because these metaphors must be s

222、ufficiently rich for boot-strapping interesting concepts,the embodiment must reflect this richness.Of course,at the moment,this is all speculation that must be corroborated by many experiments.But at the risk of being entirely wrong,let us speculate a little further.There is another,unexpected idea

223、that emerges from this research.The question of symbol grounding always entails the question of how it is possible that something like discrete symbol processing can emerge from a completely continuous dynamical sys-tem,such as a human.Rich,complex dynamics also implies many attractor states and tra

224、nsitions between them.Attractor states are,within the continuous dynamics,objec-tively identifiable,discrete states,that can,of course,also be identified by the agent itself(or himself),given the proper neural system.Once identified,the agent can start using them,for example,for planning purposes(e.

225、g.Okada et al.,2003;Kuniyoshi et al.,2004).It is interesting to note that a complex intrinsic sensory-motor dynamics implies that the neural control is no longer arbitrary,but has to be“in tune”with the physical substrate,quite in contrast to wheeled robots.Ishiguro and his colleagues(2004)have prov

226、ided a beautiful demonstration,theoretically and in a robot case study,of how control and body dynamics in a complex agent have to be coupled.If coupled properly,control is not only simpler,but the entire system tends to be more energy-efficient.Lungarella and Berthouze(2004)in a robotics case study

227、 convinc-ingly demonstrate that a judicious non-arbitrary choice of parameters coupling the neural and body dynamics facilitates the acquisition of motor skills in a developing organism.Whether these ideas on dynamics will ultimately lead to high-level cogni-tion or to conscious agents,whether in th

228、is way we can achieve the goals set out by Holland(2004),is an entirely open question.Tom Ziemke in his contribution(2004)quotes from Gerald Edelman“It is not enough to say that the mind is embodied:one has to say how.”(Edelman,1992).Bootstrapping it from complex body dynamics might be part of the a

229、nswer.In their current state,evolutionary studies are,for the time being,restricted to pro-viding ideas on the distribution of morphology,materials,control,and interaction with the environment.More varied and taxing task environments will be necessary to inves-tigate agents with more complex sensory

230、-motor dynamics on top of which cognition can bootstrap.But some of recent approaches demonstrate definite progress in this direction(e.g.(Bongard,2003).However,as alluded to in the previous section,in order to achieve truly complex organisms,it may be necessary to couple the artificial evolutionary

231、 process to the real world.To conclude,just few words about applications.While the classical approach has created many applications in terms of clever algorithms that are now widely used,the embodied approach seems to be more limited.The major applications have been in the entertainment and educatio

232、nal areas.As this paper demonstrates,the field is just be-ginning to develop a basic understanding and there are many big challenges lying ahead.We could also add a challenge,namely to exploit these technologies for practi-cal applications in industry,the environment,and services for the benefit of

233、society.Research on humanoid robots has an interesting side-effect,so to speak.Human-oids require the development of sophisticated body parts,legs,arms,hands,etc.,that can potentially be used,at least to some extent,as prosthetic devices.The fascinating research by Yokoi et al.(2004)and by Boblan et

234、 al.(2004)points in this direction.The ground breaking research by Potter and his co-workers(Bakkum et al.,2004)might eventually be employed for interfacing these devices smoothly with humans an additional intriguing perspective.As outlined in the section of ubiquitous computing,a better understandi

235、ng of em-bodied intelligence will lead to many applications in terms of so-called embedded systems,i.e.systems that autonomously interact with the real world,not only through sensing,but also by influencing the world without human intervention.These systems are not robots in the restricted sense of

236、the word(they are very different from human-oid robots,for example),but they have many of their characteristics in terms of intel-ligent,autonomous interaction with the environment.These kind of systems,also called“robotic devices”are already present in many technical applications(cars,air-planes,ho

237、usehold appliances,elevators,etc.),but by augmenting their“intelligence”,so to speak,many more applications will become possible.This way,the ideas that embodied artificial intelligence has spurred will spread to numerous scientific and technological areas for the benefit of society.Acknowledgments

238、We would like to thank the scientific director of the International Conference and Research Center for Computer Science,Prof.Reinhard Wilhelm,for suggesting this conference,and the Swiss National Science Foundation for supporting the research presented in this paper,grant#20-68198.02(“Embodied Artif

239、icial Intelligence”).We would also like to thank the members of the Artificial Intelligence Laboratory of the University of Zurich for numerous stimulating discussions on this topic.Credit also goes to Max Lungarella for his many thoughtful comments on this paper.References Bakkum,D.J.,Shkolnik,A.C.

240、,Ben-Ary,G.,Gamblen,P.,DeMarse,T.B.,and Potter,S.M.(2004).Removing some A from AI:Embodied cultured networks(this volume)Ballard,D.(1991).Animate vision.Artificial Intelligence,48,57-86.Banzhaf,W.(2004).On evolutionary design,embodiment,and artificial regulatory etworks(this volume).Boblan,I.,Bannas

241、ch,R.,Schwenk,H.,Miertsch,L.,and Schulz,A.(2004).A human like robot hand and arm with fluidic muscles:Biologically inspired construction and functional-ity.(this volume)Bellot,D.,Siegwart,R.,Bessire,P.,Tapus,A.,Cou,C.,and Diard,J.(2004).Bayesian mod-eling and reasoning for real-world robotics:Basics

242、 and examples(this volume).Blickhan,R.,Wagner,H.,and Seyfarth,A.(2003).Brain or muscles?,Rec.Res.Devel.Biome-chanics,1,215-245.Bonabeau,E.,Dorigo,M.,and Theraulaz,G.(1999).Swarm intelligence:from natural to artifi-cial systems.New York,N.Y.:Oxford University Press.Bongard,J.C.(2003).Incremental appr

243、oaches to the combined evolution of a robots body and brain.Unpublished PhD thesis.Faculty of Mathematics and Science,University of Zurich.Bongard,J.C.(2002).Evolving modular genetic regulatory networks.In Proc.IEEE 2002 Congress on Evolutionary Computation(CEC2002).MIT Press,305-311.Bongard,J.C.,an

244、d Pfeifer,R.(2001).Repeated structure and dissociation of genotypic and phenotypic complexity in artificial ontogeny.In L.Spector et al.(eds.).Proc.of the Sixth European Conference on Artificial Life,401-412.Brooks,R.A.(1991).Intelligence Without Reason.Proceedings of the 12th International Joint Co

245、nference on Artificial Intelligence(IJCAI-91),pp.569595.Brooks,R.A.,and Stein,L.A.(1993).Building brains for bodies.Memo 1439,Artificial Intel-ligence Lab,MIT,Cambridge,Mass.Collins,S.H.,Wisse,M.,and Ruina,A.(2001).A three-dimensional passive-dynamic walking robot with two legs and knees.The Interna

246、tional Journal of Robotics Research,20,607-615.Dipellegrino G,Fadiga L,Fogassi L,Gallese V,Rizzolatti,G(1992).Understanding motor events-a neuro-physiological study.Exp Brain Res 91:176-180.Edelman,G.E.(1992).Bright air,brilliant fire.On the matter of the mind.New York:Basic Books.Eggenberger,P.(199

247、7).Evolving morphologies of simulated 3d organisms based on differen-tial gene expression.In:P.Husbands,and I.Harvey(eds.).Proc.of the 4th European Con-ference on Artificial Life.Cambridge,Mass.:MIT Press.Eggenberger,P.(1999).Evolution of three-dimensional,artificial organisms:simulations of develop

248、mental processes.Unpublished PhD Dissertation,Medical Faculty,University of Zurich,Switzerland.Elman,J.L,Bates,E.A.,Johnson,H.A.,Karmiloff-Smith,A.,Parisi,D.,and Plunkett,K.(1996).Rithinking innateness:A connectionist perspective on development.Cambridge,Mass.:MIT Press.Epstein,J.M.and Axtell,R.L.(1

249、996).Growing artificial societies:social science from the bottom up.Cambridge,Mass.:MIT Press.Fadiga L,Fogassi L,Gallese V,Rizzolatti G(2000)Visuomotor neurons:Ambiguity of the discharge or motor perception?Int J Psychophysiol 35:165-177.Ferber,J.(1999).Multi-agent systems.Introduction to distribute

250、d artificial intelligence.Addi-son-Wesley.Floreano,D.,Mondada,F.,Perez-Uribe,A.,and Roggen,D.(2004).Evolution of embodied intelligence(this volume).Gallese,V.,Fadiga,L.,Fogassi,L.,and Rizzolatti G.(1996).Action recognition in the premo-tor cortex.Brain 119:593-60.Gaussier,P.,Prepin,K.,and Nadel,J.(2

251、004).Toward a cognitive system algebra.Application to facial expression learning and imitation(this volume).Gmez,G.,Lungarella,M.,Eggenberger Hotz,P.,Matsushita,K.and Pfeifer,R.(2004).Simu-lating development in a real robot:on the concurrent increase of sensory,motor,and neural complexity.The 4th an

252、nual workshop of Epigenetic Robotics(EPIROBOT04),(in press).Hafner,V.(2004).Agent-environment interaction in visual homing(this volume).Hara,and R.Pfeifer(eds.)(2003).Morpho-functional machines:the new species designing embodied intelligence.Tokyo:Springer-Verlag.Hara,F.,and Pfeifer,R.(2000).On the

253、relation among morphology,material and control in morpho-functional machines.In Meyer,Berthoz,Floreano,Roitblat,and Wilson(eds.):From Animals to Animats 6.Proceedings of the sixth International Conference on Simula-tion of Adaptive Behavior 2000,33-40.Holland,O.(2004).The future of embodied artifici

254、al intelligence:Machine consciousness?(this volume).Hosoda,K.(2004).Robot finger design for developmental tactile interaction.Anthropomor-phic robotic soft fingertip with randomly distirbuted receptors(this volume).Iida,F.and Pfeifer,R.(2004a)“Cheap”Rapid locomotion of a quadruped robot:Self-stabili

255、zation of bounding gait.F.Groesn et al.(eds.).Intelligent Autonomous Systems 8.IOS Press,642-649.Iida,F.,and Pfeifer,R.(2004b).Self-stabilization and behavioral diversity of embodied adap-tive lcomotion(this volume).Ishiguro,A.,and Kawakatsu,T.(2003).How should control and body systems be coupled?A

256、robotic case study(this volume).Janssen,B.,de Boer,B.,and Belpaeme,T.(2004).You did it on purpose!Towards intentional embodied agents(this volume).Kaplan,F.,and Oudeyer,P.-Y.(2004).Maximizing learning progress:an internal reward sys-tem for development(this volume).Kubow,T.M.,and Full,R.J.(1999).The

257、 role of the mechanical system in control:a hypothe-sis of self-stabilization in hexapedal runners,Phil.Trans.R.Soc.Lond.B,354,849-861.Kuniyoshi,Y.,Yorozu,Y.,Ohmura,Y.,Terada,K.,Otani,T.,Nagakubo,A.,and Yamamoto,T.(2004).From humanoid embodiment to theory of mind(this volume).Lambrinos,D.,Mller,R.,L

258、abhart,T.,Pfeifer,R.,Wehner,R.(2000).A mobile robot employ-ing insect strategies for navigation.Robotics and Autonomous Systems,30,39-64.Lenat,D.,Prakash,M.,and Shepher,M.(1986).CYC:Using common sense knowledge to overcome brittleness and knowledge acquistion bottlenecks.AI Magazine,vol.6,issue 4,65

259、-85.Langton,C.G.(1995).Artificial life:an overview.Cambridge,Mass.:MIT Press.Lipson,H.,and Pollack J.B.(2000),Automatic design and manufacture of artificial life forms.Nature,406,974-978.Lichtensteiger,L.(2004).The need to adaptv and its implications for embodiment(this vol-ume).Lungarella,M.,and Be

260、rthouze,L.(2004).Robot bouncing:On the synergy between neural and body dynamics(this volume).Lungarella,M.and Pfeifer,R.(2001).Information-theoretic analysis of sensory-motor data.In Proc.of the IEEE-RAS International Conference on Humanoid Robots,245-252.Lungarella,M.,Metta,G.,Pfeifer,R.and Sandini

261、,G.(2003).Developmental robotics:a survey.Connection Science,15(4),151-190.Mead,C.A.(1989).Analog VLSI and neural systems.Reading,Mass.:Addison-Wesley.Murata,S.,Kamimura,A.,Kurokawa,H.,Yoshida,E.,Tomita,K.,and Kokaji,S.(2004).Self-reconfigurable robots:platforms for emerging functionality(this volum

262、e).Nagai,Y.,Hosoda,K.,and Asada,M.(2003).Joint attention emerges through bootstrap learn-ing,Proc.of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Sys-tems(IROS2003),168-173.Nolfi,S.and Floreano,D.(2001).Evolutionary robotics:the biology,intelligence,and tech-nology of self-or

263、ganizing machines.Cambridge,MA:MIT Press.Nez,R.(2004).Do real numbers really move?The embodied cognitive foundations of mathematics(this volume).Okada,M.,Nakamura,D.,and Nakamura,Y.(2003).On-line and hierarchical design methods of dynamics based information processing system.Proc.of the 2003 IEEE/RJ

264、S Int.Confer-ence on Intelligent Robots and Systems,954-959.Pfeifer,R.(2000).On the role of embodiment in the emergence of cognition and emotion.In H.Hatano,N.Okada,and H.Tanabe(eds.).Affective minds.Amsterdam:Elsevier,43-57.Pfeifer,R.,Iida,F.,and Bongard,J.(2004).New robotics:design principles for

265、intelligent systems.Artificial Life(in press).Pfeifer,R.,and Scheier,C.(1999).Understanding intelligence.Cambridge,Mass.:MIT Press.Rechenberg,I.(1973).Evolution strategies:optimization of technical systems with principles from biological evolution(in German).Stuttgart,Germany:Frommann-Holzboog.Sims,

266、K.(1994a).Evolving virtual creatures.Computer Graphics,28,15-34.Sporns,O.,and Pegors,T.K.(2004).Information-theoretical aspects of embodied artificial intelligence(this volume).Steels,L.(2001).Language games for autonomous agents.IEEE Intelligent Systems,Sept/Oct issues.Steels,L.(2003).Evolving grou

267、nded communication for robots.Trends in Cognitive Sciences,7(7),308-312,Steels,L.(2004).The autotelic principle(this volume).te Boekhorst,R.,Lungarella,M.,and Pfeifer,R.(2003).Dimensionality reduction through sensory-motor coordination.Proc.of the 10th Int.Conf.on Neural Information Processing(ICONI

268、P03),p.496-503,LNCS 2174.Thelen,E.,and Smith,L.(1994).A dynamic systems approach to the development of cognition and action.Cambridge,Mass.:MIT Press.Thompson,A.(1996).Silicon evolution.In J.R.Koza et al.(Eds.).Genetic Programming 1996:Proc.of the First Annual Conference,Cambridge,Mass.:MIT Press,44

269、4-452.Webb B.and Consi R.C.(2000).Biorobotics-Methods&application-,Cambridge,Mass.:MIT Press.Weiser,M.(1993).Hot topics:Ubiquitous computing,IEEE Computer.Wisse,M and Frankenhuyzen,J.van,(2003)Design and Construction of MIKE;a 2D autono-mous biped based on passive dynamic walking,Proceedings of the

270、2nd International Sym-posium on Adaptive Motion of Animals and Machines,Kyoto,March.4-8,2003.Yamamoto,T.and Kuniyoshi,Y.(2001).Harnessing the robots body dynamics:a global dy-namics approach.Proc.of 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS2001),pp.518-525,Hawaii,

271、USA.Yokoi,H.Arieta,A.H.,Katoh,R.,Yu,W.,Watanabe,I.,and Mruishi,M.(2004).Mutual adaptation in a prosthetic application(this volume).Yoshikawa,Y.,Asada,M.,and Hosoda,K.(2004).Towards imitation learning from a view point of an internal observer(this volume).Ziemke,T.(2004).Embodied AU as science:Models of embodied cognition,embodied models of cognition,or both?(this volume).