EFTA01103525.pdf

Creating Intelligent Humanoid Robots Using the OpenCog AGI Architecture Research Proposalfor the Epstein Foundation Ben Goertzel January 16, 2013 Introduction At its inception in the 1950s, the Al field aimed at producing human level general intelligence in computers and robots. Within a decade or so the difficulty of that goal became evident, and the Al field refocused on producing systems displaying intelligence within narrow domains. This focus on "narrow Al" has been strikingly successful in some regards, leading to practical Al applications such as Google's search and ad engines, Deep Blue and other game- playing Als, IBM's Watson Jeopardy-player, a host of profitable Al financial trading systems, and so forth. Over the past few years, however, there has been a resurgence of research interest in the original goals of AI, often using terminology such as Human-Level Al or Artificial General Intelligence (AGI) [1,2,3,4]. The core reason for this resurgence is a feeling that, due to advances in the Al field and in allied areas such as computer and robotic hardware, computer science, cognitive psychology and neuroscience, we are in a far better position to approach these goals today than were the founders of Al in the 1950s. One may ask why, given all the amazing recent developments in applied Al and allied areas, we have not yet seen Al software systems with humanlike general intelligence. We believe there is one key ingredient missing —the effective linkage of subsymbolic Al methods, dealing with raw perceptual and motoric data, with symbolic AI methods, dealing with abstract reasoning and language, and higher level cognition. The Al field now possesses able algorithms and architectures on both the symbolic and subsymbolic sides, but without both aspects working together, human level general intelligence is hard to come by. Some researchers aim to bridge the gap by making subsymbolic Al systems intelligent enough that they can learn symbolic reasoning via experience. After all, they figure, symbolic reasoning originally evolved from subsymbolic thinking — humanity's distant evolutionary ancestors probably didn't do much symbolic reasoning. Others aim to bypass the need for subsymbolic processing, figuring that one can create a human-level Al well enough by communicating with it using text chat, and having it gather knowledge from the Web and structured databases —all sources that are easier to feed directly into a symbolic Al system. Some feel the crux of the Al problem lies on the symbolic side, and if one wants to make an Al system controlling a robot, one can simply bolt some separate perception and motor-control modules onto one's symbolic Al system. The solution we suggest is different, and in a certain sense simpler. We propose to interconnect a highly functional, primarily symbolic AGI architecture (OpenCog [5], an international open source project'), with a highly functional subsymbolic Al system (DeSTIN [6,7], developed at the University of Tennessee, Knoxville). We propose to perform this connection, not merely by linking the two systems as separate modules, but by enabling the two systems to exchange deep information regarding their internal states, and provide guidance to each other's thinking. In order to do this, we have designed a unique pattern recognition layer intended to live between DeSTIN and OpenCog, and translate between the languages of the two different systems [8]. The combined OpenCog/DeSTIN system will powerfully display a core principle of AGI called "cognitive synergy," key to the OpenCog architecture, according to which different aspects of an intelligent system are engineered to help each other out of cognitive bottlenecks. Human-level AGI, like human intelligence, is largely about practical interaction with the physical world and other beings in it. Therefore, to refine and test our approach to OpenCog/DeSTIN integration, we will pose the integrated system the task of controlling a Hanson Robokind robot in a robot lab environment — a cognitively enabled robot or "CogBot." We will specifically aim at enabling the Robokind to carry out a variety of preschool-like behaviors, such as playing with blocks and conversing about its play activities. This forms a natural extension of our current work using OpenCog to control animated characters that build things with blocks in a 3D video game world; and of prior work using OpenCog to control a Nao robot in a robot lab in a simpler way, without benefit of hybridization with DeSTIN or any similarly sophisticated perception/action system [9]. The use of a preschool-like setting enables the application of ideas from developmental psychology to guide and assess the AGI's progress [10]. http://opencog.org EFTA01103525  We don't aim at this stage to create a robot giving a perfect simulation of a human child. Both the body and mind of our proposed "CogBot" system are very different from those of any human being. Qualitatively, our aim with the robotics aspect of the project is to create a robot that is recognizably and irrefutably generally intelligent, in the rough manner of a young human child. We will also perform careful quantitative evaluations of our work, developing formal intelligence metrics for the robot via appropriately modifying measures used to gauge the intelligence of young human children, and studying how the robot's intelligence varies as one changes the configurations of the underlying Al components. As discussed in a recent article of ours in Al Magazine [11], we believe this is a robust approach to measuring incremental progress toward full human adult level AGI; certainly much more so than the Turing test (emulation of human text chat) which has proved deeply flawed in practice [12]. Due to the complexity of the underlying Al systems (OpenCog and DeSTIN), the proposed project is a multidisciplinary effort involving component problems in multiple Al areas, including computer vision and audition, humanoid robot control, computational linguistics, probabilistic reasoning, automatic program learning, assignment of credit and concept creation. Achieving the project goals will not require breakthroughs in any of these areas; the focus will rather be on integration and synergetic behavior. However, the results of this research are expected to yield interesting advances in each of these areas, in addition to the advancement toward human-level artificial general intelligence implicit in the achievement of childlike intelligence in a humanoid robot. Finally, in addition to the scientific and commercial implications of this work, we believe the broader humanitarian implications also merit some reflection. Part of our motivation for undertaking this work is a desire to guide the future development of advanced Al and robotics in a positive direction. As Ray Kurzweil and others have recently argued [13], it is a distinct possibility that the artificial intelligences of several decades hence will be more intelligent and generally competent than any human being. In this light, we consider it crucial that as robots gain more and more general intelligence and capability, they do so in the context of strong emotional and social awareness of the human world, and rich emotional interaction with human beings. We predict that deep emotional understanding is a necessary condition for an artificial intelligence to be able to accurately judge the effects of its possible actions on human welfare. So we view the work on childlike robot general intelligence, proposed here, as potentially constituting early steps toward the development of much more broadly capable generally intelligent robots and Al systems, which possess empathy and human understanding along with their intelligence. Existing & Desired Additional Funding Funding for this project is already partially in place, due to an ITF (Innovation in Technology Fund) grant obtained via the Hong Kong government, with Dr. Gino Yu as Principal Investigator and Ben Goertzel's Al consulting firm Novamente LLC as corporate sponsor (providing 10% of the funds to match the ITF's 90%). This ITF grant is titled "Artificial Intelligence Software Enabling Toy Robots to Learn, Communicate, Emotionally Bond and Display Individual Personalities" (1TS/178/12FP). The ITF grant proposal states that the software produced with the government funding will be open source, with the Hong Kong government or university not having intellectual property rights. The existing government funding amounts to US$342K from the ITF and $38K from Novamente LLC. However, the likelihood of achieving the project goals in a high-quality, broadly extensible way will be increased if additional funding can be obtained, which is the purpose of this proposal. This government funding will pay for a team of 6 PhD students and junior programmers working in a university lab; the requested additional funding would cover • A full-time senior software developer • A full time, experienced Al PhD, to carry out and help supervise Al software development • A part-time senior systems administrator • A small, dedicated compute cluster (of Linux machines) • A dedicated office / robot lab space for the project • Assistance of Novamente LLC with its corporate contribution (which would be valued due to Novamente's limited funds and limited commercial activity currently) In short, the additional funding would transform the project from an underfunded university-research-lab type initiative, into a professional R&D initiative with experienced hands-on leadership, thus at least doubling productivity and significantly increasing odds of success. Background The background for the project comes from multiple disciplinary directions — computer science, cognitive EFTA01103526 science, robotics and systems theory — and the project's conceptual direction is the result of collaboration between three interdisciplinary researchers and technologists: • Dr. Ben Goertzel: Principal Investigator; scientific leader of commercial project sponsor Novamente LLC. Dr. Goertzel is an Al researcher with a mathematics background, the leader of the international Artificial General Intelligence research community. • Dr. David Hanson: Co-Investigator; scientific leader of commercial project sponsor Hanson Robotics. Dr. Hanson's whose interdisciplinary background in arts, design and robotics led him to develop a variety of revolutionary robots including Robot Einstein and Hanson Robokind (the latter to be used in the proposed project) [see Figure 2]. These robots feature novel robot skin enabling humanlike emotional expression, and feature a unique combination of hardware and software features focused on rich emotional interaction with human users. • Dr. Itamar Arel: Scientific Advisor. Al and engineering professor at the University of Tennessee Knoxville, the creator of the DeSTIN (Deep SpatioTemporal Inference Network) software to be used in the project for robot vision and action (to serve as an intermediate layer between OpenCog and the Robokind robot) The project involves three key components, corresponding to these three researchers: • The OpenCog artificial general intelligence architecture [5,8], an open-source software project initiated by Dr. Goertzel and now developed and maintained by a global open-source community led by Goertzel and others • The DeSTIN framework for machine perception (extensible to action as well), developed by Dr. Ramer Mel and his students at the University of Tennessee, Knoxville; now an open-source software project bundled with OpenCog • Hanson's robotics hardware, the Hanson Robokind, and his open-source software for specifying and maintaining intelligent characters with individual personalities [15], -- integrated in a manner that is inspired by the prior research and thinking of Goertzel, Hanson and Arel, but also has critical novel aspects. The core of the project is a novel approach to bridging the sensation/action domain as embodied in the Robokind's sensors and actuators and recognized via the (subsymbolic) DeSTIN Al software, and the domain of symbolic, abstract Al cognition as embodied in the OpenCog cognitive architecture. OpenCog is the most practically advanced software system explicitly oriented toward Artificial General Intelligence. Compared to other contemporary AGI-oriented software systems2, OpenCog has a more professionally designed and implemented codebase, and a wider range of functionalities. Conceptually, the OpenCog architecture is unique in its integration of a number of powerful learning algorithms within a human-like cognitive architecture. OpenCog has been used in a variety of commercial projects in areas such as natural language processing, financial analysis and bioinformatics. The main thrust of current OpenCog development is the use of the system to control animated characters in a video-game world — which, following a long tradition in the Al field, is a world where most objects are built from small blocks, whose positions and interactions the Al system can fully understand and manipulate. OpenCog guides characters in the world as they explore and try to achieve their goals. This is a follow-up to earlier work using OpenCog to control virtual pets in a simpler virtual world [17]. OpenCog has also previously been used to control a Nao humanoid robot [18]. However, this was merely a prototyping activity, which was not expected to yield dramatic embodied intelligence, due to OpenCog's lack of a serious perception and action module at that time. The core aim of the present proposal is to remedy this lack. 2 Samsonovich [16] has given a good general overview of the various AGI software systems at play in the field currently, including e.g. classic systems like SOAR and ACT-R, and more modern ones like (to name just a few) Stan Franklin's LIDA system, Joscha Bach's MicroPsi and Nick Cassimatis's PolyScheme. EFTA01103527  EllikeecUnFosaY/160 Raw Figure 1. Top• Screenshots of virtual dog controlled by OpenCog engine, as it learns soccer skills via imitation and reinforcement, and builds semantic models ofits environment. Bottom: Screenshot of "blocks world" being used for current OpenCog experimentation; the robot is one ofmultiple OpenCog-controlled characters. DeSTIN, a machine perception architecture, fills a major gap in OpenCog — the processing of complex, high- bandwidth perceptual data, as is produced by camera eyes or microphones. It possesses a hierarchical architecture similar to the human visual and auditory cortices, and an efficient algorithmic implementation that exploits the massively parallel processing provided by GPU supercomputers. Currently it is being used for recognizing patterns in images and videos, but the architecture can be straightforwardly extended to audition as well, and also beyond perception to handle actuation. To connect DeSTIN and OpenCog in a maximally effective way, we have designed a unique "semantic perceptual-motor hierarchy", which sits between the two systems, incorporating aspects of each. As depicted in Figure 3, it has DeSTIN's hierarchical structure, but represents knowledge using OpenCog's symbolic semantic network representations, rather than DeSTIN's subsymbolic numerical vectors. This semantic hierarchy naturally maps into both DeSTIN and OpenCog, and enables the two systems to pass information to each other frequently as they A EFTA01103528 operate, enhancing each other's intelligence synergetically. Figure 2. Left: Dr. Hanson's Robot Einstein, probably the most expressive and emotionally evocative robot face ever constructed. Right: Hanson Robokind — the emotionally expressive humanoid robot to be used in the current project, based on a donation of two robots from Hanson Robotics. To refine and evaluate this novel approach to bridging OpenCog's symbolic reasoning and DeSTIN's subsymbolic pattern recognition activity, one requires a sufficiently sophisticated platform for receiving sensations and executing actions. The Hanson Robokind robot provides high-quality visual and auditory sensors and servomotor capability, at a level previously available only in research robots costing hundreds of thousands of US dollars). Furthermore, the Robokind's capability for facial emotional expressiveness is unparalleled in any previous commercially available robot regardless of cost. This feature is valuable because it gives the Robokind ability to elicit interesting, informative behavior from humans, thus help the OpenCog engine to gain the emotional and social knowledge it needs to interact effectively with the world.. This facial-expression capability is based on special patented flexible robot skin that was developed in Hanson's prior research robots such as the well-known Robot Einstein, and is brought to the commercial market for the first time in the Robokind (Figure 2). Project Aims The high-level objective of the proposed CogBot project is to create a software system instantiating a solution to the most fundamental problem holding back progress toward AGI: the bridging of the symbolic and subsymbolic levels of mental activity. Among the many subproblems to be addressed in this context, the most fundamental regards intelligent, synergetic interfacing between low-level robotic perception/action data and more abstract Al cognition — a problem for which we have a novel solution. On a technical level, the key aims of the project in pursuit of this objective are: 1. To create an intermediate "semantic hierarchy" connecting DeSTIN and OpenCog 2. To make various changes identified as necessary to DeSTIN, to enable effective connection with the semantic hierarchy 3. To adjust OpenCog's internal cognitive algorithms for optimal functionality on the data coming from the semantic hierarchy (mainly the PLN probabilistic logic engine, the conceptual blending algorithm for creating new concepts, and the Fishgram pattern recognition algorithm) 4. To integrate the combined OpenCog/DeSTIN software with Hanson's robot control software, and with open- EFTA01103529  source text-to speech (Festival) and speech-to-text (Sphinx) engines, to enable the system to control a Robokind humanoid robot S. To refine and evaluate this robot's capability to carry out simple "child-like" tasks in a robot lab furnished with appropriate preschool-like equipment Alongside its scientific value, this work has the potential to serve as the starting-point of a variety of commercial applications. Consumer robots are one excellent example of such an application area. Imagine a toy robot that can learn from its experience and reason about its surroundings and the simple intentions and desires of their owner, interpret, process, and express emotions, and communicate in simple English, somewhat like a small child! Such a toy would not have to display perfect, flawless intelligence to be exciting and appealing to its own — since it's just a toy, it's OK if it learns as it goes. The proposed project will develop the underlying software platform to enable such robots, and demonstrate this platform via a "proof-of-concept" demonstration prototype running on Hanson Robokind robots. A toy robot with capabilities closely inspired by those of a young human child would be invaluable for Al and robotics research, and also potentially very compelling as a commercial product, as well as a proof of concept for applications of the underlying technology to other interactive technology applications. Although Robokind is a moderately costly research robotics platform, the technology we develop in this project will be portable to other, more commercially viable toy robots -- as well as a wide variety of other physical devices ranging from home service robots to mobile phones or game consoles. To step back a bit and put it more generally: The goal of this project is to create open-source Al software for robot control, focused on enabling intelligent interaction between the robot and users, in a manner making full use of the physical context in which the robot and the users are embedded. The interaction will include learning, reasoning and emotional interplay. The results will be scientifically revolutionary, and also provide a basis for commercialization in toy robotics and many other areas Strategy and Methodology The fulfillment of the project's aims involvse a significant amount of highly technical software development, which will be carried out by the two proposed new hires, together with the 6 junior members of the current OpenCog Hong Kong team. Figure 3 gives a high-level diagram illustrating the integration of DeSTIN and OpenCog, in the context of humanoid robotics. Figure 4 depicts more of the internals of the OpenCog architecture, as currently being used for animated agent control. From OpenCog's perspective, the robot and game character are essentially the same sort of entity — the difference lying in the critical "symbolic/subsymbolic converter" component that translates between the language of perception/action (DeSTIN states) and the language of abstract cognition (OpenCog's internal Atom representation). Figure S gives a deeper view of OpenCog/DeSTIN integration. Note that in this design, the bulk of the robot's "mind" lives on a laptop or PC assumed to be on the same wifi network as the robot. In a commercial product based on this design, a portion of the robot's mind may also live in the cloud, allowing sharing of knowledge between different robots. The processor on board the robot handles real-time action response, low-level sensory processing, and communication with the rest of the robot's mind via wifi. EFTA01103530  Simulator OFOGN COG Critic Hierarchy Perceptual Action Hierarchy Hierarchy DeSTIN Figure 3. High-Level Architecture of proposed system. Key components include the Hanson Robokind robot, the OpenCog cognition engine, the DeSTIN perception/action engine, and a novel "symbolic/subsymbolic convener translating between DeSTW's subsymbolic perception/action language and OpenCog's semantic-network language. \ \ ML Conceptual Comprehension PLN SCAN MOSES Blending C -omintage - m ory) Me Intentional Memory gittentIona) MernOrY CroceduraD Memory Crlorkl C :doodle) Unified Memory Knowledge Store / t r t NL Generation 1 Perception Action Selection and Control Simulation Eng as Dialogue Control OpenCog Prime I Intelligent character in game world Figure 4: Key components of the OpenCog integrated artificial general intelligence architecture, shown in the context of intelligent game character control. The proposed robotic application is similar, but with the DeSTIN perception/action component used as an intermediary between OpenCog and the robot, as robot perception/action is much subtler than its analogue in the virtual world. EFTA01103531  OpenCog AtomSpacc Intermediate Semantic Hierarchy concept node above the semantic hierarchy level representing laces. is a DeSTIN perception level representing enure heads reference hierarchy link reference input advice link Sevin visual patterns (e g. phrase node DeSTIN centroids) corresponding to the semantic perception node aligned on axis level 2 finked to "human perpendicular to rye mouth-note-eyes ants I reel I Inp• Imago aligned on axis perpendicular to SOW •4 04•04Pee. eye' axis n2.8 semantic nodes/links formed by pattern mining Ir sensors obot DeSTIN hierarchy food data to I:4571N semantic hierarchy provides probabilistic biasing to DeSTIN Figure S: An in-depth illustration of the "intermediate semantic hierarchy" referenced in Figure .3. In the context of face recognition, this shows the interfacing between DeSTIN and OpenCog's cognitive semantic network" knowledge representation, via means of a symbolic-subsymbolic translation layer that utilizes OpenCog's knowledge representation atoms but possesses DeSTIN's hierarchical structure. This unique interfacing layer is the central scientific novelty of the proposed project. Anticipated Outcomes and Impacts This project offers the potential to introduce a dramatic advance in artificial general intelligence and cognitive robotics. It will serve as a platform for further dramatic advances, in the form of ongoing R&D aimed at producing software enabling humanoid robots to achieve humanlike general intelligence beyond the early childhood level. Its successful completion is expected to have broad impact on the Al field, inspiring other researchers to pursue integrated cognitive architectures for intelligent agent control, and in general helping to revive research interest in the original, ambitious goals of the Al field. Concretely, in order to ensure this influence happens, we intend to publish at least three papers in high-impact journals summarizing the results of the project, along with making a highly-publicized release of the open-source code developed, and launching a series of YouTube videos showing the intelligent robot children in action. Presentations at appropriate conferences will also be done, including academic robotics and Al conferences (AAAI, IEEE) as well as futurist conferences such as the Singularity Summit, Humanity+, World Future Society, etc. While the current proposal is focused on pure research, we also intend to encourage the commercialization of the technology developed in the project, initially via collaboration with Hanson Robotics and Jetta (the Hong Kong firm that manufactures Hanson's robots) on the creation and marketing of intelligent robot toys. Hanson Robotics has carefully explored the business and technical aspects of this sort of product offering, but currently lacks the Al technology to make it work on their own. Of the $21 billion market for remote-control electronic toys, about $200 million consists of higher-end robotic EFTA01103532 devices costing $100 or more (including e.g. the Nao, smart drones like the Parrot, and the Kondo robot kits).1 At lower price points, ifs hard to draw the line between robot toys like RoboSapien and "mere" electronic remote control devices. Clearly the market for - $100 robot toys could be grown dramatically via the entrance of radically superior technology into the marketplace. One could imagine a commercial toy robot with an initial hardware cost of —$99, plus a monthly subscription fee of perhaps $4.99, the latter buying online access to OpenCog AGI servers supplying the robots with advanced intelligence. Beyond this, there are a number of possibilities for commercialization of the specific cognitive robotics technology expected to result from this project, including in: • The robotics industry. The advances in general intelligence, social awareness and emotional accessibility developed for robots will make them suitable to take on more roles in the service industry, among others. • The toy industry. With toys becoming increasingly sophisticated and electronic, our proposed software can be applied to drive the behavior of new electronic toys. • The consumer electronics industry. Consumer electronics such as tablet computers and smart phones could benefit greatly from being more intelligent, more responsive to users' emotions and more predictive of users' needs. And of course, the follow-on AGI development enabled by success in our project could have much broader commercial impact. We are also enthused about the broader social implications of advanced artificial general intelligence making its initial advent in the guise of friendly, childlike humanoid robots. In the future as AGI advances beyond the childlike level, human attitudes toward AGI may become complex and contentious; we believe the best path to an agreeable future is one in which people and early-stage AGIs have a relationship of mutual social and emotional understanding. Budget Please see separate budget spreadsheet. Timeline/Milestones Please see separate document References 1. B. Goertzel and C. Pennachin, Artificial General Intelligence. Springer, 2005. 2. (AGI-01) B. G. Stan Franklin and P. W. (Editors), Proceedings of First Conference on Artificial General Intelligence. IOS Press, 2008. 3. (AGI-02) P. H. Marcus Hutter and B. G. (Editors), Proceedings of Second Conference on Artificial General Intelligence. Atlantis Press, 2008. 4. N. C. (Editor), Human-Level Intelligence (Special Issue of Artificial Intelligence Magazine). AAAI, 2006. 5. B. Goertzel, "Opencog prime: A cognitive synergy based architecture for embodied artificial general intelligence," in Proceedings of ICCI-09, Hong Kong, 2009. 6. Arel, D. Rose, and T. Karnowski, "A deep learning architecture comprising homogeneous cortical circuits for scalable spatiotemporal pattern inference." NIPS 2009 Workshop on Deep Learning for Speech Recognition and Related Applications, Dec 2009. 7. Thomas P. Karnowski, Itamar Arel, Derek Rose: Deep Spatiotemporal Feature Learning with Application to Image Classification. ICMLA 2010: 883-888 8. Goertzel, Ben (2011). Integrating a Compositional Spatiotemporal Deep Learning Network with Symbolic Representation/Reasoning within an Integrative Cognitive Architecture via an 3 Figures via personal communication from Mark Tilden. founder & chief scientist of Wowee, maker of RoboSapien EFTA01103533  Intermediary Semantic Network. Proceedings of AAAI Symposium on Cognitive Systems, Arlington VA 9. Goertzel, Ben and Hugo de Garis. XIA-MAN: An Integrative, Extensible Architecture for Intelligent Humanoid Robotics. AAAI Symposium on Biologically-Inspired Cognitive Architectures, Washington DC, November 2008 10. Goertzel, Ben and Stephan Vladimir Bugaj. AGI Preschool: A Framework for Evaluating Early-Stage Human-like AGIs. Proceedings of the Second Conference on Artificial General Intelligence, Atlantis Press. 11. Sam Adams, Itmar Arel, Joscha Bach, Robert Coop, Rod Furlan, Ben Goertzel, J. Storrs Hall, Alexei Samsonovich, Matthias Scheutz, Matthew Schlesinger, Stuart C. Shapiro, John Sowa (2012). Mapping the Landscape of Human-Level Artificial General Intelligence. Al Magazine, Winter 2012. 12. P. Hayes and K. Ford., "Turing test considered harmful," IJCAI-14, 1995 13. Kurzweil, Ray (2005). The Singularity Is Near. Viking. 14. Breazeal, Cynthia (2002). Designing Sociable Robots. MIT Press. 15. Hanson D. "Bioinspired Robotics", chapter 16 in the book Biomimetics, ed. Yoseph Bar-Cohen, CRC Press, October 2005. 16. Hanson, David and V. White. (2004). "Converging the Capabilities of ElectroActive Polymer Artificial Muscles and the Requirements of Bio-inspired Robotics", Proc. SPIE's Electroactive Polymer Actuators and Devices Conf., San Diego 17. Samsonovich, A. V. (2010). Toward a unified catalog of implemented cognitive architectures (review). In Samsonovich, A. V., Johannsdottir, K. R., Chella, A., and Goertzel, B. (Eds.). Biologically Inspired Cognitive Architectures 2010: Proceedings of the First Annual Meeting of the BICA Society. Frontiers in Artificial Intelligence and Applications, vol. 221, pp. 195-244. Amsterdam, The Netherlands: IOS Press. ISSN 0922-6389. 18. Goertzel, Ben, Cassio Pennachin, Nil Geissweiller, Moshe Looks, Andre Senna, An Heljakka, Welter Silva, Carlos Lopes . An Integrative Methodology for Teaching Embodied Non-Linguistic Agents, Applied to Virtual Animals in Second Life, in Proceedings of the First AGI Conference, Ed. Wang et al, IOS Press In EFTA01103534