Janus: a Society of Agents Janus: a Society of Agents

In this report we describe the JANUS robot project in terms of the maxims followed at the various levels of construction. The project involves designing a two-armed robot which operates in an open system. To make this possible it must have exibility and heterogeneity in its architecture. The key ingredients of JANUS are presented in the form of seven fundamental principles. These principles give rise to a number of special design features, including reeective agents, a priori knowledge, concurrency, paralle-lism and adaptivity. The robot is constructed in a progressive and dynamic way: when a particular function is required, a simple agent that carries it out is programmed and it is incorporated easily into the team architecture. As example of the implementation of the ideas presented, we connne ourselves to the lowest, motor level, showing how a complex inverse kinematics func-tionality is built into the system using simple components.

[1]  K. Lorenz Die Rückseite des Spiegels : Versuch einer Naturgeschichte menschlichen Erkennens , 1973 .

[2]  Roy Featherstone,et al.  Position and Velocity Transformations Between Robot End-Effector Coordinates and Joint Angles , 1983 .

[3]  Beno Benhabib,et al.  A complete generalized solution to the inverse kinematics of robots , 1985, IEEE J. Robotics Autom..

[4]  M. Minsky The Society of Mind , 1986 .

[5]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[6]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[7]  O. G. Selfridge,et al.  Pandemonium: a paradigm for learning , 1988 .

[8]  V. Jagannathan,et al.  Blackboard Architectures and Applications , 1989 .

[9]  Randall Beer,et al.  Intelligence as Adaptive Behavior , 1990 .

[10]  Uwe Schnepf,et al.  Robot ethology: a proposal for the research into intelligent autonomous systems , 1991 .

[11]  Stewart W. Wilson,et al.  Robot Ethology: A Proposal for the Research into Intelligent Autonomous Systems , 1991 .

[12]  N. Hogan,et al.  Does the nervous system use equilibrium-point control to guide single and multiple joint movements? , 1992, The Behavioral and brain sciences.

[13]  Sridhar Mahadevan,et al.  Automatic Programming of Behavior-Based Robots Using Reinforcement Learning , 1991, Artif. Intell..

[14]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[15]  L. Steels The Artiicial Life Roots of Artiicial Intelligence , 1993 .

[16]  F. Smieja The Pandemonium System of Reeective Agents , 1993 .

[17]  Luc Steels,et al.  The Artificial Life Roots of Artificial Intelligence , 1994, Artif. Life.

[18]  Uwe Beyer,et al.  Learning from Examples, Agent Teams and the Concept of Reflection , 1996, Int. J. Pattern Recognit. Artif. Intell..