Analogic Models for Robot Programming

Planning robot movements in an unstructured environment is investigated from the point of view of common sense reasoning as the simulation of a complex dynamical system. We first show how motor redundancy can be solved by simulating passive motion (what we call Passive Motion Paradigm). We then extend this concept in terms of Abstract Force Fields, that allow expression of a variety of problems in addition to trajectory formation (force/position control, obstacle avoidance, concurrent tasks, etc.). Furthermore, we define the notion of Hybrid Motor Schema as the composite ensemble of an analogic component (which consists of the “mental” simulation of model dynamics) and a symbolic component (which contains rules and methods for instantiating the analogic component in a given context: goal, environment, expectations, constraints, ..). The paper then describes in more detail two specific analogic models in motion planning. The first is a connectionist formulation of motor planning for a redundant anthropomorphic structure (M - nets). The second is a general framework for planning sequences of actions for assembling objects. Simulation results of preliminary implementations are presented.

[1]  Luc Steels Steps towards Common Sense , 1988, ECAI.

[2]  Daniel Bullock,et al.  Neural dynamics of planned arm movements: emergent invariants and speed-accuracy properties during trajectory formation , 1988 .

[3]  P. Johnson-Laird Mental models , 1989 .

[4]  Agostino Poggi,et al.  Integrating Spatio-Temporal Knowledge: A Hybrid Approach , 1988, ECAI.

[5]  Michael A. Wesley,et al.  AUTOPASS: An Automatic Programming System for Computer Controlled Mechanical Assembly , 1977, IBM J. Res. Dev..

[6]  Ferdinando A. Mussa-Ivaldi,et al.  The role of physical constraints in natural and artifical manipulation , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[7]  Brian V. Funt,et al.  Analogical Modes of Reasoning and Process Modeling , 1983, Computer.

[8]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[9]  Michael I. Jordan Supervised learning and systems with excess degrees of freedom , 1988 .

[10]  Robin J. Popplestone,et al.  RAPT, A Language for Describing Assemblies , 1978 .

[11]  Giuseppe Marino,et al.  Motor Knowledge Representation , 1985, IJCAI.

[12]  Giuseppe Marino,et al.  Chapter 4 nem: a language for the representation of motor knowledge , 1986 .

[13]  Michael Kuperstein,et al.  Adaptive visual-motor coordination in multijoint robots using parallel architecture , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.