Behavior-Based Primitives for Articulated Control

Abstract

Our previous work has demonstrated how biologicallyinspired behaviors can serve as an effective substrate for control, representation, and learning in mobile robots and multi-robot systems, in order to generate adaptive individual and group behavior. In this paper, we expand the behavior-based approach to the domain of manipulator control, and demonstrate first results in applying biological inspiration to a 20 degree-offreedom humanoid dynamical torso simulation. 1. Introduction Behavior-based systems take inspiration from biology, ethology, and neuroscience, in order to construct controllers for agents situated in noisy and dynamic environments (Matari'c 1997). Behaviors impose a distributed, bottom-up approach to control, which eliminates bottlenecks and enables emergent functionality (Steels 1994). Aside from its pragmatic role in achieving distributed, real-time control in robotics, the behavior-based framework has also been used to model and implement simulations of biological s...