A Distributed Adaptive Control Architecture for Autonomous Agents
Bruce L. Digney · 1995
Recently considerable interest in behavior-based robots has been generated by industrial, space and defence related activities. Such indepen-dent robots are envisioned to perform tasks where safety or economic factors prevent direct hu-man control and communication difficulties pre-vent easy remote control. Although many suc-cesses have been reported using behavior-based robots with prespecified skills and behaviors, it is clear that there are many more applications where learning and adaptation are required. In this research, a method whereby reinforcement learning can be combined into a behavior based control system is presented. Skills and behav-iors which are impossible or impractical to em-bed as predetermined responses are learned by the robot through exploration and discovery using a temporal difference reinforcement learning tech-nique. This results in what is referred to as a Distributed Adaptive Control System (DACS), effect the robot’s artificial nervous system. Pre-sented in this paper is only a general overview of the DACS architecture with many details ne-glected. A DACS is then developed for a simu-lated quadruped mobile robot. The locomotion and body coordination behavioral levels are iso-lated and evaluated. 1