Autonomous Acquisition of Behavior Trees for Robot Control

Behavior trees (BT) are a popular control architecture in the computer game industry, and have been more recently applied in robotics. One open question is how can intelligent agents/robots autonomously acquire their behavior trees for task level control? In contrast with existing approaches that either refine an initially given BT, or directly build the BT based on human feedback/demonstration, we leverage reinforcement learning (RL) that allows robots to autonomously learn control policies by repeated task interaction, but often expressed in a language more difficult to interpret than BTs. The learned control policy is then converted to a behavior tree via our proposed decanonicalization algorithm. The feasibility of this idea is based on a proposed notion of canonical behavior trees (CBT). In particular, we show (1) CBTs are sufficiently expressive to capture RL control policies, and (2) that RL can be independent of an optimal behavior permutation, despite the BT convention of left-to-right priority, thus obviating the need for a combinatorial search. Two evaluation domains help illustrate our approach.