Reconfigurable Behavior Trees: Towards an Executive Framework Meeting High-level Decision Making and Control Layer Features

Behavior Trees constitute a widespread AI tool which has been successfully\nspun out in robotics. Their advantages include simplicity, modularity, and\nreusability of code. However, Behavior Trees remain a high-level decision\nmaking engine; control features cannot be easily integrated. This paper\nproposes the Reconfigurable Behavior Trees (RBTs), an extension of the\ntraditional BTs that considers physical constraints from the robotic\nenvironment in the decision making process. We endow RBTs with continuous\nsensory information that permits the online monitoring of the task execution.\nThe resulting stimulus-driven architecture is capable of dynamically handling\nchanges in the executive context while keeping the execution time low. The\nproposed framework is evaluated on a set of robotic experiments. The results\nshow that RBTs are a promising approach for robotic task representation,\nmonitoring, and execution.\n