Active Inference and Behavior Trees for Reactive Action Planning and Execution in Robotics

We propose a hybrid combination of active inference and behavior trees (BTs) for reactive action planning and execution in dynamic environments, showing how robotic tasks can be formulated as a free-energy minimization problem. The proposed approach allows to handle partially observable initial states and improves the robustness of classical BTs against unexpected contingencies while at the same time reducing the number of nodes in a tree. In this work, the general nominal behavior is specified offline through BTs, where a new type of leaf node, the prior node, is introduced to specify the desired state to be achieved rather than an action to be executed as typically done in BTs. The decision of which action to execute to reach the desired state is performed online through active inference. This results in the combination of continual online planning and hierarchical deliberation, that is an agent is able to follow a predefined offline plan while still being able to locally adapt and take autonomous decisions at runtime. The properties of our algorithm, such as convergence and robustness, are thoroughly analyzed, and the theoretical results are validated in two different mobile manipulators performing similar tasks, both in a simulated and real retail environment.