Learning Behavior Fusion Estimation from Demonstration

A critical challenge in robot learning from demonstration is the ability to map the behavior of the trainer onto the robot´s existing repertoire of basic/primitive capabilities. Following a behavior-based approach, we aim to express a teacher´s demonstration as a linear combination (or fusion) of the robot´s primitives. We treat this problem as a state estimation problem over the space of possible linear fusion weights. We consider this fusion state to be a model of the teacher´s control policy expressed with respect to the robot´s capabilities. Once estimated under various sensory preconditions, fusion state estimates are used as a coordination policy for online robot control to imitate the teacher´s decision making. A particle filter is used to infer fusion state from control commands demonstrated by the teacher and predicted by each primitive. The particle filter allows for inference under the ambiguity over a large space of likely fusion combinations and dynamic changes to the teacher´s policy over time. We present results of our approach in a simulated and real world environments with a Pioneer 3DX mobile robot