Combining Planning and Learning of Behavior Trees for Robotic Assembly
This work addresses the high programming cost and limited flexibility in robotics for unpredictable environments, offering an incremental improvement in policy generation.
The paper tackles the problem of automatically generating Behavior Trees for robotic assembly by combining automated planning with machine learning via Genetic Programming, resulting in a method that outperforms both base approaches on various assembly tasks and transfers to real systems without additional training.
Industrial robots can solve very complex tasks in controlled environments, but modern applications require robots able to operate in unpredictable surroundings as well. An increasingly popular reactive policy architecture in robotics is Behavior Trees but as with other architectures, programming time still drives cost and limits flexibility. There are two main branches of algorithms to generate policies automatically, automated planning and machine learning, both with their own drawbacks. We propose a method for generating Behavior Trees using a Genetic Programming algorithm and combining the two branches by taking the result of an automated planner and inserting it into the population. Experimental results confirm that the proposed method of combining planning and learning performs well on a variety of robotic assembly problems and outperforms both of the base methods used separately. We also show that this type of high level learning of Behavior Trees can be transferred to a real system without further training.