Generalizing Behavior Trees and Motion-Generator (BTMG) Policy Representation for Robotic Tasks Over Scenario Parameters
We propose a generalisation of a behaviour tree and motiongenerator based robot arm policy representation for learning and solving tasks such as contact-rich tasks like peg insertion or pushing an object. We use planning to generate skill sequences needed to execute these tasks and rely on reinforcement learning to obtain parameters of the policy. We assume gaussian processes as a suitable method
