An Incremental Inverse Reinforcement Learning Approach for Motion Planning with Separated Path and Velocity Preferences

Abstract--Humans often demonstrate diverse behaviors due to their personal preferences, for instance, related to their individual execution style or personal margin for safety. In this paper, we consider the problem of integrating both path and velocity preferences into trajectory planning for robotic manipulators. We first learn reward functions that represent the user path and velocity preferences from kinesthetic demonstration. We then optimize the trajectory in two steps: first the path and then the velocity, to produce trajectories that adhere to both task requirements and user preferences. We demonstrate that our method is capable of generalizing such preferences to new scenarios. We implement our algorithm on a Franka Emika 7-DoF robot arm, and validate the functionality and flexibility of our approach in a user study. The results show that non-expert users are able to teach the robot their preferences with just a few iterations of feedback. A gentler breed of robots, "cobots", have "Stay close to the table surface", "Keep larger distance from the obstacle", and "Pass on the far side of the obstacle". A desirable trajectory not only meets the task constraints (e.g. Figure 1 illustrates how a user may demonstrate but also adheres to user preferences. Such preferences may a trajectory encoding multiple implicit preferences to correct vary between users, environments and tasks. It is infeasible the original robot plan. Manual programming is even more detrimental Peternel et al., 2014).