2022/11/28 by Paolo Torrado, Torrado, Paolo, Boling Yang +3
Engineering · Computer Science · #Advanced Control Systems Optimization #Robot Manipulation and Learning #Reinforcement Learning in Robotics
paper · pdf · doi:10.48550/arxiv.2211.15752
In this paper, we study the implementation of a model predictive controller (MPC) for the task of object manipulation in a highly uncertain environment (e.g., picking objects from a semi-flexible array of densely packed bins). As a real-time perception-driven feedback controller, MPC is robust to the uncertainties in this environment. However, our experiment shows MPC cannot control a robot to complete a sequence of motions in a heavily occluded environment due to its myopic nature. It will benefit from adding a high-level policy that adaptively adjusts the optimization problem for MPC.