Policy Search for Model Predictive Control with Application to Agile Drone Flight
This work addresses the challenge of merging learning and control for robotics, specifically in agile drone flight, representing an incremental advancement by integrating existing paradigms.
The authors tackled the problem of combining policy search and model predictive control (MPC) for robot control by using policy search to automatically choose high-level decision variables for MPC, resulting in a novel framework. They validated it on agile drone flight through fast-moving gates, achieving robust and real-time control performance in simulation and real-world experiments.
Policy Search and Model Predictive Control~(MPC) are two different paradigms for robot control: policy search has the strength of automatically learning complex policies using experienced data, while MPC can offer optimal control performance using models and trajectory optimization. An open research question is how to leverage and combine the advantages of both approaches. In this work, we provide an answer by using policy search for automatically choosing high-level decision variables for MPC, which leads to a novel policy-search-for-model-predictive-control framework. Specifically, we formulate the MPC as a parameterized controller, where the hard-to-optimize decision variables are represented as high-level policies. Such a formulation allows optimizing policies in a self-supervised fashion. We validate this framework by focusing on a challenging problem in agile drone flight: flying a quadrotor through fast-moving gates. Experiments show that our controller achieves robust and real-time control performance in both simulation and the real world. The proposed framework offers a new perspective for merging learning and control.