Correcting Nominal Models with Learned Residuals for Real-Time Control - Robotics Institute Carnegie Mellon University

MSR Thesis Defense

July

29
Tue
Si Heng Teng MSR Student Robotics Institute,
Carnegie Mellon University
Tuesday, July 29
9:30 am to 10:30 am
GHC 6501
Zoom Link Button
Correcting Nominal Models with Learned Residuals for Real-Time Control
Abstract:
Car-like robots are mechanically simple and dynamically stable, making them well-suited for applications such as inspections, surveillance, and search-and-rescue operations. Given a model of the robot’s dynamics, model predictive control (MPC) plans optimal actions with specified constraints. The performance of MPC is limited by inaccuracies in the underlying system model – high fidelity models are complex and brittle, while simple models trade accuracy for computational tractability.
This work presents a hybrid control framework that corrects predictions from a low-dimensional kinematic model through a data-driven residual network, termed the Corrective Residual Network (CRN). CRN significantly reduces model errors compared to the nominal model. CRN is integrated with MPC in a proposed algorithm called Corrective Sequential Linear-Quadratic MPC (CSLQ-MPC). CSLQ-MPC demonstrates strong performance and robustness towards model mismatch, including in scenarios with incorrect model parameters given to the nominal model.
Committee:
Dr. Aaron Johnson (advisor)
Dr. Wenshan Wang
Samuel Triest
Meeting ID: 785 031 7973 | Passcode: 54321