Tractable Stochastic Hybrid Model Predictive Control using Gaussian Processes for Repetitive Tasks in Unseen Environments
By: Leroy D'Souza, Yash Vardhan Pant, Sebastian Fischmeister
Potential Business Impact:
Helps robots learn and move better.
Improving the predictive accuracy of a dynamics model is crucial to obtaining good control performance and safety from Model Predictive Controllers (MPC). One approach involves learning unmodelled (residual) dynamics, in addition to nominal models derived from first principles. Varying residual models across an environment manifest as modes of a piecewise residual (PWR) model that requires a) identifying how modes are distributed across the environment and b) solving a computationally intensive Mixed Integer Nonlinear Program (MINLP) problem for control. We develop an iterative mapping algorithm capable of predicting time-varying mode distributions. We then develop and solve two tractable approximations of the MINLP to combine with the predictor in closed-loop to solve the overall control problem. In simulation, we first demonstrate how the approximations improve performance by 4-18% in comparison to the MINLP while achieving significantly lower computation times (upto 250x faster). We then demonstrate how the proposed mapping algorithm incrementally improves controller performance (upto 3x) over multiple iterations of a trajectory tracking control task even when the mode distributions change over time.
Similar Papers
Model Predictive Control via Probabilistic Inference: A Tutorial
Robotics
Helps robots learn better and faster.
Model Predictive Control with High-Probability Safety Guarantee for Nonlinear Stochastic Systems
Systems and Control
Keeps robots safe from making mistakes.
Physics-informed Gaussian Processes for Model Predictive Control of Nonlinear Systems
Optimization and Control
Teaches robots to follow instructions perfectly.