Adaptive Model Predictive Control by Learning Classifiers

03/13/2022
by   Rel Guzman, et al.
9

Stochastic model predictive control has been a successful and robust control framework for many robotics tasks where the system dynamics model is slightly inaccurate or in the presence of environment disturbances. Despite the successes, it is still unclear how to best adjust control parameters to the current task in the presence of model parameter uncertainty and heteroscedastic noise. In this paper, we propose an adaptive MPC variant that automatically estimates control and model parameters by leveraging ideas from Bayesian optimization (BO) and the classical expected improvement acquisition function. We leverage recent results showing that BO can be formulated as a density ratio estimation which can be efficiently approximated by simply learning a classifier. This is then integrated into a model predictive path integral control framework yielding robust controllers for a variety of challenging robotics tasks. We demonstrate the approach on classical control problems under model uncertainty and robotics manipulation tasks.

READ FULL TEXT
research
03/01/2022

Bayesian Optimisation for Robust Model Predictive Control under Model Parameter Uncertainty

We propose an adaptive optimisation approach for tuning stochastic model...
research
04/16/2021

Adaptive Robust Model Predictive Control with Matched and Unmatched Uncertainty

We propose a learning-based robust predictive control algorithm that can...
research
10/01/2020

Heteroscedastic Bayesian Optimisation for Stochastic Model Predictive Control

Model predictive control (MPC) has been successful in applications invol...
research
02/18/2020

DISCO: Double Likelihood-free Inference Stochastic Control

Accurate simulation of complex physical systems enables the development,...
research
03/07/2022

Learning Solution Manifolds for Control Problems via Energy Minimization

A variety of control tasks such as inverse kinematics (IK), trajectory o...
research
08/20/2021

Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control

In this paper we aim to provide analysis and insights (often based on vi...
research
10/11/2017

Uncertainty Averse Pushing with Model Predictive Path Integral Control

Planning robust robot manipulation requires good forward models that ena...

Please sign up or login with your details

Forgot password? Click here to reset