English

Adaptive Model Predictive Control by Learning Classifiers

Robotics 2022-04-07 v2 Artificial Intelligence Machine Learning Systems and Control Systems and Control

Abstract

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 optimisation (BO) and the classical expected improvement acquisition function. We leverage recent results showing that BO can be reformulated via 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.

Keywords

Cite

@article{arxiv.2203.06783,
  title  = {Adaptive Model Predictive Control by Learning Classifiers},
  author = {Rel Guzman and Rafael Oliveira and Fabio Ramos},
  journal= {arXiv preprint arXiv:2203.06783},
  year   = {2022}
}

Comments

To appear in the 4th Annual Learning for Dynamics & Control Conference (L4DC) 2022