BayesRace: Learning to race autonomously using prior experience

Achin Jain, Matthew O’Kelly, Pratik Chaudhari, Manfred Morari
Proceedings of the 2020 Conference on Robot Learning, PMLR 155:1918-1929, 2021.

Abstract

Autonomous race cars require perception, estimation, planning, and control modules which work together asynchronously while driving at the limit of a vehicle’s handling capability. A fundamental challenge encountered in designing these software components lies in predicting the vehicle’s future state (e.g. position, orientation, and speed) with high accuracy. The root cause is the difficulty in identifying vehicle model parameters that capture the effects of lateral tire slip. We present a model-based planning and control framework for autonomous racing that significantly reduces the effort required in system identification and control design. Our approach alleviates the gap induced by simulation-based controller design by learning from on-board sensor measurements. A major focus of this work is empirical, thus, we demonstrate our contributions by experiments on validated 1:43 and 1:10 scale autonomous racing simulations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v155-jain21b, title = {BayesRace: Learning to race autonomously using prior experience}, author = {Jain, Achin and O'Kelly, Matthew and Chaudhari, Pratik and Morari, Manfred}, booktitle = {Proceedings of the 2020 Conference on Robot Learning}, pages = {1918--1929}, year = {2021}, editor = {Kober, Jens and Ramos, Fabio and Tomlin, Claire}, volume = {155}, series = {Proceedings of Machine Learning Research}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v155/jain21b/jain21b.pdf}, url = {https://proceedings.mlr.press/v155/jain21b.html}, abstract = {Autonomous race cars require perception, estimation, planning, and control modules which work together asynchronously while driving at the limit of a vehicle’s handling capability. A fundamental challenge encountered in designing these software components lies in predicting the vehicle’s future state (e.g. position, orientation, and speed) with high accuracy. The root cause is the difficulty in identifying vehicle model parameters that capture the effects of lateral tire slip. We present a model-based planning and control framework for autonomous racing that significantly reduces the effort required in system identification and control design. Our approach alleviates the gap induced by simulation-based controller design by learning from on-board sensor measurements. A major focus of this work is empirical, thus, we demonstrate our contributions by experiments on validated 1:43 and 1:10 scale autonomous racing simulations.} }
Endnote
%0 Conference Paper %T BayesRace: Learning to race autonomously using prior experience %A Achin Jain %A Matthew O’Kelly %A Pratik Chaudhari %A Manfred Morari %B Proceedings of the 2020 Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2021 %E Jens Kober %E Fabio Ramos %E Claire Tomlin %F pmlr-v155-jain21b %I PMLR %P 1918--1929 %U https://proceedings.mlr.press/v155/jain21b.html %V 155 %X Autonomous race cars require perception, estimation, planning, and control modules which work together asynchronously while driving at the limit of a vehicle’s handling capability. A fundamental challenge encountered in designing these software components lies in predicting the vehicle’s future state (e.g. position, orientation, and speed) with high accuracy. The root cause is the difficulty in identifying vehicle model parameters that capture the effects of lateral tire slip. We present a model-based planning and control framework for autonomous racing that significantly reduces the effort required in system identification and control design. Our approach alleviates the gap induced by simulation-based controller design by learning from on-board sensor measurements. A major focus of this work is empirical, thus, we demonstrate our contributions by experiments on validated 1:43 and 1:10 scale autonomous racing simulations.
APA
Jain, A., O’Kelly, M., Chaudhari, P. & Morari, M.. (2021). BayesRace: Learning to race autonomously using prior experience. Proceedings of the 2020 Conference on Robot Learning, in Proceedings of Machine Learning Research 155:1918-1929 Available from https://proceedings.mlr.press/v155/jain21b.html.

Related Material