First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Davydov, Alexander, Djeumou, Franck, Greiff, Marcus, Suminaka, Makoto, Thompson, Michael, Subosits, John, Lew, Thomas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915405239418880
author Davydov, Alexander
Djeumou, Franck
Greiff, Marcus
Suminaka, Makoto
Thompson, Michael
Subosits, John
Lew, Thomas
author_facet Davydov, Alexander
Djeumou, Franck
Greiff, Marcus
Suminaka, Makoto
Thompson, Michael
Subosits, John
Lew, Thomas
contents Combining data-driven models that adapt online and model predictive control (MPC) has enabled effective control of nonlinear systems. However, when deployed on unstable systems, online adaptation may not be fast enough to ensure reliable simultaneous learning and control. For example, a controller on a vehicle executing highly dynamic maneuvers--such as drifting to avoid an obstacle--may push the vehicle's tires to their friction limits, destabilizing the vehicle and allowing modeling errors to quickly compound and cause a loss of control. To address this challenge, we present an active information gathering framework for identifying vehicle dynamics as quickly as possible. We propose an expressive vehicle dynamics model that leverages Bayesian last-layer meta-learning to enable rapid online adaptation. The model's uncertainty estimates are used to guide informative data collection and quickly improve the model prior to deployment. Dynamic drifting experiments on a Toyota Supra show that (i) the framework enables reliable control of a vehicle at the edge of stability, (ii) online adaptation alone may not suffice for zero-shot control and can lead to undesirable transient errors or spin-outs, and (iii) active data collection helps achieve reliable performance.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00107
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling
Davydov, Alexander
Djeumou, Franck
Greiff, Marcus
Suminaka, Makoto
Thompson, Michael
Subosits, John
Lew, Thomas
Robotics
Machine Learning
Systems and Control
Combining data-driven models that adapt online and model predictive control (MPC) has enabled effective control of nonlinear systems. However, when deployed on unstable systems, online adaptation may not be fast enough to ensure reliable simultaneous learning and control. For example, a controller on a vehicle executing highly dynamic maneuvers--such as drifting to avoid an obstacle--may push the vehicle's tires to their friction limits, destabilizing the vehicle and allowing modeling errors to quickly compound and cause a loss of control. To address this challenge, we present an active information gathering framework for identifying vehicle dynamics as quickly as possible. We propose an expressive vehicle dynamics model that leverages Bayesian last-layer meta-learning to enable rapid online adaptation. The model's uncertainty estimates are used to guide informative data collection and quickly improve the model prior to deployment. Dynamic drifting experiments on a Toyota Supra show that (i) the framework enables reliable control of a vehicle at the edge of stability, (ii) online adaptation alone may not suffice for zero-shot control and can lead to undesirable transient errors or spin-outs, and (iii) active data collection helps achieve reliable performance.
title First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling
topic Robotics
Machine Learning
Systems and Control
url https://arxiv.org/abs/2411.00107