Decision boundary learning for safe vision-based navigation via Hamilton-Jacobi reachability analysis and support vector machine

Tara Toufighi, Minh Bui, Rakesh Shrestha, Mo Chen
Proceedings of the 6th Annual Learning for Dynamics & Control Conference, PMLR 242:440-452, 2024.

Abstract

We develop a self-supervised learning method that can predict safe and unsafe high-level waypoints for robot navigation in the form of a decision boundary given solely a RGB image without knowledge of a prior map. To provide the theoretical basis for such prediction, we use a Hamilton-Jacobi reachability analysis, a formal verification method, as the oracle for labeling training datasets. Given the labeled data, our neural network learn the coefficients of a decision boundary via a soft-margin Support Vector Machine loss function to classify safe and unsafe system states. We experimentally show that our method is generalizable and generates safety decision boundaries in unseen indoor environments. Our method advantages are its explainability and accurate safety prediction, which is important for safety-critical systems. Finally, we demonstrate our method via experiments where we showcase the learning-based safe decision boundary estimation that employs monocular RGB images, and current linear speed.

Cite this Paper

BibTeX
@InProceedings{pmlr-v242-toufighi24a, title = {Decision boundary learning for safe vision-based navigation via {H}amilton-{J}acobi reachability analysis and support vector machine}, author = {Toufighi, Tara and Bui, Minh and Shrestha, Rakesh and Chen, Mo}, booktitle = {Proceedings of the 6th Annual Learning for Dynamics & Control Conference}, pages = {440--452}, year = {2024}, editor = {Abate, Alessandro and Cannon, Mark and Margellos, Kostas and Papachristodoulou, Antonis}, volume = {242}, series = {Proceedings of Machine Learning Research}, month = {15--17 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v242/toufighi24a/toufighi24a.pdf}, url = {https://proceedings.mlr.press/v242/toufighi24a.html}, abstract = {We develop a self-supervised learning method that can predict safe and unsafe high-level waypoints for robot navigation in the form of a decision boundary given solely a RGB image without knowledge of a prior map. To provide the theoretical basis for such prediction, we use a Hamilton-Jacobi reachability analysis, a formal verification method, as the oracle for labeling training datasets. Given the labeled data, our neural network learn the coefficients of a decision boundary via a soft-margin Support Vector Machine loss function to classify safe and unsafe system states. We experimentally show that our method is generalizable and generates safety decision boundaries in unseen indoor environments. Our method advantages are its explainability and accurate safety prediction, which is important for safety-critical systems. Finally, we demonstrate our method via experiments where we showcase the learning-based safe decision boundary estimation that employs monocular RGB images, and current linear speed.} }
Endnote
%0 Conference Paper %T Decision boundary learning for safe vision-based navigation via Hamilton-Jacobi reachability analysis and support vector machine %A Tara Toufighi %A Minh Bui %A Rakesh Shrestha %A Mo Chen %B Proceedings of the 6th Annual Learning for Dynamics & Control Conference %C Proceedings of Machine Learning Research %D 2024 %E Alessandro Abate %E Mark Cannon %E Kostas Margellos %E Antonis Papachristodoulou %F pmlr-v242-toufighi24a %I PMLR %P 440--452 %U https://proceedings.mlr.press/v242/toufighi24a.html %V 242 %X We develop a self-supervised learning method that can predict safe and unsafe high-level waypoints for robot navigation in the form of a decision boundary given solely a RGB image without knowledge of a prior map. To provide the theoretical basis for such prediction, we use a Hamilton-Jacobi reachability analysis, a formal verification method, as the oracle for labeling training datasets. Given the labeled data, our neural network learn the coefficients of a decision boundary via a soft-margin Support Vector Machine loss function to classify safe and unsafe system states. We experimentally show that our method is generalizable and generates safety decision boundaries in unseen indoor environments. Our method advantages are its explainability and accurate safety prediction, which is important for safety-critical systems. Finally, we demonstrate our method via experiments where we showcase the learning-based safe decision boundary estimation that employs monocular RGB images, and current linear speed.
APA
Toufighi, T., Bui, M., Shrestha, R. & Chen, M.. (2024). Decision boundary learning for safe vision-based navigation via Hamilton-Jacobi reachability analysis and support vector machine. Proceedings of the 6th Annual Learning for Dynamics & Control Conference, in Proceedings of Machine Learning Research 242:440-452 Available from https://proceedings.mlr.press/v242/toufighi24a.html.

Related Material