ABNet: Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning

Wei Xiao, Tsun-Hsuan Wang, Chuang Gan, Daniela Rus
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:68472-68490, 2025.

Abstract

Safe learning is central to AI-enabled robots where a single failure may lead to catastrophic results. Existing safe learning methods are not scalable, inefficient and hard to train, and tend to generate unstable signals under noisy inputs that are challenging to be deployed for robots. To address these challenges, we propose Adaptive explicit-Barrier Net (ABNet) in which barriers explicitly show up in the closed-form model that guarantees safety. The ABNet has the potential to incrementally scale toward larger safe foundation models. Each head of ABNet could learn safe control policies from different features and focuses on specific part of the observation. In this way, we do not need to directly construct a large model for complex tasks, which significantly facilitates the training of the model while ensuring its stable output. Most importantly, we can still formally prove the safety guarantees of the ABNet. We demonstrate the efficiency and strength of ABNet in 2D robot obstacle avoidance, safe robot manipulation, and vision-based end-to-end autonomous driving, with results showing much better robustness and guarantees over existing models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-xiao25f, title = {{ABN}et: Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning}, author = {Xiao, Wei and Wang, Tsun-Hsuan and Gan, Chuang and Rus, Daniela}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {68472--68490}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/xiao25f/xiao25f.pdf}, url = {https://proceedings.mlr.press/v267/xiao25f.html}, abstract = {Safe learning is central to AI-enabled robots where a single failure may lead to catastrophic results. Existing safe learning methods are not scalable, inefficient and hard to train, and tend to generate unstable signals under noisy inputs that are challenging to be deployed for robots. To address these challenges, we propose Adaptive explicit-Barrier Net (ABNet) in which barriers explicitly show up in the closed-form model that guarantees safety. The ABNet has the potential to incrementally scale toward larger safe foundation models. Each head of ABNet could learn safe control policies from different features and focuses on specific part of the observation. In this way, we do not need to directly construct a large model for complex tasks, which significantly facilitates the training of the model while ensuring its stable output. Most importantly, we can still formally prove the safety guarantees of the ABNet. We demonstrate the efficiency and strength of ABNet in 2D robot obstacle avoidance, safe robot manipulation, and vision-based end-to-end autonomous driving, with results showing much better robustness and guarantees over existing models.} }
Endnote
%0 Conference Paper %T ABNet: Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning %A Wei Xiao %A Tsun-Hsuan Wang %A Chuang Gan %A Daniela Rus %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-xiao25f %I PMLR %P 68472--68490 %U https://proceedings.mlr.press/v267/xiao25f.html %V 267 %X Safe learning is central to AI-enabled robots where a single failure may lead to catastrophic results. Existing safe learning methods are not scalable, inefficient and hard to train, and tend to generate unstable signals under noisy inputs that are challenging to be deployed for robots. To address these challenges, we propose Adaptive explicit-Barrier Net (ABNet) in which barriers explicitly show up in the closed-form model that guarantees safety. The ABNet has the potential to incrementally scale toward larger safe foundation models. Each head of ABNet could learn safe control policies from different features and focuses on specific part of the observation. In this way, we do not need to directly construct a large model for complex tasks, which significantly facilitates the training of the model while ensuring its stable output. Most importantly, we can still formally prove the safety guarantees of the ABNet. We demonstrate the efficiency and strength of ABNet in 2D robot obstacle avoidance, safe robot manipulation, and vision-based end-to-end autonomous driving, with results showing much better robustness and guarantees over existing models.
APA
Xiao, W., Wang, T., Gan, C. & Rus, D.. (2025). ABNet: Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:68472-68490 Available from https://proceedings.mlr.press/v267/xiao25f.html.

Related Material