Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy

Haimin Hu, Zixu Zhang, Kensuke Nakamura, Andrea Bajcsy, Jaime Fernández Fisac
Proceedings of The 7th Conference on Robot Learning, PMLR 229:3830-3850, 2023.

Abstract

An outstanding challenge for the widespread deployment of robotic systems like autonomous vehicles is ensuring safe interaction with humans without sacrificing performance. Existing safety methods often neglect the robot’s ability to learn and adapt at runtime, leading to overly conservative behavior. This paper proposes a new closed-loop paradigm for synthesizing safe control policies that explicitly account for the robot’s evolving uncertainty and its ability to quickly respond to future scenarios as they arise, by jointly considering the physical dynamics and the robot’s learning algorithm. We leverage adversarial reinforcement learning for tractable safety analysis under high-dimensional learning dynamics and demonstrate our framework’s ability to work with both Bayesian belief propagation and implicit learning through large pre-trained neural trajectory predictors.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-hu23b, title = {Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy}, author = {Hu, Haimin and Zhang, Zixu and Nakamura, Kensuke and Bajcsy, Andrea and Fisac, Jaime Fern\'{a}ndez}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {3830--3850}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/hu23b/hu23b.pdf}, url = {https://proceedings.mlr.press/v229/hu23b.html}, abstract = {An outstanding challenge for the widespread deployment of robotic systems like autonomous vehicles is ensuring safe interaction with humans without sacrificing performance. Existing safety methods often neglect the robot’s ability to learn and adapt at runtime, leading to overly conservative behavior. This paper proposes a new closed-loop paradigm for synthesizing safe control policies that explicitly account for the robot’s evolving uncertainty and its ability to quickly respond to future scenarios as they arise, by jointly considering the physical dynamics and the robot’s learning algorithm. We leverage adversarial reinforcement learning for tractable safety analysis under high-dimensional learning dynamics and demonstrate our framework’s ability to work with both Bayesian belief propagation and implicit learning through large pre-trained neural trajectory predictors.} }
Endnote
%0 Conference Paper %T Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy %A Haimin Hu %A Zixu Zhang %A Kensuke Nakamura %A Andrea Bajcsy %A Jaime Fernández Fisac %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-hu23b %I PMLR %P 3830--3850 %U https://proceedings.mlr.press/v229/hu23b.html %V 229 %X An outstanding challenge for the widespread deployment of robotic systems like autonomous vehicles is ensuring safe interaction with humans without sacrificing performance. Existing safety methods often neglect the robot’s ability to learn and adapt at runtime, leading to overly conservative behavior. This paper proposes a new closed-loop paradigm for synthesizing safe control policies that explicitly account for the robot’s evolving uncertainty and its ability to quickly respond to future scenarios as they arise, by jointly considering the physical dynamics and the robot’s learning algorithm. We leverage adversarial reinforcement learning for tractable safety analysis under high-dimensional learning dynamics and demonstrate our framework’s ability to work with both Bayesian belief propagation and implicit learning through large pre-trained neural trajectory predictors.
APA
Hu, H., Zhang, Z., Nakamura, K., Bajcsy, A. & Fisac, J.F.. (2023). Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:3830-3850 Available from https://proceedings.mlr.press/v229/hu23b.html.

Related Material