Surrogate Assisted Generation of Human-Robot Interaction Scenarios

Varun Bhatt, Heramb Nemlekar, Matthew Christopher Fontaine, Bryon Tjanaka, Hejia Zhang, Ya-Chuan Hsu, Stefanos Nikolaidis
Proceedings of The 7th Conference on Robot Learning, PMLR 229:513-539, 2023.

Abstract

As human-robot interaction (HRI) systems advance, so does the difficulty of evaluating and understanding the strengths and limitations of these systems in different environments and with different users. To this end, previous methods have algorithmically generated diverse scenarios that reveal system failures in a shared control teleoperation task. However, these methods require directly evaluating generated scenarios by simulating robot policies and human actions. The computational cost of these evaluations limits their applicability in more complex domains. Thus, we propose augmenting scenario generation systems with surrogate models that predict both human and robot behaviors. In the shared control teleoperation domain and a more complex shared workspace collaboration task, we show that surrogate assisted scenario generation efficiently synthesizes diverse datasets of challenging scenarios. We demonstrate that these failures are reproducible in real-world interactions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-bhatt23a, title = {Surrogate Assisted Generation of Human-Robot Interaction Scenarios}, author = {Bhatt, Varun and Nemlekar, Heramb and Fontaine, Matthew Christopher and Tjanaka, Bryon and Zhang, Hejia and Hsu, Ya-Chuan and Nikolaidis, Stefanos}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {513--539}, 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/bhatt23a/bhatt23a.pdf}, url = {https://proceedings.mlr.press/v229/bhatt23a.html}, abstract = {As human-robot interaction (HRI) systems advance, so does the difficulty of evaluating and understanding the strengths and limitations of these systems in different environments and with different users. To this end, previous methods have algorithmically generated diverse scenarios that reveal system failures in a shared control teleoperation task. However, these methods require directly evaluating generated scenarios by simulating robot policies and human actions. The computational cost of these evaluations limits their applicability in more complex domains. Thus, we propose augmenting scenario generation systems with surrogate models that predict both human and robot behaviors. In the shared control teleoperation domain and a more complex shared workspace collaboration task, we show that surrogate assisted scenario generation efficiently synthesizes diverse datasets of challenging scenarios. We demonstrate that these failures are reproducible in real-world interactions.} }
Endnote
%0 Conference Paper %T Surrogate Assisted Generation of Human-Robot Interaction Scenarios %A Varun Bhatt %A Heramb Nemlekar %A Matthew Christopher Fontaine %A Bryon Tjanaka %A Hejia Zhang %A Ya-Chuan Hsu %A Stefanos Nikolaidis %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-bhatt23a %I PMLR %P 513--539 %U https://proceedings.mlr.press/v229/bhatt23a.html %V 229 %X As human-robot interaction (HRI) systems advance, so does the difficulty of evaluating and understanding the strengths and limitations of these systems in different environments and with different users. To this end, previous methods have algorithmically generated diverse scenarios that reveal system failures in a shared control teleoperation task. However, these methods require directly evaluating generated scenarios by simulating robot policies and human actions. The computational cost of these evaluations limits their applicability in more complex domains. Thus, we propose augmenting scenario generation systems with surrogate models that predict both human and robot behaviors. In the shared control teleoperation domain and a more complex shared workspace collaboration task, we show that surrogate assisted scenario generation efficiently synthesizes diverse datasets of challenging scenarios. We demonstrate that these failures are reproducible in real-world interactions.
APA
Bhatt, V., Nemlekar, H., Fontaine, M.C., Tjanaka, B., Zhang, H., Hsu, Y. & Nikolaidis, S.. (2023). Surrogate Assisted Generation of Human-Robot Interaction Scenarios. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:513-539 Available from https://proceedings.mlr.press/v229/bhatt23a.html.

Related Material