Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed Racing

Jonathan DeCastro, Andrew Silva, Deepak Gopinath, Emily Sumner, Thomas Matrai Balch, Laporsha Dees, Guy Rosman
Proceedings of The 8th Conference on Robot Learning, PMLR 270:2599-2628, 2025.

Abstract

Tight coordination is required for effective human-robot teams in domains involving fast dynamics and tactical decisions, such as multi-car racing. In such settings, robot teammates must react to cues of a human teammate’s tactical objective to assist in a way that is consistent with the objective (e.g., navigating left or right around an obstacle). To address this challenge, we present _Dream2Assist_, a framework that combines a rich world model able to infer human objectives and value functions, and an assistive agent that provides appropriate expert assistance to a given human teammate. Our approach builds on a recurrent state space model to explicitly infer human intents, enabling the assistive agent to select actions that align with the human and enabling a fluid teaming interaction. We demonstrate our approach in a high-speed racing domain with a population of synthetic human drivers pursuing mutually exclusive objectives, such as “stay-behind” and “overtake”. We show that the combined human-robot team, when blending its actions with those of the human, outperforms synthetic humans alone and several baseline assistance strategies, and that intent-conditioning enables adherence to human preferences during task execution, leading to improved performance while satisfying the human’s objective.

Cite this Paper


BibTeX
@InProceedings{pmlr-v270-decastro25a, title = {Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed Racing}, author = {DeCastro, Jonathan and Silva, Andrew and Gopinath, Deepak and Sumner, Emily and Balch, Thomas Matrai and Dees, Laporsha and Rosman, Guy}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {2599--2628}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/decastro25a/decastro25a.pdf}, url = {https://proceedings.mlr.press/v270/decastro25a.html}, abstract = {Tight coordination is required for effective human-robot teams in domains involving fast dynamics and tactical decisions, such as multi-car racing. In such settings, robot teammates must react to cues of a human teammate’s tactical objective to assist in a way that is consistent with the objective (e.g., navigating left or right around an obstacle). To address this challenge, we present _Dream2Assist_, a framework that combines a rich world model able to infer human objectives and value functions, and an assistive agent that provides appropriate expert assistance to a given human teammate. Our approach builds on a recurrent state space model to explicitly infer human intents, enabling the assistive agent to select actions that align with the human and enabling a fluid teaming interaction. We demonstrate our approach in a high-speed racing domain with a population of synthetic human drivers pursuing mutually exclusive objectives, such as “stay-behind” and “overtake”. We show that the combined human-robot team, when blending its actions with those of the human, outperforms synthetic humans alone and several baseline assistance strategies, and that intent-conditioning enables adherence to human preferences during task execution, leading to improved performance while satisfying the human’s objective.} }
Endnote
%0 Conference Paper %T Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed Racing %A Jonathan DeCastro %A Andrew Silva %A Deepak Gopinath %A Emily Sumner %A Thomas Matrai Balch %A Laporsha Dees %A Guy Rosman %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-decastro25a %I PMLR %P 2599--2628 %U https://proceedings.mlr.press/v270/decastro25a.html %V 270 %X Tight coordination is required for effective human-robot teams in domains involving fast dynamics and tactical decisions, such as multi-car racing. In such settings, robot teammates must react to cues of a human teammate’s tactical objective to assist in a way that is consistent with the objective (e.g., navigating left or right around an obstacle). To address this challenge, we present _Dream2Assist_, a framework that combines a rich world model able to infer human objectives and value functions, and an assistive agent that provides appropriate expert assistance to a given human teammate. Our approach builds on a recurrent state space model to explicitly infer human intents, enabling the assistive agent to select actions that align with the human and enabling a fluid teaming interaction. We demonstrate our approach in a high-speed racing domain with a population of synthetic human drivers pursuing mutually exclusive objectives, such as “stay-behind” and “overtake”. We show that the combined human-robot team, when blending its actions with those of the human, outperforms synthetic humans alone and several baseline assistance strategies, and that intent-conditioning enables adherence to human preferences during task execution, leading to improved performance while satisfying the human’s objective.
APA
DeCastro, J., Silva, A., Gopinath, D., Sumner, E., Balch, T.M., Dees, L. & Rosman, G.. (2025). Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed Racing. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:2599-2628 Available from https://proceedings.mlr.press/v270/decastro25a.html.

Related Material