Dreaming to Assist: Learning to Align with Human Objectives for Shared Control in High-Speed Racing
This addresses the challenge of effective human-robot coordination in fast-paced, tactical domains like racing, though it is incremental as it builds on existing world model and intent inference methods.
The paper tackles the problem of aligning robot assistance with human tactical objectives in high-speed racing, demonstrating that the combined human-robot team outperforms synthetic humans alone and baseline strategies while adhering to human preferences.
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 the synthetic humans alone as well as 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.