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

Keywords: Recurrent State-Space Models, Human-Robot Interactions, Shared-Control

TL;DR: We propose a recurrent state space model capable of reasoning over human intents, enabling an assistive agent to select actions that align with the human and enabling a fluid teaming interaction, and demonstrate it in a high-speed racing domain.

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.

Video: https://youtu.be/PVugoxqX5Co

Website: https://dream2assist.github.io/

Student Paper: no

Submission Number: 417