Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control

原文：Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control

作者：Jonathan DeCastro, Thomas Balch, Emily Sumner, Deepak Gopinath, Laporsha Dees, Patricio Reyes Gomez, Elliot Weiss, Megan Applegate-Kenton, Todd Rowell, John Leonard, Avinash Balachandran, Guy Rosman

来源：arXiv cs.RO（机器人）

正文

Computer Science > Robotics

arXiv:2610.34650v1 (cs)

[Submitted on 26 Oct 2026]

Title:Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control

Authors:Jonathan DeCastro, Thomas Balch, Emily Sumner, Deepak Gopinath, Laporsha Dees, Patricio Reyes Gomez, Elliot Weiss, Megan Applegate-Kenton, Todd Rowell, John Leonard, Avinash Balachandran, Guy Rosman

View a PDF of the paper titled Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control, by Jonathan DeCastro and 11 other authors

View PDF

HTML (experimental)

Abstract:Assistive agents in shared-control settings face a dual challenge: acting proactively to align with the human’s intentions while remaining legible enough for the human to comprehend and fluently respond in real time. We present Dream2Assist, a model-based reinforcement learning framework for tightly-coupled shared decision making that addresses both sides of this challenge. Our approach extends a recurrent state-space world model with intent inference, enabling an assistive policy trained via fictitious co-play to anticipate and support discrete human objectives without overriding human agency. Beyond the computational framework, we describe the full deployment pipeline needed to translate a world-model-based policy into a safe, human-centered system in a resource-efficient way. Crucially, we address the sim-to-real-human gap via policy down-selection and reward restructuring within an iterative human-machine interface design. We validate the framework through three human-subjects studies and a preliminary on-vehicle deployment spanning two qualitatively distinct domains: high-speed racing (N=30) and urban driving with richer intent structure (N=10). Our results demonstrate that intent conditioning yields measurable improvements in torque alignment and collision rate. We surface key design insights and practices for deploying learning-based assistive agents in safety-critical, real-time human-robot teaming.

Comments:

32 pages, 18 figures, 16 tables

Subjects:

Robotics (cs.RO); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG)

ACM classes:

I.2.9; I.2.6; H.5.2

Cite as:

arXiv:2610.34650 [cs.RO]

(or

arXiv:2610.34650v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2610.34650

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

机器人 · 人机交互 · 机器学习

由「前沿雷达」于 2026-10-26 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。