ChronoDreamer: Action-Conditioned World Model as an Online Simulator for Robotic Planning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhou, Zhenhao, Negrut, Dan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909972634271744
author Zhou, Zhenhao
Negrut, Dan
author_facet Zhou, Zhenhao
Negrut, Dan
contents We present ChronoDreamer, an action-conditioned world model for contact-rich robotic manipulation. Given a history of egocentric RGB frames, contact maps, actions, and joint states, ChronoDreamer predicts future video frames, contact distributions, and joint angles via a spatial-temporal transformer trained with MaskGIT-style masked prediction. Contact is encoded as depth-weighted Gaussian splat images that render 3D forces into a camera-aligned format suitable for vision backbones. At inference, predicted rollouts are evaluated by a vision-language model that reasons about collision likelihood, enabling rejection sampling of unsafe actions before execution. We train and evaluate on DreamerBench, a simulation dataset generated with Project Chrono that provides synchronized RGB, contact splat, proprioception, and physics annotations across rigid and deformable object scenarios. Qualitative results demonstrate that the model preserves spatial coherence during non-contact motion and generates plausible contact predictions, while the LLM-based judge distinguishes collision from non-collision trajectories.
format Preprint
id arxiv_https___arxiv_org_abs_2512_18619
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ChronoDreamer: Action-Conditioned World Model as an Online Simulator for Robotic Planning
Zhou, Zhenhao
Negrut, Dan
Artificial Intelligence
Robotics
We present ChronoDreamer, an action-conditioned world model for contact-rich robotic manipulation. Given a history of egocentric RGB frames, contact maps, actions, and joint states, ChronoDreamer predicts future video frames, contact distributions, and joint angles via a spatial-temporal transformer trained with MaskGIT-style masked prediction. Contact is encoded as depth-weighted Gaussian splat images that render 3D forces into a camera-aligned format suitable for vision backbones. At inference, predicted rollouts are evaluated by a vision-language model that reasons about collision likelihood, enabling rejection sampling of unsafe actions before execution. We train and evaluate on DreamerBench, a simulation dataset generated with Project Chrono that provides synchronized RGB, contact splat, proprioception, and physics annotations across rigid and deformable object scenarios. Qualitative results demonstrate that the model preserves spatial coherence during non-contact motion and generates plausible contact predictions, while the LLM-based judge distinguishes collision from non-collision trajectories.
title ChronoDreamer: Action-Conditioned World Model as an Online Simulator for Robotic Planning
topic Artificial Intelligence
Robotics
url https://arxiv.org/abs/2512.18619