iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Chuanrui, Wu, Zhengxian, Lu, Guanxing, Tang, Yansong, Wang, Ziwei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917001838985216
author Zhang, Chuanrui
Wu, Zhengxian
Lu, Guanxing
Tang, Yansong
Wang, Ziwei
author_facet Zhang, Chuanrui
Wu, Zhengxian
Lu, Guanxing
Tang, Yansong
Wang, Ziwei
contents Learned world models hold significant potential for robotic manipulation, as they can serve as simulator for real-world interactions. While extensive progress has been made in 2D video-based world models, these approaches often lack geometric and spatial reasoning, which is essential for capturing the physical structure of the 3D world. To address this limitation, we introduce iMoWM, a novel interactive world model designed to generate color images, depth maps, and robot arm masks in an autoregressive manner conditioned on actions. To overcome the high computational cost associated with three-dimensional information, we propose MMTokenizer, which unifies multi-modal inputs into a compact token representation. This design enables iMoWM to leverage large-scale pretrained VideoGPT models while maintaining high efficiency and incorporating richer physical information. With its multi-modal representation, iMoWM not only improves the visual quality of future predictions but also serves as an effective simulator for model-based reinforcement learning (MBRL) and facilitates real-world imitation learning. Extensive experiments demonstrate the superiority of iMoWM across these tasks, showcasing the advantages of multi-modal world modeling for robotic manipulation. Homepage: https://xingyoujun.github.io/imowm/
format Preprint
id arxiv_https___arxiv_org_abs_2510_09036
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation
Zhang, Chuanrui
Wu, Zhengxian
Lu, Guanxing
Tang, Yansong
Wang, Ziwei
Robotics
Learned world models hold significant potential for robotic manipulation, as they can serve as simulator for real-world interactions. While extensive progress has been made in 2D video-based world models, these approaches often lack geometric and spatial reasoning, which is essential for capturing the physical structure of the 3D world. To address this limitation, we introduce iMoWM, a novel interactive world model designed to generate color images, depth maps, and robot arm masks in an autoregressive manner conditioned on actions. To overcome the high computational cost associated with three-dimensional information, we propose MMTokenizer, which unifies multi-modal inputs into a compact token representation. This design enables iMoWM to leverage large-scale pretrained VideoGPT models while maintaining high efficiency and incorporating richer physical information. With its multi-modal representation, iMoWM not only improves the visual quality of future predictions but also serves as an effective simulator for model-based reinforcement learning (MBRL) and facilitates real-world imitation learning. Extensive experiments demonstrate the superiority of iMoWM across these tasks, showcasing the advantages of multi-modal world modeling for robotic manipulation. Homepage: https://xingyoujun.github.io/imowm/
title iMoWM: Taming Interactive Multi-Modal World Model for Robotic Manipulation
topic Robotics
url https://arxiv.org/abs/2510.09036