Saved in:
Bibliographic Details
Main Authors: Zhang, Yizheng, Yu, Zhenjun, Lai, Jiaxin, Lu, Cewu, Han, Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.07770
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908487457439744
author Zhang, Yizheng
Yu, Zhenjun
Lai, Jiaxin
Lu, Cewu
Han, Lei
author_facet Zhang, Yizheng
Yu, Zhenjun
Lai, Jiaxin
Lu, Cewu
Han, Lei
contents We introduce AgentWorld, an interactive simulation platform for developing household mobile manipulation capabilities. Our platform combines automated scene construction that encompasses layout generation, semantic asset placement, visual material configuration, and physics simulation, with a dual-mode teleoperation system supporting both wheeled bases and humanoid locomotion policies for data collection. The resulting AgentWorld Dataset captures diverse tasks ranging from primitive actions (pick-and-place, push-pull, etc.) to multistage activities (serve drinks, heat up food, etc.) across living rooms, bedrooms, and kitchens. Through extensive benchmarking of imitation learning methods including behavior cloning, action chunking transformers, diffusion policies, and vision-language-action models, we demonstrate the dataset's effectiveness for sim-to-real transfer. The integrated system provides a comprehensive solution for scalable robotic skill acquisition in complex home environments, bridging the gap between simulation-based training and real-world deployment. The code, datasets will be available at https://yizhengzhang1.github.io/agent_world/
format Preprint
id arxiv_https___arxiv_org_abs_2508_07770
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AgentWorld: An Interactive Simulation Platform for Scene Construction and Mobile Robotic Manipulation
Zhang, Yizheng
Yu, Zhenjun
Lai, Jiaxin
Lu, Cewu
Han, Lei
Robotics
We introduce AgentWorld, an interactive simulation platform for developing household mobile manipulation capabilities. Our platform combines automated scene construction that encompasses layout generation, semantic asset placement, visual material configuration, and physics simulation, with a dual-mode teleoperation system supporting both wheeled bases and humanoid locomotion policies for data collection. The resulting AgentWorld Dataset captures diverse tasks ranging from primitive actions (pick-and-place, push-pull, etc.) to multistage activities (serve drinks, heat up food, etc.) across living rooms, bedrooms, and kitchens. Through extensive benchmarking of imitation learning methods including behavior cloning, action chunking transformers, diffusion policies, and vision-language-action models, we demonstrate the dataset's effectiveness for sim-to-real transfer. The integrated system provides a comprehensive solution for scalable robotic skill acquisition in complex home environments, bridging the gap between simulation-based training and real-world deployment. The code, datasets will be available at https://yizhengzhang1.github.io/agent_world/
title AgentWorld: An Interactive Simulation Platform for Scene Construction and Mobile Robotic Manipulation
topic Robotics
url https://arxiv.org/abs/2508.07770