Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |