RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913810009292800 |
|---|---|
| author | Geng, Haoran Wang, Feishi Wei, Songlin Li, Yuyang Wang, Bangjun An, Boshi Cheng, Charlie Tianyue Lou, Haozhe Li, Peihao Wang, Yen-Jen Liang, Yutong Goetting, Dylan Xu, Chaoyi Chen, Haozhe Qian, Yuxi Geng, Yiran Mao, Jiageng Wan, Weikang Zhang, Mingtong Lyu, Jiangran Zhao, Siheng Zhang, Jiazhao Zhang, Jialiang Zhao, Chengyang Lu, Haoran Ding, Yufei Gong, Ran Wang, Yuran Kuang, Yuxuan Wu, Ruihai Jia, Baoxiong Sferrazza, Carlo Dong, Hao Huang, Siyuan Wang, Yue Malik, Jitendra Abbeel, Pieter |
| author_facet | Geng, Haoran Wang, Feishi Wei, Songlin Li, Yuyang Wang, Bangjun An, Boshi Cheng, Charlie Tianyue Lou, Haozhe Li, Peihao Wang, Yen-Jen Liang, Yutong Goetting, Dylan Xu, Chaoyi Chen, Haozhe Qian, Yuxi Geng, Yiran Mao, Jiageng Wan, Weikang Zhang, Mingtong Lyu, Jiangran Zhao, Siheng Zhang, Jiazhao Zhang, Jialiang Zhao, Chengyang Lu, Haoran Ding, Yufei Gong, Ran Wang, Yuran Kuang, Yuxuan Wu, Ruihai Jia, Baoxiong Sferrazza, Carlo Dong, Hao Huang, Siyuan Wang, Yue Malik, Jitendra Abbeel, Pieter |
| contents | Data scaling and standardized evaluation benchmarks have driven significant advances in natural language processing and computer vision. However, robotics faces unique challenges in scaling data and establishing evaluation protocols. Collecting real-world data is resource-intensive and inefficient, while benchmarking in real-world scenarios remains highly complex. Synthetic data and simulation offer promising alternatives, yet existing efforts often fall short in data quality, diversity, and benchmark standardization. To address these challenges, we introduce RoboVerse, a comprehensive framework comprising a simulation platform, a synthetic dataset, and unified benchmarks. Our simulation platform supports multiple simulators and robotic embodiments, enabling seamless transitions between different environments. The synthetic dataset, featuring high-fidelity physics and photorealistic rendering, is constructed through multiple approaches. Additionally, we propose unified benchmarks for imitation learning and reinforcement learning, enabling evaluation across different levels of generalization. At the core of the simulation platform is MetaSim, an infrastructure that abstracts diverse simulation environments into a universal interface. It restructures existing simulation environments into a simulator-agnostic configuration system, as well as an API aligning different simulator functionalities, such as launching simulation environments, loading assets with initial states, stepping the physics engine, etc. This abstraction ensures interoperability and extensibility. Comprehensive experiments demonstrate that RoboVerse enhances the performance of imitation learning, reinforcement learning, world model learning, and sim-to-real transfer. These results validate the reliability of our dataset and benchmarks, establishing RoboVerse as a robust solution for advancing robot learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_18904 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning Geng, Haoran Wang, Feishi Wei, Songlin Li, Yuyang Wang, Bangjun An, Boshi Cheng, Charlie Tianyue Lou, Haozhe Li, Peihao Wang, Yen-Jen Liang, Yutong Goetting, Dylan Xu, Chaoyi Chen, Haozhe Qian, Yuxi Geng, Yiran Mao, Jiageng Wan, Weikang Zhang, Mingtong Lyu, Jiangran Zhao, Siheng Zhang, Jiazhao Zhang, Jialiang Zhao, Chengyang Lu, Haoran Ding, Yufei Gong, Ran Wang, Yuran Kuang, Yuxuan Wu, Ruihai Jia, Baoxiong Sferrazza, Carlo Dong, Hao Huang, Siyuan Wang, Yue Malik, Jitendra Abbeel, Pieter Robotics Data scaling and standardized evaluation benchmarks have driven significant advances in natural language processing and computer vision. However, robotics faces unique challenges in scaling data and establishing evaluation protocols. Collecting real-world data is resource-intensive and inefficient, while benchmarking in real-world scenarios remains highly complex. Synthetic data and simulation offer promising alternatives, yet existing efforts often fall short in data quality, diversity, and benchmark standardization. To address these challenges, we introduce RoboVerse, a comprehensive framework comprising a simulation platform, a synthetic dataset, and unified benchmarks. Our simulation platform supports multiple simulators and robotic embodiments, enabling seamless transitions between different environments. The synthetic dataset, featuring high-fidelity physics and photorealistic rendering, is constructed through multiple approaches. Additionally, we propose unified benchmarks for imitation learning and reinforcement learning, enabling evaluation across different levels of generalization. At the core of the simulation platform is MetaSim, an infrastructure that abstracts diverse simulation environments into a universal interface. It restructures existing simulation environments into a simulator-agnostic configuration system, as well as an API aligning different simulator functionalities, such as launching simulation environments, loading assets with initial states, stepping the physics engine, etc. This abstraction ensures interoperability and extensibility. Comprehensive experiments demonstrate that RoboVerse enhances the performance of imitation learning, reinforcement learning, world model learning, and sim-to-real transfer. These results validate the reliability of our dataset and benchmarks, establishing RoboVerse as a robust solution for advancing robot learning. |
| title | RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2504.18904 |