Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911171059122176 |
|---|---|
| author | Ni, Fei Zhang, Min Li, Pengyi Yuan, Yifu Zhang, Lingfeng Liu, Yuecheng Han, Peilong Kou, Longxin Ma, Shaojin Qiao, Jinbin Bravo, David Gamaliel Arcos Wang, Yuening Hu, Xiao Zhang, Zhanguang Yao, Xianze Li, Yutong Zhang, Zhao Wen, Ying Chen, Ying-Cong Liang, Xiaodan Lin, Liang He, Bin Bou-Ammar, Haitham Wang, He Xu, Huazhe Deng, Jiankang Luo, Shan Jiang, Shuqiang Pan, Wei Gao, Yang Zafeiriou, Stefanos Peters, Jan Zhuang, Yuzheng Zhang, Yingxue Zheng, Yan Tang, Hongyao Hao, Jianye |
| author_facet | Ni, Fei Zhang, Min Li, Pengyi Yuan, Yifu Zhang, Lingfeng Liu, Yuecheng Han, Peilong Kou, Longxin Ma, Shaojin Qiao, Jinbin Bravo, David Gamaliel Arcos Wang, Yuening Hu, Xiao Zhang, Zhanguang Yao, Xianze Li, Yutong Zhang, Zhao Wen, Ying Chen, Ying-Cong Liang, Xiaodan Lin, Liang He, Bin Bou-Ammar, Haitham Wang, He Xu, Huazhe Deng, Jiankang Luo, Shan Jiang, Shuqiang Pan, Wei Gao, Yang Zafeiriou, Stefanos Peters, Jan Zhuang, Yuzheng Zhang, Yingxue Zheng, Yan Tang, Hongyao Hao, Jianye |
| contents | Embodied AI development significantly lags behind large foundation models due to three critical challenges: (1) lack of systematic understanding of core capabilities needed for Embodied AI, making research lack clear objectives; (2) absence of unified and standardized evaluation systems, rendering cross-benchmark evaluation infeasible; and (3) underdeveloped automated and scalable acquisition methods for embodied data, creating critical bottlenecks for model scaling. To address these obstacles, we present Embodied Arena, a comprehensive, unified, and evolving evaluation platform for Embodied AI. Our platform establishes a systematic embodied capability taxonomy spanning three levels (perception, reasoning, task execution), seven core capabilities, and 25 fine-grained dimensions, enabling unified evaluation with systematic research objectives. We introduce a standardized evaluation system built upon unified infrastructure supporting flexible integration of 22 diverse benchmarks across three domains (2D/3D Embodied Q&A, Navigation, Task Planning) and 30+ advanced models from 20+ worldwide institutes. Additionally, we develop a novel LLM-driven automated generation pipeline ensuring scalable embodied evaluation data with continuous evolution for diversity and comprehensiveness. Embodied Arena publishes three real-time leaderboards (Embodied Q&A, Navigation, Task Planning) with dual perspectives (benchmark view and capability view), providing comprehensive overviews of advanced model capabilities. Especially, we present nine findings summarized from the evaluation results on the leaderboards of Embodied Arena. This helps to establish clear research veins and pinpoint critical research problems, thereby driving forward progress in the field of Embodied AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15273 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI Ni, Fei Zhang, Min Li, Pengyi Yuan, Yifu Zhang, Lingfeng Liu, Yuecheng Han, Peilong Kou, Longxin Ma, Shaojin Qiao, Jinbin Bravo, David Gamaliel Arcos Wang, Yuening Hu, Xiao Zhang, Zhanguang Yao, Xianze Li, Yutong Zhang, Zhao Wen, Ying Chen, Ying-Cong Liang, Xiaodan Lin, Liang He, Bin Bou-Ammar, Haitham Wang, He Xu, Huazhe Deng, Jiankang Luo, Shan Jiang, Shuqiang Pan, Wei Gao, Yang Zafeiriou, Stefanos Peters, Jan Zhuang, Yuzheng Zhang, Yingxue Zheng, Yan Tang, Hongyao Hao, Jianye Robotics Embodied AI development significantly lags behind large foundation models due to three critical challenges: (1) lack of systematic understanding of core capabilities needed for Embodied AI, making research lack clear objectives; (2) absence of unified and standardized evaluation systems, rendering cross-benchmark evaluation infeasible; and (3) underdeveloped automated and scalable acquisition methods for embodied data, creating critical bottlenecks for model scaling. To address these obstacles, we present Embodied Arena, a comprehensive, unified, and evolving evaluation platform for Embodied AI. Our platform establishes a systematic embodied capability taxonomy spanning three levels (perception, reasoning, task execution), seven core capabilities, and 25 fine-grained dimensions, enabling unified evaluation with systematic research objectives. We introduce a standardized evaluation system built upon unified infrastructure supporting flexible integration of 22 diverse benchmarks across three domains (2D/3D Embodied Q&A, Navigation, Task Planning) and 30+ advanced models from 20+ worldwide institutes. Additionally, we develop a novel LLM-driven automated generation pipeline ensuring scalable embodied evaluation data with continuous evolution for diversity and comprehensiveness. Embodied Arena publishes three real-time leaderboards (Embodied Q&A, Navigation, Task Planning) with dual perspectives (benchmark view and capability view), providing comprehensive overviews of advanced model capabilities. Especially, we present nine findings summarized from the evaluation results on the leaderboards of Embodied Arena. This helps to establish clear research veins and pinpoint critical research problems, thereby driving forward progress in the field of Embodied AI. |
| title | Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.15273 |