Survey of Vision-Language-Action Models for Embodied Manipulation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915612549185536 |
|---|---|
| author | Li, Haoran Chen, Yuhui Cui, Wenbo Liu, Weiheng Liu, Kai Zhou, Mingcai Zhang, Zhengtao Zhao, Dongbin |
| author_facet | Li, Haoran Chen, Yuhui Cui, Wenbo Liu, Weiheng Liu, Kai Zhou, Mingcai Zhang, Zhengtao Zhao, Dongbin |
| contents | Embodied intelligence systems, which enhance agent capabilities through continuous environment interactions, have garnered significant attention from both academia and industry. Vision-Language-Action models, inspired by advancements in large foundation models, serve as universal robotic control frameworks that substantially improve agent-environment interaction capabilities in embodied intelligence systems. This expansion has broadened application scenarios for embodied AI robots. This survey comprehensively reviews VLA models for embodied manipulation. Firstly, it chronicles the developmental trajectory of VLA architectures. Subsequently, we conduct a detailed analysis of current research across 5 critical dimensions: VLA model structures, training datasets, pre-training methods, post-training methods, and model evaluation. Finally, we synthesize key challenges in VLA development and real-world deployment, while outlining promising future research directions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15201 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Survey of Vision-Language-Action Models for Embodied Manipulation Li, Haoran Chen, Yuhui Cui, Wenbo Liu, Weiheng Liu, Kai Zhou, Mingcai Zhang, Zhengtao Zhao, Dongbin Robotics Artificial Intelligence Embodied intelligence systems, which enhance agent capabilities through continuous environment interactions, have garnered significant attention from both academia and industry. Vision-Language-Action models, inspired by advancements in large foundation models, serve as universal robotic control frameworks that substantially improve agent-environment interaction capabilities in embodied intelligence systems. This expansion has broadened application scenarios for embodied AI robots. This survey comprehensively reviews VLA models for embodied manipulation. Firstly, it chronicles the developmental trajectory of VLA architectures. Subsequently, we conduct a detailed analysis of current research across 5 critical dimensions: VLA model structures, training datasets, pre-training methods, post-training methods, and model evaluation. Finally, we synthesize key challenges in VLA development and real-world deployment, while outlining promising future research directions. |
| title | Survey of Vision-Language-Action Models for Embodied Manipulation |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2508.15201 |