Survey of Vision-Language-Action Models for Embodied Manipulation
It addresses the need for improved universal robotic control frameworks in embodied AI, but is incremental as it synthesizes existing research rather than presenting new findings.
This survey reviews Vision-Language-Action models for embodied manipulation, analyzing their development, key dimensions like structures and training methods, and identifying challenges and future directions to enhance robotic control in AI systems.
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.