摘要
Vision-Language-Action (VLA) models mark a transformative advancement in artificial intelligence, aiming to unify perception, natural language understanding, and embodied action within a single computational framework. This foundational review presents a comprehensive synthesis of recent advancements in Vision-Language-Action models, systematically organized across five thematic pillars that structure the landscape of this rapidly evolving field. We begin by establishing the conceptual foundations of VLA systems, tracing their evolution from cross-modal learning architectures to generalist agents that tightly integrate vision-language models (VLMs), action planners, and hierarchical controllers.
Our methodology adopts a rigorous literature review framework, covering over 80 VLA models published in the past three years. Key progress areas include architectural innovations, efficient training strategies, and real-time inference accelerations. We explore diverse application domains such as autonomous vehicles, medical and industrial robotics, precision agriculture, humanoid robotics, and augmented reality.
The review further addresses major challenges across real-time control, multimodal action representation, system scalability, generalization to unseen tasks, and ethical deployment risks. Drawing from the state-of-the-art, we propose targeted solutions including agentic AI adaptation, cross-embodiment generalization, and unified neuro-symbolic planning. We outline a forward-looking roadmap where VLA models, VLMs, and agentic AI converge to strengthen socially aligned, adaptive, and general-purpose embodied agents. This work, therefore, is expected to serve as a foundational reference for advancing intelligent, real-world robotics and artificial general intelligence.
结论
In this comprehensive review, we systematically evaluated the recent developments, methodologies, and applications of Vision-Language-Action (VLA) models published over the last three years. Our analysis began with the foundational concepts of VLAs, defining their role as multi-modal systems that unify visual perception, natural language understanding, and action generation in physical or simulated environments. We traced their evolution and timeline, detailing key milestones that marked the transition from isolated perception-action modules to fully unified, instruction-following robotic agents. We highlighted how multi-modal integration has matured from loosely coupled pipelines to transformer-based architectures that enable seamless coordination between modalities.
Next, we examined tokenization and representation techniques, focusing on how VLAs encode visual and linguistic information, including action primitives and spatial semantics. We explored learning paradigms, detailing the datasets and training strategies—from supervised learning and imitation learning to reinforcement learning and multi-modal pretraining—that have shaped VLA performance. In the 'adaptive control and real-time execution' section, we discussed how modern VLAs are optimized for dynamic environments, analyzing policies that support latency-sensitive tasks. We then categorized major architectural innovations, surveying over 50 recent VLA models. This discussion included advancements in model design, memory systems, and interaction fidelity.