視覺-語言-行動模型：概念、進展、應用與挑戰

Vision-Language-Action Models: Concepts, Progress, Applications and Challenges

May 7, 2025

作者: Ranjan Sapkota, Yang Cao, Konstantinos I. Roumeliotis, Manoj Karkee

cs.AI

摘要

視覺-語言-動作（Vision-Language-Action, VLA）模型標誌著人工智慧領域的一次變革性進步，旨在將感知、自然語言理解與具身行動統一於單一的計算框架中。本基礎性綜述全面整合了近期VLA模型的進展，並系統性地以五大主題支柱組織了這一快速發展領域的現狀。我們首先確立了VLA系統的概念基礎，追溯其從跨模態學習架構到緊密整合視覺-語言模型（VLMs）、動作規劃器與分層控制器的通用型代理的演進歷程。我們的研究方法採用嚴謹的文獻綜述框架，涵蓋了過去三年內發表的80多個VLA模型。關鍵進展領域包括架構創新、參數高效訓練策略以及即時推理加速。我們探討了多樣化的應用領域，如人形機器人、自動駕駛車輛、醫療與工業機器人、精準農業以及增強現實導航。本綜述進一步探討了即時控制、多模態動作表示、系統可擴展性、對未見任務的泛化能力以及倫理部署風險等主要挑戰。基於最新技術，我們提出了針對性的解決方案，包括代理型AI適應、跨具身泛化以及統一的神經符號規劃。在展望性討論中，我們勾勒了一條未來發展路線圖，其中VLA模型、VLMs與代理型AI將匯聚成具有社會對齊性、適應性與通用目的的具身代理。本工作為推動智能現實世界機器人與人工通用智慧的發展提供了基礎性參考。>視覺-語言-動作，代理型AI，AI代理，視覺-語言模型

English

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, parameter-efficient training strategies, and real-time inference accelerations. We explore diverse application domains such as humanoid robotics, autonomous vehicles, medical and industrial robotics, precision agriculture, and augmented reality navigation. 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. In our forward-looking discussion, we outline a future roadmap where VLA models, VLMs, and agentic AI converge to power socially aligned, adaptive, and general-purpose embodied agents. This work serves as a foundational reference for advancing intelligent, real-world robotics and artificial general intelligence. >Vision-language-action, Agentic AI, AI Agents, Vision-language Models