具身人工智能中视觉-语言-动作模型的综述
A Survey on Vision-Language-Action Models for Embodied AI
AI总结：
本文综述了具身人工智能中视觉-语言-动作模型的发展，探讨了其在机器人任务中的应用，分类了三种主要研究方向，并讨论了面临的挑战与未来方向。
摘要：
具身人工智能被视为通用人工智能的核心，因其涉及控制具身代理在物理世界中执行任务。在大型语言模型和视觉-语言模型的成功基础上，视觉-语言-动作（VLA）模型应运而生，用于解决语言条件的机器人任务。最近VLAs的普及需要全面的综述以捕捉快速发展的景观。本文首次对VLAs进行综述，提供了详细的分类，分为三个主要研究方向：第一方向聚焦于VLA的个体组件；第二方向致力于开发能够预测低级动作的VLA控制策略；第三方向包含能够将长期任务分解为子任务的高层任务规划器，从而引导VLA遵循更一般的用户指令。此外，本文还提供了相关资源的详尽总结，包括数据集、模拟器和基准测试。最后，讨论了VLAs面临的挑战并概述了具身人工智能中具有前景的未来方向。本文综述的配套仓库可在：https://github.com/yueen-ma/Awesome-VLA。
英文摘要：
Embodied AI is widely recognized as a cornerstone of artificial general intelligence (AGI) because it involves controlling embodied agents to perform tasks in the physical world. Building on the success of large language models (LLMs) and vision-language models (VLMs), a new category of multimodal models -- referred to as vision-language-action (VLA) models -- has emerged to address language-conditioned robotic tasks in embodied AI by leveraging their distinct ability to generate actions. The recent proliferation of VLAs necessitates a comprehensive survey to capture the rapidly evolving landscape. To this end, we present the first survey on VLAs for embodied AI. This work provides a detailed taxonomy of VLAs, organized into three major lines of research. The first line focuses on individual components of VLAs. The second line is dedicated to developing VLA-based control policies adept at predicting low-level actions. The third line comprises high-level task planners capable of decomposing long-horizon tasks into a sequence of subtasks, thereby guiding VLAs to follow more general user instructions. Furthermore, we provide an extensive summary of relevant resources, including datasets, simulators, and benchmarks. Finally, we discuss the challenges facing VLAs and outline promising future directions in embodied AI. A curated repository associated with this survey is available at: https://github.com/yueen-ma/Awesome-VLA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
