外观
论文arXiv 2609.160741 个月前
用于机器人学习与控制的 World-Action Models：综述
原文链接：World-Action Models for Robot Learning and Control: A Survey（arXiv 2609.16074 · 发布日期：2026-09-13）
World-Action Models for Robot Learning and Control: A Survey
本文综述面向机器人的 WAM，将未来世界预测与可执行动作生成结合，并在操作、导航和自动驾驶应用中梳理评测。
核心要点
- 开放环境机器人需在部分可观测、物理约束和动态任务情境下预判动作后果。
- 文章界定 WAM 与传统世界模型、模型式强化学习、视频生成和反应式 VLA 的关系。
- 综述以统一分类整理表示、转移建模、动作接口、架构、训练流程、数据模态和扩展策略。
- 回顾操作、导航和自动驾驶应用及评测数据、基准、指标和协议，并给出项目页面。
英文摘要 (Abstract)
Robots operating in open environments act under partial observability, physical constraints, and dynamic task contexts. Beyond mapping observations and language instructions to actions, they must anticipate how candidate actions may affect future states and task-relevant outcomes. Recent advances in world models, video generation, and Vision-Language-Action (VLA) policies have motivated the development of World-Action Models (WAMs), which couple future world prediction with executable action generation. This survey provides a robotics-oriented review of WAMs. We clarify their scope relative to conventional world models, model-based reinforcement learning, action-conditioned video generation, and reactive VLA policies, and organize existing methods through a unified taxonomy covering representations, transition modeling, action interfaces, architectures, training pipelines, data modalities, and scaling strategies. We further review applications of WAMs in manipulation, navigation, and autonomous driving, and we summarize the datasets, benchmarks, metrics, and protocols used to evaluate WAM systems. Finally, we discuss key challenges in action alignment, world-action factorization, spatial and multi-view consistency, long-horizon memory, neural simulation for closed-loop policy learning, and efficient inference. Taken together, this survey aims to provide a concise technical foundation for integrating predictive world modeling with action generation, toward more reliable embodied robot intelligence. Project page: https://rcl-robotics.github.io/Awesome-World-Action-Models.
作者：Zuxing Lu, Hongjia Zhai, Guanzhi Wang, Huajian Zeng, Jiaqi Yang, Jingyu Liu, Lei Cheng, Yuantai Zhang, Yuheng Qiu, Zezhou Cheng
来源
本页事实对应的公开页面，以原文为准。