# 连接语言与动作：语言条件机器人操作综述

> 原文链接：https://robotics.hellobike.com/papers/2026-07-29-2312-10807
> 频道：papers | 更新日期：2026-07-29 | 标签：arxiv, cs.RO
> 核心摘要：该综述面向自然语言指令执行问题，按语言融入机器人系统的方式系统梳理语言条件机器人操作进展。

# 连接语言与动作：语言条件机器人操作综述

::: v-pre
> 原文链接：[Bridging language and action: A survey of language-conditioned robot manipulation](https://arxiv.org/abs/2312.10807)（arXiv 2312.10807 · 发布日期：2026-07-29）

**Bridging language and action: A survey of language-conditioned robot manipulation**

该综述面向自然语言指令执行问题，按语言融入机器人系统的方式系统梳理语言条件机器人操作进展。

## 核心要点

- 动机是让机器人理解并执行自然语言指令，促进人与机器人智能体的顺畅沟通与协作。
- 综述将方法分为状态评估、策略条件、认知规划推理、统一视觉-语言-动作模型四类。
- 进一步从动作粒度、数据与监督、系统成本与延迟、环境评估和任务规格五个轴分析技术。
- 文章强调领域关键争论，并讨论提升泛化能力和解决安全问题的开放挑战与未来方向。

## 英文摘要 (Abstract)

Language-conditioned robot manipulation is an emerging field aimed at enabling seamless communication and cooperation between humans and robotic agents by teaching robots to comprehend and execute instructions conveyed in natural language. This interdisciplinary area integrates scene understanding, language processing, and policy learning to bridge the gap between human instructions and robot actions. In this comprehensive survey, we systematically explore recent advancements in language-conditioned robot manipulation. We categorize existing methods based on the primary ways language is integrated into the robot system, namely language for state evaluation, language as a policy condition, language for cognitive planning and reasoning, and language in unified vision-language-action models. Specifically, we further analyze state-of-the-art techniques from five axes of action granularity, data and supervision regimes, system cost and latency, environments and evaluations, and task specification. Additionally, we highlight the key debates in the field. Finally, we discuss open challenges and future research directions, focusing on potentially enhancing generalization capabilities and addressing safety issues in language-conditioned robot manipulators.

作者：Xiangtong Yao, Hongkuan Zhou, Oier Mees, Yuan Meng, Ted G. Xiao, Yonatan Bisk, Jean Oh, Edward Johns, Mohit Shridhar, Dhruv Shah
:::

## 原始参考来源 (Sources)

- [arXiv 2312.10807：Bridging language and action: A survey of language-conditioned robot manipulation](https://arxiv.org/abs/2312.10807)