Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation

📄 arXiv: 2609.20822v1 📥 PDF

作者: Bingxin Xu, Yuzhang Shang, Zhen Dong, Emilio Ferrara

分类: cs.RO, cs.AI, cs.CL, cs.CV

发布日期: 2026-09-17


💡 一句话要点

提出SafeHarness以解决机器人操作中的安全问题

🎯 匹配领域: 支柱一:机器人控制 (Robot Control)

关键词: 编码代理 机器人操作 安全性 路径规划 障碍物感知 控制模块 任务成功率 碰撞避免

📋 核心要点

  1. 现有编码代理在机器人操作中未能有效处理安全约束,导致频繁碰撞障碍物。
  2. 论文提出SafeHarness,通过障碍物感知的路径规划和接触执行模块,增强代理的安全性。
  3. 实验结果表明,SafeHarness在任务成功率和碰撞避免率上均显著优于现有方法,提升幅度分别为6.5%和27.0%。

📝 摘要(中文)

编码代理已成为机器人操作的有前景范式:语言模型编写机器人控制器程序,使得这些代理能够在没有特定训练的情况下操作机器人。然而,这种范式的安全性尚未得到验证。本文评估了在安全约束下的编码代理,发现代理在大多数情况下会与障碍物发生碰撞,忽视安全性。为了解决这一问题,提出了SafeHarness,通过两个障碍物感知的控制模块,使代理能够优先考虑安全约束。实验结果显示,SafeHarness在任务成功率和避免碰撞率上均超过了现有技术,分别达到了71.9%和87.5%。

🔬 方法详解

问题定义:本文旨在解决编码代理在机器人操作中未能优先考虑安全约束的问题。现有方法在任务完成时常常忽视与障碍物的碰撞,导致安全隐患。

核心思路:论文的核心解决思路是引入SafeHarness,通过障碍物感知的路径规划和接触执行,使得代理在操作过程中能够优先考虑安全约束。这样设计是为了确保代理在执行任务时不仅关注目标,还能有效避免障碍物。

技术框架:整体架构包括两个主要模块:障碍物感知路径规划和障碍物感知接触执行。路径规划模块负责生成安全的行进路线,而接触执行模块则确保在接触时避免障碍物。

关键创新:最重要的技术创新点在于引入了障碍物感知的控制模块,使得代理在路径规划和接触执行时能够动态调整,优先考虑安全约束。这与现有方法的本质区别在于,现有方法通常只关注任务完成,而忽视安全性。

关键设计:在路径规划中,代理将障碍物视为边界框,并生成候选路线;在接触执行中,选择的接触位置确保避免障碍物。具体的参数设置和损失函数设计未在摘要中详细说明,需参考论文的具体内容。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,SafeHarness在任务成功率上达到了71.9%,在避免碰撞率上达到了87.5%,分别比现有技术提升了6.5%和27.0%。这些结果表明,SafeHarness显著增强了编码代理在安全机器人操作中的能力。

🎯 应用场景

该研究的潜在应用领域包括工业机器人、服务机器人和自主移动设备等。通过提高机器人在复杂环境中的安全性,能够有效降低事故风险,提升操作效率,具有重要的实际价值和广泛的应用前景。

📄 摘要(原文)

Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robots without robot-specific training.Whether this paradigm is also safe, however, has not been asked. We evaluate coding agent under a safety constraint, where each task pairs a manipulation goal with an obstacle the robot must not touch. The agent pursues the goal but collides with the obstacle in most cases, treating task completion as its sole objective while neglecting safety. The agent reasons about the obstacle in its traces, and the prompt already forbids touching it, so neither perception nor instruction is at fault; the fault lies in the planning, where the stated constraint never becomes a priority. By decomposing manipulation into a route phase and a contact-rich moment, we locate the source of the failure. Along the route, the model cannot prioritize the safety constraint, having no notion of a clearing route and none of replanning once a chosen route becomes infeasible. At the contact, it is unaware that contact execution is bounded by the same constraint. To close this gap, we present SafeHarness, which equips the model with two obstacle-aware harnesses that enable it to prioritize the safety constraint. Obstacle-aware route planning grounds the objects as bounding boxes and draws candidate routes over them as sequences of waypoints. The agent then plans a route in advance, verifies it, replans when necessary, and only then executes it. Obstacle-aware contact execution instead selects the contact position so that the contact itself avoids the obstacle. SafeHarness attains 71.9% task success and 87.5% collision avoidance, surpassing the previous SOTA by 6.5% and 27.0%, respectively. These results are $2.3\times$ and $1.5\times$ those of the same agent without harnesses.