发表机构
USC; UCF; UCSB（南加州大学; 中佛罗里达大学; 加州大学圣塔芭芭拉分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出SafeHarness，通过障碍物感知的路径规划与接触执行框架，使编码智能体在机器人操作中优先考虑安全约束，显著提升任务成功率与碰撞避免率。
AI 中文摘要
编码智能体已成为机器人操作领域一种颇具前景的范式：语言模型将机器人控制器编写为程序，以此方式构建的智能体现在无需特定于机器人的代码即可操作机器人。然而，这种范式是否安全尚未得到探讨。我们在安全约束下评估编码智能体，其中每个任务都将操作目标与机器人不得触碰的障碍物配对。智能体追求目标，但在大多数情况下会与障碍物发生碰撞，将任务完成视为其唯一目标而忽视安全。智能体在其轨迹中会推理障碍物，且提示已禁止触碰障碍物，因此感知和指令均无过错；问题出在规划环节，即所声明的约束从未成为优先事项。通过将操作分解为路径阶段和接触密集时刻，我们定位了失败根源。沿路径行进时，模型无法优先考虑安全约束，因为它既没有清障路径的概念，也没有在所选路径变得不可行时重新规划的概念。在接触时刻，它未意识到接触执行同样受该约束限制。为弥合这一差距，我们提出了SafeHarness，它为模型配备了两种障碍物感知约束框架，使其能够优先考虑安全约束。障碍物感知路径规划将物体表示为边界框，并在其上绘制候选路径作为航点序列。智能体随后预先规划路径、验证路径、必要时重新规划，然后才执行。障碍物感知接触执行则选择接触位置，使接触本身避开障碍物。SafeHarness实现了71.9%的任务成功率和87.5%的碰撞避免率，分别比之前的SOTA高出6.5%和27.0%。这些结果分别是同一智能体无约束框架时的2.3倍和1.5倍。
英文摘要
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 agents 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. 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. 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 81.2% task success and 91.9% collision avoidance with GPT-6-Astra, surpassing the previous SOTA by 13.7 and 23.0 points, and the same agent without harnesses by 31.2 and 57.5 points, respectively.
