代码驱动：具身编码智能体结合主动视觉与物理反馈实现空中操作
Fly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical Feedback
AI总结：
该研究针对空中操作中具身编码智能体执行反馈的缺陷，提出主动反馈框架，通过仿真诊断程序补充缺失证据，显著提升任务成功率，且优化后的程序可直接在真实机器人上运行。
摘要：
具身编码智能体通过生成可执行程序并基于执行反馈进行优化，从自然语言指令中构建机器人策略。这种优化假设执行反馈能揭示任务是否成功，且失败时能提供足够证据指导程序修订。空中操作在两方面违背该假设：有效载荷约束限制了机载相机的覆盖范围，使任务关键结果处于机器人视野之外（部分可观测性）；强动态耦合和有限控制裕度导致物理交互脆弱（交互鲁棒性有限），且无法明确失败原因。重复查看相同反馈无法恢复从未收集的观测结果，也无法区分现有证据无法辨别的失败原因。为获取缺失证据，我们提出主动反馈（Active Feedback, AF），这是一种主动的“查看与探测”框架。当执行反馈留下未解决问题时，智能体合成独立的诊断程序，在仿真中运行以从信息丰富的视角检查未观测到的结果（查看），或通过针对性物理交互测试失败原因的假设（探测）。在6项模拟空中操作任务中，每个条件下进行60次试验，与相同编码智能体配置和任务执行限制下的终端反馈相比，AF将错误完成声明从25降至5，最终任务成功率从31.7%提升至75%。使用共享机器人API，在仿真中经AF优化的任务程序无需修改任务程序源代码即可在真实空中操作机器人上运行，并在现实世界中完成多阶段操作任务。这些结果表明，可执行诊断填补了具身编码智能体执行反馈的空白，改善了空中操作中的完成评估和程序优化。
英文摘要：
Embodied coding agents construct robot policies from natural-language instructions by generating executable programs and refining them from execution feedback. This refinement assumes that execution feedback reveals whether the task succeeded and, after a failure, provides sufficient evidence to guide program revision. Aerial manipulation violates this assumption in two ways. Payload constraints restrict onboard camera coverage and leave task-critical outcomes outside the robot's view (partial observability), while strong dynamic coupling and limited control margins make physical interactions fragile (limited interaction robustness) and leave failure causes unresolved. Re-examining the same feedback cannot recover observations that were never collected or separate failure causes that the available evidence does not distinguish. To acquire this missing evidence, we introduce Active Feedback (AF), an active "View and Probe" framework. When execution feedback leaves unresolved questions, the agent synthesizes a separate diagnostic program that runs in simulation to inspect unseen outcomes from informative viewpoints (View) or test hypotheses about failure causes through targeted physical interactions (Probe). Across six simulated aerial manipulation tasks with 60 trials per condition, AF reduces false completion declarations from 25 to 5 and raises final task success from 31.7% to 75% compared with terminal feedback under the same coding-agent configuration and task-execution limit. Using shared robot APIs, task programs refined with AF in simulation run on a physical aerial manipulator without task-program source-code modification and complete multi-stage manipulation tasks in the real world. These results show that executable diagnosis fills gaps in execution feedback for embodied coding agents, improving both completion assessment and program refinement in aerial manipulation.
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。
