行动前先观察：面向开放世界移动操作的智能体-接口对齐监督
Look Before You Move: Agent-Interface-Aligned Supervision for Open-World Mobile Manipulation
AI总结：
本研究提出Agent-Interface Data Alignment（AIDA）数据收集流程，训练出的AIDA-OWMM智能体在开放世界移动操作任务中表现优异，还可迁移至真实机器人及导航任务，验证了方法的有效性。
摘要：
开放世界移动操作要求机器人根据语言指令找到目标物体、接近该物体并将其移动至目标容器。为这些任务训练视觉语言模型（VLM）智能体需要动作选择和主动视觉的演示。现有流程常将规划轨迹转换为高级动作标签，但最短路径进度为决定观察位置提供的监督有限。我们提出Agent-Interface Data Alignment（AIDA，智能体-接口数据对齐），一种数据收集流程，其中教师通过部署智能体的技能接口直接选择并执行动作。针对移动操作，我们设计教师以维持目标可见性、恢复丢失的目标，并接近以执行抓取或放置。我们添加基于模板的空间推理监督，并使用共享框架在训练和推理期间组织观测、历史和输出。由此得到的智能体AIDA-OWMM在170个保留的OWMM任务回合中实现71.76%的全任务成功率。教师敏感性分析显示，主动视觉演示可提升学生智能体的成功率。经模拟训练的智能体在真实移动机器人上实现38%的端到端成功率，且无需额外训练。将AIDA应用于EmbodiedBench的导航子集，进一步证明该流程对导航任务的实用性。
英文摘要：
Open-world mobile manipulation requires a robot to find an object, approach it, and move it to a target receptacle from a language instruction. Training vision-language model (VLM) agents for these tasks requires demonstrations of both action selection and active vision. Existing pipelines often convert planned trajectories into high-level action labels, but shortest-path progress provides limited supervision for deciding where to look. We introduce Agent-Interface Data Alignment (AIDA), a data collection pipeline in which a teacher directly selects and executes actions through the deployed agent's skill interface. For mobile manipulation, we design teachers that maintain target visibility, recover lost targets, and approach for picking or placing. We add template-based spatial reasoning supervision and use a shared harness to organize observations, history, and outputs during training and inference. The resulting agent, AIDA-OWMM, achieves 71.76% full-task success on 170 held-out OWMM episodes. Teacher sensitivity analysis shows that active-vision demonstrations improve student success. The simulation-trained agent achieves 38% end-to-end success on a real mobile robot without additional training. Applying AIDA to a navigation subset of EmbodiedBench further demonstrates the pipeline's utility for navigation tasks.
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。
