面向移动操作的主动感知运动生成
Active-Perceptive Motion Generation for Mobile Manipulation
AI总结：
本文提出 ActPerMoMa 主动感知运动生成框架，通过滚动时域路径采样与视觉信息增益、抓取可达性的效用权衡，提升移动操作机器人在杂乱场景中的抓取性能，并完成仿真验证与真实世界迁移。
摘要：
移动操作（MoMa）系统兼具机动性与灵巧性的优势，这是因为它们能够在更大的空间中移动并与环境交互。然而，即使配备了机载传感器（例如嵌入式相机），在家庭等非结构化且杂乱的环境中提取与任务相关的视觉信息仍然具有挑战性。在本工作中，我们为移动操作机器人引入了一种主动感知流程，用于生成对操作任务具有信息量的运动，例如在未知、杂乱场景中的抓取任务。我们提出的方法 ActPerMoMa 通过采样路径并计算逐路径效用，以滚动时域方式生成机器人路径。这些效用在用于场景重建的视觉信息增益（IG）最大化与面向任务的目标（例如抓取成功）之间进行权衡，具体通过最大化抓取可达性来实现。我们在仿真实验中展示了方法的有效性：使用双臂 TIAGo++ MoMa 机器人在带有障碍物的杂乱场景中执行移动抓取。我们通过实验分析了各种效用和参数的贡献，并与包含和不包含主动感知目标的代表性基线进行了比较。最后，我们展示了将该移动抓取策略迁移到真实世界，表明这是主动感知型 MoMa 的一个有前景方向。
英文摘要：
Mobile Manipulation (MoMa) systems incorporate the benefits of mobility and dexterity, due to the enlarged space in which they can move and interact with their environment. However, even when equipped with onboard sensors, e.g., an embodied camera, extracting task-relevant visual information in unstructured and cluttered environments, such as households, remains challenging. In this work, we introduce an active perception pipeline for mobile manipulators to generate motions that are informative toward manipulation tasks, such as grasping in unknown, cluttered scenes. Our proposed approach, ActPerMoMa, generates robot paths in a receding horizon fashion by sampling paths and computing path-wise utilities. These utilities trade-off maximizing the visual Information Gain (IG) for scene reconstruction and the task-oriented objective, e.g., grasp success, by maximizing grasp reachability. We show the efficacy of our method in simulated experiments with a dual-arm TIAGo++ MoMa robot performing mobile grasping in cluttered scenes with obstacles. We empirically analyze the contribution of various utilities and parameters, and compare against representative baselines both with and without active perception objectives. Finally, we demonstrate the transfer of our mobile grasping strategy to the real world, indicating a promising direction for active-perceptive MoMa.
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。
