GAMMA：基于在线抓取位姿融合的可抓取性感知移动操作策略学习
GAMMA: Graspability-Aware Mobile MAnipulation Policy Learning based on Online Grasping Pose Fusion
AI总结：
本文提出GAMMA，通过在线融合、去冗余与去离群的抓取位姿构建强化学习观测状态，从而在移动接近过程中保持时间一致的抓取观测，并依据位姿数量与质量评估可抓取性。
摘要：
移动操作是机器人助理的一项基础任务，并在机器人学界受到广泛关注。移动操作固有的一个关键挑战，是在接近目标以进行抓取时对其进行有效观测。在本工作中，我们提出一种可抓取性感知的移动操作方法，该方法由在线抓取位姿融合框架驱动，能够实现时间一致的抓取观测。具体而言，系统会在线整理预测得到的抓取位姿，以剔除冗余及离群的抓取位姿；这些位姿可被编码为用于强化学习的抓取位姿观测状态。此外，对抓取位姿进行实时融合，还能够直接评估可抓取性，评估同时涵盖抓取位姿的数量与质量。
英文摘要：
Mobile manipulation constitutes a fundamental task for robotic assistants and garners significant attention within the robotics community. A critical challenge inherent in mobile manipulation is the effective observation of the target while approaching it for grasping. In this work, we propose a graspability-aware mobile manipulation approach powered by an online grasping pose fusion framework that enables a temporally consistent grasping observation. Specifically, the predicted grasping poses are online organized to eliminate the redundant, outlier grasping poses, which can be encoded as a grasping pose observation state for reinforcement learning. Moreover, on-the-fly fusing the grasping poses enables a direct assessment of graspability, encompassing both the quantity and quality of grasping poses.
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。
