重新审视机器人操作中的关节部件感知
Revisiting Articulated Parts Perception in Robot Manipulation
AI总结：
提出几何主结构（GPS）作为关节部件的新表示，结合VR设备实现高效标注，训练通用模型，在零样本下达到73%操作成功率。
摘要：
我们被各种带有可移动关节部件的物体所包围，例如盒子、把手、门。对关节部件的准确且可泛化的感知对于增强机器人操作能力至关重要。基于这一需求，近期在关节部件感知方面的工作遵循两个主要方向：一类工作使用基于姿态的表示，这需要高人力成本；与此同时，基于可供性的方法通过点跟踪提取未来物体运动，无需额外人工，但受限于低质量数据。在本文中，我们提出了一种新的关节部件表示——几何主结构（GPS），它是部件几何结构的抽象，以平衡可扩展性和质量。为了实现高效且可扩展的数据收集，GPS与便携式虚拟现实（VR）设备集成，只需一分钟即可标注一个物体序列。这种直接的人工标注比估计的可供性提供了更高质量。利用高效的VR-GPS系统，我们收集了6个部件类别下234个物体的41K帧数据，并训练了一个以单张RGB-D物体图像为输入的通用GPS模型。对于物体操作，我们基于GPS预测部署了一个启发式策略。无需任何领域内微调，我们的方法在9个物体的270个初始状态下达到了73%的成功率。我们的代码、数据和可复用工具可在 https://enlighten0707.github.io/gps 获取。
英文摘要：
We are surrounded by various objects with movable, articulated parts, e.g., box, handle, door. An accurate and generalizable perception of articulated parts is essential to enhance robotic manipulation capabilities. Building on this need, recent efforts in articulated parts perception have followed two main directions: One line of work uses pose-based representation, which requires high manual cost; in parallel, affordance-based methods extract future object motion from point tracking without additional manual efforts, but suffer from low-quality data. In this paper, we propose a new representation of articulated parts, Geometric Primary Structure (GPS), an abstraction of the part geometry structure to balance scalability and quality. For efficient and scalable data collection, GPS is integrated with a portable Virtual Reality (VR) device and requires only one minute to annotate one object sequence. This direct human annotation provides higher quality than the estimated affordance. With this efficient VR-GPS system, we collect 41K frames for 234 objects across six part classes, and train a generalizable GPS model with a single RGB-D object image as input. For object manipulation, we deploy a heuristic policy based on GPS prediction. Without any in-domain fine-tuning, our method achieves an 73% success rate, covering 270 initial states for 9 objects. Our code, data and reusable tool are available at https://enlighten0707.github.io/gps.
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。
