论文标题
使用纯对象检测的移动机器人操纵
Mobile Robot Manipulation using Pure Object Detection
论文作者
论文摘要
本文使用对象检测解决了移动机器人操纵的问题。我们的方法将检测和控制用作免费的功能，这些功能从现实世界中的相互作用中学习。我们仅基于检测而开发一种端到端的操作方法，并引入以任务为中心的少数弹出对象检测（TFOD）来学习新对象和设置。我们的机器人收集了自己的培训数据，并自动确定何时重新训练检测以提高各种子任务的性能（例如，掌握）。值得注意的是，检测训练是低成本的，我们的机器人学会了使用以下四次注释来操纵新对象。在物理实验中，我们的机器人从单击的注释和新颖的更新配方中学习了视觉控制，操纵了混乱和其他移动设置中的新对象，并在现有的视觉伺服控制和深度估计基准中实现了最先进的结果。最后，我们开发了一个TFOD基准，以支持机器人技术的未来对象检测研究：https：//github.com/griffbr/tfod。
This paper addresses the problem of mobile robot manipulation using object detection. Our approach uses detection and control as complimentary functions that learn from real-world interactions. We develop an end-to-end manipulation method based solely on detection and introduce Task-focused Few-shot Object Detection (TFOD) to learn new objects and settings. Our robot collects its own training data and automatically determines when to retrain detection to improve performance across various subtasks (e.g., grasping). Notably, detection training is low-cost, and our robot learns to manipulate new objects using as few as four clicks of annotation. In physical experiments, our robot learns visual control from a single click of annotation and a novel update formulation, manipulates new objects in clutter and other mobile settings, and achieves state-of-the-art results on an existing visual servo control and depth estimation benchmark. Finally, we develop a TFOD Benchmark to support future object detection research for robotics: https://github.com/griffbr/tfod.
