在近日召开的 ICRA (国际机器人与自动化会议)大会上,上海交大-非夕科技联合实验室展示了最新研究成果「AnyGrasp」([https://graspnet.net/anygrasp.html](https://graspnet.net/anygrasp.html)),第一次实现机器人对于任意场景的任意物体的通用高速抓取,在机械臂硬件构型、相机不作限制的情况下,让机器人拥有比肩人类抓取能力的可能。
【1】EGAD! an Evolved Grasping Analysis Dataset for diversity and reproducibility in robotic manipulation,Douglas Morrison , Peter Corke , Jurgen Leitner,IEEE Robotics & Automation Letters, 2020
【2】Learning ambidextrous robot grasping policies, Jeffrey Mahler, Matthew Matl, Vishal Satish, Michael Danielczuk, Bill DeRose, Stephen McKinley, Ken Goldberg, Science Robotics, 2019
【3】GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping, Hao-Shu Fang; Chenxi Wang; Minghao Gou; Cewu Lu, CVPR, 2020