Convolutional multi-grasp detection using grasp path for RGBD images
Lists
Only you see this
Abstract
Highlights•A fairer evaluation on grasp quality using the relationship between predicted grasp and mapped grasp.•Introduce the concept of grasp path to reveal the distribution of ground truths.•Back-propagate the “real” error to update the detection model.•Experiments are performed on both public dataset and real-world scenario.
BibTeX
@article{chen2019convolutional,
author = {Lu Chen and Panfeng Huang and Zhongjie Meng},
title = {{Convolutional multi-grasp detection using grasp path for RGBD images}},
journal = {Robotics Auton. Syst},
year = {2019},
doi = {10.1016/j.robot.2019.01.009},
}Loading related content...