What question did this study set out to answer?

This work aims to enhance the detection of robotic grasps in RGB-D views by applying a deep learning approach.

Deep learning for detecting robotic grasps

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates robotic grasp detection in RGB-D scenes, suggesting improved grasping performance.

This work aims to enhance the detection of robotic grasps in RGB-D views by applying a deep learning approach.
Two-step cascaded system using two deep networks for grasp detection.
First network rapidly prunes unlikely candidate grasps with fewer features.
Second network re-evaluates top detections with more features for accuracy.
Improved detection performance on an RGB-D robotic grasping dataset.
Successfully executed grasps on two different robotic platforms.

Lenz et al. (2015) studied this question.

View Full Paper

Ask AI

Bookmark