6-DoF Closed-Loop Grasping with Reinforcement Learning
Sverre Herland,Kerstin Bach,Ekrem Misimi,Sverre Herland,Kerstin Bach,Ekrem Misimi
We present a novel vision-based, 6-DoF grasping framework based on Deep Reinforcement Learning (DRL) that is capable of directly synthesizing continuous 6-DoF actions in cartesian space. Our proposed approach uses visual observations from an eye-in-hand RGB-D camera, and we mitigate the sim-to-real gap with a combination of domain randomization, image augmentation, and segmentation tools. Our meth...
