Learning to Generate 6-DoF Grasp Poses with Reachability Awareness

10/14/2019

∙

by   Xibai Lou, et al.

∙

8

∙

share

Motivated by the stringent requirements of unstructured real-world where a plethora of unknown objects reside in arbitrary locations of the surface, we propose a voxel-based deep 3D Convolutional Neural Network (3D CNN) that generates feasible 6-DoF grasp poses in unrestricted workspace with reachability awareness. Unlike the majority of works that predict if a proposed grasp pose within the restricted workspace will be successful solely based on grasp pose stability, our approach further learns a reachability predictor that evaluates if the grasp pose is reachable or not from robot's own experience. To avoid the laborious real training data collection, we exploit the power of simulation to train our networks on a large-scale synthetic dataset. To our best knowledge, this work is the first attempt to take into account the reachability when proposing feasible grasp poses. Experimental results in both simulation and real-world demonstrate that our reachability aware 3D CNN grasping outperforms several other approaches and achieves 82.5% grasping success rate on unknown objects.