Learning to Generate 6-DoF Grasp Poses with Reachability Awareness

TL;DR

This paper introduces a voxel-based 3D CNN that generates feasible 6-DoF grasp poses with reachability awareness, trained in simulation, and demonstrates high success rates on unknown objects in real-world tests.

Contribution

It presents a novel approach combining grasp pose generation with reachability prediction using deep learning, trained entirely in simulation.

Findings

Achieves 82.5% grasp success rate on unknown objects.

Outperforms existing methods in simulation and real-world tests.

Introduces a reachability predictor integrated with grasp pose generation.

Abstract

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. This work is an early attempt that simultaneously evaluates grasping reachability from learned knowledge while proposing feasible grasp poses with 3D CNN. Experimental results in both simulation and real-world demonstrate that our approach outperforms several other methods and achieves 82.5% grasping success rate on unknown objects.