Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Rendering

TL;DR

This paper introduces NeuGraspNet, a neural surface rendering approach for 6DoF robotic grasping in cluttered scenes from any viewpoint, enabling effective grasp detection without scene exploration.

Contribution

It presents a novel neural rendering-based method for 6DoF grasp detection that leverages surface rendering and shared feature spaces, improving grasp prediction in cluttered, partially observed scenes.

Findings

Outperforms existing implicit and semi-implicit grasping methods.

Demonstrated successful real-world grasping with a mobile robot.

Operates effectively from random viewpoints in cluttered environments.

Abstract

A significant challenge for real-world robotic manipulation is the effective 6DoF grasping of objects in cluttered scenes from any single viewpoint without the need for additional scene exploration. This work reinterprets grasping as rendering and introduces NeuGraspNet, a novel method for 6DoF grasp detection that leverages advances in neural volumetric representations and surface rendering. It encodes the interaction between a robot's end-effector and an object's surface by jointly learning to render the local object surface and learning grasping functions in a shared feature space. The approach uses global (scene-level) features for grasp generation and local (grasp-level) neural surface features for grasp evaluation. This enables effective, fully implicit 6DoF grasp quality prediction, even in partially observed scenes. NeuGraspNet operates on random viewpoints, common in mobile manipulation scenarios, and outperforms existing implicit and semi-implicit grasping methods. The real-world applicability of the method has been demonstrated with a mobile manipulator robot, grasping in open, cluttered spaces. Project website at https://sites.google.com/view/neugraspnet