Multi-Fingered Grasp Planning via Inference in Deep Neural Networks

TL;DR

This paper introduces a deep neural network-based method for multi-fingered grasp planning that predicts grasp success probabilities and infers optimal configurations, validated on a physical robot with superior performance.

Contribution

It is the first to directly plan high-quality multi-fingered grasps in configuration space using deep neural networks without external planners.

Findings

Outperforms existing neural network-based grasp planning methods.

Object conditional prior improves grasp inference accuracy.

Validated on a physical robot with successful grasping results.

Abstract

We propose a novel approach to multi-fingered grasp planning leveraging learned deep neural network models. We train a voxel-based 3D convolutional neural network to predict grasp success probability as a function of both visual information of an object and grasp configuration. We can then formulate grasp planning as inferring the grasp configuration which maximizes the probability of grasp success. In addition, we learn a prior over grasp configurations as a mixture density network conditioned on our voxel-based object representation. We show that this object conditional prior improves grasp inference when used with the learned grasp success prediction network when compared to a learned, object-agnostic prior, or an uninformed uniform prior. Our work is the first to directly plan high quality multi-fingered grasps in configuration space using a deep neural network without the need of an external planner. We validate our inference method performing multi-finger grasping on a physical robot. Our experimental results show that our planning method outperforms existing grasp planning methods for neural networks.