Modeling Grasp Type Improves Learning-Based Grasp Planning

TL;DR

This paper introduces a probabilistic, learning-based grasp planner that explicitly models grasp type, enabling real-time planning of both power and precision grasps for unseen objects with partial visual data.

Contribution

It presents the first supervised learning approach to explicitly plan both power and precision grasps, improving success rates over models without grasp type encoding.

Findings

Modeling grasp type improves grasp success rate

Learning a prior over grasp configurations enhances inference

The approach works with partial visual information on unseen objects

Abstract

Different manipulation tasks require different types of grasps. For example, holding a heavy tool like a hammer requires a multi-fingered power grasp offering stability, while holding a pen to write requires a multi-fingered precision grasp to impart dexterity on the object. In this paper, we propose a probabilistic grasp planner that explicitly models grasp type for planning high-quality precision and power grasps in real-time. We take a learning approach in order to plan grasps of different types for previously unseen objects when only partial visual information is available. Our work demonstrates the first supervised learning approach to grasp planning that can explicitly plan both power and precision grasps for a given object. Additionally, we compare our learned grasp model with a model that does not encode type and show that modeling grasp type improves the success rate of generated grasps. Furthermore we show the benefit of learning a prior over grasp configurations to improve grasp inference with a learned classifier.