Fast geometry-based computation of grasping points on three-dimensional point clouds

Brayan S Zapata-Impata,Pablo Gil,Fernando Torres,Jorge Pomares

doi:10.1177/1729881419831846

Brayan S Zapata-Impata, Pablo Gil + Show 2 more

Open Access

https://doi.org/10.1177/1729881419831846

Copy DOI

Abstract

Industrial and service robots deal with the complex task of grasping objects that have different shapes and which are seen from diverse points of view. In order to autonomously perform grasps, the robot must calculate where to place its robotic hand to ensure that the grasp is stable. We propose a method to find the best pair of grasping points given a three-dimensional point cloud with the partial view of an unknown object. We use a set of straightforward geometric rules to explore the cloud and propose grasping points on the surface of the object. We then adapt the pair of contacts to a multi-fingered hand used in experimentation. We prove that, after performing 500 grasps of different objects, our approach is fast, taking an average of 17.5 ms to propose contacts, while attaining a grasp success rate of 85.5%. Moreover, the method is sufficiently flexible and stable to work with objects in changing environments, such as those confronted by industrial or service robots.

Highlights

Robotic grasping is an important topic in industrial and service robotics with a broad multidisciplinary approach, such as motion planning, control and perception, among others.[1]
The grasping problem focuses on determining a set of contact points on the surface of the object in order to automatically carry out a manipulation task, either using robots with grippers or multi-fingered hands.[2]
With the changes introduced in this work, we evaluate more appropriately the angle defined by the line that connects the grasping points and the axis of the objects

Summary

Introduction

Robotic grasping is an important topic in industrial and service robotics with a broad multidisciplinary approach, such as motion planning, control and perception, among others.[1]. The field of robotic grasping when robots operate in unknown environments or under changing conditions is still being researched. These situations are currently becoming more frequent in a wide variety of applications within Industry 4.0, such as the flexible manufacturing processes in smart factories,[5] the restocking and warehouse tasks in smart stores,[6,7] automated deliveries from distribution centres and logistics[8] or household assistants,[9] among others

Objectives

Methods

Findings

Conclusion