Transferring Experience from Simulation to the Real World for Precise Pick-And-Place Tasks in Highly Cluttered Scenes

01/12/2021
by   Kilian Kleeberger, et al.
5

In this paper, we introduce a novel learning-based approach for grasping known rigid objects in highly cluttered scenes and precisely placing them based on depth images. Our Placement Quality Network (PQ-Net) estimates the object pose and the quality for each automatically generated grasp pose for multiple objects simultaneously at 92 fps in a single forward pass of a neural network. All grasping and placement trials are executed in a physics simulation and the gained experience is transferred to the real world using domain randomization. We demonstrate that our policy successfully transfers to the real world. PQ-Net outperforms other model-free approaches in terms of grasping success rate and automatically scales to new objects of arbitrary symmetry without any human intervention.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

research
10/03/2021

Precise Object Placement with Pose Distance Estimations for Different Objects and Grippers

This paper introduces a novel approach for the grasping and precise plac...
research
04/01/2020

Learning to Place Objects onto Flat Surfaces in Human-Preferred Orientations

We study the problem of placing a grasped object on an empty flat surfac...
research
08/07/2016

Deep Learning a Grasp Function for Grasping under Gripper Pose Uncertainty

This paper presents a new method for parallel-jaw grasping of isolated o...
research
09/04/2019

Directional Semantic Grasping of Real-World Objects: From Simulation to Reality

We present a deep reinforcement learning approach to grasp semantically ...
research
09/21/2022

GP-net: Grasp Proposal for Mobile Manipulators

We present the Grasp Proposal Network (GP-net), a Convolutional Neural N...
research
05/13/2020

Action Image Representation: Learning Scalable Deep Grasping Policies with Zero Real World Data

This paper introduces Action Image, a new grasp proposal representation ...
research
01/04/2021

A Pushing-Grasping Collaborative Method Based on Deep Q-Network Algorithm in Dual Perspectives

Aiming at the traditional grasping method for manipulators based on 2D c...

Please sign up or login with your details

Forgot password? Click here to reset