Self-Supervised Learning for Joint Pushing and Grasping Policies in Highly Cluttered Environments

03/04/2022
by   Kamal Mokhtar, et al.
0

Robots often face situations where grasping a goal object is desirable but not feasible due to other present objects preventing the grasp action. We present a deep Reinforcement Learning approach to learn grasping and pushing policies for manipulating a goal object in highly cluttered environments to address this problem. In particular, a dual reinforcement learning model approach is proposed, which presents high resilience in handling complicated scenes, reaching 98 environment. To evaluate the performance of the proposed approach, we performed two extensive sets of experiments in packed objects and a pile of objects scenarios. Experimental results showed that the proposed method worked very well in both scenarios and outperformed the recent state-of-the-art approaches

READ FULL TEXT

page 1

page 2

page 4

page 5

page 6

research
03/19/2021

MVGrasp: Real-Time Multi-View 3D Object Grasping in Highly Cluttered Environments

Nowadays service robots are entering more and more in our daily life. In...
research
06/28/2022

Dext-Gen: Dexterous Grasping in Sparse Reward Environments with Full Orientation Control

Reinforcement learning is a promising method for robotic grasping as it ...
research
11/02/2021

A Hybrid Approach for Learning to Shift and Grasp with Elaborate Motion Primitives

Many possible fields of application of robots in real world settings hin...
research
03/08/2020

Online Self-Supervised Learning for Object Picking: Detecting Optimum Grasping Position using a Metric Learning Approach

Self-supervised learning methods are attractive candidates for automatic...
research
05/18/2021

Adaptive ABAC Policy Learning: A Reinforcement Learning Approach

With rapid advances in computing systems, there is an increasing demand ...
research
09/17/2019

Split Deep Q-Learning for Robust Object Singulation

Extracting a known target object from a pile of other objects in a clutt...
research
08/26/2020

Self-Supervised Goal-Conditioned Pick and Place

Robots have the capability to collect large amounts of data autonomously...

Please sign up or login with your details

Forgot password? Click here to reset