Information-Theoretic Exploration for Adaptive Robotic Grasping in Clutter Based on Real-Time Pixel-Level Grasp Detection
- 1 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 71 (3) , 2683-2693
Abstract
Robust robotic grasping in clutter still remains a challenging problem despite its great practical value. This article presents an information-theoretic exploration approach that aims to improve the grasp estimation quality in a complex environment. First, a lightweight grasp detector that is composed of inverted residual blocks and a pyramid pooling module is proposed to make more accurate pixelwise predictions in real time, which are then projected to the workspace. To measure the uncertainty of estimations in the workspace, a two-dimensional grasp entropy (2D-GE) is defined, and the Gaussian process is applied to regress the variation of the information gain that is approximated by 2D-GEs. Finally, guided by the information gain, depth cost, and distance cost, our approach is able to actively collect and fuse estimations from multiple informative viewpoints through the exploration that finally converges to a refined best grasp, resulting improved grasping performance with a higher success rate and environmental adaptability in clutter. Simulation and robotic experiment are both performed to demonstrate the effectiveness of our method and compare it to baselines.Keywords
Funding Information
- National Key R&D Program of China (2017YFC0110804)
This publication has 33 references indexed in Scilit:
- Gaussian processes autonomous mapping and exploration for range-sensing mobile robotsAutonomous Robots, 2017
- Grasp Pose Detection in Point CloudsThe International Journal of Robotics Research, 2017
- Viewpoint selection for grasp detection2017
- Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics2017
- Warped Gaussian Processes Occupancy Mapping With Uncertain InputsIEEE Robotics and Automation Letters, 2017
- Active vision for dexterous grasping of novel objects2016
- Deep learning for detecting robotic graspsThe International Journal of Robotics Research, 2015
- Gaussian process occupancy mapsThe International Journal of Robotics Research, 2012
- Domain transform for edge-aware image and video processingACM Transactions on Graphics, 2011
- Efficient grasping from RGBD images: Learning using a new rectangle representation2011