Economical Precise Manipulation and Auto Eye-Hand Coordination with Binocular Visual Reinforcement Learning

Page view(s)
5
Checked on Dec 02, 2024
Economical Precise Manipulation and Auto Eye-Hand Coordination with Binocular Visual Reinforcement Learning
Title:
Economical Precise Manipulation and Auto Eye-Hand Coordination with Binocular Visual Reinforcement Learning
Journal Title:
2024 9th International Conference on Control and Robotics Engineering (ICCRE)
Keywords:
Publication Date:
16 July 2024
Citation:
Y. Chen et al., "Economical Precise Manipulation and Auto Eye-Hand Coordination with Binocular Visual Reinforcement Learning," 2024 9th International Conference on Control and Robotics Engineering (ICCRE), Osaka, Japan, 2024, pp. 6-11, doi: 10.1109/ICCRE61448.2024.10589902.
Abstract:
Precision robotic manipulation tasks (insertion, screwing, precise pick, precise place) are required in many scenarios. Previous methods achieved good performance on such manipulation tasks. However, such methods typically require tedious calibration or expensive sensors. 3D/RGB-D cameras and torque/force sensors add to the cost of the robotic application and may not always be economical. In this work, we aim to address these issues by only 2 low-cost webcams, and minimize the reliance on manual eye-hand calibration. We propose Binocular Alignment Learning (BAL), which could automatically learn the eye-hand coordination and points alignment capabilities to solve the four tasks. Our work focuses on working with unknown eye-hand coordination and proposes different ways of performing eye-in-hand camera calibration automatically. The algorithm was trained in simulation and used a practical pipeline to achieve sim2real and test it on the real robot. Our method achieves a competitively good result with minimal cost on the four tasks. The video link of our work: https://youtu.be/gfcsGtT8IoU
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - AME Programmatic Fund
Grant Reference no. : A18A2b0046
Description:
© 2024 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2835-3722
Files uploaded:

File Size Format Action
iccre-2024-paper.pdf 5.43 MB PDF Request a copy