Motion ReTouch: Motion Modification Using Four-Channel Bilateral Control
Inami, Koki, Sakaino, Sho, Tsuji, Toshiaki
–arXiv.org Artificial Intelligence
--Recent research has demonstrated the usefulness of imitation learning in autonomous robot operation. In particular, teaching using four-channel bilateral control, which can obtain position and force information, has been proven effective. However, control performance that can easily execute high-speed, complex tasks in one go has not yet been achieved. We propose a method called Motion ReT ouch, which retroactively modifies motion data obtained using four-channel bilateral control. The proposed method enables modification of not only position but also force information. This was achieved by the combination of multilateral control and motion-copying system. The proposed method was verified in experiments with a real robot, and the success rate of the test tube transfer task was improved, demonstrating the possibility of modification force information. I. INTRODUCTION In recent years, imitation learning [1] [2] [3], a learning-based approach that enables robots to imitate human behavior, has been attracting attention.
arXiv.org Artificial Intelligence
Feb-28-2025
- Country:
- Asia > Japan
- Honshū > Kantō
- Ibaraki Prefecture > Tsukuba (0.05)
- Saitama Prefecture > Saitama (0.05)
- Honshū > Kantō
- North America > United States (0.04)
- Asia > Japan
- Genre:
- Research Report > New Finding (0.86)
- Technology:
- Information Technology > Artificial Intelligence > Robots (1.00)