Embodied Interface for Enhanced Teleoperation of Intelligent Robots

2023 Fiscal Year Final Research Report

• Project/Area Number: 22K14222
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 20020:Robotics and intelligent system-related
• Research Institution: Nagoya University
• Principal Investigator: Zhu Yaonan 名古屋大学, 工学研究科, 特任助教 (80924068)
• Project Period (FY): 2022-04-01 – 2024-03-31
• Keywords: 遠隔操作 / インターフェース / 協調制御 / 知能ロボティクス

Outline of Final Research Achievements

In this research project, an interface that considers human embodiment was developed to enable intuitive teleoperation, and a shared control method was proposed to reduce operator workload and enhance operation efficiency. In the first year, a vision-based tactile sensor was attached to a parallel gripper to estimate the grasping force, and by integrating it with a commercial tactile device, a teleoperation system capable of providing force feedback was developed. In the final year, grasping poses were detected from point cloud data obtained using an RGBD camera, and the feasible grasping pose was selected considering the manipulability of the robot arm to assist grasping operations. This shared control method contributed to improved operability during teleoperation and reduced task completion time. The research outcomes were published at international journals and conferences.

Free Research Field

ロボット工学

Academic Significance and Societal Importance of the Research Achievements

本研究は直感的な遠隔操作を可能にする身体性を伴う操作インターフェイスと協調制御手法を開発した。これにより遠隔操作の操作性向上及び操作者の負担軽減を実現した。本研究の成果は家庭、医療、農業など多岐にわたる分野での応用が期待できる。また、AIによる協調制御の実現は遠隔操作の知識が限られたユーザーでも直感的な操作を可能にし、遠隔操作システムの一般化と普及に寄与する。身体性を考慮したインターフェースとAIの統合により直感的な操作方法を確立することで、遠隔操作の課題解決、人・AIロボット協働の発展に貢献した点で学術的意義がある。