Construction of simultaneous execution theory of object recognition and manipulation in robot work with an uncertain environment

2020 Fiscal Year Final Research Report

• Project/Area Number: 18K04048
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 20020:Robotics and intelligent system-related
• Research Institution: Ritsumeikan University (2019-2020); Osaka University (2018)
• Principal Investigator: Uemura Mitsunori 立命館大学, 理工学部, 准教授 (00512443)
• Project Period (FY): 2018-04-01 – 2021-03-31
• Keywords: ロボット作業 / 不確定環境 / 環境認識 / ロボット制御 / 軽量 / 高逆可動

Outline of Final Research Achievements

In this project, we obtained the following results.(1) We manufactured a wire drive mechanism, wire drive robot, and hand that are lightweight and have high back-drivability.(2) We constructed an algorithm that enables acquisition of movement information and segmentation of uncertain objects from feature points on moving images and movement information of each pixel.(3) We proposed a control method that detects the direction of the mechanical center of gravity of an uncertain object by controlling the robot so as to suppress the rotation of the object. After the robot detects the direction of the center of gravity, the robot can stably grasp the uncertain object by sandwiching the center of gravity.

Free Research Field

ロボティクス

Academic Significance and Societal Importance of the Research Achievements

不確定環境下でロボットが作業するために必要な、ハードウェアと環境認識、物体操作に関する新しい枠組みを提案した。本枠組みでは、ロボットと不確定な物体との接触を利用し、物体の動きを利用した認識や、物体の動きを抑制する制御により、物体情報がわからなくても物体を認識しつつ、安定に把持できる。
本手法を拡張していけば、現在産業界で人手に頼っている作業の多くを自動化することができると期待できる。