An Online Robot Collision Detection and Identification Scheme by Supervised Learning and Bayesian Decision Theory

• Published in: IEEE transactions on automation science and engineering Vol. 18; no. 3; pp. 1144 - 1156
• Main Authors: Zhang, Zengjie, Qian, Kun, Schuller, Bjorn W., Wollherr, Dirk
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.07.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accidental collisions; Anomaly monitoring; Bayesian analysis; Classifiers; Collaboration; Collision avoidance; collision detection and identification (CDI); collision event pipeline; Datasets; Decision theory; Event handling; Fault detection; fault detection and isolation; human-robot interaction; Machine learning; Reliability engineering; Response time; Robot arms; robot safety; Robot sensing systems; Robots; Signal classification; Structural reliability; Supervised learning; Time series analysis; Torque sensors (robotics)

This article is dedicated to developing an online collision detection and identification (CDI) scheme for human-collaborative robots. The scheme is composed of a signal classifier and an online diagnosor, which monitors the sensory signals of the robot system, detects the occurrence of a physical hu...