Architecture design for performing grasp-and-lift tasks in brain–machine-interface-based human-in-the-loop robotic system

• Published in: IET Cyber-Physical Systems: Theory & Applications Vol. 4; no. 3; pp. 198 - 203
• Main Author: Chang, Yuchou
• Format: Journal Article
• Language: English
• Published: Southampton The Institution of Engineering and Technology 01.09.2019; John Wiley & Sons, Inc; Wiley
• Subjects: BMI-based human–robot systems; Brain; Brain research; brain-computer interfaces; brain-controlled robot; brain–machine interface controlled robots; brain–machine-interface-based human-in-the-loop robotic system; Collaboration; Communication; Electroencephalography; end effectors; Evacuations & rescues; grasp-and-lift tasks; Grasping (robotics); grippers; hardware-in-the loop simulation; human assistive GAL tasks; human brain activities; human intelligence; Human performance; human-in-the-loop robotic system; human-robot interaction; human–robot collaborative manipulations; human–robot interactions; learning (artificial intelligence); machine intelligence; Machine learning; Man-machine interfaces; medical robotics; medical signal processing; mobile robots; Nervous system; neurophysiology; nonstationary signals; Robotics; Robots; Robust control; Signal classification; Special Issue: Social and Human Aspects of Cyber-Physical Systems; Spinal cord; hardware-in-the loop simulation; electroencephalography; human-robot interaction; grippers; BMI-based human–robot systems; brain-computer interfaces; human–robot collaborative manipulations; medical robotics; machine intelligence; mobile robots; grasp-and-lift tasks; human assistive GAL tasks; brain-controlled robot; human-in-the-loop robotic system; human intelligence; brain–machine-interface-based human-in-the-loop robotic system; nonstationary signals; medical signal processing; human brain activities; brain–machine interface controlled robots; end effectors; neurophysiology; learning (artificial intelligence); human–robot interactions
• ISSN: 2398-3396; 2398-3396
• DOI: 10.1049/iet-cps.2018.5066

Human-in-the-loop robotic system is an emerging technique in recent years. Human intelligence as well as machine intelligence are incorporated to accomplish tasks efficiently and effectively. However, grasp-and-lift (GAL) tasks through human–robot interactions are still a problem in an unstructured environment like urban search and rescue. Human assistive GAL tasks enable robots to complete search or rescue procedures quickly and accurately. Brain–machine interface (BMI) controlled robots have demonstrated promising applications in human–robot collaborative manipulations. In this study, an architecture of human–robot team is proposed for performing GAL tasks in BMI-based human–robot systems. The proposed architecture contains several workflows from both human and robot aspects to improve performance. In addition, human brain activities are generally considered as non-stationary signals with varying spatial and temporal distributions. To enhance robustness and stability of brain-controlled robot's GAL tasks, a new method via adaptive boosting mechanism is proposed. The proposed multiple subjects' adaptive boosting is able to suppress noisy data and outliers in multiple subjects’ electroencephalogram signals, and therefore enhance accuracy and robustness of intention and sensation signal classification in GAL tasks. Preliminary results show that the new architecture is feasible with ethical establishment and the proposed method can outperform traditional methods.