Kernel Reinforcement Learning-Assisted Adaptive Decoder Facilitates Stable and Continuous Brain Control Tasks

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 31; pp. 4125 - 4134
• Main Authors: Zhang, Xiang, Chen, Shuhang, Wang, Yiwen
• Format: Journal Article
• Language: English
• Published: New York IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptive control; Brain; Brain modeling; Brain-machine interface; Closed loops; Continuity (mathematics); continuous brain control; Control tasks; Decoders; Decoding; Feedback control; Kalman filters; Kernel; kernel reinforcement learning; Kernels; Learning; Man-machine interfaces; Mapping; Movement; Neural prostheses; Prostheses; Prosthetics; Rats; Reinforcement; Sensory feedback; stability over days; state-observation model; Task analysis; Trajectory; Trajectory control

Brain-Machine Interfaces (BMIs) assist paralyzed people to brain control (BC) the neuro-prosthesis continuously moving in space. During the BC process, the subject imagines the movement of the real limb and adapts the brain activity according to the sensory feedback. The neural adaptation in the clo...