Robotic arm control system based on brain-muscle mixed signals

Aiming at the existing problems of BCI (brain computer interface), such as single input signal source, low accuracy feature recognition, and less output control instructions, this paper proposes a robotic arm system based on EEG (electroencephalogram) EMG (electromyogram) mixed signals. The flow is follows: Firstly, unilateral left right hand motor imagery collected synchronously. Then signals are extracted classified, corresponding classification instructions obtained. Finally, multi-instruction real-time realized under instruction. experimental verification results show that: 10 subjects all multi-command arm, average was more than 94%, were good, success rate tasks 80%. proposed enriches diversity hybrid provides theoretical basis application foundation for extended in control.