基于实时意图识别的外骨骼机器人步态切换  

Gait Switching of Exoskeleton Robot Based on Real-Time Intention Recognition

作　　者：宋春宁[1] 郭子铭 王灿[2] SONG Chun-ning;GUO Zi-ming;WANG Can(College of Electrical Engineering,Guangxi University,Nanning Guangxi 530004,China;Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen Guangdong 518055,China)

机构地区：[1]广西大学电气工程学院,广西南宁530004 [2]中国科学院深圳先进技术研究院,广东深圳518055

出　　处：《计算机仿真》2021年第12期334-340,共7页Computer Simulation

基　　金：国家自然科学基金(51767005,2017YBF1302303);广西自然科学基金(2016GXNSFAA380328)。

摘　　要：根据外骨骼穿戴者的实时运动意图,切换外骨骼机器人的行走步态,是外骨骼机器人研究热点问题之一。针对外骨骼机器人能够根据穿戴者的运动意图控制步态切换问题,提出采集人体表面肌电信号进行解码,通过BP神经网络识别穿戴者的运动意图,实现外骨骼进行步态规划,利用关节角度与足底压力的相关性以及重心轨迹,对所规划的步态的稳定性进行分析,依据不同的运动意图完成步态进行实时切换,验证了基于实时意图识别控制的外骨骼步态切换的可行性。According to the real-time motion intention of exoskeleton wearers, switching the walking gait of theexoskeleton robot is one of the hot issues in the research of the exoskeleton robot. Aiming at the problem that exoskel-eton robot can control gait switching according to the wearer’s motion intention, this paper proposes to collect humansurface EMG signal for decoding, identify the wearer’s motion intention by BP neural network, realize the exoskeletongait planning, analyze the stability of the planned gait by using the correlation between joint angle and plantar pres-sure and center of gravity trajectory. The feasibility of exoskeleton gait switching based on real-time intention recogni-tion control is verified.

关 键 词：外骨骼机器人 意图识别 步态规划 稳定 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]