Concurrent and Continuous Prediction of Finger Kinetics and Kinematics via Motoneuron Activities
Concurrent and Continuous Prediction of Finger Kinetics and Kinematics via Motoneuron Activities
复制标题
DOI：
10.1109/tbme.2022.3232067
复制
发表时间：
2022-12
影响因子：
4.6
通讯作者：
R. Roy;Yang Zheng;Derek G. Kamper;Xiaogang Hu
中科院分区：
文献类型：
--
作者：
R. Roy;Yang Zheng;Derek G. Kamper;Xiaogang Hu
目的：鲁棒的神经解码预期的运动输出是至关重要的，使辅助设备的直观控制，如机械手，执行日常任务。现有的神经解码器很少能同时预测运动和运动变量。目前的研究开发了一种连续神经解码方法，可以同时预测多个手指的指尖力和关节角度。方法：通过分解手指外源性肌肉的高密度肌电图（HD EMG）信号，获得运动神经元的放电活动。首先对识别出的运动神经元进行分组，然后针对每个手指（食指或中指）和任务（手指力量和动态运动）组合进行细化。然后将精炼的运动神经元组（单独的矩阵）直接应用于涉及手指力和两个手指产生的动态运动任务的实时新肌电图数据。基于肌电振幅的预测也进行了比较。结果：我们发现新开发的解码方法在手指力和关节角估计方面都优于肌电振幅法，预测误差更低（力：3.47±0.43 vs 6.64±0.69% MVC，关节角：5.40±0.50°vs 12.8±0.65°），估计和记录的电机输出之间的相关性更高（力：0.75±0.02 vs 0.66±0.05，关节角：0.94±0.01 vs 0.5±0.05）。两个手指的表现也是一致的。结论：所开发的神经解码算法能够实时准确并发地预测多根手指的指力和关节角度。意义：我们的方法可以实现与辅助机器人手的直观交互，并允许执行灵巧的手技能，包括力控制任务和动态运动控制任务。
Objective: Robust neural decoding of intended motor output is crucial to enable intuitive control of assistive devices, such as robotic hands, to perform daily tasks. Few existing neural decoders can predict kinetic and kinematic variables simultaneously. The current study developed a continuous neural decoding approach that can concurrently predict fingertip forces and joint angles of multiple fingers. Methods: We obtained motoneuron firing activities by decomposing high-density electromyogram (HD EMG) signals of the extrinsic finger muscles. The identified motoneurons were first grouped and then refined specific to each finger (index or middle) and task (finger force and dynamic movement) combination. The refined motoneuron groups (separate matrix) were then applied directly to new EMG data in real-time involving both finger force and dynamic movement tasks produced by both fingers. EMG-amplitude-based prediction was also performed as a comparison. Results: We found that the newly developed decoding approach outperformed the EMG-amplitude method for both finger force and joint angle estimations with a lower prediction error (Force: 3.47±0.43 vs 6.64±0.69% MVC, Joint Angle: 5.40±0.50° vs 12.8±0.65°) and a higher correlation (Force: 0.75±0.02 vs 0.66±0.05, Joint Angle: 0.94±0.01 vs 0.5±0.05) between the estimated and recorded motor output. The performance was also consistent for both fingers. Conclusion: The developed neural decoding algorithm allowed us to accurately and concurrently predict finger forces and joint angles of multiple fingers in real-time. Significance: Our approach can enable intuitive interactions with assistive robotic hands, and allow the performance of dexterous hand skills involving both force control tasks and dynamic movement control tasks.