Stroeve S
Measurement and Control Laboratory, Faculty of Mechanical Engineering and Marine Technology, Delft University of Technology, The Netherlands.
Biol Cybern. 1996 Jul;75(1):73-83. doi: 10.1007/BF00238741.
The goal of this paper is the learning of neuromuscular control, given the following necessary conditions: (1) time delays in the control loop, (2) non-linear muscle characteristics, (3) learning of feedforward and feedback control, (4) possibility of feedback gain modulation during a task. A control system and learning methodology that satisfy those conditions is given. The control system contains a neural network, comprising both feedforward and feedback control. The learning method is backpropagation through time with an explicit sensitivity model. Results will be given for a one degree of freedom arm with two muscles. Good control results are achieved which compare well with experimental data. Analysis of the controller shows that significant differences in controller characteristics are found if the loop delays are neglected. During a control task the system shows feedback gain modulation, similar to experimentally found reflex gain modulation during rapid voluntary contraction. If only limited feedback information is available to the controller the system learns to co-contract the antagonistic muscle pair. In this way joint stiffness increases and stable control is more easily maintained.
（1）控制回路中的时间延迟；（2）非线性肌肉特性；（3）前馈和反馈控制的学习；（4）任务执行期间反馈增益调制的可能性。给出了一种满足这些条件的控制系统和学习方法。该控制系统包含一个神经网络，包括前馈和反馈控制。学习方法是带有显式灵敏度模型的时间反向传播。将给出具有两块肌肉的单自由度手臂的结果。取得了良好的控制结果，与实验数据相比效果良好。对控制器的分析表明，如果忽略回路延迟，会发现控制器特性存在显著差异。在控制任务期间，系统显示出反馈增益调制，类似于在快速自主收缩期间实验发现的反射增益调制。如果控制器只有有限的反馈信息，系统会学习共同收缩拮抗肌对。通过这种方式，关节刚度增加，更易于维持稳定控制。
