Study on Dynamics based Intelligence of Hyper-redundant Mechanical Systems with Variable Constraints

我们将非线性系统的“基于动力学的控制”的概念推广到非完整超冗余度系统。提出了基于动力学控制的超冗余度系统的强化学习算法，研究结果如下：1.推导了具有非完整约束的超冗余度系统动力学模型。具有非完整约束的超冗余度系统基于模型的控制律的构造和所提出的控制律的有效性的实验证明。基于动力学的无限维系统控制律的构造和柔性机械系统控制律有效性的实验论证。基于动力学控制的超余度系统强化学习算法设计5。以冗余度蛇形机器人为例验证了强化学习方法的有效性

We have extended the concept of "Dynamic based Control" of the nonlinear system to the nonholonomic hyperredundant systems. We have proposed the reinforcement learning algorithm for the hyperredundant systems based on the dynamics based control.The results obtained in the research are as follows:1. Derivation of dynamic model of hyperredundant systems with nonholonomic constraints2. Construction of model based control law for hyperredundant systems with nonholonomic constraints and experimental demonstration of effectiveness of the proposed control law3. Construction of dynamics based control law for infinite dimensional systems and experimental demonstration of effectiveness of the proposed control law for flexible mechanical systems4. Design of the reinforcement learning algorithm for the hyperredundant systems based on the dynamics based control5. Experimental demonstration of effectiveness of the proposed reinforcement learning method by using a redundant snake-like robot