An Improved Artificial Immune Algorithm for Trajectory Optimization Based on Comprehensive Index

In this paper, we focus on the trajectory optimization of upper limb rehabilitation robot for stroke patients. It is essential to balance the effectiveness and the comfort in guaranteeing the rehabilitation efficacy. According to the actual condition of stroke patients, the human engineering index, smoothness index, minimum energy criterion index, pain index and rehabilitation index are considered as key issues of a multi-objective problem. Then the artificial immune genetic algorithm is used to optimize the problem. In order to ensure the population diversity, a niche evolution algorithm is applied to prevent premature convergence effectively. It is shown by simulations that a fast convergence to global optimum and a smooth trajectory could be gotten via the immune algorithm. Velocity and acceleration curves are stable and without saltation, which meets the standards of upper limb movement characteristics.