Carrying Robot Walking Control Based on Genetic Algorithm

To complete the control of exoskeleton carrying robot perfectly, the human-machine interaction forces model should be identified, which can be simulated using spring-damper model, that is, the coefficient elasticity and damping should be gotten. For the coupling of the several joints, the parameters should be optimized from the system global performance. In this paper, genetic algorithm is used to identification interaction parameters. Pseudo-gradient is introduced and the individual pseudo-gradient justification is used in genetic algorithm. Annealing selection according to the fitness is given to keep the population diversity, and the memory mechanism is added to speed up evolution. Combing the characteristics of the lower extremity carrying robot walking, the detail human-machine interaction forces identification method using the improved genetic algorithm is given and the quasi-Newton iterative learning control simulation results show the validity of the method.