A NOVEL GENETIC ALGORITHM FOR ROBOT PATH PLANNING IN ENVIRONMENT CONTAINING LARGE NUMBERS OF IRREGULAR OBSTACLES

Robot path planning in environment containing large numbers of irregular obstacles is a typical nonlinear problem. At present there are many genetic algorithms used to solve this problem. However,for those algorithms,there are some deficiencies in generating the initial population,constructing the special genetic operators,and so on. In order to overcome those deficiencies,a novel genetic algorithm is presented. In this algorithm,the mutable length encoding scheme for broken lines is adopted,the initial population is generated based on the randomly-instructed searching strategy,and the corresponding special crossover and mutation operators are designed. The validity and high-efficiency of the proposed algorithm is validated by the simulation results.