No abstract

To solve the task allocation of multi-robot systems, a novel explosive evolution - based immune genetic algorithm (EIGA) is presented. On the basis of the immune genetic algorithm (IGA), the population number of EIGA is increased quickly through explosive evolutionary mode, and then the better individuals are selected through the comparison of allelic genes, which can improve the population quality with the premise of ensuring the population diversity, and enhance the search speed and search precision of EIGA. Compared with the IGA and genetic algorithm (GA), the simulation results indicate that the proposed EIGA is characterized by quick convergence speed, high optimization precision and good stability, and the tasks are allocated rationally and scientifi-cally which realizes the task cooperation of multi-robot systems well.

To solve the mobile robot path planning in uncertain environments, a new path planning algorithm is presented on the basis of the biological immune network. The environment surrounding the robot is taken as the antigen, and the behavior strategy of robot is taken as the antibody. The selection model of antibody concentration is defined based on the Jernes idiotypic immune network hypothesis, and the mobile robot path planning is realized through the selection of the antibody concentration. The simulation of path planning for mobile robot in multi-obstacle environments shows that the robot can find a safe path in complicated environments, which verifies the better adaptivity of proposed planning model. The simulation in dynamic environments shows that the robot can safely avoid all dynamic obstacles, which verifies the better flexility of new algorithm.

No abstract

By making use of the characteristics of ergodicity, randomicity and regularity of chaotic variables and information entropy, a novel chaotic small-world algorithm is presented to improve the optimization performance of the simple small-world algorithm. Compared with the corresponding simple small-world algorithm and the modified genetic algorithm approach, the optimization results of selected complex functions indicate that the proposed chaotic small-world algorithm is characterized by a strong search capability and a quick convergence speed. A study of parameter performance of the chaotic small-world algorithm aids in further improvement of its optimization capability. Additionally, the chaotic small-world algorithm is applied to mobile robot path planning, and the global path is optimized by the chaotic small-world algorithm based on a MAKLINK graph. Finally, experimental results verify the validity of the chaotic smallworld algorithm for robot path planning.