A Novel Immune Network Strategy for Robot Path Planning in Complicated Environments

Abstract

To solve the path planning in complicated environments, an improved artificial immune network strategy for robot path planning is presented. Taking the environment surrounding the robot and robot action as antigen and antibody respectively, an artificial immune network is constructed through the stimulation and suppression between the antigen and antibody, and the optimal path is searched in the network. To further improve the convergence property of immune network, the planning results of artificial potential field (APF) method is taken as the prior knowledge, and the instruction definition of new antibody is initialized through the vaccine extraction and inoculation. The accessibility of proposed improved immune network algorithm (IINA) is analyzed using the Markov chain theory. Compared with simple immune network algorithm (SINA) and ant colony algorithm (ACA), simulation results indicate that the proposed algorithm is characterized by high convergence speed, short planning path and self-learning, which solves the path planning well in complicated environments.