LAUSR

This paper proposes a hybrid improved quantum-behaved particle swarm optimization (LTQPSO) for autonomous mobile robot (AMR) trajectory planning in the environment with random obstacles. The algorithm combines the individual particle evolutionary rate and the swarm dispersion with natural selection method in particle evolution process. It is tested on several benchmark functions and proved that the convergence capability and accuracy are better than conventional QPSO, WQPSO and IQPSOS algorithms. To assess the effectiveness and feasibility of the proposed method on real problems, it is applied to the trajectory planning for AMR in the environment with random obstacles. The relationships between basic parameters are analyzed and formulated according to initial distribution of the LTQPSO. To show the high capability of the improved method, the LTQPSO is compared with QPSO, WQPSO and IQPSOS in the aspects of solution quality, robustness and convergence property. Experimental results demonstrate that the modified LTQPSO is very effective.