Online Time-Optimal Trajectory Planning for Robotic Manipulators Using Adaptive Elite Genetic Algorithm with Singularity Avoidance

Abstract

In this paper, a new method of online planning high smooth and time-optimal trajectory for robotic manipulators that applies an adaptive elite genetic algorithm with singularity avoidance (AEGA-SA) is presented. The strategy is designed as a combination of the time-optimal trajectory planning with quintic polynomial in Cartesian space. For improving optimization performance, elitist group and adaptive adjustment mechanisms are used based on genetic algorithm (GA) framework. In the meantime, GA is combined with singularity avoidance mechanism to avoid the singularities appearing in the trajectory, improves the recognition capability of optimum solution. Experimental results show that, the proposed approach is more effective and better performance than the original GA and its variants, with ensuring a both smooth and efficiency performance for the robotic manipulators.