Multi-Objective Genetic Algorithm-Based Time Optimal Trajectory Planning and Robot Control

This This paper describes the use of a Genetic Algorithm (GA) for the problem of point-to-point robot path planning and control. The problem consist of generating trajectories, for a two d.o.f robot to move from a starting position to a destination in a task space, represented by a two dimensional map, with obstacles that the Robot must evade. The role of the GA is to optimize possible paths based on two criteria: length and difficulty. First a conventional GA is used to evaluate its ability to solve this problem (using only one criteria for optimization). Due to the fact that in real time, more criteria (or objectives) are to be optimized, then we extended the conventional GA to implement the ideas of Pareto optimality, making it a Multi Objective Genetic Algorithm (MOGA). Simulation results are presented for robots with two degrees of freedom, considering two objectives optimization, Bi-Objective Genetic Algorithm (BOGA). A subsequent analysis of the spread and solutions distribution along the converged non-dominated Pareto front is carried out, in terms of the achieved diversity. The effectiveness and capability of the proposed approaches are demonstrated through simulation studies