Vision-Aided Path Planning Using Low-Cost Gene Encoding for a Mobile Robot

Path planning is intrinsically regarded as a multi-objective optimization problem (MOOP) that simultaneously optimizes the shortest path and least collision-free distance to obstacles. This work develops novel optimized approach using genetic algorithm (GA) drive evolutionary (MOEA) for of mobile robot in given finite environment. To represent positions integer-type genes chromosome GA, grid-based method also introduced relax complex environment simple map. The system architecture composed robot, embedded with operating (ROS), ArUco laptop, executing algorithms image processing. Both simulations experimental results are presented verify feasibility proposed method. In applications, this can be employed commercial ball-collecting or an object-carrying robot.