A Vision-Based Pathfinder using MOEA with Low-Cost Gene Encoding for Navigating a Mobile Robot

The pathfinding is generally regarded as a multi-objective optimization problem that simultaneously optimizes the shortest path and the least collision-free distance to obstacles. This work develops an MOEA-based algorithm of pathfinding to navigate a mobile robot to avoid the obstacles in a given finite environment. A grid-based method is also introduced for mapping of the environment to efficiently encode the robot's position to be chromosomes. The hardware architecture is built by a mobile robot and its working environment, as well as the Aruco system and a computer running the algorithms of pathfinding and image processing. Both simulations and experimental results are presented to verify the feasibility of the proposed method. In applications, this work can be employed in a commercial ball collecting or object-carrying robot.