Mobile Robots with Dynamic Obstacle Avoidance

Abstract

Robots with autonomous navigation capabilities have become increasingly popular after the advances in robotic automation, particularly in the area of pathfinding algorithms. These algorithms enable robots to safely traverse through complex environments with both stationary and moving obstacles. Applications of this field range from data acquisition to surveys of hazardous situations and transportation by industrial robots. The most commonly utilized approach for two-dimensional obstacle avoidance is grid-based pathfinding algorithms. These methods function by initially generating a grid consisting of nodes and edges based on the environment. In this paper, we explore an implementation of a variation of the A* pathfinding algorithm on a 15×15 grid. The A* algorithm was chosen because it guarantees finding the optimal route between starting and ending points. A* is a grid-based algorithm that falls under the category of search-based algorithms. The Maximum Velocity Obstacle (MVO) algorithm undergoes rigorous testing to evaluate its performance, and we examine how the simulation input parameters influence the algorithm's effectiveness. The experimental results indicate that the MVO algorithm is an efficient and reliable solution for dynamic obstacle avoidance in a grid-based setting. Moreover, this study demonstrates that the algorithm can be further optimized by using more advanced techniques such as combining it with existing pathfinding algorithms, like artificial neural networks. This would enable the robot to adapt to unpredictable environments in future research.