AI Summary & Key Takeaways
AI InsightThrough these analyses, we shed light on the performance of Kalman and particle filters when applied in conjunction with the A* algorithm for path tracking, offering valuable insights into their effectiveness in real-world, noisy environments.
📌 3 Key Takeaways
Abstract
Autonomous robots face significant challenges in path planning and continuous motion planning in indoors due to their ability to navigate within these complex spaces. These complex problems arise in a wide range of application environments, including indoor areas such as corridors, rooms, and similar spaces. This study presents a comparative simulation analysis of path-finding techniques employed for indoor autonomous robot navigation. Conventional path-finding techniques, including Voronoi diagram and potential field, have been selected to illustrate these established methods. However, they were found to be unreliable and insufficient in coping with the intricacies of real-world situations characterised by non-linearity. Various artificial intelligence techniques were evaluated to showcase the superiority of artificial intelligence over conventional methods. The methods included genetics algorithm and neural networks. The use of these artificial intelligence methods proved their ability to handle complex navigation tasks with greater ease and strength, highlighting their vital contribution in overcoming obstacles. Additionally, we utilize the well-known A* algorithm as a benchmark to evaluate and compare the performance of filtering techniques, particularly Kalman and particle filters in the context of path tracking under diverse conditions, including scenarios with gaussian and exponential noise. Through these analyses, we shed light on the performance of Kalman and particle filters when applied in conjunction with the A* algorithm for path tracking, offering valuable insights into their effectiveness in real-world, noisy environments.