Evolution of Path Planning Techniques For Mobile Robot – A Mini Review
S R Anuvarshini, S. Pranesh, M. Sreedevi, M. S. Sureshkumar · 2025
Mobile robot path planning has been greatly improved with advances in artificial intelligence, optimization methods, and real-time computing power. In this mini review, an examination has been conducted on the evolution of mobile robot path planning strategies, ranging from classical deterministic algorithms to modern AI-driven approaches. Classic techniques like Dijkstra's algorithm and A* have been first employed, with probabilistic methods like RRT and PRM for high-dimensional and dynamic environments. Fuzzy logic, genetic algorithms, and neural networks have been integrated to enhance adaptability. Recent advancements with respect to reinforcement learning, deep learning, and hybrid AI methods have facilitated robots to autonomously navigate in complex, unstructured environments. Computational overhead, energy efficiency, and multi-robot coordination have been recognized as challenges, and research has focused on scalable and adaptive solutions. The review presented herein has offered an in-depth overview of the state-of-the-art methods, their limitations, and pointed to the directions of future research such as the necessity of real-time adaptability, decentralized coordination, and energy-aware planning. The results provided are anticipated to be a useful guideline for future research in mobile robot navigation in autonomous mode.