Automotive navigation for mobile robots: Comprehensive review

• Definition and Classification of Robots: The paper begins by defining robots per ISO standards as programmable machines with multiple axes of actuation, distinguishing between fixed robots and mobile robots. Mobile robots utilize various locomotion methods, including wheeled, legged, tracked, or hybrid systems. • Interconnected Navigation Challenges: Mobile robot navigation is framed around three core, interdependent challenges: mapping, localization, and path planning. These challenges require integrated solutions, especially when adapting to dynamic changes and emergency situations. • Advancements in Sensing and Algorithmic Technologies: Recent breakthroughs in sensor technologies—such as LIDAR, vision systems, and radar—combined with deep learning-based and integrated algorithmic approaches, have significantly advanced mobile robot navigation, although the research is dispersed across numerous publications. • Interdisciplinary Integration for Practical Applications: The field spans multiple disciplines including robotics, computer vision, control theory, and artificial intelligence. This interdisciplinary nature is crucial for deploying mobile robots effectively across diverse settings like industrial, medical, military, and exploratory environments. • Consolidation of Research and Future Directions: The paper aims to synthesize existing research into a cohesive resource, critically evaluating current methodologies and identifying open questions. This consolidation is intended to provide a clear roadmap for future studies and help practitioners make informed decisions on system design and sensor selection. Effective navigation of mobile robots in a dynamic environment poses complex challenges, including mapping, localization, and path planning. These factors are interdependent and require robust solutions for successful robot navigation. The complexity of the task increases due to the unpredictability of dynamic obstacles that resemble humans or other robots. This research proposes an in-depth investigation into these navigation challenges, emphasizing the development of hybrid algorithms that manage interdependencies more effectively. The aim is to evaluate the performance of various navigation algorithms against a set of clearly defined metrics such as success rate, path efficiency, computational cost, and adaptability to environmental changes. This paper will give special attention to algorithms incorporating machine learning and real-time data analysis to manage dynamic obstacles better; also, it will explore the adaptability and scalability of these algorithms in simulated environments of varying complexity and size, preparing them for real-world applicability. This research intends to bridge the gap between theoretical algorithms and their implementation in real-world scenarios through theoretical analysis, comparative evaluation, and practical field tests. By achieving these objectives, we anticipate offering comprehensive insights and best practices for mobile robot navigation in dynamic environments, paving the way for innovative solutions that enhance robot autonomy and efficiency.