Probabilistic Mapping and Navigation: A Survey of Bayesian Meta-Learning for Autonomous Robots

Abstract

Abstract Bayesian Meta-Learning’s role in the autonomous navigation of mobile robots remains unexplored; this systematic review highlights the effectiveness of Bayesian Meta-Learning in enhancing probabilistic mapping and navigation in mobile autonomous robots. The paper initially compares Bayesian Meta-Learning with existing techniques that have been the cornerstone of probabilistic mapping and navigation, such as Kalman filters and particle filters. It then meticulously examines the critical metrics, including path planning, obstacle avoidance, active localization, navigation in dynamic environments, and mapping accuracy, highlighting the substantial impact of Bayesian Meta-Learning in enhancing these critical aspects of autonomous navigation in mobile robots. The approach enhances adaptability and learning in mobile robots, highlighting its potential to transform autonomous navigation. In addition to emphasizing the positive outcomes of the research, the review also acknowledges a substantial research gap and aims to provide novel insights for future exploration. Future research directions include lifelong learning, uncertainty-aware exploration, integration of prior knowledge, and improvements in human-robot interaction to enhance existing paradigms and advance robust autonomous robotic systems. Therefore, this study accentuates the affirmative findings regarding Bayesian Meta-Learning and recognizes and contributes to the broader research landscape within the field.