Research on Robot Autonomous Navigation Technology based on Q-Learning

DOI

10.2991/978-94-6463-823-3_40How to use a DOI?

Keywords

Q-learning; autonomous navigation; dynamic environments; path planning; reinforcement learning

Abstract

This study investigates Q-learning-based autonomous navigation technologies for robots operating in dynamic environments. The research integrates reinforcement learning with perception systems to improve obstacle detection and path planning capabilities. Hybrid frameworks combine Q-learning with global planning algorithms, ensuring a balance between computational efficiency and adaptability. Additionally, enhanced exploration strategies and reward mechanisms are introduced to mitigate convergence issues in complex scenarios. Applications cover diverse robotic platforms, including autonomous vehicles, UAVs, and multi-agent systems, demonstrating reliable navigation in both simulations and real-world tests. The model-free approach enables real-time adjustments for unexpected obstacles and unknown environments. Layered architectures and state-space optimizations prioritize computational efficiency and responsiveness. Challenge’s future directions emphasize multi-sensor fusion and deep reinforcement learning extensions to enhance robustness. The findings underscore Q-learning’s adaptability and scalability in autonomous systems, offering practical solutions for dynamic navigation tasks across varied domains. The study also highlights the importance of integrating ethical considerations and safety constraints into the design of autonomous navigation systems, ensuring compliance with regulatory standards and promoting trust in real-world applications.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Hongxiao Wang
PY  - 2025
DA  - 2025/08/31
TI  - Research on Robot Autonomous Navigation Technology based on Q-Learning
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 405
EP  - 414
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_40
DO  - 10.2991/978-94-6463-823-3_40
ID  - Wang2025
ER  -