Optimizing mobile robot navigation through neuro-symbolic fusion of Deep Deterministic Policy Gradient (DDPG) and fuzzy logic

• Main Authors: Nasary, Muhammad Faqiihuddin, Mohd Ibrahim, Azhar, Al Mahmud, Suaib, Shafie, Amir Akramin, Mardzuki, Muhammad Imran
• Format: Proceeding Paper
• Language: English; English; English
• Published: Springer Nature 2024
• Subjects: T Technology (General)
• Online Access: http://irep.iium.edu.my/112824/3/112824_Optimizing%20mobile%20robot%20navigation%20through%20neuro-symbolic%20fusion%20of%20Deep%20Deterministic%20Policy%20Gradient%20%20and%20fuzzy%20logic.pdf; http://irep.iium.edu.my/112824/2/112824_Optimizing%20Mobile%20Robot%20Navigation%20Through%20Neuro-Symbolic%20Fusion%20of%20Deep%20Deterministic%20Policy%20Gradient%20%28DDPG%29%20and%20Fuzzy%20Logic_Scopus.pdf; http://irep.iium.edu.my/112824/1/ROBOVIS_Latest.pdf; http://irep.iium.edu.my/112824/; https://doi.org/10.1007/978-3-031-59057-3_18

Mobile robot navigation has been a sector of great importance in the autonomous systems research arena for a while. For ensuring successful navigation in com-plex environments several rule-based traditional approaches have been employed previously which possess several drawbacks in terms of ensuring navigation and obstacle avoidance efficiency. Compared to them, reinforcement learning is a novel technique being assessed for this purpose lately. However, the constant re-ward values in reinforcement learning algorithms limits their performance capabil-ities. This study enhances the Deep Deterministic Policy Gradient (DDPG) algo-rithm by integrating fuzzy logic, creating a neuro-symbolic approach that imparts advanced reasoning capabilities to the mobile agents. The outcomes observed in the environment resembling real-world scenarios, highlighted remarkable perfor-mance improvements of the neuro-symbolic approach, displaying a success rate of 0.71% compared to 0.39%, an average path length of 35 meters compared to 25 meters, and an average execution time of 120 seconds compared to 97 sec-onds. The results suggest that the employed approach enhances the navigation performance in terms of obstacle avoidance success rate and path length, hence could be reliable for navigation purpose of mobile agents.