Solving the Traveling Saleman Problem Using Reinforcement Learning

Liang, Jiazhao

doi:10.1109/eebda56825.2023.10090654

Cited by 2 publications

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Navigating Intelligence: A Survey of Google OR‐Tools and Machine Learning for Global Path Planning in Autonomous Vehicles

Benoit,

Asef

2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

We offer a new in‐depth investigation of global path planning (GPP) for unmanned ground vehicles, an autonomous mining samplingrobot named ROMIE. GPP is essential for ROMIE's optimal performance, which istranslated into solving the traveling salesman problem, a complexgraph theory challenge that is crucial for determining the most effective routeto cover all sampling locations in a mining field. This problem is central toenhancing ROMIE's operational efficiency and competitiveness against humanlabor by optimizing cost and time. The primary aim of this research is toadvance GPP by developing, evaluating, and improving a cost‐efficient softwareand web application. We delve into an extensive comparison and analysis of Google operations research (OR)‐Tools optimization algorithms. Our study is driven by the goal of applyingand testing the limits of OR‐Tools capabilities by integrating ReinforcementLearning techniques for the first time. This enables us to compare thesemethods with OR‐Tools, assessing their computational effectiveness andreal‐world application efficiency. Our analysis seeks to provide insights intothe effectiveness and practical application of each technique. Our findingsindicate that Q‐Learning stands out as the optimal strategy, demonstratingsuperior efficiency by deviating only 1.2% on average from the optimalsolutions across our datasets.

show abstract