An Extended Horizon Tactical Decision-Making for Automated Driving Based on Monte Carlo Tree Search
Uloženo v:
| Název: | An Extended Horizon Tactical Decision-Making for Automated Driving Based on Monte Carlo Tree Search |
|---|---|
| Autoři: | Essalmi, Karim, Garrido, Fernando, Nashashibi, Fawzi |
| Přispěvatelé: | ESSALMI, Karim |
| Zdroj: | 2025 IEEE Intelligent Vehicles Symposium (IV). :1127-1132 |
| Publication Status: | Preprint |
| Informace o vydavateli: | IEEE, 2025. |
| Rok vydání: | 2025 |
| Témata: | FOS: Computer and information sciences, Computer Science - Robotics, Automated driving, Monte Carlo Tree Search, [INFO.INFO-RB] Computer Science [cs]/Robotics [cs.RO], Long-term planning, Maneuver planning, Robotics (cs.RO), Decision-making |
| Popis: | This paper introduces COR-MCTS (Conservation of Resources - Monte Carlo Tree Search), a novel tactical decision-making approach for automated driving focusing on maneuver planning over extended horizons. Traditional decision-making algorithms are often constrained by fixed planning horizons, typically up to 6 seconds for classical approaches and 3 seconds for learning-based methods limiting their adaptability in particular dynamic driving scenarios. However, planning must be done well in advance in environments such as highways, roundabouts, and exits to ensure safe and efficient maneuvers. To address this challenge, we propose a hybrid method integrating Monte Carlo Tree Search (MCTS) with our prior utility-based framework, COR-MP (Conservation of Resources Model for Maneuver Planning). This combination enables long-term, real-time decision-making, significantly enhancing the ability to plan a sequence of maneuvers over extended horizons. Through simulations across diverse driving scenarios, we demonstrate that COR-MCTS effectively improves planning robustness and decision efficiency over extended horizons. 6 pages, 5 figures, submitted and accepted to the IEEE Intelligent Vehicles Symposium Conference (IV 2025) |
| Druh dokumentu: | Article Conference object |
| Popis souboru: | application/pdf |
| DOI: | 10.1109/iv64158.2025.11097338 |
| DOI: | 10.48550/arxiv.2504.15869 |
| Přístupová URL adresa: | http://arxiv.org/abs/2504.15869 https://inria.hal.science/hal-05074607v1/document https://inria.hal.science/hal-05074607v1 |
| Rights: | STM Policy #29 arXiv Non-Exclusive Distribution |
| Přístupové číslo: | edsair.doi.dedup.....26c969a233b9a70ce8125c8a1c598a71 |
| Databáze: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | This paper introduces COR-MCTS (Conservation of Resources - Monte Carlo Tree Search), a novel tactical decision-making approach for automated driving focusing on maneuver planning over extended horizons. Traditional decision-making algorithms are often constrained by fixed planning horizons, typically up to 6 seconds for classical approaches and 3 seconds for learning-based methods limiting their adaptability in particular dynamic driving scenarios. However, planning must be done well in advance in environments such as highways, roundabouts, and exits to ensure safe and efficient maneuvers. To address this challenge, we propose a hybrid method integrating Monte Carlo Tree Search (MCTS) with our prior utility-based framework, COR-MP (Conservation of Resources Model for Maneuver Planning). This combination enables long-term, real-time decision-making, significantly enhancing the ability to plan a sequence of maneuvers over extended horizons. Through simulations across diverse driving scenarios, we demonstrate that COR-MCTS effectively improves planning robustness and decision efficiency over extended horizons.<br />6 pages, 5 figures, submitted and accepted to the IEEE Intelligent Vehicles Symposium Conference (IV 2025) |
|---|---|
| DOI: | 10.1109/iv64158.2025.11097338 |