To optimize ship operations under complex ocean environments, a collaborative research team from China and Singapore has proposed an advanced joint speed-route planning framework based on Deep Reinforcement Learning (DRL). Ship navigation is highly vulnerable to dynamic ocean environment variations; adverse sea states not only spike fuel consumption but also drastically threaten navigational safety.
The team published their study in Communications in Transportation Research ( https://doi.org/10.26599/COMMTR.2026.9640040 ).
“We developed a Dueling Double Deep Q-Network (D3QN)-based framework with a unique dual-mode mechanism specifically engineered to handle distinct weather scenarios,” says Yangyu Zhou, a Ph.D. candidate at the State Key Laboratory of Coastal and Offshore Engineering, Dalian University of Technology.
Dual-mode optimization for fuel efficiency and safety
Under normal weather conditions, the framework shifts its priority to economic efficiency and fuel consumption reduction. It integrates ERA5 reanalysis wind and wave products with OSCAR current datasets to build a dynamic ocean environment. Instead of relying on static inputs or simplistic empirical formulas, the method accurately captures hydrodynamic performance by analyzing actual propulsion thrust against environmental wave-and-wind resistance under a step-wise constant power assumption.
Extensive numerical simulations demonstrate the superior optimization capabilities of this framework. Under normal weather conditions, the D3QN-based route dynamically adapted the ship speed and route to capitalize on the favorable environment, achieving the reduction in total fuel consumption while strictly honoring the targeted Estimated Time of Arrival (ETA).
Overcoming extreme typhoon challenges with physical consistency
When facing extreme weather conditions like typhoons, conventional reanalysis datasets often smooth out localized peaks, underestimating critical wave heights. To resolve this data limitation, the extreme weather mode pairs high-resolution wind data with a Simulating WAves Nearshore (SWAN) numerical model alongside a typhoon wind field correction algorithm to accurately reconstruct the typhoon wave fields.
“In case studies simulating extreme events like Typhoon Hagupit and Typhoon Kalmaegi, traditional methods such as Dijkstra or Genetic Algorithms failed to plan viable, safe routes,” explains Dr. Yuanyuan Xu, a lecturer at Chongqing Jiaotong University. “In contrast, the proposed DRL-based framework maintained exceptional stability, successfully planning detour routing that safely bypassed high-wave and strong-wind waters.”
Future work will enhance the framework with statistical ensemble forecast metrics to systematically mitigate weather uncertainty. The framework will also adapt to coastal terrains using land-collision masks and shore safety margins, while incorporating the multi-objective optimization method.
About Communications in Transportation Research
Communications in Transportation Research was launched in 2021, with academic support provided by Tsinghua University and China Intelligent Transportation Systems Association. The Editors-in-Chief are Professor Xiaobo Qu, a member of the Academia Europaea from Tsinghua University, and Professor Xiaopeng (Shaw) Li from University of Wisconsin–Madison. The journal mainly publishes high-quality, original research and review articles that are of significant importance to emerging transportation systems, aiming to serve as an international platform for showcasing and exchanging innovative achievements in transportation and related fields, fostering academic exchange and development between China and the global community.
It has been indexed in SCIE, SSCI, Ei Compendex, Scopus, CSTPCD, CSCD, OAJ, DOAJ, TRID and other databases. It was selected as Q1 Top Journal in the Engineering and Technology category of the Chinese Academy of Sciences (CAS) Journal Ranking List. In 2022, it was selected as a High-Starting-Point new journal project of the “China Science and Technology Journal Excellence Action Plan”. In 2024, it was selected as the Support the Development Project of “High-Level International Scientific and Technological Journals”. The same year, it was also chosen as an English Journal Tier Project of the “China Science and Technology Journal Excellence Action Plan PhaseⅡ”. In 2024, it received the first impact factor (2023 IF) of 12.5, ranking Top1 (1/58, Q1) among all journals in "TRANSPORTATION" category. In 2026, its 2025 IF was announced as 12.7, maintaining the Top1 position (1/66, Q1) in the same category.
From Volume 6 (2026), Communications in Transportation Research will be published by Tsinghua University Press on the SciOpen platform with the official journal website at https://www.sciopen.com/journal/2097-5023 . We kindly request that all new manuscript submissions be made through the journal’s submission system at https://mc03.manuscriptcentral.com/commtr . For any submission-related inquiries, please contact the Editorial Office at commtr_e@mail.tsinghua.edu.cn.
Communications in Transportation Research
A Ship Weather Routing Framework Based on the Dual-Mode Deep Reinforcement Learning
30-Sep-2026