Low-carbon path planning for inland vessels using a novel FMORL framework

日本語

本研究は内航船舶の低炭素運航を実現するため、新しい多目的強化学習フレームワーク（FMORL）を提案。経路計画においてCO2排出量を最小化しつつ、運航コストや時間とのトレードオフを考慮する。中国の内陸水路を対象としたケーススタディにより、提案手法の有効性を実証している。

English

This study proposes a novel multi-objective reinforcement learning framework (FMORL) for low-carbon path planning of inland vessels. It optimizes routes to minimize CO2 emissions while considering trade-offs with operational costs and time. A case study on Chinese inland waterways demonstrates the effectiveness of the proposed approach.

In the global GX context

This paper contributes to maritime decarbonization by introducing a reinforcement learning approach for low-carbon route optimization in inland shipping. It is particularly relevant for regions with extensive inland waterway networks and offers a methodological framework that could be adapted for other transport modes.