Artificial intelligence aided decision system for ferry drop and pick up operation

By using an AI-assisted decision-making system for ferry trailer swapping operations, which leverages multi-agent deep reinforcement learning and future value prediction networks, the system solves the problems of cargo space fragmentation and channel blockage caused by the decoupling of vehicle voyages and cargo space allocation. This enables more comprehensive loading optimization and stability assessment, thereby improving overall operational efficiency.

CN121788002BActive Publication Date: 2026-07-24BEIJING XINPING LOGISTICS CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING XINPING LOGISTICS CO LTD
Filing Date
2026-02-26
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

In existing ferry trailer swapping operations, the decoupling of vehicle voyages and deck allocation leads to short-sighted decision-making, resulting in low cabin capacity utilization, channel blockage, and increased difficulty in stability verification, especially in real-time operation environments where global optimization is difficult to achieve.

Method used

An AI-assisted decision-making system for ferry trailer swapping operations is adopted. It uses a multi-agent deep reinforcement learning model for online reasoning, combined with a future value prediction network and a stability rapid assessment unit, to achieve coupled optimization of voyages and cabins, and generate feasibility verification and dynamic adjustments.

Benefits of technology

It improves overall loading feasibility and operational smoothness, reduces the probability of infeasible command output, and enhances robustness to dynamic disturbances and cabin capacity utilization.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121788002B_ABST
    Figure CN121788002B_ABST
Patent Text Reader

Abstract

The application discloses a ferry drop and pull operation artificial intelligence auxiliary decision system and relates to the technical field of intelligent logistics scheduling.The application aims at the problems of short-sighted decision, fragmentation of cabin capacity and channel blockage caused by decoupling of voyage selection and berth selection in the existing system, realizes coupling optimization of voyage and berth through joint output in the same decision cycle and message vector interaction of the scheduling / loading unit, and thus improves overall loading feasibility and continuous operation fluency; aiming at the problem that it is difficult to quantize the potential influence of the current distribution on the future vehicle queue under the real-time continuous arrival scene, the application generates a vehicle flow scene through a future value prediction network combined with reservation vehicle flow information or historical arrival distribution, evaluates and sorts long-term returns of candidate voyage actions, and makes the voyage selection have foresight.
Need to check novelty before this filing date? Find Prior Art