Agent-based vehicle scheduling for dockyard operation

How to route multiple straddle carriers or vehicles during loading and unloading operation in a dockyard is non-trivial problem. The objective of the routing is to minimise either the total travel distance or the operation time. The routing problem consists of both the container allocation problem and the carrier allocation problem. The container allocation problem can be formed as a transportation problem. In other words, the containers both in the ship and on the yard bays can be divided into multiple classes, each of which will be unloaded and loaded by a quay crane. However, in the carrier allocation problem, the sequence of yard-bays that a carrier visits needs to be decided dynamically.

The aim of this project is to design a multi-agent architecture for a team of autonomous vehicles or straddle carriers to autonomously load and unload containers in a dockyard. Apart from identifying optimal paths and plans based on a priori data, an important part of the system architecture will be the handling of dynamic scheduling. A decentralised approach will be adopted in the design, which will be compared with the centralised approach being currently adopted in dockyard. Therefore straddle carriers or autonomous vehicles will need to be able to communicate with each other to form cooperative plans, negotiate routes and schedule the use of the loading crane for excessively large or heavy cargo. There will also be a clear need for the system architecture to include a low-level reactive based control layer for real-time obstacle avoidance.

This project is funded by EPSRC (27,800) and GCS Ltd. (13,200) on a CASE Award (01/10/2000 and 30/09/2003).



For further Information, please email: