Marine shipping is collectively viewed as a group of intelligent agents, each possessing resources of sensing, communication, information processing, and decision-making. The marine traffic control problem is considered that of achieving organized, consistent behavior of the group by exploiting the knowledge and resources possessed by agents in the group, and the marine traffic control system is treated as a distributed problem-solving network. Ships are all processing nodes in the network, and they are connected with each other by some communication protocol. The approach is embodied in a system called DIPSACOM. Organizational structuring and an expectation-based negotiation mechanism for achieving effective cooperation between ships are elaborated. Simulation results demonstrating the effectiveness of the distributed problem-solving approach are presented.<<ETX>>
[1]
Randall Steeb,et al.
Strategies of Cooperation in Distributed Problem Solving
,
1983,
IJCAI.
[2]
Victor R. Lesser,et al.
Functionally Accurate, Cooperative Distributed Systems
,
1988,
IEEE Transactions on Systems, Man, and Cybernetics.
[3]
Mark S. Fox,et al.
An Organizational View of Distributed Systems
,
1988,
IEEE Transactions on Systems, Man, and Cybernetics.
[4]
Randall Davis,et al.
Frameworks for Cooperation in Distributed Problem Solving
,
1988,
IEEE Transactions on Systems, Man, and Cybernetics.
[5]
Edmund H. Durfee,et al.
Using Partial Global Plans to Coordinate Distributed Problem Solvers
,
1987,
IJCAI.