AUTONOMOUS VEHICLE SCHEDULING USING THE CONTRACT NET PROTOCOL IN A TRUCK TERMINAL

This paper describes the scheduling of autonomous vehicles in a truck terminal by using the contract net protocol (CNP). This makes the task assignment of vehicles more efficient. The tasks are loading and unloading between trucks, and autonomous vehicles performed these tasks. The CNP is a task allocation paradigm developed in distributed artificial intelligence (DAI). In the CNP, the allocation is realized by a negotiation process between agents with tasks to be executed and agents that may be able to execute those tasks. In this paper, the decision making criteria of the agents were formalized that were left undefined in the CNP on the basis of utility theory. In addition, through a computer simulation, the relationship between the criteria and system performance were investigated, and appropriate criteria were decided. In the scheduling, satisfying the following two items were used as the objectives. Item 1 is that the unloading of goods is executed more quickly by fewer vehicles. Item 2 is, compared with other trucks, the waiting time of the truck for a vehicle to arrive to initiate a task from the announced time is minimal. From the simulation results, criteria with the estimated arriving time and time to perform the task are presented as appropriate scheduling parameters.

  • Supplemental Notes:
    • Five volumes of papers and one volume of abstracts comprise the published set of conference materials.
  • Corporate Authors:

    VERTIS

    TORANOMOM 34 MORI BUILDING 1-25-5
    TORANOMON, MINATOKU, TOKYO 105  Japan 
  • Authors:
    • Suetake, N
    • Ikari, H
    • Unoki, T
  • Conference:
  • Publication Date: 1995-11

Language

  • English

Media Info

  • Pagination: p. 942

Subject/Index Terms

Filing Info

  • Accession Number: 00722017
  • Record Type: Publication
  • Report/Paper Numbers: Volume 2
  • Files: TRIS
  • Created Date: Jun 23 1996 12:00AM