USING INTELLIGENT AGENTS FOR DYNAMIC URBAN TRAFFIC CONTROL SYSTEMS

In the research, the applicability of autonomous intelligent agents are investigated in Urban Traffic Control (UTC), and why these Artificial Intelligent strategies are useful. Designing, implementing, optimising and adjusting UTC systems involves quite some effort and knowledge. A system is proposed that autonomously can adapt to changing environments. The main advantages from the Artificial Intelligent Agents (ALA) are: (1) Self adjustability is an integral part of ALA based traffic control unit, (both long (road works) and short term (accidents) changes are covered); and (2) The more flexible, traffic control unit can be optimised while the unit is operating. For self-evaluation, -optimising and -adjusting UTC we need a fully pro-active, real-time traffic control system. Such a UTC system requires monitoring system of traffic, a rule or model base for evaluation and adjustment, a model of the surrounds and an efficient diagnostic routine for both traffic light operations as well as rule and parameter adjustments. A computer model is used to get insight into the technical and functional applicability of autonomous UTC. The UTC model system is based on several intersection traffic signalling agents (TSA) and some authority agents. Agents will sometimes be required to work autonomously, but will often be commanded or influenced by others. A TSA makes decisions based on goals, capability, knowledge, perception and traffic data. If necessary an agent can request for additional information or receive goals or orders from its authority agent. Our research shows that UTC systems based on agent technology can adapt and respond to traffic conditions in real-time and in the meantime making better use of the capacity of the intersection. In case of unsaturated intersections the strategy proves to be better than intersections with detectors. In saturated situations (degree of saturation >0.5) delays per vehicle on a single approach intersection could improve by 5% to 15%. For the covering abstract see ITRD E105068.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/0860503232
• Corporate Authors:

  PTRC Education and Research Services Limited

  Glenthorne House, Hammersmith Grove
  London W6OL9,   England 
• Authors:
  • Roozemond, D A
• Publication Date: 1999-9

Language

• English

Media Info

• Features: References;
• Pagination: p. 317-27
• Serial:
  • TRAFFIC MANAGEMENT, SAFETY AND INTELLIGENT TRANSPORT SYSTEMS. PROCEEDINGS OF SEMINAR D HELD AT THE AET EUROPEAN TRANSPORT CONFERENCE, ROBINSON COLLEGE, CAMBRIDGE, UK, 27-29 SEPTEMBER 1999, VOLUME P432
  • Publisher: PTRC Education and Research Services Limited
  • ISSN: 0952-3103

Subject/Index Terms

• TRT Terms: Area traffic signal control; Conferences; Continuous structures; Decision making; Evaluation and assessment; Expert systems; Highway capacity; Intelligent transportation systems; Intersections; Mathematical models; Policy; Real time control; Real time data processing; Surveillance; Traffic signals; Urban areas
• ITRD Terms: 669: Area traffic control; 643: Capacity (road, footway); 8525: Conference; 9006: Continuous; 2248: Decision process; 9020: Evaluation (assessment); 8626: Expert system; 8735: Intelligent transport system; 455: Junction; 6473: Mathematical model; 173: Policy; 8679: Real time; 9101: Surveillance; 565: Traffic signal; 313: Urban area
• Subject Areas: Highways; Operations and Traffic Management; Policy;

Filing Info

• Accession Number: 00793723
• Record Type: Publication
• Source Agency: Transport Research Laboratory
• ISBN: 0-86050-323-2
• Files: ITRD
• Created Date: Jun 15 2000 12:00AM