Traffic Prediction for Agent Route Planning

Authors:
Jan D. Gehrke;Janusz Wojtusiak
Affiliations:
Center for Computing Technologies (TZI), University of Bremen, Bremen, Germany 28359;Machine Learning and Inference Laboratory, George Mason University, Fairfax, USA VA 22030
Venue:
ICCS '08 Proceedings of the 8th international conference on Computational Science, Part III
Year:
2008

Citing 3
Cited 8

An Adjustable Description Quality Measure for Pattern Discovery Usingthe AQ Methodology

Journal of Intelligent Information Systems - Special issue on methodologies for intelligent information systems
An adaptive solution to dynamic transport optimization

Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems
The AQ21 Natural Induction Program for Pattern Discovery: Initial Version and its Novel Features

ICTAI '06 Proceedings of the 18th IEEE International Conference on Tools with Artificial Intelligence

Designing a Simulation Middleware for FIPA Multiagent Systems

WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 02
Agent Strategy Generation by Rule Induction in Predator-Prey Problem

ICCS 2009 Proceedings of the 9th International Conference on Computational Science
n-gram geo-trace modeling

Pervasive'11 Proceedings of the 9th international conference on Pervasive computing
Agent-based system with learning capabilities for transport problems

ICCCI'11 Proceedings of the Third international conference on Computational collective intelligence: technologies and applications - Volume Part II
Learning dynamic adaptation strategies in agent-based traffic simulation experiments

MATES'11 Proceedings of the 9th German conference on Multiagent system technologies
Machine learning in agent-based stochastic simulation: Inferential theory and evaluation in transportation logistics

Computers & Mathematics with Applications
Toward coupling sensor data and volunteered geographic information (VGI) with agent-based transport simulation in the context of smart cities

Proceedings of the First ACM SIGSPATIAL Workshop on Sensor Web Enablement
Modeling of route planning system based on Q value-based dynamic programming with multi-agent reinforcement learning algorithms

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a methodology and initial results of predicting traffic by autonomous agents within a vehicle route planning system. The traffic predictions are made using AQ21, a natural induction system that learns and applies attributional rules. The presented methodology is implemented and experimentally evaluated within a multiagent-based simulation system. Initial results obtained by simulation indicate advantage of agents using AQ21 predictions when compared to naïve agents that make no predictions and agents that use only weather-related information.