Presented by: David Nikaido & Tiffany Hunt Presented by: David - PowerPoint PPT Presentation

Presented by: David Nikaido & Tiffany Hunt Presented by: David Nikaido & Tiffany Hunt Faculty Mentor: Dr. Christine Drennon

� Introduction � Literature Review � Agent � Agent � Enviroment � Future Work � Timeline � Timeline � Conclusion

Modeling Modeling Traffic Traffic in a Multi Multi ‐ Agent ent System with Geographic ystem with Geographic Informatio Information Systems Information Information Syst Systems (GIS) ystems (GIS) (GIS) (GIS) Trinity Summer REU 2009 Goals: Simulate traffic in San Antonio Goals: Simulate traffic in San Antonio ◦ Agents ◦ Enviroment

� Our goals are to build off of last years traffic simulation model in two ways: ◦ Create a citywide map structure C t it id t t ◦ Implement driving agent behavior p g g

� “A behavioral multi-agent model for road tra c simulation.” Doniec, Mandiau, Piechowiak and Espie.

� Three types of behavior ◦ Normative ◦ Opportunistic ◦ Anticipatory

� “A collaborative driving system based on multiagent modeling and simulations.” Halle’, Chaib-draa

Traffic Control Layer Management Layer Guidance Layer y Input Input Input output output output

� Graphical Information Systems(GIS) ◦ Spatial ◦ Data ◦ Pretty ◦ Pretty

� Types of agents: ◦ Road agents ◦ Traffic lights ◦ Signs ◦ Signs ◦ Sensors � Path finding algorithm � Shortest path � Alternate path � Alternate path

� Autonomous driver agents (DARPA) � User functionality: ◦ Change traffic rules ◦ Change driver behavior Change driver behavior ◦ Measure traffic flow ◦ Change road structure

� Week 3 - 4: ◦ Translate last year’s code to Scala � Week 5 - 7: ◦ Implement agent behavior Implement agent behavior ◦ GUI � Week 8 – 9: k ◦ Optimize code and future work

� Can be useful for testing traffic infrastructure � FUN!! � Can be used to measure real world data