Calling All CarsCell Phone Networks and the Future of Traffic

Document Sample
Calling All CarsCell Phone Networks and the Future of Traffic Powered By Docstoc
					 Calling All Cars: Cell Phone
Networks and the Future of
                        Traffic
                     Jeremiah Dunn
Overview
 Introduction
 Mobile Millenium
 Goal
 Complexity of the Problem
 Gathering Data
 Data Fusion
 Modeling the Flow of Traffic
 Mobile Century
 Conclusion
Introduction
 Fixation of humanity on futuristic cars & autonomous
  travel has drastically changed the modern car.
 While not quite going in that direction, cheap sensors
  and network availability are essentially boosting the
  “brainpower” of our driving environment.
 Between road-side sensors, dashboard GPS, and
  Smart phones many companies are provided with
  traffic data collection.
Mobile Millenium
 Started in 2007
 One of the first large-scale projects for traffic
  monitoring
 Run by Nokia, NAVTEQ, and UC Berkeley

 Only able to be conceived and work thanks to the rise
  of the “smart-phone” thanks to embedded GPS
Goal
 Merge road-side sensor networks with smartphone
  GPS feedback to generate a real-time traffic
  monitoring situation.
Complexity of the Solution
Gathering Data
 VTLs (Virtual Trip Lines): to prevent constant packet
  transfer, the phone will only upload statistics when it
  crosses a “checkpoint” along the VTLs.
Data Fusion
 Incoming data from many sources
   GPS
     Buses
     Taxis
     Cars
   Static Sensors
     Loop Detectors
     RFID tag readers
 GPS may have faulty Data
   Walkers/Parked/etc
Modeling the Flow of Traffic
 Obvious way to think about modeling traffic is by
  individual cars
 Designed a new set of algorithms based on fluid
  mechanics
Mobile Century
 All this data collection culminated in 2008 in a test
   100 Cars mixed in a 10-mile stretch in Norther
    California
   10 Hours and accounted for 2-5% of the cars on the
    highway
   Mobile Millinum vs Google Maps w/ Traffic
 Noticed a sudden red blotch appeared on the test
  stretch, but it took several minutes to appear on
  Google’s system.
Conclusion
 Was able to detect and report a slow-down in under a
  minute
 Proved that only a few cars were needed to get the
  system to run efficiently (2-5%)
 Successful test has led to the concept and technology
  demonstrated to become widespread into Google’s
  mobile Maps app.
 Proved that the mobile scene was better performed
  than any static detector system.

				
DOCUMENT INFO
Shared By:
Categories:
Tags:
Stats:
views:0
posted:12/11/2013
language:Unknown
pages:11
 hongmei  liu hongmei liu
About