Your SlideShare is downloading. ×
EDF2014: Ralf-Peter Schaefer, Head of Traffic Product Unit, TomTom, Germany: Probe Data Analytics and Processing for Traffic Information, Traffic Planning and Traffic Management
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×

Saving this for later?

Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime - even offline.

Text the download link to your phone

Standard text messaging rates apply

EDF2014: Ralf-Peter Schaefer, Head of Traffic Product Unit, TomTom, Germany: Probe Data Analytics and Processing for Traffic Information, Traffic Planning and Traffic Management

6,834
views

Published on

Industry Keynote Talk by Ralf-Peter Schaefer, Head of Traffic Product Unit, TomTom, Germany at the European Data Forum 2014, 20 March 2014 in Athens, Greece: Probe Data Analytics and Processing for …

Industry Keynote Talk by Ralf-Peter Schaefer, Head of Traffic Product Unit, TomTom, Germany at the European Data Forum 2014, 20 March 2014 in Athens, Greece: Probe Data Analytics and Processing for Traffic Information, Traffic Planning and Traffic Management.

Published in: Technology, Business

0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total Views
6,834
On Slideshare
0
From Embeds
0
Number of Embeds
15
Actions
Shares
0
Downloads
21
Comments
0
Likes
1
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide
  • Animated, updated GSM, supersized imageRange of different sources, to enable reliable traffic detection on all roads in all situationsQuality of each source is important: precision of location (GPS better than GSM) and update frequency (logged every 2-5s, uploaded ~every 2 minutes)LIVE PND are connected TomTom GPS navigation devicesIn dash navigation currently limited to Europe (Renault, Fiat, Mazda)iPhone data is only from users of TomTom navigation application on the device – and GPS trace data only passed to TomTom if the user subscribes to LIVE services and the device is docked in the TomTom holderBusiness solutions is the TomTom unit focused on connected products for fleet owners (delivery vans, maintenance cars, etc)3rd party GPS data only used in selected countries (USA, South Africa & New Zealand)GSM probes only active in 8 countries (notably not in USA)Incident data = journalistic data describing the cause of the congestion / delay e.g. accident
  • Animated, updated GSM, supersized imageRange of different sources, to enable reliable traffic detection on all roads in all situationsQuality of each source is important: precision of location (GPS better than GSM) and update frequency (logged every 2-5s, uploaded ~every 2 minutes)LIVE PND are connected TomTom GPS navigation devicesIn dash navigation currently limited to Europe (Renault, Fiat, Mazda)iPhone data is only from users of TomTom navigation application on the device – and GPS trace data only passed to TomTom if the user subscribes to LIVE services and the device is docked in the TomTom holderBusiness solutions is the TomTom unit focused on connected products for fleet owners (delivery vans, maintenance cars, etc)3rd party GPS data only used in selected countries (USA, South Africa & New Zealand)GSM probes only active in 8 countries (notably not in USA)Incident data = journalistic data describing the cause of the congestion / delay e.g. accident
  • Each yellow dot represents a measurement of a certain speed (vertical axis) at a certain time of the week (horizontal axis).The blue bars mark mean speeds for time bins, and the white line is the speed profile generated from it after filtering etc.What’s interesting is that while most measurements are around 40-50 km/h. there is also a cluster of measurements at around 5-10 km/h.What is it? Let’s take a look…
  • In this diagram, each pink bar represents the total number of measurements at a certain speed on our road segment.What we see is very typical of urban roads, and we call it bimodal behavior; either traffic flows well, at 43 km/h, or sometimes, the road gets congested, then it’s 6 km/h.We analyze these speed frequencies in 1-hour bins and compute from it a “jam probability” and a “jam speed”, which we may use in routing in the future.
  • As a second example, let’s take a look at a segment of Autobahn, on the A9 freeway just south of Berlin.
  • Again, each yellow dot represents a speed measurement at a certain time of the week.Most measurements are around 130, 140 km/h, but there is again a separate cluster at almost exactly 90 km/h.This doesn’t look like jam mode, it’s too fast! What’s going on?
  • Transcript

    • 1. Big (Traffic) Data Probe Data Analytics and Processing for Traffic Information, Traffic Planning and Traffic Management Ralf-Peter Schäfer Fellow & VP Traffic and Travel Information Product Unit ralf-peter.schaefer@tomtom.com 1 Copyrights: TomTom Internal BV 2014
    • 2. 2 A B 2
    • 3. 3 Huge investment and maintenance costs to detect traffic information Typically every 2 km a loop required to get precise real-time traffic infos Can we do better?
    • 4. 4 Change
    • 5. 5 Facebook Social Activity Graph (friend interactions)
    • 6. Traffic Community of 350M+ connected users • 9 trillion anonymous speed measurements (9.000.000.000.000) • 8 billion speed measurements per day (6.000.000.000) • 22 trillion driving seconds (22.000.000.000.000) • Speed estimation via map matching and data analytics
    • 7. 7 IQ Routes GPS PROBE DATA
    • 8. 8 Time-Space Characteristics t x 4 Local detection (loops) Moving Detection Floating Car 1 1 2 1 2 Probe vehicle (e.g. GPS)
    • 9. From Modeling to Measuring 9 Classical tools for observing traffic flow: Simulation and Data from Loop-Detectors Simulated elementary traffic jam patterns: Interpolated and smoothed data from loop detectors:
    • 10. From Modeling to Measuring 10 Direct speeds observations with GPS probe data • GPS data allows traffic observation everywhere • Independent from stationary devices • Sampling rate sufficient for real-time traffic information
    • 11. TomTom Congestion Index Europe (Q3 2013) Traveltime delays compared to free flow situation at night hours 11 http://www.tomtom.com/congestionindex
    • 12. Speeds Over Time (City, e.g. Berlin) 12 Sun Mon Tue Wed Thu Fri Sat speed
    • 13. Speed Frequencies Weekdays (City e.g. Berlin) 13 6 km/h 43 km/h numberofprobes
    • 14. Speed Probe Data (Freeway, e.g. A9 south of Berlin) 14
    • 15. Speeds Over Time (Freeway , e.g. A9 south of Berlin) 15 Sun Mon Tue Wed Thu Fri Sat speed
    • 16. ORIGIN-DESTINATION ZONE ANALYSIS 16 Data collection of origin-destination data is difficult Current techniques include - Stop cars: road side interviews - Get address from license plate and send survey - Telephone interview - Panel fills in a diary of their movements - Point to point tracking: license plates (full) or bluetooth (sample)
    • 17. 17 Selected link: links to links Selected link: zones to zones A B A 30 5 B 10 20 OD MatrixRoute choice
    • 18. Detailed junction analysis per path Speed measurements over time Speed measurements grouped by day of the week Speed frequency distribution, free flow estimate Distribution of Travel time delta
    • 19. Junction Stop Characteristics Number of average stops per traversal Average stop time per traversal
    • 20. Data fusion Send to users GPS Probe Data GSM Probe Data Journalistic info Historic Traffic Map Data Various input sources 20 REAL-TIME TRAFFIC INFO FROM USERS TO USERS
    • 21. Probe Data Example of Traffic Incident GPS and GSM input sources and incident output message 21 • Example from Dec 13, 2011 • Near Stuttgart, Germany • GPS data from floating cars • Speed data matched to road elements • GSM data from mobile phone calls • Sophisticated algorithm • After fusion and incident detection • Live incident output to PND
    • 22. JAM TAIL WARNINGS Detection of jam tails for a safety warning in the navigation unit • Over 35% of drivers have admitted to experiencing an accident caused by sudden or unexpected traffic holdups • Jam ahead warning messages in traffic output can be used to create these safety messages with great accuracy 22
    • 23. Real-time road speed data Enable traffic information and traffic management  Measured speed on each road segment  On all important roads  Without the need of road-side equipment  By using Floating Car Data  Updated every minute 23 TOMTOM TRAFFIC Traffic Flow Flow conditions (speed) on all roads
    • 24. 24 The TomTom Traffic Manifesto If 10% of the road drivers use HD Traffic guided navigation in conurbations there is a 1. Individual journey time reduction for informed users by up to 15% 2. A collective journey time reduction for ALL by up to 5% http://www.tomtom.com/trafficmanifesto
    • 25. 10% 10% How to estimate the journey time reduction claims in the TomTom Manifesto? Use of traffic modelling and simulation in a simplified road network Assume a share of equipped navigation users (e.g. traffic guided drivers) Assume high acceptance rate for detour choices when approaching a traffic jam! Results from simulation below for medium and high traffic flow Source: F. Leurent, T. Nguyen, TRB 2010.
    • 26. 26 Dynamic Navigation for personal and collective benefits 24 Hour Time Lapse – NYC
    • 27. 27 5 day historical– NYC Monday 31 minutes Tuesday 16 minutes Wednesday 9 minutes Thursday 18 minutes Friday 4 minutes Time Saved: 1 Hour, 18 Minutes
    • 28. The (future) Traffic Management Challenge Load balanced vs unbalanced routing system using dynamic route guidance vs.
    • 29. Educated Guess – Probe Data Source? 29
    • 30. Educated Guess 2nd – Probe Data Source? 30
    • 31. Thank You ralf-peter.schaefer@tomtom.com