v track: energy-aware traffic delay estimation using mobile phones
DESCRIPTION
V Track: Energy-Aware Traffic Delay Estimation Using Mobile Phones. Lenin Ravindranath , Arvind Thiagarajan, Katrina LaCurts, Sivan Toledo, Jacob Eriksson, Sam Madden, Hari Balakrishnan. Massachusetts Institute of Technology. Motivation. Traffic delays and congestion Wasted fuel - PowerPoint PPT PresentationTRANSCRIPT
VTrack: Energy-Aware Traffic Delay Estimation Using Mobile Phones
Lenin Ravindranath, Arvind Thiagarajan, Katrina LaCurts, Sivan Toledo, Jacob Eriksson, Sam Madden, Hari Balakrishnan
Massachusetts Institute of Technology
Motivation
• Traffic applications– Real time traffic congestion information– Route planning - traffic aware routing– Traffic delay prediction
• Traffic delays and congestiono Wasted fuelo Commuter frustration
• 4.2 billion hours in 2007 spent struck in traffic
Estimate current delay on each road segment
Vtrack Goal• Route planning• Hot spot detection
Road segment delay estimates
Approaches
• Flow monitoring sensors– High deployment cost
• GPS equipped probe vehicles– Cover large areas– Deployment cost
• End user smart phones– Large penetration and massive amount of data– Sensors: GPS, Wi-Fi, GSM– On roads and time useful for other users
Challenges
Inaccuracy of position samples
Energyconsumption
GSM
GPS
Wi-Fi
50m 200m5m
VTrack– Wi-Fi– Infrequent GPS samples
Wi-Fi localization• War driving: Access point - GPS mapping• AP observations -> Centroid location
• Noise• Outliers• Outages
Delay estimation
• Map matching- Sequence of segments
• Find delay on road segments
Map matchingHidden Markov Model
S1S2
S3
p1 p2
p3
p4 S1
S2 S3
1/3
1/3
1/3
S1
S2
S3
S1
S2
S3
S1
S2
S3
S1
S2
S3
p1 p2 p3 p4
Viterbi
• Noise- Gaussian
• Outliers- Speed constraint
• Outages- Interpolation
Dealing with outages
Delay on segments
S1S2
S3
p1 p2
p3
p4
p1 p2 p3 p4
S1 S1 S3 S3
T (S1) = t(p2) – t(p1) + ½ (t(p3) – t (p2))
T (S3) = t(p4) – t(p3) + ½ (t(p3) – t (p2))
VTrack
Applications• Route Planning– Shortest time path between a source and a destination
• Hotspot detection– Finding road segments that are highly congested
Evaluation• Analyzed over 800 hours of drive data • 25 cars with both GPS and Wi-Fi
Key Results
• HMM based map matching is robust to noise– Trajectories with median error less than 10%
• Delay estimates from Wi-Fi are accurate enough for route planning– Though individual segment delay estimates have 25%
median error– Over 90% of shortest paths have travel times within
15% of true shortest path• Accurately detect over 80% hotspots with less
than 5% false positives
Further work
• Sampling GPS infrequently– Improves the accuracy of Wi-Fi based estimates– Analyzed energy consumption
• Adaptive sampling– Dynamically selects best sensor– Based on road networks, accuracy, energy
• Segment delay prediction