Internet of Things, IoT

1. 1Copyright © 2012 Tata Consultancy Services Limited
A Smart Transport Application of Cyber-
Physical Systems:
Road Surface Monitoring with mobile devices
S Bilal, Krishnan S, Arpan Pal, Balamuralidhar P
TCS Innovation Labs

2. 2
OutlineOutline
 Motivation – Intelligent Transportation Use Case
 Modeling
 Approach
 Results
 Feature Extraction
 Feature definitions
 Results
 Concluding Remarks

3. 3
Intelligent TransportationIntelligent Transportation
M2m Cloud
Bus Tracking System
Location ( GPS), Speed, Accelerometer, Passenger
Ids
Valid passenger lists, Route Info
• Can we map the Road Condition?
• Can we predict Vehicle Condition?
• Can we detect Bad Driving Behavior?
Pilot at TCS, Siruseri Campus
Business Problems

4. 4
Vehicle Model Driven Sensor Data AnalysisVehicle Model Driven Sensor Data Analysis
CONSTANTS WE CAN MEASURE
Vehicle Type & Driving Behavior Road Condition Monitoring
Road Condition & Driving Behavior Car Prognosis
Road Condition & Vehicle Type Driving Behavior Analysis
Acceleration a(t) = f (H(t), v(t), R(t), D(t))
H(t)
System
Identification Tools

5. 5
MotivationMotivation
 Need for a synthetic data generation
 Experimentation is time consuming and can't provide exhaustive
analysis
 Measurement influenced by multiple parameters (e.g. mobile
position, car type)
 Our Work
 Model based approach to synthetic accelerometer data
generation.
 Preliminary results on using synthetically generated data to
understand road-vehicle interaction

6. 6
ModelingModeling
 Aim: Model the interaction of road anomaly – vehicle interaction as
captured by a mobile phone in the form of acceleration profile.
 Features considered
 Five Road types (A to E as per ISO classification)
 Four car types (saloons: large, medium, small; small mass)
 Selectable: mass, natural frequency, tire radius.
 Road anomaly: step pothole.
 Impact area types: smooth, loose pebbles, muddy soil

7. 7
Modeling - InteractionModeling - Interaction
 Modeling approach:
 First principles modeling of tire
motion
 Tire launches as horizontally
launched projectile into pothole
 Tire bounces out of the pothole.
 Only one tire goes through the
pothole and hence the other axle is
firmly in place.

8. 8
Modeling – Road gradeModeling – Road grade
 Road grade modeling
 5 road types – PSD based ISO classes
 Data generation based on approaches in literature
 Generated road profile passed through quarter car to get
acceleration data
Road
Generator
Road
Type
Car
Model
Car type
Pothole
Generator
+
Pothole
parameters
Synthetic
Data

9. 9
Modeling - ResultsModeling - Results
 Experiment:
 Tata Nano (small mass) at 30
km/hr
 5 cm deep pothole on a bad
(Class D) road.
 Device: Samsung Galaxy smart
phone accelerometer at 18
Hz.
 Limitations
 Pothole exit modeling

10. 10
FeaturesFeatures
 Features: Useful for pothole detection.
 Literature: Time (amplitude) and freq. (PSD) domain.
 In this work, we use Jerk → Rate of change of Z-direction acceleration:
 Feature 1 – maximum of abs value of jerk - max(abs(diff(Az))
 Feature 2 - energy of the jerk in a time window.

11. 11
Feature 1 – Different Road typesFeature 1 – Different Road types

12. 12
Feature 1 – Different Car typesFeature 1 – Different Car types

13. 13
Feature 2 – Different Road typesFeature 2 – Different Road types

14. 14
Feature 2 – Different Car typesFeature 2 – Different Car types

15. 15
Feature 1 Validation: Max. of Jerk in Window (5cm pothole)Feature 1 Validation: Max. of Jerk in Window (5cm pothole)

16. 16
Feature 2 Validation: Energy of JerkFeature 2 Validation: Energy of Jerk

17. 17
Concluding RemarksConcluding Remarks
 CPS: integration of process and computation → enables quick
reporting of events
 We illustrated one such work for road grade monitoring.
 We have illustrated the use of synthetically generation
accelerometer data for analysis.
 Proposed features are useful to indicate sharp irregularities in a road
profile.

18. 18Copyright © 2012 Tata Consultancy Services Limited
Questions ?
arpan.pal@tcs.com