System and method for detecting anomaly associated with driving of a vehicle

• US 9,165,325 B2
• Filed: 07/09/2014
• Issued: 10/20/2015
• Est. Priority Date: 07/10/2013
• Status: Active Grant

• Current Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Original Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Inventors: Chakravarty, Tapas, Ghose, Avik, Bhaumik, Chirabrata, Purushothaman, Balamuralidhar, Chowdhury, Arijit
• Primary Examiner(s): BUTLER, RODNEY ALLEN
• Application Number:
  US14/327,211
• Publication Number:
  US 20150019067A1
• Time in Patent Office: 468 Days
• US Class Current: 1/1
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 2756/10 Involving external transmission of data to or from the vehicle
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: G05B 23/0232 based on qualitative trend analysis, e.g. system evolution
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/085 using electronic data carriers

Abstract

Disclosed are a device, system and methods for detecting an anomaly associated with driving of a vehicle. Z-axis acceleration data is determined at the device. Based on the Z-axis acceleration data, jerk energies are computed and transmitted to the system for analysis. Further, the jerk energies are received for a plurality of trips at the system. Further, at the system, statistical analysis is performed on the jerk energies for determining a hazard rate for each trip of the plurality of trips. Then based on the hazard rate determined for each of the plurality of trips, a trend analysis is performed. Based on the trend analysis, any anomaly associated with the driving of the vehicle is detected. Further, the anomaly detected may be notified to a person associated with the device or with a monitoring terminal.

Claims

1. A system for detecting an anomaly associated with driving of a vehicle for a plurality of trips, the system comprising:

a processor; and

a memory coupled to the processor, wherein the memory has a plurality of modules stored therein that are executable by the processor, the plurality of modules comprising;

a receiving module configured to receive jerk energies for a trip of the plurality of trips from a device computing the jerk energies;

a statistical analysis module coupled to the receiving module to receive the jerk energies therefrom, wherein the statistical analysis module performs a statistical analysis of the jerk energies and determines a hazard rate for the trip based upon the statistical analysis;

a trend analysis module coupled to the statistical analysis module to receive the hazard rate for the trip, wherein the trend analysis module performs a trend analysis of the hazard rate of each trip of the plurality of trips; and

an anomaly detection module coupled to the trend analysis module to receive the trend analysis, wherein the anomaly detection module detects any anomaly associated with the driving of the vehicle based on the trend analysis.

2. The system of claim 1, wherein the statistical analysis module determines the hazard rate using the one or more statistical parameters and the percentile value.

3. The system of claim 1, wherein the statistical analysis module performs the statistical analysis by:

obtaining one or more statistical parameters of the jerk energies, wherein the statistical parameters comprises a shape parameter (k) and a scale parameter (λ

), and wherein the shape parameter (k) and the scale parameter (λ

) each conform to a Weibull distribution; and

determining a percentile value (X_high) for the jerk energies.

4. The system of claim 1, wherein the trend analysis module performs the trend analysis by:

processing the hazard rate of each trip of the plurality of trips;

determining a mean-value, an upper-bound value, and a lower-bound value based on the processing of the hazard rate of the plurality of trips; and

performing the trend analysis based upon the upper-bound value and the lower-bound value of the hazard rate of the plurality of trips.

5. The system of claim 3, wherein the statistical analysis module determines the hazard rate using the one or more statistical parameters and the percentile value.

6. The system of claim 3, further comprising a notification module coupled to the anomaly detection module to receive a signal indicative of the presence of an anomaly and configured to notify a person about the anomaly associated with the vehicle, wherein the person may be any one of a driver driving the vehicle and a person monitoring the driving of the vehicle through a monitoring terminal.

7. A method for detecting an anomaly associated with driving of a vehicle for a plurality of trips, the method comprising:

receiving, by a processor, jerk energies for a trip of plurality of trips from a device computing the jerk energies;

performing, by a processor, a statistical analysis of the jerk energies to determine a hazard rate for the trip based upon the statistical analysis;

performing, by the processor, a trend analysis of the hazard rate for each trip of the plurality of trips; and

detecting, by the processor, any anomaly associated with the driving of the vehicle based on the trend analysis.

8. The method for claim 7, wherein the performing the statistical analysis comprises:

obtaining one or more statistical parameters of jerk energies, wherein the statistical parameters comprises a shape parameter (k) and a scale parameter (λ

), and wherein the shape parameter (k) and the scale parameter (λ

) are conform to a Weibull distribution; and

determining a percentile value (X_high) for the jerk energies.

9. The method of claim 7, wherein the performing the trend analysis comprises:

processing the hazard rate of each trip of the plurality of trips;

determining a mean-value, an upper-bound value, and a lower-bound value based on the processing of the hazard rate of the plurality of trips; and

performing the trend analysis based upon the upper-bound value and the lower-bound value of the hazard rate of the plurality of trips.

10. The method of claim 8, wherein the determination of the hazard rate is performed using the one or more statistical parameters and the percentile value.