Dynamic learning driving system and method

• US 10,407,078 B2
• Filed: 04/26/2016
• Issued: 09/10/2019
• Est. Priority Date: 04/26/2016
• Status: Active Grant

• Current Assignee: Sivalogeswaran Ratnasingam
• Original Assignee: Sivalogeswaran Ratnasingam
• Inventors: Ratnasingam, Sivalogeswaran
• Primary Examiner(s): Amin, Bhavesh V
• Application Number:
  US15/139,322
• Publication Number:
  US 20170305434A1
• Time in Patent Office: 1,232 Days
• Field of Search: None
• CPC Class Codes: B60K 2360/175 Autonomous driving
• CPC Class Codes: B60K 35/00 Instruments specially adapted for vehicles; Arrangement of instruments in or on vehicles
• CPC Class Codes: B60K 35/28 characterised by the type of the output information, e.g. video entertainment or vehicle dynamics information; characterised by the purpose of the output information, e.g. for attracting the attention of the driver
• CPC Class Codes: B60W 2050/146 Display means
• CPC Class Codes: B60W 2556/05 Big data
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 2556/55 using telemetry
• CPC Class Codes: B60W 2556/65 Data transmitted between vehicles
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: G05D 1/0011 associated with a remote control arrangement
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0297 by controlling means in a control room
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A system, method, and computer program product are described for dynamically assessing and improving driver performance, including that of an autonomous driving system. Based on received electronic driver performance messages, the system determines whether an instant feedback message is required to dynamically adjust driving behavior of a subject driver or autonomous driving system. If yes, then the system provides an instant feedback message, otherwise the system provides an aggregate feedback message, calibration message, and/or coaching recommendation as appropriate. An aggregate feedback message may be provided based at least on integral rating and/or driver performance score calculated and based at least on the driver performance messages received over a predetermined time period. The system may be adapted to perform one or more of the following: calculate insurance premium, insurance coverage, calculate cost of hiring a vehicle, monitor driving quality of drivers, recruit drivers, provide incentives, provide coaching, provide driver performance reports, and inform a third party about the driving performance of a subject driver.

Claims

1. A dynamic learning autonomous driving system, comprising:

at least one observer user device, each observer user device including a computer processor, a transceiver, a proximity sensor, and a user communications interface, said computer processor being configured to identify a target vehicle being driven by an autonomous driving system; and

a remote computer processor, said remote computer processor being configured to obtain the identification of the target vehicle being driven by the autonomous driving system from said observer user device, said remote computer processor being configured to aggregate, from a plurality of said observer user devices, vehicle driving data of the target vehicle being driven by the autonomous driving system, said remote computer processor being configured to adjust at least one calibration factor to improve driving performance of the autonomous driving system of the identified target vehicle based on the aggregate vehicle driving data obtained from said plurality of observer user devices.

2. A system for dynamically adjusting driving behaviour, comprising:

a computer processor configured to identify a target vehicle being driven by a subject driver, wherein identifying includes using a proximity sensor in at least one of the target vehicle and a vehicle carrying an observer user device; and

a non-transitory computer readable medium encoded with a computer program coupled to said computer processor that when executed cause the processor to;

receive at least one driver performance message from a plurality of observer user devices over a communications network, the driver performance message including an identity of the target vehicle and data relating to at least one driver performance metric associated with the subject driver of the target vehicle; and

determine a driver performance score of the subject driver based on an aggregation of driver performance messages from the plurality of observer user devices for a plurality of driver performance metrics verify the correctness of the received driver performance message by comparing the data relating to the driver performance metric associated with the subject driver with data obtained from at least one sensor data wherein the sensor is either in the observer user device or in the target vehicle or in the environment.

3. The system of claim 2, wherein the computer program encoded on said non-transitory computer readable medium includes instructions that when executed by said computer processor cause said computer processor to send an aggregate driver feedback message to a user device in the target vehicle within a predetermined time of an initial driver performance message being received at the remote computer processor, the initial driver performance message including at least one of the identity of the target vehicle, the identity of the subject driver, and the identity of the observer user device, the driver performance message further including data relating to at least one driver performance metric associated with the subject driver of the target vehicle.

4. The system of claim 2, wherein the computer program encoded on said non-transitory computer readable medium includes instructions that when executed by said computer processor cause said computer processor to generate one of an insurance premium and a cost of hiring a vehicle for the subject driver based on the driver performance score.

5. A method for dynamically adjusting driving behaviour, comprising:

identifying, with an observer user device, at least one of a target vehicle and a subject driver associated with the target vehicle;

receiving, at a remote computer processor, at least one driver performance message from a plurality of the observer user devices over a communications network, the driver performance message including the identity of the target vehicle and/or the identity of the subject driver, the driver performance message further including data relating to at least one driver performance metric associated with the subject driver of the target vehicle;

determining, at the remote computer processor, a driver performance score of the subject driver based on an aggregation of some or all driver performance messages from the plurality of observer user devices; and

wherein identifying includes using a proximity sensor in at least one of the target vehicle and a vehicle carrying the observer user device.

6. The method of claim 5, further comprising wherein sending a driver feedback message to the subject driver through the communication network, after an initial driver performance message being received at the remote computer processor.

7. The method of claim 5, further comprising flagging, at a database of driver profiles, a driver profile of the subject driver with a negative rating if the driver performance score of the subject driver is below a predetermined threshold.

8. The method of claim 7, wherein the negative rating triggers a recommendation for driver coaching for the subject driver.

9. The method of claim 5, further comprising flagging, at a database of driver profiles, a driver profile of the subject driver with a positive rating if the driver performance score of the subject driver is above a predetermined threshold.

10. The method of claim 9, wherein the positive rating triggers a reward or discount for the subject driver.

11. The method of claim 5, wherein the driver performance score is determined by combining driver performance messages relating to a particular driver performance metric associated with the subject driver.

12. The method of claim 5, wherein the determination of the driver performance score is conducted after normalizing the data related to a driver performance metric, wherein the normalization is performed to account for individual differences between the observer users in providing the driver performance messages to the subject driver.

13. The method of claim 5, further comprising verifying, with a proximity sensor in the observer user device, the data related to a driver performance metric associated with the subject driver wherein the data related to the driver performance metric is verified for correctness by comparing with the proximity sensor data.

15. The method of claim 5, further comprising generating, using the driver performance score, at least one of an insurance premium for the subject driver and a cost of hiring a vehicle.

16. The method of claim 5, further comprising verifying, with at least one onboard proximity sensor in the target vehicle which produces vehicle driving data, the data relating to the at least one driver performance metric associated with the subject driver wherein the data relating to the driver performance metric is verified for correctness by comparing with the onboard proximity sensor data.

17. The method of claim 5, wherein the determination of the driver performance score is conducted after removing outliers outside a predetermined range in the data relating to a driver performance metric.

19. The method of claim 5, further comprising verifying, by comparing the data relating to the driver performance metric associated with the subject driver with driver performance messages received from other observer user devices wherein the comparison is performed to check whether the data relating to the driver performance metric received from one observer user is correct compared to the driver performance messages received from other observer users.

14. A method for dynamically adjusting driving behaviour, comprising:

identifying, with an observer user device, at least one of a target vehicle and a subject driver associated with the target vehicle;

receiving, at a remote computer processor, at least one driver performance message from at least one of the observer user devices over a communications network, the driver performance message including at least one of an identity of the target vehicle, an identity of the subject driver, and an identity of the observer user device, the driver performance message further including data relating to at least one driver performance metric associated with the subject driver of the target vehicle; and

checking whether an instant feedback message is required;

if instant feedback is required, then sending, from the remote computer processor, a driver feedback message through a network interface, addressed to an address of the subject driver associated with the target vehicle only after an initial driver performance message being received at the remote computer processor, the initial driver performance message including at least one of the identity of the target vehicle, the identity of the subject driver, and the identity of the user device, the driver performance message further including data relating to at least one driver performance metric associated with the subject driver of the target vehicle verify the correctness of the received driver performance message by comparing the data relating to the driver performance metric associated with the subject driver with data obtained from at least one sensor data wherein the sensor is in the observer user device or in the target vehicle or in the environment.

18. A method for dynamically adjusting driving behaviour, comprising:

identifying, with an observer user device, at least one of a target vehicle and a subject driver associated with the target vehicle;

receiving, at a remote computer processor, at least one driver performance message from at least one of the observer user devices over a communications network, the driver performance message including at least one of an identity of the target vehicle, an identity of the subject driver, and an identity of the observer user device, the driver performance message further including data relating to at least one driver performance metric associated with the subject driver of the target vehicle; and

determining, at the remote computer processor, a driver performance score of the subject driver based on an aggregation of some or all driver performance messages from the plurality of observer user devices;

wherein the determination of the driver performance score is based on the receiving of driver performance messages within a first predetermined time period, and further comprises;

generating an estimated driver performance score for a second predetermined time period, based on the determination of the driver performance score over the first predetermined time period wherein the second predetermined time period is in the future;

determining a second driver performance score of the subject driver based on an aggregation of some or all driver performance messages from the plurality of observer user devices over a third predetermined time period; and

recalculating an insurance premium of the subject driver if the difference between the estimated driver performance score and the second driver performance score is above a predetermined threshold.

20. A method for dynamically adjusting driving behaviour, comprising:

identifying, with an observer user device, at least one of a target vehicle and a subject driver associated with the target vehicle;

receiving, at a remote computer processor, at least one driver performance message from at least one of the observer user devices over a communications network, the driver performance message including at least one of an identity of the target vehicle, an identity of the subject driver, and an identity of the observer user device, the driver performance message further including data relating to at least one driver performance metric associated with the subject driver of the target vehicle;

determining, at the remote computer processor, a driver performance score of the subject driver based on an aggregation of some or all driver performance messages from the plurality of observer user devices; and

wherein the subject driver is an autonomous driving system coupled to the target vehicle.

21. A computer program product embodied in a computer readable storage medium for dynamically adjusting driving behaviour, the computer program product comprising programming instructions that when executed, cause a coupled processor to:

identify, with an observer user device, a target vehicle being driven by a subject driver;

receive, at a remote computer processor, at least one driver performance message from at least one observer user device over a communications network, the driver performance message including at least one of an identity of the target vehicle, an identity of the subject driver, and an identity of the observer user device, the driver performance message further including data relating to at least one driver performance metric associated with the subject driver of the target vehicle; and

send an instant driver feedback message to a user device in the target vehicle after an initial driver performance message being received at the remote computer processor, the initial driver performance message including at least one of the identity of the target vehicle, the identity of the subject driver, and the identity of the observer user device, the driver performance message further including data relating to at least one driver performance metric associated with the subject driver of the target vehicle wherein the initial driver performance message is initiated by the observer user.

22. The computer program product of claim 21, further comprising programming instructions causing the coupled computer to verify with at least one on board proximity sensor in the target vehicle which produces vehicle driving data, the data related to the at least one driver performance metric associated with the subject driver wherein the data related to the driver performance metric is verified for correctness by comparing with the proximity sensor data.

23. The computer program product of claim 21, further comprising programming instructions causing the coupled computer to generate one of an insurance premium and a cost of hiring a vehicle for the subject driver based on a driver performance score wherein, the driver performance score of the subject driver is determined based on an aggregate of some or all the driver performance messages from the plurality of observer user devices for at least one driver performance metric.

24. The computer program product of claim 21, further comprising programming instructions causing the coupled computer to determine a driver performance score based on the receiving of driver performance messages within a first predetermined time period, wherein the programming instructions further cause the coupled computer to:

generate an estimated driver performance score for a second predetermined time period, based on the determination of the driver performance score over the first predetermined time period wherein the second predetermined time period is in the future;

determine a second driver performance score of the subject driver based on an aggregate of some or all driver performance messages from the plurality of observer user devices over a third predetermined time period; and

recalculate an insurance premium of the subject driver if the difference between the estimated driver performance score and the second driver performance score is above a predetermined threshold.