Method and system for risk modeling in autonomous vehicles

• US 10,012,993 B1
• Filed: 12/07/2017
• Issued: 07/03/2018
• Est. Priority Date: 12/09/2016
• Status: Active Grant

• Current Assignee: Zendrive, Inc.
• Original Assignee: Zendrive, Inc.
• Inventors: Matus, Jonathan, Risbood, Pankaj
• Primary Examiner(s): Badii, Behrang
• Application Number:
  US15/835,284
• Publication Number:
  US 20180164825A1
• Time in Patent Office: 208 Days
• CPC Class Codes: B60W 2050/0075 Automatic parameter input, automatic initialising or calibrating means
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2420/408 Radar; Laser, e.g. lidar
• CPC Class Codes: B60W 2554/4026 Cycles
• CPC Class Codes: B60W 2554/4029 Pedestrians
• CPC Class Codes: B60W 2554/4046 Behavior, e.g. aggressive or erratic
• CPC Class Codes: B60W 2554/406 Traffic density
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 30/00 Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: B60W 50/0098 Details of control systems ensuring comfort, safety or stability not otherwise provided for
• CPC Class Codes: B60W 50/082 Selecting or switching between different modes of propelling
• CPC Class Codes: B60W 60/00188 related to detected security violation of control systems, e.g. hacking of moving vehicle
• CPC Class Codes: B60W 60/0053 from vehicle to occupant
• CPC Class Codes: B60W 60/0059 Estimation of the risk associated with autonomous or manual driving, e.g. situation too complex, sensor failure or driver incapacity
• CPC Class Codes: B64C 39/02 characterised by special use
• CPC Class Codes: B64C 39/024 of the remote controlled vehicle type, i.e. RPV
• CPC Class Codes: B64D 11/0624 Arrangements of electrical connectors, e.g. for earphone, internet or electric supply
• CPC Class Codes: G05D 1/00 : Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots drive control systems specially adapted for autonomous road vehicles B60W60/00
• CPC Class Codes: G06F 18/00 : Pattern recognition
• CPC Class Codes: G06F 18/23 : Clustering techniques
• CPC Class Codes: G06Q 40/08 : Insurance
• CPC Class Codes: G06V 20/56 : exterior to a vehicle by using sensors mounted on the vehicle
• CPC Class Codes: G06V 40/20 : Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G08G 1/0112 : from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/096725 : where the received information generates an automatic action on the vehicle control
• CPC Class Codes: G08G 5/00 : Traffic control systems for aircraft , e.g. air-traffic control [ATC]
• CPC Class Codes: G08G 5/003 : Flight plan management

Abstract

A method for adaptive risk modeling for an autonomous vehicle, the method comprising: retrieving parameters of an identified driving mission of the autonomous vehicle; in response to the parameters of the identified driving mission, generating values of: a comparative autonomous parameter, a mix model parameter, a surrounding risk parameter, a geographic operation parameter, and a security risk parameter upon evaluating situational inputs associated with the identified driving mission with a comparative autonomous model, a mix model, a sensor-surrounding model, a geography-dependent model, and a security risk model generated using sensor and supplementary data extraction systems associated with the autonomous vehicle; upon generating values, generating a risk analysis with a rule-based algorithm; and contemporaneously with execution of the identified driving mission, implementing a response action associated with control of the autonomous vehicle, based upon the risk analysis.

Claims

1. A method for adaptive risk modeling for an autonomous vehicle, the method comprising:

with sensor systems associated with the autonomous vehicle, generating;

a comparative autonomous model that compares autonomous vehicle operation to human driving operation in a set of driving scenarios,

a mix model characterizing operation of the autonomous vehicle in mixed-traffic driving scenarios,

a sensor-surrounding model characterizing surroundings of the autonomous vehicle;

with a supplementary data extraction system, generating;

a geography-dependent model characterizing geographic location-specific acceptable driving behaviors;

with a security diagnostic system associated with the autonomous vehicle, generating a security risk model characterizing security risks of the autonomous vehicle;

in response to an identified driving mission of the autonomous vehicle, generating values of;

a comparative autonomous parameter, a mix model parameter, a surrounding risk parameter, a geographic operation parameter, and a security risk parameter upon evaluating situational inputs associated with the identified driving mission with the comparative autonomous model, the mix model, the sensor-surrounding model, the geography-dependent model, and the security risk model;

upon generating values, generating a risk analysis upon processing values of the comparative autonomous parameter, the mix model parameter, the surrounding risk parameter, the geographic operation parameter, and the security risk parameter with a rule-based algorithm; and

contemporaneously with execution of the identified driving mission, implementing a response action associated with control of the autonomous vehicle, based upon the risk analysis.

2. The method of claim 1, wherein generating the comparative autonomous model comprises extracting at least one of a position characteristic, a velocity characteristic, and an acceleration characteristic from sensor systems associated with the autonomous vehicle during operation by a human entity and a non-human entity.

3. The method of claim 1, wherein generating the sensor-surrounding model comprises extracting an environmental dataset from an environment-sensing sensor system associated with the autonomous vehicle, and evaluating a set of specifications of the autonomous vehicle against features of the environmental dataset to determine appropriateness of the autonomous vehicle for the identified driving mission.

4. The method of claim 1, wherein generating the mix model comprises extracting a mixed traffic dataset characterizing interactions of the vehicle with a set of traffic types from a set of sensors, and tagging the mixed traffic dataset with mixed traffic event objects.

5. The method of claim 1, wherein generating the geography-dependent model comprises establishing a first interface between the autonomous vehicle and a control system in communication with a computing system and a second interface between the computing system and the supplementary data extraction system.

6. The method of claim 1, wherein processing at least one of the comparative autonomous parameter, the mix model parameter, the surrounding risk parameter, the geographic operation parameter, and the security risk parameter is based on combination of model outputs for improving accuracy of the risk analysis.

7. The method of claim 6, wherein combination of model outputs comprises determining a first weight associated with at least one of the comparative autonomous parameter, the mix model parameter, the surrounding risk parameter, the geographic operation parameter, and the security risk parameter;

determining a second weight associated with at least one of the comparative autonomous parameter, the mix model parameter, the surrounding risk parameter, the geographic operation parameter, and the security risk parameter; and

combining parameter values based on the first and the second weights for improving the accuracy of the risk analysis.

8. The method of claim 1, wherein implementing the response action associated with control of the autonomous vehicle comprises generating and executing control instructions for modified operation of the autonomous vehicle using control interfaces with subsystems of the autonomous vehicle.

17. The method of claim 1, further comprising:

obtaining a set of computer-implemented rules defining the at least one of the comparative autonomous parameter, the mix model parameter, the surrounding risk parameter, the geographic operation parameter, and the security risk parameter as a function of risk feature types associated with outputs of at least one of the comparative autonomous model, the mix model, the sensor-surrounding model, the geography-dependent model, and the security risk model; and

wherein generating the risk analysis comprises generating the risk analysis based on the set of computer-implemented rules.

9. A method for adaptive risk modeling for an autonomous vehicle, the method comprising:

retrieving parameters of an identified driving mission of the autonomous vehicle;

in response to the parameters of the identified driving mission, generating values of;

a comparative autonomous parameter, a mix model parameter, a surrounding risk parameter, a geographic operation parameter, and a security risk parameter upon evaluating situational inputs associated with the identified driving mission with a comparative autonomous model, a mix model, a sensor-surrounding model, a geography-dependent model, and a security risk model generated using sensor and supplementary data extraction systems associated with the autonomous vehicle;

upon generating values, generating a risk analysis upon processing values of the comparative autonomous parameter, the mix model parameter, the surrounding risk parameter, the geographic operation parameter, and the security risk parameter with a rule-based algorithm; and

contemporaneously with execution of the identified driving mission, implementing a response action associated with control of the autonomous vehicle, based upon the risk analysis.

10. The method of claim 9, further comprising:

with sensor systems associated with the autonomous vehicle, generating;

the comparative autonomous model that compares autonomous vehicle operation to human driving operation in a set of driving scenarios,

the mix model characterizing operation of the autonomous vehicle in mixed-traffic driving scenarios, and

the sensor-surrounding model characterizing surroundings of the autonomous vehicle.

11. The method of claim 10, wherein generating the comparative autonomous model comprises extracting at least one of a position characteristic, a velocity characteristic, and an acceleration characteristic from sensor systems associated with the autonomous vehicle during operation by a human entity and a non-human entity.

12. The method of claim 10, wherein generating the mix model comprises extracting a mixed traffic dataset characterizing interactions of the vehicle with a set of traffic types from a set of sensors, and tagging the mixed traffic dataset with mixed traffic event objects.

13. The method of claim 9, further comprising:

with a supplementary data extraction system, generating the geography-dependent model characterizing geographic location-specific acceptable driving behaviors.

14. The method of claim 9, further comprising with a security diagnostic system coupled to the autonomous vehicle, generating the security risk model characterizing security risks of the autonomous vehicle.

15. The method of claim 9, wherein retrieving parameters of the identified driving mission of the autonomous vehicle comprises receiving an input sourced from at least one of a passenger and an operator of the autonomous vehicle, the input indicative of a destination.

16. The method of claim 9, wherein processing at least one of the comparative autonomous parameter, the mix model parameter, the surrounding risk parameter, the geographic operation parameter, and the security risk parameter is based on weighted combination of model outputs for improving accuracy of the risk analysis.

18. The method of claim 9, wherein implementing the response action associated with control of the autonomous vehicle comprises generating and executing control instructions for modified operation of the autonomous vehicle using control interfaces with subsystems of the autonomous vehicle.

19. The method of claim 9, wherein implementing the response action associated with control of the autonomous vehicle comprises transmitting the risk analysis to a vehicle control platform, and modifying, from the vehicle control platform, operational rules of units of the autonomous vehicle.