IP Library › Granted Patent US 11,008,000
Granted Patent B2
US 11,008,000 · App. 16/013,459 · Granted May 18, 2021

Risk processing for vehicles having autonomous driving capabilities

Inventors: Hsun-Hsien Chang (Brookline, MA); Noam Weinstein (Cambridge, MA); Eric Wolff (Cambridge, MA); Philipp Robbel (Cambridge, MA); Jacob C. Cheuvront (Waltham, MA); Karl Iagnemma (Belmont, MA); Katarzyna Anna Marczuk (Singapore, SG)
Assignee: Motional AD LLC
B60W30/09B60W30/0953B60W30/0956B60W30/10B60W30/18163B60W50/0097G07C5/008B60W2050/0089B60W2520/06B60W2520/10B60W2540/30B60W2552/00B60W2554/80
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,008,000
App. No.
16/013,459
Granted
May 18, 2021
Kind
B2
Abstract

Among other things, sensor signals are received using a vehicle comprising an autonomous driving capability. A risk associated with operating the vehicle is identified based on the sensor signals. The autonomous driving capability is modified in response to the risk. The operation of the vehicle is updated based on the modifying of the autonomous capability.

Claims (78)

1. An apparatus comprising:

a processor configured to:

process data to learn a pattern of known risks corresponding to driving a vehicle comprising an autonomous driving capability, wherein learning the pattern of known risks comprises:

inferring, using a learning algorithm, one or more of (i) regions satisfying criteria indicative of elevated probability of accidents, (ii) time periods corresponding to the elevated probability of accidents, (iii) road configurations, or (iv) a distribution of risks within an region or within a time period, and

determining the pattern of known risks based on the inferences using the learning algorithm;

identify, using the pattern of known risks, a risk during a particular instance of driving the vehicle;

modify the autonomous driving capability in response to the identified risk;

update operation of the vehicle during the particular instance of driving the vehicle based on modifying the autonomous driving capability; and

prepare a report of a risk, wherein preparing the report comprises:

extracting and aggregating, from sensor signals, information associated with the risk,

evaluating, using the information associated with the risk, one or more of overlapping geographic zones, overlapping time periods, or report frequencies,

generating the report based on the evaluating, and

sending the report to a remote entity; and

an alarm configured to issue an alert of the identified risk.

2. The apparatus of claim 1 , wherein identifying the risk comprises detecting or predicting the risk.

3. The apparatus of claim 1 , wherein the data comprises at least one of sensor signals, or known or predicted risks.

4. The apparatus of claim 3 , wherein identifying the risk comprises at least one of:

analyzing the sensor signals to determine a position of an object,

analyzing the sensor signals to evaluate a speed of an object,

analyzing the sensor signals to evaluate speed profiles of two or more objects over time,

analyzing the sensor signals to identify a boundary of an object,

analyzing the sensor signals to identify overlapping boundaries of two or more objects, or

analyzing the sensor signals to determine a concentration of a chemical.

5. The apparatus of claim 3 , wherein identifying the risk comprises analyzing the sensor signals to segment one or more objects in an image or a video.

6. The apparatus of claim 5 , further comprising:

identifying an object in a driving environment; and

in response to identifying the object in the driving environment:

determining a boundary of the object, and

tracking the object by following the boundary.

7. The apparatus of claim 1 , wherein identifying the risk comprises assessing a threat.

8. The apparatus of claim 1 , wherein identifying the risk comprises evaluating a driving behavior of at least one of the vehicle or another vehicle.

9. The apparatus of claim 8 , wherein evaluating a driving behavior comprises evaluating at least one of a speed, a heading, a trajectory, or a vehicular operation.

10. The apparatus of claim 1 , wherein updating the operation of the vehicle comprises executing at least one of a lane change by a motion planning system of the vehicle, or a trajectory change by the motion planning system of the vehicle.

11. The apparatus of claim 1 , wherein the processor is configured to treat analyzed sensor signals as prior information to a perception system of the vehicle in response to the risk.

12. The apparatus of claim 1 , wherein the processor is configured to invoke intervention on an operation of the vehicle from a remote operator in response to the risk.

13. The apparatus of claim 1 , wherein updating the operation of the vehicle comprises at least one of:

generating and inserting new machine instructions into existing machine instructions of an operation of the vehicle, or

generating an input to an operation of the vehicle.

14. The apparatus of claim 1 , wherein preparing a report of a risk comprises one of:

recording an environment of the risk,

stitching images or videos to form a view of the risk,

removing private information associated with the risk,

providing a graphical user interface to allow a user to provide information associated with the risk, or

integrating two or more reports associated with the risk.

15. The apparatus of claim 1 , wherein the processor is configured to receive the report of the risk from a remote data source.

16. The apparatus of claim 1 , wherein the processor is configured to assess a risk factor of the vehicle.

17. The apparatus of claim 16 , wherein assessing the risk factor comprises one of: determining a risk associated with passing through a risky region, determining a risk associated with a driving distance or a driving time period, determining a risk associated with an aging component of the vehicle, determining a risk associated with an inactive autonomous driving capability, determining a risk based on a profile of a user of the vehicle, determining a risk based on social network information of a user of the vehicle, determining a risk associated with a driving behavior, or determining a risk associated with following traffic rules.

18. The apparatus of claim 1 , wherein determining the pattern of known risks based on the inferences using the learning algorithm comprises using a probabilistic model to determine risks corresponding to one or more of the regions, the time periods, or the road configurations.

19. The apparatus of claim 1 , wherein determining the pattern of known risks based on the inferences using the learning algorithm comprises using historical information about driving properties of vehicles that have previously traveled along similar trajectories at similar times.

20. A method comprising:

processing data to learn a pattern of known risks corresponding to driving a vehicle comprising an autonomous driving capability, wherein learning the pattern of known risks comprises:

inferring, using a learning algorithm, one or more of (i) regions satisfying criteria indicative of elevated probability of accidents, (ii) time periods corresponding to elevated probability of accidents, (iii) road configurations, or (iv) a distribution of risks within an region or within a time period, and

determining the pattern of known risks based on the inferences using the learning algorithm;

receiving sensor signals using the vehicle during a particular instance of driving the vehicle;

identifying, using the pattern of known risks, a risk associated with operating the vehicle based on the sensor signals during a particular instance of driving the vehicle;

modifying the autonomous driving capability in response to the identified risk;

updating the operation of the vehicle during the particular instance of driving the vehicle based on modifying the autonomous driving capability; and

preparing a report of a risk, wherein preparing the report comprises:

extracting and aggregating, from sensor signals, information associated with the risk,

evaluating, using the information associated with the risk, one or more of overlapping geographic zones, overlapping time periods, or report frequencies,

generating the report based on the evaluating, and

sending the report to a remote entity.

21. A vehicle having autonomous driving capabilities, the vehicle comprising:

steering, acceleration, and deceleration devices that respond to control signals from a driving control system to drive the vehicle autonomously on a road network;

a monitoring element on the vehicle that:

processes data to learn a pattern of known risks corresponding to driving the vehicle, wherein learning the pattern of known risks comprises:

inferring, using a learning algorithm, one or more of (i) regions satisfying criteria indicative of elevated probability of accidents, (ii) time periods corresponding to elevated probability of accidents, (iii) road configurations, or (iv) a distribution of risks within an region or within a time period, and

determining the pattern of known risks based on the inferences using the learning algorithm,

receives sensor signals during a particular instance of driving the vehicle; and

identifies, using the pattern of known risks, a risk associated with operating the vehicle based on the sensor signals during a particular instance of driving the vehicle; and

a controller that responds to the risk by configuring the driving control system to:

modify the autonomous driving capability in response to the identified risk;

based on modifying the autonomous capability, update an operation of the vehicle during the particular instance of driving the vehicle to maneuver the vehicle to a goal location; and

prepare a report of a risk, wherein preparing the report comprises:

extracting and aggregating, from sensor signals, information associated with the risk,

evaluating, using the information associated with the risk, one or more of overlapping geographic zones, overlapping time periods, or report frequencies,

generating the report based on the evaluating, and

sending the report to a remote entity.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 12, 2021
From: APTIV TECHNOLOGIES LIMITED
To: MOTIONAL AD LLC
Reel/Frame 054888/0250 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 26, 2018
From: CHANG, HSUN-HSIEN; WEINSTEIN, NOAM; WOLFF, ERIC; ROBBEL, PHILIPP; CHEUVRONT, JACOB C.; IAGNEMMA, KARL; MARCZUK, KATARZYNA ANNA
To: APTIV TECHNOLOGIES LIMITED
Reel/Frame 046473/0768 →
Continuity (2)
Provisional Application 62522254 · Jun 20, 2017
Related Publication 20180362031A1 · Dec 20, 2018
Cited By (3)
US 12,392,627 US 12,654,746 US 12,670,794