SAFETY SYSTEM FOR A VEHICLE

• US 20200133281A1
• Filed: 12/27/2019
• Published: 04/30/2020
• Est. Priority Date: 12/27/2019
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation, MobilEye Vision Technologies Ltd. (Intel Corporation)
• Inventors: GOMEZ GUTIERREZ, David, KRISHNAN, Ranganath, FELIP LEON, Javier, AHUJA, Nilesh, NDIOUR, Ibrahima
• Granted Patent: US 11,314,258 B2
• Time in Patent Office: Days
• CPC Class Codes: B60W 2050/0005 Processor details or data handling, e.g. memory registers or chip architecture
• CPC Class Codes: B60W 2050/0028 Mathematical models, e.g. for simulation
• CPC Class Codes: B60W 2554/402 Type
• CPC Class Codes: B60W 2556/20 Data confidence level
• CPC Class Codes: B60W 2720/10 Longitudinal speed
• CPC Class Codes: B60W 2754/30 Longitudinal distance
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 40/02 related to ambient conditions
• CPC Class Codes: B60W 50/0225 Failure correction strategy
• CPC Class Codes: B60W 60/0018 by employing degraded modes, e.g. reducing speed, in response to suboptimal conditions
• CPC Class Codes: G05D 1/0214 in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13
• CPC Class Codes: G05D 1/0221 involving a learning process

Abstract

A safety system for a vehicle may include one or more processors configured to determine uncertainty data indicating uncertainty in one or more predictions from a driving model during operation of a vehicle; change or update one or more of the driving model parameters to one or more changed or updated driving model parameters based on the determined uncertainty data; and provide the one or more changed or updated driving model parameters to a control system of the vehicle for controlling the vehicle to operate in accordance with the driving model including the one or more changed or updated driving model parameters.

Claims

1. A safety system for a vehicle, the safety system comprising:

one or more processors configured to

determine uncertainty data indicating uncertainty in one or more predictions from a driving model including predefined driving model parameters, during operation of a vehicle;

change or update one or more of the driving model parameters to one or more changed or updated driving model parameters based on the determined uncertainty data; and

provide the one or more changed or updated driving model parameters to a control system of the vehicle for controlling the vehicle to operate in accordance with the driving model including the one or more changed or updated driving model parameters.

2. The safety system of claim 1, further comprising:

a memory coupled to the one or more processors and storing the driving model parameters of the driving model.

3. The safety system of claim 1,

wherein the one or more processors are configured to implement a safety driving model.

4. The safety system of claim 1,

wherein the one or more changed or updated driving model parameters meet with a predefined safety criterion in accordance with the driving model.

5. The safety system of claim 1,

wherein the one or more processors are configured to determine the uncertainty data using a trained system.

6. The safety system of claim 5,

wherein the trained system comprises a neural network.

7. The safety system of claim 6,

wherein the neural network comprises a Bayesian neural network.

8. The safety system of claim 5,

wherein the uncertainty data indicate at least one of uncertainty due to noise in input data of the trained system or uncertainty due to uncertainty in model parameters of the trained system.

9. The safety system of claim 1,

wherein the one or more predictions include one or more classifications of one or more objects included in image data.

10. The safety system of claim 1,

wherein the one or more changed or updated driving model parameters comprise a maximum allowed velocity of the vehicle.

11. The safety system of claim 1,

wherein the one or more changed or updated driving model parameters comprise a safe longitudinal distance for the vehicle.

12. The safety system of claim 1,

wherein the one or more processors are further configured to

determine an average distance at which objects are detected with a predefined confidence level based on the uncertainty data, and

change or update the one or more driving model parameters to the one or more changed or updated driving model parameters based on the determined average distance.

13. The safety system of claim 12,

wherein the one or more processors are configured to determine the average distance using a trained system.

14. The safety system of claim 13,

wherein the trained system comprises a fully connected neural network.

15. The safety system of claim 14,

wherein the one or more processors are further configured to determine whether to give control to a human driver based on the determined uncertainty data.

16. A method of operating a safety system for a vehicle, the method comprising:

determining uncertainty data indicating uncertainty in one or more predictions from a driving model including predefined driving model parameters, during operation of a vehicle;

changing or updating one or more of the driving model parameters to one or more changed or updated driving model parameters based on the determined uncertainty data; and

providing the one or more changed or updated driving model parameters to a control system of the vehicle for controlling the vehicle to operate in accordance with the driving model including the one or more changed or updated driving model parameters.

17. The method of claim 16,

wherein determining the uncertainty data comprises using a Bayesian neural network.

18. The method of claim 16, further comprising:

determining an average distance at which objects are detected with a predefined confidence level based on the uncertainty data, and

changing or updating the one or more driving model parameters to the one or more changed or updated driving model parameters based on the determined average distance.

19. A vehicle, comprising:

a control system configured to control the vehicle to operate in accordance with a driving model including predefined driving model parameters;

a safety system, comprising one or more processors configured to;

determine uncertainty data indicating uncertainty in one or more predictions from the driving model during the operation of the vehicle;

change or update one or more of the driving model parameters to one or more changed or updated driving model parameters based on the determined uncertainty data; and

provide the one or more changed or updated driving model parameters to the control system for controlling the vehicle to operate in accordance with the driving model including the one or more changed or updated driving model parameters.

20. The vehicle of claim 19,

wherein the one or more processors are further configured to determine the uncertainty data using a Bayesian neural network.