Passing vehicle on shoulder

Patent metadata

Field	Value
Publication number	US-12545294-B2
Application number	US-202318238438-A
Country	US
Kind code	B2
Filing date	Aug 25, 2023
Priority date	Aug 25, 2023
Publication date	Feb 10, 2026
Grant date	Feb 10, 2026

Abstract

A method of passing an object on the side of the road by receiving a first signal from a first sensor configured to detect a presence of the object positioned on a shoulder of a road; determining a first value; assigning a first confidence value to a confidence level, wherein the first confidence value is associated with the first value; responsive to the first confidence value exceeding a confidence threshold, adjusting a first operating parameter of a vehicle; responsive to entering a threshold range of the object, receiving a second signal from a second sensor; determining a second value associated with the second signal; assigning a second confidence value to the confidence level, wherein the second confidence value is associated with the second value; responsive to the second confidence value exceeding a second confidence threshold, adjusting a second operating parameter of the vehicle.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
receiving, by a processor, a first signal from a first sensor configured to detect a presence of an object positioned on a shoulder of a road; determining, by the processor, a first value associated with the first signal by classifying, using a binary classification machine learning model executed by the processor, the first signal into the first value, the first value indicating the presence of the object; assigning, using the binary classification machine learning model, a first confidence value to a confidence level, wherein the first confidence value is associated with the first value and indicates a likelihood that the first value correctly indicates the presence of the object; storing, by the processor, the first confidence value in a memory; responsive to the first confidence value exceeding a confidence threshold, adjusting, by the processor, a first operating parameter of a vehicle traveling on the road; responsive to entering a threshold range of the object, receiving, by the processor, a second signal from a second sensor configured to detect the presence of the object on the shoulder of the road; determining, by the processor, a second value associated with the second signal by classifying, using a detailed classification machine learning model executed by the processor, the second signal into the second value, the second value indicating a detailed classification of the object; assigning, using the detailed classification machine learning model, a second confidence value to the confidence level, wherein the second confidence value is associated with the second value and indicates a likelihood that the second value correctly indicates the detailed classification of the object; storing, by the processor, the second confidence value in the memory; and responsive to the second confidence value exceeding a second confidence threshold, adjusting, by the processor, a second operating parameter of the vehicle.

2 . The computer-implemented method of claim 1 , wherein the second operating parameter is adjusted to avoid the vehicle running out of a drivable surface.

3 . The computer-implemented method of claim 1 , wherein the first sensor is configured to collect data from which the processor can determine a binary classification of the object.

4 . The computer-implemented method of claim 1 , wherein the first sensor and the second sensor are positioned on the vehicle traveling on the road.

5 . The computer-implemented method of claim 1 , wherein the vehicle is an autonomous vehicle.

6 . The computer-implemented method of claim 1 , wherein the first sensor is an image-collecting camera, and the second sensor is a light detection and ranging (“LIDAR”) sensor.

7 . The computer-implemented method of claim 1 , wherein the first operating parameter and the second operating parameter are one of an engine speed, steering angle, braking amount, gear engagement, lighting status, and aural warning.

8 . The computer-implemented method of claim 1 , wherein the processor is remote to the vehicle and communicatively coupled to a vehicle control system locally housed on the vehicle, the vehicle control system configured to implement adjusting the first operating parameter and the second operating parameter.

9 . A system comprising:
a non-transitory computer-readable medium comprising instructions that are configured to be executed by at least one processor associated with an automated vehicle to: receive a first signal from a first sensor configured to detect a presence of an object positioned on a shoulder of a road; determine a first value associated with the first signal by classifying, using a binary classification machine learning model executed by the processor, the first signal into the first value, the first value indicating the presence of the object; assign, using the binary classification machine learning model, a first confidence value to a confidence level, wherein the first confidence value is associated with the first value and indicates a likelihood that the first value correctly indicates the presence of the object; store the first confidence value in a memory; responsive to the first confidence value exceeding a confidence threshold, adjust a first operating parameter of a vehicle traveling on the road; responsive to entering a threshold range of the object, receive a second signal from a second sensor configured to detect the presence of the object on the shoulder of the road; determine a second value associated with the second signal by classifying, using a detailed classification machine learning model executed by the processor, the second signal into the second value, the second value indicating a detailed classification of the object; assign, using the detailed classification machine learning model, a second confidence value to the confidence level, wherein the second confidence value is associated with the second value and indicates a likelihood that the second value correctly indicates the detailed classification of the object; store the second confidence value in the memory; and responsive to the second confidence value exceeding a second confidence threshold, adjust a second operating parameter of the vehicle.

10 . The system of claim 9 , wherein the at least one processor is remote to the vehicle and communicatively coupled to a vehicle control system locally housed on the vehicle, the vehicle control system configured to implement adjusting the first operating parameter and the second operating parameter.

11 . The system of claim 9 , wherein the second operating parameter is adjusted to avoid the vehicle running out of a drivable surface.

12 . The system of claim 9 , wherein the first sensor is configured to collect data from which the at least one processor can determine a binary classification of the object.

13 . The system of claim 9 , wherein the first sensor and the second sensor are positioned on the vehicle traveling on the road.

14 . The system of claim 9 , wherein the vehicle is an autonomous vehicle.

15 . The system of claim 9 , wherein the first sensor is an image-collecting camera, and the second sensor is a light detection and ranging (“LIDAR”) sensor.

16 . The system of claim 9 , wherein the first operating parameter and the second operating parameter are one of an engine speed, steering angle, braking amount, gear engagement, lighting status, and aural warning.

17 . A vehicle comprising a processor configured to:
receive a first signal from a first sensor configured to detect a presence of an object positioned on a shoulder of a road; determine a first value associated with the first signal by classifying, using a binary classification machine learning model executed by the processor, the first signal into the first value, the first value indicating the presence of the object; assign, using the binary classification machine learning model, a first confidence value to a confidence level, wherein the first confidence value is associated with the first value and indicates a likelihood that the first value correctly indicates the presence of the object; store the first confidence value in a memory; responsive to the first confidence value exceeding a confidence threshold, adjust a first operating parameter of the vehicle; responsive to entering a threshold range of the object, receive a second signal from a second sensor configured to detect the presence of the object on the shoulder of the road; determine a second value assoc

Assignees

• Torc Robotics Inc

Inventors

• Petrin Joshua
• Madsen Garrett
• Chaudhry Haseeb
• Cunningham Andrew
• Blankenhorn John
• Brown Paul
• Davis William
• Mateti Kiron
• Kriener Robert

Classifications

• B60W2420/408

  Radar; Laser, e.g. lidar · CPC title

• B60W2420/403

  Image sensing, e.g. optical camera · CPC title

• B60W2510/0638

  Engine speed · CPC title

• B60W2510/1005

  Transmission ratio engaged · CPC title

• B60W2510/20

  Steering systems · CPC title