IP Library Granted Patent US 12691870
Granted Patent B2
US 12691870 · App. 18/666,045 · Granted Jul 28, 2026

Predictive frozen scene for uninterrupted operation of automated evasive maneuver systems

Inventors: Reza Zarringhalam (Whitby, CA); Mohammadali Shahriari (Markham, CA); Milad Jalaliyazdi (Richmond Hill, CA); Dmitriy Feldman (W Bloomfield, MI); Assaad Krichene (Novi, MI)
Assignee: GM GLOBAL TECHNOLOGY OPERATIONS LLC
B60W30/09B60W40/06B60W2420/403B60W2420/408B60W2554/20B60W2556/00
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 12691870
App. No.
18/666,045
Granted
Jul 28, 2026
Kind
B2
Abstract

A vehicle control system including a sensor for detecting an object location, a memory for storing an environment map indicative of a driving environment coordinated with a host vehicle location, a processor configured to estimate a line and object quality, to determine an uncertainty in response to historical motion of the objects, to detect a loss of sensor data in response to the data signal, to generate a frozen scene construction in response to the line and object quality and the uncertainty, to localize a host vehicle location with respect to the frozen scene construction, to regenerate an object data and a lane data in response to the frozen science and the localized host vehicle location, and to generate a vehicle motion path in response to the object data and lane data, and a vehicle controller for controlling the host vehicle in response to the vehicle motion path.

Claims (54)

1 . A system for performing a vehicle maneuver comprising:

a sensor set to generate a data signal indicative of an object location and a lane line location;

a memory having instructions stored thereon; and

a processor coupled to the memory and the sensor set, the processor to execute the instructions to:

determine a lane line quality and an object quality;

detect a loss of sensor data from the sensor set;

estimate a lane line and object quality,

determine an uncertainty in response to historical motion of the objects,

generate a frozen scene construction in response to the lane line and object quality and the uncertainty,

localize a host vehicle location with respect to the frozen scene construction using an environment map stored in the memory,

regenerate an object data and a lane data in response to the frozen scene and the localized host vehicle location, and

generate a vehicle motion path in response to the regenerated object data and lane data; and

a vehicle controller in communication with the processor, the vehicle controller to control the host vehicle in response to the vehicle motion path.

2 . The system for performing the vehicle maneuver of claim 1 wherein the sensor set includes a vehicle mounted camera and wherein the object location is determined in response to an image recognition algorithm performed by an image processor.

3 . The system for performing the vehicle maneuver of claim 1 wherein the vehicle maneuver algorithm is initiated in response to an acceleration detected by an inertial measurement unit exceeding a threshold value.

4 . The system for performing the vehicle maneuver of claim 1 wherein the object data and the lane data are reconstructed in response to a vehicle telemetry data and an object reconstruction model.

5 . The system for performing the vehicle maneuver of claim 1 wherein the object data and the lane data are reconstructed un response to an uncertainty characterization in response to a historical linear object behavior uncertainty.

6 . The system for performing the vehicle maneuver of claim 1 wherein the frozen scene construction is predicted based on measurement model probabilities and covariances and a covariance adaption.

7 . The system for performing the vehicle maneuver of claim 1 wherein the estimate of the line and object quality and the determination of the uncertainty are performed in response to a prediction of an upcoming evasive maneuver.

8 . The system for performing the vehicle maneuver of claim 1 wherein the set includes a LiDAR.

9 . The system for performing the vehicle maneuver of claim 1 wherein the set includes a radar, a LiDAR and a camera.

10 . A method for providing a vehicle maneuver comprising:

generating a data signal by a sensor set indicative of an object location and a lane line location;

storing, on a memory, an environment map indicative of a driving environment coordinated with a host vehicle location;

determining, by a processor, a lane line quality and an object quality;

detecting, by the processor, a loss of sensor data in response to the data signal;

determining an uncertainty in response to historical motion of the objects;

generating, by the processor, a frozen scene construction in response to the lane line quality, the object quality and the uncertainty;

localizing, by the processor, a host vehicle location with respect to the frozen scene construction;

regenerating, by the processor, an object data and a lane data in response to the frozen scene and the localized host vehicle location;

generating, by the processor, a vehicle motion path in response to the object data and lane data; and

controlling, by a vehicle controller, the host vehicle in response to the vehicle motion path.

11 . The method for providing the vehicle maneuver of claim 10 wherein the sensor set includes a vehicle mounted camera and wherein the object location is determined in response to an image recognition algorithm performed by an image processor.

12 . The method for providing the vehicle maneuver of claim 10 further including generating a user alert indicative of a lane hazard in response to the vehicle speed reduction control signal.

13 . The method for providing the vehicle maneuver of claim 10 wherein the object data and the lane data are reconstructed in response to a vehicle telemetry data and an object reconstruction model.

14 . The method for providing the vehicle maneuver of claim 10 wherein the host lane speed reduction is determined in response to a user preference associated with the first hazard.

15 . The method for providing the vehicle maneuver of claim 10 wherein the object data and the lane data are reconstructed un response to an uncertainty characterization in response to a historical linear object behavior uncertainty.

16 . The method for providing the vehicle maneuver of claim 10 wherein the frozen scene construction is predicted based on measurement model probabilities and covariances and a covariance adaption.

17 . The method for providing the vehicle maneuver of claim 10 wherein the vehicle maneuver algorithm is initiated in response to an acceleration detected by an inertial measurement unit exceeding a threshold value.

18 . The method for providing the vehicle maneuver of claim 10 wherein the set includes at least one of a radar, a LiDAR and a camera.

19 . A vehicle control system for performing an evasive steering maneuver comprising:

a camera to capturing an image of a field of view including an object within the field of view;

a distance sensor to detect a distance to the object;

an inertial measurement unit (IMU) to detect an acceleration of a host vehicle;

a memory having instructions stored thereon;

a processor coupled to the camera, the distance sensor, the IMU, and the memory, the processor to execute the instructions to:

detect a loss of sensor data signal from at least one of the camera and the distance sensor;

determine a lane line quality and an object quality in response to the acceleration of the host vehicle exceeding a threshold acceleration;

generate a frozen scene construction in response to the lane line quality, the object quality, and an uncertainty based on historical motion of the object;

localize a host vehicle location with respect to the frozen scene construction;

regenerate an object data and a lane data in response to the frozen scene and the localized host vehicle location; and

generate a vehicle motion path for an evasive steering maneuver in response to the regenerated object data and lane data; and

a vehicle controller to control the host vehicle along the vehicle motion path in response in response to the vehicle motion path.

20 . The vehicle control system for performing the evasive steering maneuver algorithm of claim 19 , wherein the object is a proximate vehicle.