Systems and methods to manage tracking of objects through occluded regions

Patent metadata

Field	Value
Publication number	US-12567331-B2
Application number	US-202318179193-A
Country	US
Kind code	B2
Filing date	Mar 6, 2023
Priority date	Mar 6, 2023
Publication date	Mar 3, 2026
Grant date	Mar 3, 2026

Abstract

Exemplary embodiments include systems and methods to maintain tracking of an object that passes into an occluded area, including defining a map of a driving area; defining one or more occlusion areas within the map; detecting an object using sensor data from one or more sensors; creating an object track for the object detected using sensor data; determining that the object track entered one of the one or more occlusion areas; and maintaining the object track while the object track remains in the one or more occlusion areas.

First claim

What is claimed is:

1 . A method, comprising:
defining, using a computing device comprising a processor and a memory, a map of a driving area; defining, using the computing device, an occlusion map within the map of the driving area, the occlusion map comprising one or more occlusion areas; recording sensor data of an environment of a vehicle using one or more sensors; detecting, using the computing device, an object using the sensor data; creating, using the computing device, an object track for the object detected using sensor data; determining, using the computing device, whether the object track has entered any of the one or more occlusion areas; maintaining, using the computing device and the one or more sensors, the object track while the object track remains in any of the one or more occlusion areas; dropping the object track when a probability that the object is no longer in the one or more occlusion areas has surpassed a threshold; and driving the vehicle based on the object track.

2 . The method of claim 1 , further comprising maintaining the object track while the object remains undetected by the one or more sensors.

3 . The method of claim 1 , further comprising dropping the object track when the object exits the one or more occlusion areas,
wherein the object is determined to have exited the one or more occlusion areas when the object is detected by the one or more sensors.

4 . The method of claim 1 , further comprising dropping the object track when a probability that the object is no longer in one or more occlusion areas has surpassed a threshold.

5 . The method of claim 1 , further comprising updating a probability location of the object while the object remains undetected by the one or more sensors and within the one or more occlusion areas.

6 . The method of claim 5 , wherein a certainty of the probability location manifests in an area of probability in which the object may be within the one or more occlusion areas along the object track.

7 . The method of claim 6 , wherein the probability location is determined with less certainty the longer the object remains in the one or more occlusion areas.

8 . The method of claim 7 , wherein the less certainty results in a larger area of probability associated with the object along the object track.

9 . A method, comprising:
defining, using a computing device comprising a processor and a memory, a map of a driving area having a driving surface including one or more drive lanes for a vehicle to traverse; recording sensor data of an environment of the vehicle using one or more sensors; detecting an object, separate from the vehicle, using the sensor data; defining an occlusion map within the map of the driving area, the occlusion map comprising one or more occlusion areas, wherein an occlusion area is an area that is obstructed by another object, and/or is in an area not detectable by the one or more sensors, and/or is within a set proximity to the vehicle; creating an object track for the object detected using sensor data, wherein the object track is determined from data received from the one or more sensors before the object enters the one or more occlusion areas and is configured to provide a predicted location as the object remains within the one or more occlusion areas; determining whether the object track has entered any of the one or more occlusion areas; determining a predicted location of the object within the one or more occlusion areas, wherein the predicted location comprises an area based on the object track; updating the predicted location of the object, increasing an area of the predicted location as time increases as the object remains within the one or more occlusion areas; dropping the object track when a probability that the object is no longer in the one or more occlusion areas has surpassed a threshold; and driving the vehicle based on the object track.

10 . The method of claim 9 , further comprising dropping the object track when the object exits the one or more occlusion areas,
wherein the object is determined to have exited the one or more occlusion areas when the object is detected by the one or more sensors.

11 . A system, comprising:
one or more sensors configured to generate sensor data of an environment of a vehicle; and a computing device, comprising a processor and a memory, wherein the memory is configured to store instructions that, when executed by the processor, are configured to cause the processor to:
define a map of a driving area of the vehicle;
detect an object from the sensor data;
define an occlusion map within the map of the driving area, the occlusion map comprising one or more occlusion areas;
create an object track for the object detected and configured to maintain the object track when the object is determined to enter the one or more occlusion areas;
drop the object track when a probability that the object is no longer in the one or more occlusion areas has surpassed a threshold; and
drive the vehicle based on the object track.

12 . The system of claim 11 , wherein the instructions, when executed by the processor, are further configured to cause the processor to drop the object track when it is determined that the one or more occlusion areas is cleared.

13 . The system of claim 11 , wherein:
the instructions, when executed by the processor, are further configured to cause the processor to drop the object track when it is determined that the object has exited the one or more occlusion areas, and the object is determined to have exited the one or more occlusion areas when the object is detected by the one or more sensors.

14 . The system of claim 11 , wherein the instructions, when executed by the processor, are further configured to cause the processor to update a probability location of the object while the object remains undetected by the one or more sensors and within the one or more occlusion areas.

15 . The system of claim 14 , wherein the instructions, when executed by the processor, are further configured to cause the processor to:
define a certainty of the probability location; and manifest the certainty as an area of probability in which the object may be within the one or more occlusion areas along the object track.

16 . The system of claim 15 , wherein the instructions, when executed by the processor, are further configured to cause the processor to determine the probability location with less certainty the longer the object remains in the one or more occlusion areas.

17 . The system of claim 16 , wherein the instructions, when executed by the processor, are further configured to cause the processor to define a reduction in the certainty as a larger area of probability associated with the object along the object track.

Assignees

• Kodiak Robotics Inc

Inventors

• Otis Collin
• Du Toit Philip C

Classifications

• G06V20/58

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• B60W60/0027

  using trajectory prediction for other traffic participants · CPC title

• B60W2554/4048

  Field of view, e.g. obstructed view or direction of gaze · CPC title

• B60W30/0956

  the prediction being responsive to traffic or environmental parameters · CPC title

• B60W2554/4041

  Position · CPC title