Collision avoidance using an object contour

Patent metadata

Field	Value
Publication number	US-12030522-B2
Application number	US-202017138710-A
Country	US
Kind code	B2
Filing date	Dec 30, 2020
Priority date	Dec 30, 2020
Publication date	Jul 9, 2024
Grant date	Jul 9, 2024

Abstract

Techniques for collision avoidance using an object contour are discussed. A trajectory associated with a vehicle may be received. Sensor data can be received from a sensor associated with the vehicle. A bounding contour may be determined and associated with an object represented in the sensor data. Based on the trajectory, a simulated position of the vehicle can be determined. Additionally, a predicted position of the bounding contour can be determined. Based on the simulated position of the vehicle and the predicted position of the bounding contour, a distance between the vehicle and the object may be determined. An action can be performed based on the distance between the vehicle and the object.

First claim

What is claimed is:

1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions executable by the one or more processors, wherein the instructions, when executed, cause the system to perform operations comprising:
receiving a trajectory associated with an autonomous vehicle traversing an environment;
receiving sensor data from a sensor associated with the autonomous vehicle;
determining, based on the sensor data, a bounding contour associated with an object represented in the sensor data;
determining, based on a location of the autonomous vehicle along the trajectory, a predicted position and orientation of the bounding contour;
determining, based on ray casting from the location of the autonomous vehicle along the trajectory, a distance between the location and the bounding contour predicted at the predicted position and orientation; and
controlling the autonomous vehicle based on the distance,
wherein controlling the autonomous vehicle includes validating the trajectory or invalidating the trajectory based at least in part on a number of bounding contour edges a ray casting ray passes through, and
wherein the bounding contour includes a polygon representing a convex hull having more than four edges associated with a top-down view of the object.

2. The system of claim 1 , the operations further comprising:
connecting at least two points of the sensor data, wherein the polygon is determined based on the connecting of the at least two points.

3. The system of claim 1 , wherein the distance is a first distance, and wherein the operations further comprise determining a second distance based on an axis-aligned bounding box corresponding to the object.

4. The system of claim 1 , the operations further comprising:
comparing the distance to a threshold, wherein the threshold is based on a velocity of the autonomous vehicle and an object type associated with the object.

5. A method comprising:
receiving a trajectory associated with a vehicle;
receiving sensor data from a sensor associated with the vehicle;
determining a bounding contour associated with an object represented in the sensor data;
determining, based on the trajectory, a predicted position of the vehicle;
determining a predicted position of the bounding contour associated with the object;
determining, based on ray casting from the predicted position of the vehicle along the trajectory and the predicted position of the bounding contour, a distance between the vehicle and the object; and
controlling the vehicle based on the distance between the vehicle and the object,
wherein controlling the vehicle includes validating the trajectory or invalidating the trajectory based at least in part on a number of bounding contour edges a ray casting ray passes through, and
wherein the bounding contour includes a polygon representing a convex hull having more than four edges associated with a top-down view of the object.

6. The method of claim 5 , wherein the polygon representing the convex hull associated with the object is determined by connection of at least two points of the sensor data.

7. The method of claim 5 , wherein validating the trajectory is based on the number of bounding contour edges being an even number and invalidating the trajectory is based on the number of bounding contour edges being an odd number.

8. The method of claim 5 , wherein determining the distance between the vehicle and the object is based at least in part on ray casting.

9. The method of claim 5 , further comprising determining a predicted orientation of the bounding contour.

10. The method of claim 9 , wherein the predicted orientation is based at least in part on a predicted trajectory associated with the object.

11. The method of claim 5 , wherein the sensor is a lidar sensor and the sensor data comprises lidar data.

12. The method of claim 5 , further comprising representing the bounding contour as a representation of a plurality of connected points.

13. The method of claim 5 , wherein the distance is a first distance, the method further comprising determining a second distance based on an axis-aligned bounding box.

14. The method of claim 5 , further comprising:
comparing the distance to a threshold, wherein the threshold is based on at least one of a velocity of the vehicle or an object type associated with the object.

15. The method of claim 5 , further comprising:
determining, based at least in part on an orientation of the vehicle, an axis-aligned bounding box associated with the bounding contour.

16. The method of claim 5 , wherein the bounding contour associated with the object includes at least five boundary edges.

17. One or more non-transitory computer-readable media storing instructions that, when executed, cause one or more processors to perform operations comprising:
receiving a trajectory associated with a vehicle;
receiving sensor data from a sensor associated with the vehicle;
determining a bounding contour associated with an object represented in the sensor data;
determining, based on the trajectory, a predicted position of the vehicle;
determining a predicted position of the bounding contour associated with the object;
determining, based on ray casting from the predicted position of the vehicle along the trajectory and the predicted position of the bounding contour, a distance between the vehicle and the object; and
controlling the vehicle based on the distance between the vehicle and the object,
wherein controlling the vehicle includes validating the trajectory or invalidating the trajectory based at least in part on a number of bounding contour edges a ray casting ray passes through, and
wherein the bounding contour includes a polygon representing a convex hull having more than four edges associated with a top-down view of the object.

18. The one or more non-transitory computer-readable media of claim 17 , wherein the polygon representing the convex hull associated with the object is determined by connection of at least two points of the sensor data.

19. The one or more non-transitory computer-readable media of claim 17 , wherein the operations further comprise:
determining an axis-aligned bounding box associated with the bounding contour; and
determining a second distance between the vehicle and the object based on the axis-aligned bounding box.

Assignees

• Zoox Inc

Inventors

• Chen Yuanyuan
• Das Subhasis
• Kularatne Dhanushka Nirmevan
• Mcclelland Mark Jonathon
• O′Neal Troy Donovan
• Wang Zeng

Classifications

• B60W2420/408

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

• 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

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06T15/06

  Ray-tracing · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title