Collision avoidance perception system

Patent metadata

Field	Value
Publication number	US-11500385-B2
Application number	US-201916588529-A
Country	US
Kind code	B2
Filing date	Sep 30, 2019
Priority date	Sep 30, 2019
Publication date	Nov 15, 2022
Grant date	Nov 15, 2022

Abstract

A collision avoidance system may validate, reject, or replace a trajectory generated to control a vehicle. The collision avoidance system may comprise a secondary perception component that may receive sensor data, receive and/or determine a corridor associated with operation of a vehicle, classify a portion of the sensor data associated with the corridor as either ground or an object, determine a position and/or velocity of at least the nearest object, determine a threshold distance associated with the vehicle, and control the vehicle based at least in part on the position and/or velocity of the nearest object and the threshold distance.

First claim

What is claimed is:

1. A method comprising:
receiving a trajectory for controlling operation of an autonomous vehicle;
receiving sensor data from a sensor associated with the autonomous vehicle;
at least one of determining or receiving a corridor indicative of a bounded region in front of the autonomous vehicle in which the autonomous vehicle is constrained to travel, wherein the bounded region is based at least in part on the trajectory and is associated with at least one of a width or length of the autonomous vehicle;
determining, as a first subset of the sensor data, a sensor data segmentation indicating a ground classification and associated with the corridor;
determining a second subset of the sensor data associated with the corridor and an object classification, wherein first subset is different from the second subset and the second subset comprising a portion of the sensor data that represents an inside of the corridor;
determining, based at least in part on the second subset, a position and a velocity associated with at least a portion of an object; and
determining, based at least in part on at least one of the position or the velocity, to:
control the autonomous vehicle to perform the trajectory, or
control the autonomous vehicle to perform a contingent trajectory.

2. The method of claim 1 , wherein:
the velocity is a first velocity; and
the method further comprises:
determining a threshold distance associated with a second velocity associated with the autonomous vehicle, and
at least one of determining a first distance from the autonomous vehicle to the position of the object or a second distance from the autonomous vehicle to a point of the first subset that is furthest from the autonomous vehicle.

3. The method of claim 2 , wherein controlling the autonomous vehicle to perform the trajectory is based at least in part on:
determining that the first distance meets or exceeds the threshold distance, and
determining that the second distance meets or exceeds the threshold distance.

4. The method of claim 2 , wherein controlling the autonomous vehicle to perform the contingent trajectory is based at least in part on:
determining that the first distance is less than the threshold distance, or
determining that the second distance is less than the threshold distance.

5. The method of claim 1 , wherein classifying the first subset of the sensor data as the ground classification comprises at least one of:
fitting a line to at least part of the sensor data;
determining, as the first subset, first points of the sensor data that are within a threshold distance of the line; or
determining, as the first subset, first points that have a variance in spacing less than or equal to a variance threshold.

6. The method of claim 1 , wherein classifying the second subset of the sensor data as the object classification comprises at least one of:
fitting a line to at least part of the sensor data;
determining, as the second subset, second points of the sensor data that are above the line; or
determining that an angle between two points of the second subset is outside a range of angles or a spacing between the two points is outside a range of distances.

7. The method of claim 1 , wherein:
determining the corridor indicative of the bounded region in front of the autonomous vehicle in which the autonomous vehicle is constrained to travel is performed by a first component of the autonomous vehicle; and
determining the position and the velocity associated with at least the portion of the object is performed by a second component of the autonomous vehicle.

8. A system comprising:
one or more sensors;
one or more processors; and
a memory storing processor-executable instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
receiving sensor data from a sensor associated with a vehicle;
at least one of receiving or determining a corridor associated with operation of the vehicle, wherein the corridor identifies a region associated with a width of the vehicle;
determining a first subset of the sensor data associated with the corridor and a ground classification;
determining a second subset of the sensor data associated with the corridor and an object classification, the second subset comprising a portion of the sensor data that represents an inside of the corridor;
determining, based at least in part on a first velocity of the vehicle, a threshold distance; and
controlling the vehicle based at least in part on the threshold distance and the second subset.

9. The system of claim 8 , wherein controlling the vehicle is further based at least in part on determining, based at least in part on the second subset, a position and a second velocity associated with at least a portion of an object.

10. The system of claim 9 , wherein controlling the vehicle further comprises:
determining at least one of a first distance from the vehicle to the position or, based at least in part on at least one of the first velocity or the second velocity, a second distance from the vehicle to a predicted position of the object; and
causing the vehicle to execute a contingent trajectory based at least in part on determining that at least one of the first distance or the second distance is less than the threshold distance.

11. The system of claim 8 , wherein controlling the vehicle further comprises:
determining a distance from the vehicle to a furthest point of the first subset; and
causing the vehicle to follow a contingent trajectory based at least in part on determining that the distance is less than the threshold distance.

12. The system of claim 8 , wherein controlling the vehicle further comprises:
determining a first distance from the vehicle to a furthest point of the first subset or a second distance from the vehicle to a nearest point of the second subset; and
causing the vehicle to follow a trajectory based at least in part on determining that the first distance and the second distance meet or exceed the threshold distance.

13. The system of claim 8 , wherein classifying the first subset of the sensor data as the ground classification comprises at least one of:
fitting a line to at least part of the sensor data;
determining, as the first subset, first points of the sensor data that are within a second threshold distance of the line; or
determining, as the first subset, first points that have a variance in spacing or variance in angular displacement less than or equal to a variance threshold.

14. The system of claim 8 , wherein classifying the second subset of the sensor data as the object classification comprises at least one of:
fitting a line to at least part of the sensor data;
determining, as the second subset, second points of the sensor data that are above the line; or
determining that an angle between two points of the second subset is outside a range of angles or a spacing between the two points is outside a range of distances.

15. The system of claim 8 , wherein determining the second subset of the sensor data associated with the corridor and the object classification is based at least in part on excluding an additional portion of the sensor data that is outside of the corridor.

16. A non-transitory computer-readable medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving sensor data from a sensor associated with a vehicle;
at least one of determining or receiving a corridor associat

Assignees

• Zoox Inc

Inventors

• Wang Chuang
• Cohen Joshua Kriser
• Philbin James William Vaisey
• Boydston Jacob Daniel
• Xie Yuesong
• Ren Hang
• Zhang Yuan

Classifications

• B60W30/0953 Primary

  the prediction being responsive to vehicle dynamic parameters · CPC title

• B60W2554/4041

  Position · CPC title

• B60W2552/15

  Road slope, i.e. the inclination of a road segment in the longitudinal direction · CPC title

• B60W2554/4042

  Longitudinal speed · CPC title

• B60W2554/40

  Dynamic objects, e.g. animals, windblown objects · CPC title