Collision avoidance system with trajectory validation

Patent metadata

Field	Value
Publication number	US-11104332-B2
Application number	US-201816218182-A
Country	US
Kind code	B2
Filing date	Dec 12, 2018
Priority date	Dec 12, 2018
Publication date	Aug 31, 2021
Grant date	Aug 31, 2021

Abstract

A vehicle may include a primary system and a secondary system to validate operation of the primary system and to control the vehicle to avoid collisions. For example, the secondary system may receive multiple trajectories from the primary system, such as a primary trajectory and a secondary, contingent, trajectory associated with a deceleration or other maneuver. The secondary system may determine if a trajectory is associated with a potential collision, if the trajectory is consistent with a current or previous pose, if the trajectory is compatible with a capability of the vehicle, etc. The secondary system may select the primary trajectory if valid, the secondary trajectory if the primary trajectory is invalid, or another trajectory generated by the secondary system if the primary trajectory and the secondary trajectory are invalid. If no valid trajectory is determined, the vehicle may decelerate at a maximum rate.

First claim

What is claimed is:

1. A vehicle system comprising:
a first system comprising one or more first processors and one or more first memories comprising instructions that, when executed by the one or more first processors, cause the one or more first processors to:
receive sensor data from one or more sensors; and
generate, based at least in part on the sensor data, a first trajectory for an autonomous vehicle and a second trajectory for the autonomous vehicle; and

a second system comprising one or more second processors and one or more second memories comprising instructions that, when executed by the one or more second processors, cause the one or more second processors to:
receive the first trajectory and the second trajectory from the first system;
receive at least a portion of the sensor data;
determine, based at least in part on the at least the portion of the sensor data, an object in an environment;
determine an object trajectory for the object;
perform first collision detection with the first trajectory and the object trajectory to determine a first state associated with the first trajectory, wherein the first collision detection comprises determining whether or not the vehicle would collide with the object based at least in part on the first trajectory and the object trajectory;
perform second collision detection with the second trajectory and the object trajectory to determine a second state associated with the second trajectory, wherein the second collision detection comprises determining whether or not the vehicle would collide with the object based at least in part on the second trajectory and the object trajectory;
determine, based at least in part on the first state and the second state, a third trajectory for the autonomous vehicle, the third trajectory comprising at least one of the first trajectory, the second trajectory, or a fourth trajectory generated by the second system; and
control the autonomous vehicle based at least in part on the third trajectory.

2. The vehicle system of claim 1 , wherein:
the first state indicates that the first trajectory is associated with an estimated collision; and
the one or more second memories of the second system further comprise instructions that, when executed by the one or more second processors, cause the one or more second processors to:
send, to the first system and based at least in part on the first state, a message indicating one or more of a time to collision, extents of the object, a velocity of the object, a location of the object, or a point of collision.

3. The vehicle system of claim 1 , wherein:
at least one of the first state indicates that the first trajectory is associated with a first estimated collision or the second state indicates that the second trajectory is associated with a second estimated collision;
the third trajectory comprises at least one of the second trajectory or the fourth trajectory; and
the one or more second memories of the second system further comprise instructions that, when executed by the one or more second processors, cause the one or more second processors to:
maintain control of the autonomous vehicle based at least in part on the third trajectory;
receive a signal to release control of the autonomous vehicle from the third trajectory;
receive a fifth trajectory from the first system; and
control the autonomous vehicle based at least in part on the fifth trajectory and the signal.

4. A method comprising:
receiving, from a first component, a first trajectory for a vehicle and a second trajectory for the vehicle;
receiving, by a second component, at least a portion of sensor data;
determining, by the second component and based at least in part on the at least the portion of the sensor data, an object in an environment;
identifying, by the second component and based at least in part on the at least the portion of the sensor data, an object trajectory of the object;
performing, by the second component, one or more first validation operations with the first trajectory to determine a first state associated with the first trajectory, wherein performing the one or more first validation operations comprises at least determining whether the vehicle moving along the first trajectory will collide with the object moving along the object trajectory;
performing, by the second component, one or more second validation operations with the second trajectory to determine a second state associated with the second trajectory, wherein performing the one or more second validation operations comprises at least determining whether the vehicle moving along the second trajectory will collide with the object moving along the object trajectory;
determining, by the second component and based at least in part on the first state and the second state, a third trajectory for the vehicle, the third trajectory comprising at least one of the first trajectory, the second trajectory, or a fourth trajectory generated by the second component; and
controlling the vehicle based at least in part on the third trajectory.

5. The method of claim 4 , wherein performing the one or more first validation operations further comprises at least one of:
determining whether the first trajectory was generated less than a threshold amount of time from a current time;
determining whether the first trajectory is consistent with a current or previous pose of the vehicle; or
determining whether the first trajectory is compatible with a capability of the vehicle.

6. The method of claim 4 , wherein performing the one or more second validation operations further comprises at least one of:
determining whether the second trajectory was generated less than a threshold amount of time from a current time;
determining whether the second trajectory is consistent with a current or previous pose of the vehicle; or
determining whether the second trajectory is compatible with a capability of the vehicle.

7. The method of claim 4 , wherein the first state indicates that the first trajectory is invalid and the second state indicates that the second trajectory is invalid, the method further comprises:
generating, by the second component and based at least in part on the second trajectory, the fourth trajectory, the fourth trajectory comprising a modification of the second trajectory; and
performing, by the second component, one or more third validation operations with the fourth trajectory and the object trajectory to determine a third state associated with the fourth trajectory, the third state indicating that the fourth trajectory is valid,
wherein determining the third trajectory for the vehicle comprises determining, as the third trajectory and based at least in part on the third state, the fourth trajectory.

8. The method of claim 4 , wherein the first state indicates that the first trajectory is invalid and the second state indicates that the second trajectory is invalid, the method further comprises:
generating, by the second component and based at least in part on the second trajectory, a fifth trajectory, the fifth trajectory comprising a modification of the second trajectory;
performing, by the second component, one or more third validation operations with the fifth trajectory and the object trajectory to determine a third state associated with the fifth trajectory, the third state indicating that the fifth trajectory is invalid; and
generating, by the second component, the fourth trajectory, the fourth trajectory being associated with a maximum deceleration rate,
wherein determining the third trajectory comprises determining, as the third trajectory and based at least in part on the third state, the fourth trajectory.

9. The method of claim 8 ,

Assignees

• Zoox Inc

Inventors

• King Andrew Lewis
• Packer Jefferson Bradfield
• Somers Robert Edward
• Wimmershoff Marc

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

• B60W60/00272

  relying on extrapolation of current movement · CPC title

• B60W2554/00

  Input parameters relating to objects · CPC title

• B60W30/0956

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

• B60R21/0134

  responsive to imminent contact with an obstacle {, e.g. using radar systems} · CPC title