System and method for determining pose data for a vehicle

Patent metadata

Field	Value
Publication number	US-9915947-B1
Application number	US-201615054441-A
Country	US
Kind code	B1
Filing date	Feb 26, 2016
Priority date	Feb 26, 2016
Publication date	Mar 13, 2018
Grant date	Mar 13, 2018

Abstract

Example systems and methods are disclosed for determining vehicle pose data for an autonomous vehicle. The vehicle computer system may receive pose data from multiple pose measurement systems of the autonomous vehicle. Each pose measurement system may include one or more corresponding sensors of the autonomous vehicle. The vehicle computer system may determine a pose data quality for the received pose data for each pose measurement system. The vehicle computer system may set the vehicle pose data to the pose data of the pose measurement system with the highest pose data quality. The vehicle computer system may control the autonomous vehicle based on the vehicle pose data.

First claim

What is claimed is:

1. A method comprising:
receiving, at a vehicle computer system for an autonomous vehicle, first pose data for the autonomous vehicle and first pose data quality for the first pose data from a first processor, wherein the first processor determines the first pose data based on first sensor data from a first inertial measurement unit (IMU), a first wheel speed sensor, and a first Global Positioning System (GPS) receiver and determines the first pose data quality based on crosschecking the first sensor data;
receiving, at the vehicle computer system for the autonomous vehicle, second pose data for the autonomous vehicle and second pose data quality for the second pose data from a second processor, wherein the second processor determines the second pose data based on second sensor data from a second IMU, a second wheel speed sensor, and a second GPS receiver and determines the second pose data quality based on crosschecking the second sensor data; and
controlling, by the vehicle computer system, motion of the autonomous vehicle based on the first pose data quality, the second pose data quality, and at least one of the first pose data or the second pose data.

2. The method of claim 1 , wherein the vehicle computer system receives the first pose data from the first processor via a first communication channel and the vehicle computer system receives the second pose data from the second processor via a second communication channel that is independent of the first communication channel.

3. The method of claim 1 , wherein the vehicle computer system receives a first pose data message from the first processor that includes the first pose data, the first pose data quality, and a first pose data message timestamp, wherein the vehicle computer system receives a second pose data message from the second processor that includes the second pose data, the second pose data quality, and a second pose data message timestamp.

4. The method of claim 1 , wherein the first pose data quality and the second pose data quality are selected from the group consisting of good, marginal, and bad.

5. The method of claim 1 , wherein controlling motion of the autonomous vehicle based on the first pose data quality, the second pose data quality, and at least one of the first pose data or the second pose data comprises:
comparing the first pose data quality and the second pose data quality;
controlling the autonomous vehicle based on the first pose data if the first pose data quality is higher than the second pose data quality; and
controlling the autonomous vehicle based on the second pose data if the second pose data quality is higher than the first pose data quality.

6. The method of claim 1 , wherein controlling motion of the autonomous vehicle based on the first pose data quality, the second pose data quality, and at least one of the first pose data or the second pose data comprises:
determining whether either of the first pose data quality or the second pose data quality is at a predetermined high level;
controlling the autonomous vehicle normally if at least one of the first pose data quality or the second pose data quality is at the predetermined high level; and
controlling the autonomous vehicle to perform an emergency maneuver if neither the first pose data quality nor the second pose data quality is at the predetermined high level.

7. The method of claim 6 , wherein controlling the autonomous vehicle to perform the emergency maneuver comprises controlling the autonomous vehicle to pull over and park.

8. The method of claim 6 , wherein controlling the autonomous vehicle to perform the emergency maneuver comprises controlling the autonomous vehicle to stop immediately.

9. A non-transitory computer-readable medium storing instructions that are executable by one or more computing devices, wherein executing the instructions causes the one or more computing devices to perform functions comprising:
receiving, at a vehicle computer system for an autonomous vehicle, first pose data for the autonomous vehicle and first pose quality data for the first pose data from a first processor, wherein the first processor determines the first pose data based on first sensor data from a first inertial measurement unit (IMU), a first wheel speed sensor, and a first Global Positioning System (GPS) receiver and determines the first pose data quality based on crosschecking the first sensor data;
receiving, at the vehicle computer system for the autonomous vehicle, second pose data for the autonomous vehicle and second pose data quality for the second pose data from a second processor, wherein the second processor determines the second pose data based on second sensor data from a second IMU, a second wheel speed sensor, and a second GPS receiver and determines the second pose data quality based on crosschecking the second sensor data; and
controlling, by the vehicle computer system, motion of the autonomous vehicle based on the first pose data quality, the second pose data quality, and at least one of the first pose data or the second pose data.

10. The non-transitory computer-readable medium of claim 9 , wherein the first pose data quality and the second pose data quality are selected from the group consisting of good, marginal, and bad.

11. The non-transitory computer readable medium of claim 9 , wherein controlling motion of the autonomous vehicle based on the first pose data quality, the second pose data quality, and at least one of the first pose data or the second pose data comprises:
comparing the first pose data quality and the second pose data quality;
controlling the autonomous vehicle based on the first pose data if the first pose data quality is higher than the second pose data quality; and
controlling the autonomous vehicle based on the second pose data if the second pose data quality is higher than the first pose data quality.

12. The non-transitory computer readable medium of claim 9 , wherein controlling motion of the autonomous vehicle based on the first pose data quality, the second pose data quality, and at least one of the first pose data or the second pose data comprises:
determining whether either of the first pose data quality or the second pose data quality is at a predetermined high level;
controlling the autonomous vehicle normally if at least one of the first pose data quality or the second pose data quality is at the predetermined high level; and
controlling the autonomous vehicle to perform an emergency maneuver if neither the first pose data quality nor the second pose data quality is at the predetermined high level.

13. The non-transitory computer readable medium of claim 12 , wherein controlling the autonomous vehicle to perform the emergency maneuver comprises controlling the autonomous vehicle to pull over and park.

14. The non-transitory computer readable medium of claim 12 , wherein controlling the autonomous vehicle to perform the emergency maneuver comprises controlling the autonomous vehicle to stop immediately.

15. A system, comprising:
a first pose measurement system for an autonomous vehicle, comprising:
a first inertial measurement unit (IMU);
a first wheel speed sensor;
a first Global Positioning System (GPS) receiver; and
a first processor, wherein the first processor is configured to determine first pose data for the autonomous vehicle based on first sensor data from the first IMU, the first wheel speed sensor, and the first GPS receiver and configured to determine first pose data quality for the first pose data based on crosschecking the first sensor data;

a second pose measurement

Assignees

• Waymo Llc

Inventors

• Laforge Seth Michael
• Robinson Craig Lewin
• Tisdale John
• Smith Russell

Classifications

• B60W50/023

  Avoiding failures by using redundant parts · CPC title

• G05D1/0268

  using internal positioning means · CPC title

• G05D1/0278

  using satellite positioning signals, e.g. GPS · CPC title

• G05D2201/02

  Physics · mapped topic

• G05D1/0088 Primary

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title