Methods and systems to assess vehicle capabilities

Patent metadata

Field	Value
Publication number	US-11809190-B2
Application number	US-202117246048-A
Country	US
Kind code	B2
Filing date	Apr 30, 2021
Priority date	Apr 30, 2021
Publication date	Nov 7, 2023
Grant date	Nov 7, 2023

Abstract

Performance anomalies in autonomous vehicle can be difficult to identify, and the impact of such anomalies on systems within the autonomous vehicle may be difficult to understand. In examples, systems of the autonomous vehicle are modeled as nodes in a probabilistic graphical network. Probabilities of data generated at each of the nodes is determined. The probabilities are used to determine capabilities associated with higher level functions of the autonomous vehicle.

First claim

What is claimed is:

1. An autonomous vehicle comprising:
a first sensor configured to output first sensor data and associated with a first uncertainty;
a second sensor configured to output second sensor data and associated with a second uncertainty;
a computing subsystem configured to generate subsystem data based at least in part on the first sensor data and the second sensor data;
a vehicle controller;
one or more processors; and
memory storing one or more computer-readable media storing instructions executable by the one or more processors to perform operations comprising:
receiving, at the computing subsystem, the first sensor data, the first uncertainty, the second sensor data, and the second uncertainty;
determining, based at least in part on the first sensor data and the second sensor data, the subsystem data;
determining, based at least in part on a model and using the first uncertainty and the second uncertainty, a third uncertainty associated with the subsystem data;
determining, based at least in part on the third uncertainty, a vehicle capability metric;
receiving a request to control the autonomous vehicle to perform a task, performance of the task being based, at least in part, on the subsystem data;
receiving a range of vehicle capability metrics associated with the autonomous vehicle being able to safely perform the task;
determining, as a comparison, whether the vehicle capability metric is within the range of vehicle capability metrics; and
controlling the autonomous vehicle, via the vehicle controller, to perform the task based at least in part on the comparison.

2. The autonomous vehicle of claim 1 , wherein the determining the third uncertainty is based at least in part on a probabilistic graphical model of the autonomous vehicle, the probabilistic graphical model comprising a first node associated with the first sensor, a second node associated with the second sensor, and a third node associated with the computing subsystem, the first node and the second node being connected to the third node.

3. The autonomous vehicle of claim 2 , wherein the probabilistic graphical model comprises a Bayesian network.

4. The autonomous vehicle of claim 1 , wherein the range of vehicle capability metrics comprises a first range and a second range, the operations further comprising:
generating a first instruction to control the autonomous vehicle according to nominal functionality in response to the comparison indicating that the vehicle capability metric is within the first range; and
generating a second instruction to control the autonomous vehicle according to modified functionality in response to the comparison indicating that the vehicle capability metric is within the second range.

5. The autonomous vehicle of claim 4 , wherein the generating the second instruction to control the autonomous vehicle comprises:
determining one or more modified task parameters associated with performance of the task by the autonomous vehicle; and
generating the second instruction to comport operation of the autonomous vehicle with the modified task parameters.

6. The autonomous vehicle of claim 1 , the operations further comprising:
receiving time information associated with at least one of the first sensor data, the second sensor data or the subsystem data,
wherein the determining the vehicle capability metric is further based at least in part on the time information.

7. The autonomous vehicle of claim 1 , wherein the task comprises at least one of:
planning a trajectory;
following a trajectory;
travelling in a traffic lane;
travelling relative to objects in an environment of the autonomous vehicle;
changing a lane of travel; or
travelling safely in an environment of the autonomous vehicle.

8. A method comprising:
receiving, from a sensor associated with a vehicle, sensor data and a first uncertainty associated with the sensor data;
generating, based at least in part on the sensor data and at a computing subsystem of the vehicle, subsystem data;
generating, based at least in part on the first uncertainty and an error associated with the computing subsystem, a second uncertainty associated with the subsystem data;
determining, based at least in part on the second uncertainty, a vehicle capability metric associated with a task to be performed by the vehicle using the subsystem data; and
controlling the vehicle to perform the task based at least in part on the vehicle capability metric.

9. The method of claim 8 , wherein the determining the second uncertainty is based at least in part on a probabilistic graphical model of the vehicle, the probabilistic graphical model comprising a first node associated with the sensor and a second node associated with the computing subsystem, wherein the first node is a leaf of the second node.

10. The method of claim 9 , wherein the probabilistic graphical model comprises a Bayesian network.

11. The method of claim 8 , further comprising receiving time information associated with at least one of the sensor data or the subsystem data,
wherein the determining the vehicle capability metric is further based at least in part on the time information.

12. The method of claim 8 , further comprising:
comparing the vehicle capability metric to a range of vehicle capability metrics associated with the task; and
generating, based at least in part on the comparison, one or more control commands for performing the task.

13. The method of claim 12 , wherein the one or more control commands comprise a first control command for performing the task according to nominal functionality or a second control command for performing the task according to modified functionality.

14. The method of claim 13 , wherein the one or more control commands comprise the second control command, the generating the second control command comprising:
determining one or more modified task parameters associated with performance of the task; and
generating the second control command to comport performance of the task with the modified task parameters.

15. The method of claim 14 , wherein the modified task parameters comprise at least one of:
a reduced maximum speed of the vehicle;
a reduced maximum acceleration of the vehicle;
an increased physical distance; or
an increased time gap.

16. The method of claim 8 , wherein the generating the subsystem data comprises at least one of:
generating information about a state of the vehicle;
generating information about an object in an environment of the vehicle; or
generating a trajectory for the vehicle.

17. The method of claim 8 , further comprising:
receiving additional information comprising at least one of memory usage associated with the vehicle or network usage associated with vehicle,
wherein the vehicle capability metric is further based at least in part on the additional information.

18. A non-transitory computer-readable medium storing instructions, the instructions being executable by one or more processors to perform acts comprising:
receiving, from a sensor associated with a vehicle, sensor data and an uncertainty associated with the sensor data;
generating, based at least in part on the sensor data and at a computing subsystem of the vehicle, sub system data;
generating, based at least in part on the first uncertainty and an error associated with the computing subsystem, a second uncertainty associated with the subsystem data;
determining, based at least in part on the second uncertainty, a vehicle capability metric associated with a task to be

Assignees

• Zoox Inc

Inventors

• Reschka Andreas Christian
• Gacka Thomas Bernard
• Macgregor Collin

Classifications

• G05D1/0214 Primary

  in accordance with safety or protection criteria, e.g. avoiding hazardous areas (monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13) · CPC title

• B60W50/0205

  Diagnosing or detecting failures; Failure detection models · CPC title

• B60W60/0015

  specially adapted for safety · CPC title

• G01C21/3415

  Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents · CPC title

• G05D1/0055

  with safety arrangements · CPC title