Software application for sensor analysis

Patent metadata

Field	Value
Publication number	US-11529973-B1
Application number	US-202017093274-A
Country	US
Kind code	B1
Filing date	Nov 9, 2020
Priority date	Nov 9, 2020
Publication date	Dec 20, 2022
Grant date	Dec 20, 2022

Abstract

A method includes determining a target specification map that is associated with a task and that indicates, for each respective region of a plurality of regions around a vehicle equipped with a sensor, a target value of a parameter of the sensor. The method also includes determining a capability specification map that indicates, for each respective region, an attained value of the parameter that the sensor is configured to provide. The method additionally includes comparing the capability specification map to the target specification map to determine, for each respective region, a disparity between the target value and the attained value. The method further includes, based on the comparing, identifying one or more of: a first subset of the plurality of regions where the target value exceeds the attained value or a second subset of the plurality of regions where the attained value meets or exceeds the target value.

First claim

What is claimed is:

1. A computer-implemented method comprising:
determining a target specification map associated with a corresponding task, wherein the target specification map indicates, for each respective region of a plurality of regions around a vehicle equipped with a sensor, a target value of a parameter of the sensor;
determining a capability specification map that indicates, for each respective region of the plurality of regions, an attained value of the parameter that the sensor is configured to provide;
comparing the capability specification map to the target specification map to determine, for each respective region of the plurality of regions, a disparity between the target value and the attained value; and
based on comparing the capability specification map to the target specification map, identifying one or more of: (i) a first subset of the plurality of regions where the target value exceeds the attained value or (ii) a second subset of the plurality of regions where the attained value meets or exceeds the target value.

2. The computer-implemented method of claim 1 , wherein determining the target specification map associated with the corresponding task comprises:
obtaining a plurality of sensor data representing instances of an object to be detected in connection with performing the corresponding task;
determining, based on the plurality of sensor data and for each respective region of the plurality of regions, one or more attribute values associated with one or more of the instances of the object being represented in the respective region by the plurality of sensor data; and
determining, for each respective region of the plurality of regions, the target value of the parameter of the sensor based on the one or more attribute values.

3. The computer-implemented method of claim 2 , wherein the plurality of sensor data is captured by one or more sensors on one or more vehicles and represents the instances of the object from one or more points of view associated with the one or more vehicles.

4. The computer-implemented method of claim 1 , wherein determining the target specification map associated with the corresponding task comprises:
determining, for an object to be detected in connection with performing the corresponding task, a plurality of candidate locations of instances of the object relative to the vehicle;
determining, based on the plurality of candidate locations of the instances of the object relative to the vehicle and for each respective region of the plurality of regions, one or more attribute values associated with one or more of the instances of the object being represented in the respective region; and
determining, for each respective region of the plurality of regions, the target value of the parameter of the sensor based on the one or more attribute values.

5. The computer-implemented method of claim 4 , wherein determining the plurality of candidate locations of the instances of the object relative to the vehicle comprises:
determining a plurality of candidate locations of the instances of the object within an environment;
determining a plurality of candidate road geometries within the environment between the vehicle and the instances of the object; and
determining the plurality of candidate locations of the instances of the object relative to the vehicle based on the plurality of candidate location of the instances of the object within the environment and the plurality of candidate road geometries within the environment.

6. The computer-implemented method of claim 1 , wherein determining the target specification map associated with the corresponding task comprises:
determining a maneuver to be performed by the vehicle as part of the corresponding task in response to detection of an object;
determining a minimum distance between the vehicle and the object that allows the vehicle to perform the maneuver; and
determining, for each respective region of the plurality of regions around the vehicle, the target value of the parameter of the sensor based on the minimum distance such that the object is detectable before the vehicle reaches the minimum distance between the vehicle and the object.

7. The computer-implemented method of claim 1 , wherein the vehicle is equipped with a plurality of sensors, and wherein determining the capability specification map comprises:
determining, for each respective region of the plurality of regions around the vehicle, the attained value of the parameter that the plurality of sensors is configured to provide based on a respective attained value of the parameter that each respective sensor of the plurality of sensors is configured to provide.

8. The computer-implemented method of claim 1 , wherein determining the capability specification map comprises:
determining, for each respective region of the plurality of regions around the vehicle, the attained value of the parameter that the sensor is configured to provide based on a position of the sensor on the vehicle.

9. The computer-implemented method of claim 1 , wherein determining the capability specification map comprises:
determining an illumination map that represent, for each respective region of the plurality of regions around the vehicle, a corresponding extent of illumination that one or more light sources on the vehicle are configured to provide;
determining, for each respective region of the plurality of regions around the vehicle, a corresponding light sensitivity value of the sensor; and
determining, for each respective region of the plurality of regions around the vehicle and based on (i) the corresponding light sensitivity value and (ii) the corresponding extent of illumination, a minimum reflectance of an object that the sensor is configured to detect.

10. The computer-implemented method of claim 1 , wherein the plurality of regions around the vehicle are represented in a reference frame of the vehicle.

11. The computer-implemented method of claim 1 , wherein the sensor is a camera, and wherein the parameter of the sensor comprises one or more of (i) an angular resolution of the camera, (ii) a dynamic range of the camera, or (iii) a frame rate of the camera.

12. The computer-implemented method of claim 1 , wherein the sensor is a light detection and ranging (LIDAR) device, and wherein the parameter of the sensor comprises one or more of (i) a minimum range measurable by the LIDAR device, (ii) a maximum range measurable by the LIDAR device expressed as a function of reflectivity, (iii) a beam size of light generated by the LIDAR device, or (iv) a point density expressed as a function of object distance.

13. The computer-implemented method of claim 1 , wherein the sensor is a radio detection and ranging (RADAR) device, and wherein the parameter of the sensor comprises one or more of (i) a minimum range measurable by the RADAR device, (ii) a maximum range measurable by the RADAR device expressed as a function of RADAR cross-section, (iii) a minimum relative speed measurable by the RADAR device, (iv) a maximum relative speed measurable by the RADAR device, (v) an angular accuracy of the RADAR device, or (vi) a minimum angular difference between two targets resolvable by the RADAR device.

14. The computer-implemented method of claim 1 , further comprising:
determining that the sensor is configured to provide sufficient sensor data for execution of the corresponding task based on the second subset of the plurality of regions comprising at least a threshold number of regions; and
based on determining that the sensor is configured to provide sufficient sensor data for execution of the corresponding

Assignees

• Waymo Llc

Inventors

• Dittmer Jeremy
• Evans Ruffin
• Nangia Vaibhav
• Ingram Benjamin
• Chubb Erik
• Winetraub Yonatan

Classifications

• G01S17/58

  Velocity or trajectory determination systems; Sense-of-movement determination systems · CPC title

• G01S13/931

  of land vehicles · CPC title

• G06V20/588

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title

• G01S17/931

  of land vehicles · CPC title

• G01S13/89

  for mapping or imaging · CPC title