Method and data processing device for analyzing a sensor assembly configuration and at least semi-autonomous robots

Patent metadata

Field	Value
Publication number	US-12162162-B2
Application number	US-202016823706-A
Country	US
Kind code	B2
Filing date	Mar 19, 2020
Priority date	Mar 20, 2019
Publication date	Dec 10, 2024
Grant date	Dec 10, 2024

Abstract

A method for analyzing a sensor assembly configuration of an at least semi-autonomous robot includes determining a plurality of spatial segments that spatially subdivide an environment of the robot. The method further includes determining an available individual component performance of a respective individual component of the sensor assembly configuration in relation to the spatial segments. The method further includes determining a sensor assembly requirement that must be satisfied by the sensor assembly configuration in relation to the spatial segments. A linear optimization function with parameters that include the spatial segments, the individual component performances, and the sensor assembly requirements is generated and then solved according to the method. The solution of the linear optimization function indicates if the environment of the robot is configured to be captured by the sensor assembly configuration in accordance with the sensor assembly requirement. A data processing device in one embodiment executes the method.

First claim

What is claimed is:

1. A method for analyzing a sensor assembly configuration of an at least semi-autonomous robot, comprising:
determining a plurality of spatial segments that subdivide an environment of the robot spatially, the plurality of spatial segments varying from one another in both distance and direction from the robot;
determining individual component performances of respective individual components of a plurality of individual components of the sensor assembly configuration, the individual component performances for each respective individual component including a respective value for every respective spatial segment in the plurality of spatial segments that indicates how well the respective individual component performs in relation to the respective spatial segment;
determining at least one sensor assembly requirement that must be satisfied by the sensor assembly configuration, the at least one sensor assembly requirement including values indicating how well the sensor assembly must perform in relation to respective spatial segments in the plurality of spatial segments;
generating a linear optimization function, the parameters of which include at least the plurality of spatial segments, the individual component performances, and the at least one sensor assembly requirement;
determining which individual components of the plurality of individual components are at a minimum necessary for satisfying the at least one sensor assembly requirement by solving the linear optimization function, wherein the solution of the linear optimization function indicates at least whether the environment of the robot is configured to be captured by the sensor assembly configuration in accordance with the at least one sensor assembly requirement; and
adjusting, in an automated manner, a configuration of the sensor assembly in a specification of the sensor assembly based on the solution of the linear optimization function.

2. The method according to claim 1 , wherein determining the individual component performances includes specifying one or more characteristics of the individual component, the one or more characteristics selected from:
at least one environment perception capability of the individual component,
at least one functional weakness of the individual component,
a satisfiability of safety requirements by the individual component, and
at least one dependency on one or more of (i) other components within the sensor assembly configuration and (ii) other components of an architecture of the robot.

3. The method according to claim 1 , wherein determining the at least one sensor assembly requirement includes specifying one or more characteristics of the individual component, the one or more characteristics selected from:
at least one environment perception function to be performed,
at least one functional weakness to be avoided,
at least one safety requirement to be satisfied,
at least one dependency on one or more of (i) other components within the sensor assembly configuration to be avoided and (ii) other components of an architecture of the robot to be avoided, and
at least one cost factor associated with the respective individual component.

4. The method according to claim 1 , wherein one or more of the individual component performances and the at least one sensor assembly requirement is specified by a number of integers.

5. The method according to claim 1 , wherein the linear optimization function is generated as an integer linear program.

6. The method according to claim 1 , wherein the generated linear optimization function yields:
Minimize c T x,
with the following conditions:
Ax≥b,
0≤ x≤ 1, and

x∈Z,

wherein x is a variable vector for a component of the sensor assembly configuration, c is a parameter vector for costs of the respective individual component, A is a matrix with a modelling of the individual component performances, and b is a vector with a modelling of the at least one sensor assembly requirements.

7. The method according to claim 1 , wherein the plurality of spatial segments around the robot are determined so that their sum completely covers a space around the robot up to a predetermined distance relative to the robot.

8. The method according to claim 1 , wherein one or more of (i) the individual component performances are determined for every single one of the plurality of spatial segments and (ii) the at least one sensor assembly requirement being satisfied is determined for every single one of the plurality of spatial segments.

9. The method according to claim 1 , wherein the sensor assembly configuration is checked using the solution of the linear solution function.

10. The method according to claim 1 , wherein a computer program that includes commands causes a computer to execute the method when the computer program is executed by the computer.

11. The method according to claim 10 , wherein the computer program is stored on a machine-readable storage medium.

12. A data processing device configured to execute a method for analyzing a sensor assembly configuration of an at least semi-autonomous robot, the method including:
determining a plurality of spatial segments that subdivide an environment of the robot spatially, the plurality of spatial segments varying from one another in both distance and direction from the robot;
determining individual component performances of respective individual components of a plurality of individual components of the sensor assembly configuration, the individual component performances for each respective individual component including a respective value for every respective spatial segment in the plurality of spatial segments that indicates how well the respective individual component performs in relation to the respective spatial segment;
determining at least one sensor assembly requirement that must be satisfied by the sensor assembly configuration, the at least one sensor assembly requirement including values indicating how well the sensor assembly must perform in relation to respective spatial segments in the plurality of spatial segments;
generating a linear optimization function, the parameters of which include at least the plurality of spatial segments, the individual component performances, and the at least one sensor assembly requirement;
determining which individual components of the plurality of individual components are at a minimum necessary for satisfying the at least one sensor assembly requirement by solving the linear optimization function, wherein the solution of the linear optimization function indicates at least whether the environment of the robot is configured to be captured by the sensor assembly configuration in accordance with the at least one sensor assembly requirement; and
adjusting, in an automated manner, a configuration of the sensor assembly in a specification of the sensor assembly based on the solution of the linear optimization function.

13. An at least semi-autonomous robot, comprising:
a sensor assembly configuration that is configured to be one or more of analyzed and configured by a method, the method including:
determining a plurality of spatial segments that subdivide an environment of the robot spatially, the plurality of spatial segments varying from one another in both distance and direction from the robot;
determining individual component performances of respective individual components of a plurality of individual components of the sensor assembly configuration, the individual component performances for each respective individual component including a respective value for every respective spatial segment

Assignees

• Bosch Gmbh Robert

Inventors

• Schneider Peter

Classifications

• G07C3/00

  Registering or indicating the condition or the working of machines or other apparatus, other than vehicles · CPC title

• B25J9/1697

  Vision controlled systems · CPC title

• G06F17/16

  Matrix or vector computation {, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization (matrix transposition G06F7/78)} · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G01S2013/9327

  Sensor installation details · CPC title