Filtering of operating scenarios in the operation of a vehicle

Patent metadata

Field	Value
Publication number	US-12165442-B2
Application number	US-202217688294-A
Country	US
Kind code	B2
Filing date	Mar 7, 2022
Priority date	Mar 10, 2021
Publication date	Dec 10, 2024
Grant date	Dec 10, 2024

Abstract

A computer-implemented method for filtering operating scenarios during the operation of a vehicle. The method includes receiving at least one time series of data, storing time-ordered data points of the at least one time series of data in a first memory, generating a trace diagram for the time-ordered data points stored in the first memory, checking whether the trace diagram generated is new in comparison to one or more existing trace diagrams, and storing the time-ordered data points stored in the first memory, in a second memory if the trace diagram generated is new.

First claim

What is claimed is:

1. A computer-implemented method comprising:
during a drive of a vehicle:
obtaining, by the vehicle, at least one time series of data that is at least partly generated by the vehicle and that corresponds to the drive;
storing, by the vehicle, time-ordered data points of the at least one time series of data in a first memory; and
generating, by a processor of the vehicle, a trace diagram for the time-ordered data points stored in the first memory;

checking whether the trace diagram generated is new in comparison to one or more existing trace diagrams;
in response to a result of the checking being that the trace diagram is new, storing the time-ordered data points, stored in the first memory, in a second memory;
based on the storage of the trace diagram in the second memory, updating an autonomous driving functionality of the vehicle according to the trace diagram in the second memory; and
performing, by the vehicle, an autonomous drive using the updated autonomous driving functionality.

2. The method as recited in claim 1 , wherein the one or more time series of data are acquired at least partly via at least one sensor of the vehicle.

3. The method as recited in claim 1 , wherein the one or more time series of data include at least one of: data of a video data stream, RADAR data, LIDAR data, position data, environmental data, vehicle data, and user data.

4. The method as recited in claim 1 , wherein the time-ordered data points of the one or more time series of data correspond to at least one of an immediately preceding period of time and a number of immediately preceding data points of the at least one time series of data.

5. The method as recited in claim 1 , wherein the time-ordered data points of the one or more time series of data characterize an operating scenario.

6. The method as recited in claim 1 , wherein the trace diagram is a graph, including:
one or more nodes, each node corresponding to a value range of data in a space spanned by value ranges of the time-ordered data points; and
for at least some pairs of the nodes, a respective edge between the respective nodes of the respective pair, wherein each edge has at least one arrow direction, the arrow direction in each case indicating a direction of a transition between value ranges belonging to the nodes of the respective pair.

7. The method as recited in claim 6 , wherein each of one or more of the edges has opposite arrow directions.

8. The method as recited in claim 6 , wherein the generating of the trace diagram for the time-ordered data points stored in the first memory includes:
clustering y-values of the time-ordered data points of the at least one time series of data into at least two clusters in a space whose dimensionality corresponds to a number of the at least one time series of data;
identifying at least one cluster as a node in the trace diagram;
analyzing the transitions between clusters on the basis of the time-ordered data points; and
identifying at least one transition as edge between two nodes in the trace diagram.

9. The method as recited in claim 8 , wherein the clustering is performed using unsupervised learning.

10. The method as recited in claim 8 , further comprising:
evaluating at least one of a frequency and dwell time of a cluster based on the time-ordered data points; and
adding the at least one of the frequency and dwell time of the cluster to the node identified with the cluster in the trace diagram.

11. The method as recited in claim 1 , wherein the first memory is a circular buffer.

12. The method as recited in claim 1 , wherein the time-ordered data points stored in the second memory are uploaded manually or automatically via at least one communication module of the vehicle to a server outside of the vehicle.

13. The method as recited in claim 1 , wherein the method is repeated in a next time step, by which the first memory is updated with another time series of data.

14. A non-transitory computer-readable medium on which is stored instructions that are executable by a computer of a vehicle and that, when executed by the computer, cause the computer to perform the following steps:
during a drive of the vehicle:
obtaining at least one time series of data that is at least partly generated by the vehicle and that corresponds to the drive;
storing time-ordered data points of the at least one time series of data in a first memory; and
generating a trace diagram for the time-ordered data points stored in the first memory;

checking whether the trace diagram generated is new in comparison to one or more existing trace diagrams;
in response to a result of the checking being that the trace diagram is new, storing the time-ordered data points, stored in the first memory, in a second memory; and
performing an autonomous drive using an autonomous driving functionality that is updated according to the trace diagram based on the storage of the trace diagram in the second memory.

15. A computer system, comprising:
a first memory of a vehicle; and
a control unit of the vehicle, wherein the control unit is configured to:
during a drive of the vehicle:
obtain at least one time series of data that is at least partly generated by the vehicle and that corresponds to the drive;
store time-ordered data points of the at least one time series of data in the first memory; and
generate a trace diagram for the time-ordered data points stored in the first memory;

check whether the trace diagram generated is new in comparison to one or more existing trace diagrams;
in response to a result of the checking being that the trace diagram is new, store the time-ordered data points, stored in the first memory, in a second memory; and
perform an autonomous drive using an autonomous driving functionality that is updated according to the trace diagram based on the storage of the trace diagram in the second memory.

Assignees

• Bosch Gmbh Robert

Inventors

• Reiter Antonia
• Raghupatruni Indrasen
• Bescos Del Castillo Maria Belen
• Bartelt Christian
• Drechsel Guido
• Hoffmann Lars
• Metzger Noah

Classifications

• G06F17/40 Primary

  Data acquisition and logging (for input to computer G06F3/00) · CPC title

• G06F11/3684

  for test design, e.g. generating new test cases · CPC title

• G06F11/3476

  Data logging (G06F11/14, G06F11/2205 take precedence) · CPC title

• G06F16/787

  using geographical or spatial information, e.g. location · CPC title

• G06N3/088

  Non-supervised learning, e.g. competitive learning · CPC title