Method for processing sensor data in a control device of a vehicle

Patent metadata

Field	Value
Publication number	US-12583470-B2
Application number	US-202418441257-A
Country	US
Kind code	B2
Filing date	Feb 14, 2024
Priority date	Feb 21, 2023
Publication date	Mar 24, 2026
Grant date	Mar 24, 2026

Abstract

A method for processing sensor data in a control device of a vehicle. The method includes: evaluating sensor data generated by different sensors of the vehicle for detecting its environment, via different evaluation functions which convert at least part of the sensor data as input data into output data, wherein the output data are assigned a priority using an assignment rule based on known insufficiencies of the sensors and/or the evaluation functions and the output data are used according to their priority in order to update an environment model that stores information about objects in the environment of the vehicle; recognizing an insufficiency that differs from the known insufficiencies using at least a part of the sensor data and/or at least a part of the output data; updating the assignment rule based on the recognized insufficiency.

First claim

The invention claimed is:

1 . A method for processing sensor data in a control device of a vehicle, wherein the vehicle includes different sensors configured to detect an environment of the vehicle and generate the sensor data, wherein the method comprises the following steps:
evaluating, by the control device, the sensor data via different evaluation functions, each of the different evaluation functions being configured to convert at least part of the sensor data as input data into output data, wherein the output data of each of the different evaluation functions are assigned a respective priority using an assignment rule based on known insufficiencies of the sensors and/or the evaluation functions and the output data are used according to their priority to update an environment model that stores information about objects in the environment of the vehicle; recognizing, by the control device, an insufficiency that differs from the known insufficiencies using at least a part of the sensor data and/or at least a part of the output data; updating, by the control device, the assignment rule based on the recognized insufficiency, so that the output data of at least one of the evaluation functions are assigned a different priority in the future than the priority currently assigned to the output data; and controlling, by the control device, the vehicle using the updated assignment rule, wherein a data structure mapping at least part of the environment of the vehicle and deviating from the environment model is stored in the control device, and wherein at least one of the evaluation functions is configured to convert the input data into the output data using the data structure.

2 . The method according to claim 1 , wherein the recognition of the insufficiency includes:
a mutual comparison of the output data of different ones of the evaluation functions; and/or a mutual comparison of the input data of different ones of the evaluation functions; and/or a comparison of the output data respective input data.

3 . The method according to claim 1 , wherein:
the insufficiency is further recognized using the data structure, and/or the recognized insufficiency is an error in the data structure.

4 . The method according to claim 3 , wherein the data structure is: (i) a digital map, or (ii) a digital twin, or (iii) a combination of a digital map and a digital twin.

5 . The method according to claim 1 , wherein the assignment rule is updated only when the recognized insufficiency is relevant to safety.

6 . The method according to claim 1 , wherein the assignment rule defines different priorities or different boundary conditions including: (i) different weather conditions and/or (ii) different road conditions, and wherein the assignment rule assigns the respective priority to the output data based on current boundary conditions.

7 . The method according to claim 1 , wherein the assignment rule assigns a higher priority to the output data, the lower the insufficiencies assigned to the output data.

8 . The method according to claim 1 , wherein:
a region of the environment of the vehicle detected by the sensors is mapped by a two-dimensional or three-dimensional grid and each insufficiency is assigned to at least one grid element of the grid; and the assignment rule assigns the respective priority to the output data depending on which grid elements the insufficiencies assigned to the output data are assigned to.

9 . The method according to claim 1 , further comprising:
transmitting a message with respect to the recognized insufficiency to a data processing device located outside the vehicle.

10 . The method according to claim 1 , wherein communication data are received in the control device via: (i) a wireless data communication link which connects the vehicle to at least one further vehicle and/or (ii) at least one infrastructure element for data communication, and the input data for at least one of the evaluation functions further include at least a part of the communication data.

11 . A control device of a vehicle, comprising:
a processor coprocessing sensor data in the control device of the vehicle, wherein the vehicle includes different sensors configured to detect an environment of the vehicle and generate the sensor data, wherein the processor is configured to: evaluate the sensor data via different evaluation functions, each of the different evaluation functions being configured to convert at least part of the sensor data as input data into output data, wherein the output data of each of the different evaluation functions are assigned a respective priority using an assignment rule based on known insufficiencies of the sensors and/or the evaluation functions and the output data are used according to their priority to update an environment model that stores information about objects in the environment of the vehicle; recognize an insufficiency that differs from the known insufficiencies using at least a part of the sensor data and/or at least a part of the output data; update the assignment rule based on the recognized insufficiency, so that the output data of at least one of the evaluation functions are assigned a different priority in the future than the priority currently assigned to the output data; and control the vehicle using the updated assignment rule, wherein a data structure mapping at least part of the environment of the vehicle and deviating from the environment model is stored in the control device, and wherein at least one of the evaluation functions is configured to convert the input data into the output data using the data structure.

12 . A system for a vehicle, wherein the system comprises:
different sensors configured to detect an environment of the vehicle; and a control device including a processor coprocessing sensor data in the control device, wherein the vehicle includes the different sensors configured to detect the environment of the vehicle and generate the sensor data, wherein the control device is configured to: evaluate the sensor data via different evaluation functions, each of the different evaluation functions being configured to convert at least part of the sensor data as input data into output data, wherein the output data of each of the different evaluation functions are assigned a respective priority using an assignment rule based on known insufficiencies of the sensors and/or the evaluation functions and the output data are used according to their priority to update an environment model that stores information about objects in the environment of the vehicle; recognize an insufficiency that differs from the known insufficiencies using at least a part of the sensor data and/or at least a part of the output data; update the assignment rule based on the recognized insufficiency, so that the output data of at least one of the evaluation functions are assigned a different priority in the future than the priority currently assigned to the output data; and control the vehicle using the updated assignment rule, wherein a data structure mapping at least part of the environment of the vehicle and deviating from the environment model is stored in the control device, and wherein at least one of the evaluation functions is configured to convert the input data into the output data using the data structure.

13 . A non-transitory computer-readable medium on which is stored a computer program for processing sensor data in a control device of a vehicle, wherein the vehicle includes different sensors configured to detect an environment of the vehicle and generate the sensor data, wherein the computer program,

Assignees

• Bosch Gmbh Robert

Inventors

• Heyl Andreas
• Schneider Peter
• Reuter Stephan
• Kienle Theresa
• Gussner Thomas

Classifications

• B60W50/0205

  Diagnosing or detecting failures; Failure detection models · CPC title

• B60W2556/35

  Data fusion · CPC title

• B60W2050/0215

  Sensor drifts or sensor failures · CPC title

• G06V10/80

  Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level (multimodal speaker identification or verification G10L17/10) · CPC title

• G06V20/56

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