DE102019211006B4 - Evaluation of sensor data from a vehicle - Google Patents

Abstract

Method for evaluating sensor data of a vehicle with the following steps: - providing (S1) a digital environment map for a current real environment of the vehicle; - detecting (S2) sensor data, in particular by means of a sensor of the vehicle, with regard to the real vehicle environment; - merging (S3) the sensor data with the digital map of the environment in such a way that the sensor data are related to the digital map of the environment,- wherein data of the digital map of the environment and the sensor data are each classified with regard to their reliability,- wherein data of the digital map of the environment that a certified sensor, in particular an ASIL-certified sensor, is assigned a higher reliability than data generated with a non-certified and/or weaker than ASIL-certified sensor.

Description

FIELD OF THE INVENTION

The present invention relates to a method for evaluating sensor data from a vehicle.

TECHNICAL BACKGROUND

DE 10 2015 01 0542 A1 shows a method for generating a digital map of the surroundings.

From the DE 10 2015 206 605 A1 shows a driver assistance system for a vehicle for calibrating a sensor arrangement.

the DE 10 2017 222 183 A1 discloses a method for monitoring multiple environmental sensors of a motor vehicle.

the DE 10 2011 112 404 A1 shows a method for determining a position of a motor vehicle by detecting at least one object in the surroundings of the motor vehicle.

From the DE 10 2010 049 215 A1 discloses a method for determining a vehicle environment, in which current local environment data are determined by means of an environment sensor.

SUMMARY OF THE INVENTION

• - ein Verfahren zum Auswerten von Sensordaten eines Fahrzeugs mit den folgenden Schritten: Bereitstellen einer digitalen Umgebungskarte zu einer aktuellen realen Umgebung des Fahrzeugs; Erfassen von Sensordaten, insbesondere mittels eines Sensors des Fahrzeugs, bezüglich der realen Fahrzeugumgebung; Fusionieren der Sensordaten mit der digitalen Umgebungskarte.

It is intended:

• - A method for evaluating sensor data of a vehicle with the following steps: providing a digital environment map to a current real environment of the vehicle; Acquisition of sensor data, in particular by means of a sensor of the vehicle, with regard to the real vehicle environment; Merging the sensor data with the digital map of the environment.

Motor vehicles within the meaning of this patent application are motor-driven land vehicles. This also includes rail vehicles.

Automated driving requires reliable road information based on high-resolution HD map data. HD map data is a 2D representation of a vehicle environment and includes, for example, vehicle lanes, traffic lights, road signs, lane geometries, and the like.

A digital environment map is a high-resolution 3D representation of a vehicle environment and can contain various components, for example an HD map, lidar data, lidar point clouds, lidar-classified objects, camera-classified objects, radar data, satellite data and/or the like. The representation in a digital map of the area can be accurate to a few centimeters. A digital map of the surroundings can be made available, for example, via the Internet using a central data store.

A sensor, also known as a detector, (measuring variable or measurement) pickup or (measuring) probe, is a technical component that detects certain physical, chemical properties or states, e.g. B. temperature, humidity, pressure, speed, brightness, acceleration, pH, ionic strength, electrochemical potential and / or the material properties of its environment can be qualitatively or quantitatively detected as a measurand. These variables are recorded using physical or chemical effects and converted into an electrical signal that can be further processed as sensor data. Vehicle sensors are mounted on a vehicle to sense a vehicle environment. Sensor data that is recorded by vehicle sensors is vehicle environment-related sensor data.

Static objects are non-moving objects. Non-static objects are moving objects.

A driving maneuver is, for example, braking, accelerating, steering, changing lanes, turning, parking and the like.

ASIL stands for Automotive Safety Integrity Level and is a safety requirement level specified by ISO 26262 for safety-related systems in motor vehicles.

Computer program products typically include a sequence of instructions that, when the program is loaded, cause the hardware to perform a specific method that leads to a specific result.

The idea underlying the invention is to merge a digital map of the surroundings with sensor data of a vehicle so that the vehicle can access both the sensor data and the digital map of the surroundings and the sensor data can be classified in the digital map of the surroundings.

Advantageous refinements and developments result from the further dependent claims and from the description with reference to the figures of the drawing.

According to a preferred development of the invention, the sensor data are digita len environment map checked. Accordingly, it is possible to validate data from vehicle sensors while driving using the digital environment map.

In order to merge sensor data with the digital map of the surroundings, it is advantageous if the data of the digital map of the surroundings guarantee a certain minimum level of reliability. In this case, the digital environment map forms an additional validation option for sensor data that relate to a vehicle environment. It is thus possible to validate grids and/or the classification of objects. This prevents incorrect interpretation of sensor data.

Data in digital maps of the environment are often validated by repeatedly driving on a section of road. The validation of sensor data using data of different reliability creates an advantageous alternative.

According to the invention, data from the digital environment map and sensor data are each classified with regard to their reliability.

It is expedient if, in the event of a contradiction between first data, in particular sensor data, with a first reliability and second data, in particular data from the digital map of the surroundings, with a second reliability, data with the lower reliability, in particular sensor data, are not taken into account or are weighted less will.

For example, it is advantageous for autonomous driving to decide between the contradictory sensor data in the event of a contradiction between different sensor data. Accordingly, an algorithm will disregard or give less weight to sensor data with a lower reliability and make a decision based on the more reliable data source.

This reduces the risk of incorrect decisions being made by an algorithm due to defective sensors.

According to the invention, data of the digital environment map that was generated with a certified sensor, in particular with an ASIL-certified sensor, is assigned a higher reliability than data that was generated with a non-certified and/or weaker than ASIL-certified sensor. In particular, it is possible to validate a digital environment map with ASIL-certified vehicle sensors. This means that data from the digital environment map has the same reliability as sensor data from ASIL-certified sensors. This is advantageous compared to HD map data or data from a digital map of the surroundings, which result from a data source classified as unreliable or less reliable.

According to a preferred development of the invention, sensor data relating to the real environment of the vehicle are filtered using the digital environment map with regard to data relating to static objects.

Accordingly, provision can be made to compare sensor data relating to the vehicle environment with the digital map of the environment. If differences are found between the sensor data and the digital map of the surroundings, it is possible for a computer program or a vehicle driver to focus primarily on the differences. It is thus possible to identify dynamic objects or to filter out static objects.

According to a preferred development of the invention, a position of the vehicle is determined on the basis of the fusion of the sensor data with the digital map of the surroundings. In particular, it is advantageous to determine a position of the vehicle in the digital map of the surroundings by means of lidar data, in particular with a lidar point cloud.

Based on a comparison of the digital map of the surroundings with the sensor data of the vehicle, an exact position of the vehicle in the digital map of the surroundings and an orientation or direction of travel of the vehicle can be determined.

If a direction of travel or orientation of the vehicle is determined by comparing the sensor data of the vehicle and the digital vehicle environment, the orientation of the vehicle can be determined before the vehicle is moved in a corresponding direction of travel.

According to a preferred development of the invention, sensor data are predicted using the digital environment map.

Accordingly, the digital surroundings map provides information on a vehicle surroundings to a larger area than the vehicle sensors. The driving strategy and route planning can be adjusted based on this digital horizon. In this way, sensor data relating to a more distant vehicle environment can be predicted. Driving situations can also be predicted.

For example, it is conceivable that another vehicle is located in front of a host vehicle, which has access to its sensor data and access to a digital map of the surroundings, which obscures the sensors' view of the area in front of the other vehicle, in particular its lane. For example, if the other vehicle is heading for the end of a lane and the end of the lane is covered by the other vehicle, this can lead to dangerous driving situations due to the other vehicle suddenly cutting in opposite the host vehicle. Such driving situations can be predicted by comparing the sensor data of the host vehicle with the data of a digital map of the surroundings. It is thus possible to react to driving situations at an early stage, such that potentially dangerous driving situations do not arise.

Accordingly, it is expedient if driving maneuvers or a route are planned based on the prediction of sensor data.

According to a preferred development of the invention, driving maneuvers and/or a route are planned on the basis of the fusion of the sensor data with the digital map of the surroundings.

The computer program product according to an embodiment of the invention executes the steps of a method according to the preceding description when the computer program product runs on a computer, in particular an in-vehicle computer. If the program in question is used on a computer, the computer program product produces an effect, namely the merging of sensor data from a vehicle with a digital map of the surroundings of a vehicle.

character list

• 1 ein schematisches Blockdiagramm einer Ausführungsform der Erfindung;

The present invention is explained in more detail below with reference to the exemplary embodiments given in the schematic figures of the drawings. They show:

• 1 a schematic block diagram of an embodiment of the invention;

The accompanying drawings are provided to provide a further understanding of embodiments of the invention. They illustrate embodiments and, together with the description, serve to explain principles and concepts of the invention. Other embodiments and many of the foregoing advantages will become apparent by reference to the drawings. The elements of the drawings are not necessarily shown to scale with respect to one another.

In the figures of the drawings, elements, features and components that are identical, have the same function and have the same effect--unless stated otherwise--are each provided with the same reference symbols.

DESCRIPTION OF EXEMPLARY EMBODIMENTS

1 shows a block diagram corresponding to a method for evaluating sensor data of a vehicle. In step S1, a digital environment map is provided for a current real environment of the vehicle; in step S2 sensor data are recorded by means of a sensor of the vehicle with regard to the real vehicle environment; In step S3, sensor data are merged with the digital map of the surroundings.

Claims (11)

Procedure for evaluating sensor data from a vehicle with the following steps: - Providing (S1) a digital environment map to a current real environment of the vehicle; - Detection (S2) of sensor data, in particular by means of a sensor of the vehicle, with respect to the real vehicle environment; - Merging (S3) the sensor data with the digital map of the environment in such a way that the sensor data are related to the digital map of the environment, - wherein data of the digital environment map and the sensor data are classified in terms of their reliability, - wherein data of the digital environment map generated with a certified sensor, in particular an ASIL-certified sensor, is assigned a higher reliability than data generated with a non-certified and/or weaker than ASIL-certified sensor. Method for evaluating sensor data from a vehicle claim 1 , whereby the sensor data are checked using the digital environment map. Method for evaluating sensor data from a vehicle claim 1 , where in the case of a contradiction between first data, in particular data of the digital map of the surroundings, with a first reliability and second data, in particular sensor data, with a second reliability, the data with the lower reliability, in particular sensor data, are not taken into account or are weighted less. Method for evaluating sensor data of a vehicle according to one of the above Claims, wherein sensor data relating to the real environment of the vehicle are filtered by means of the digital map of the environment with regard to data on stationary objects. Method for evaluating sensor data of a vehicle according to one of the preceding claims, wherein a position of the vehicle is determined on the basis of the fusion of the sensor data with the digital map of the surroundings. Method for evaluating sensor data of a vehicle according to one of the preceding claims, wherein sensor data are predicted using the digital map of the surroundings. Method for evaluating sensor data from a vehicle claim 6 , wherein a vehicle position is determined in the digital vehicle environment map using lidar sensor data. Method for evaluating sensor data from a vehicle claim 6 or claim 7 , An orientation of the vehicle being determined on the basis of sensor data, such that the orientation of the vehicle is known before the vehicle is moved in a corresponding direction of travel. Method for evaluating sensor data of a vehicle according to one of Claims 6 until 8th , driving maneuvers and/or a route being planned on the basis of the prediction. Method for evaluating sensor data of a vehicle according to one of the preceding claims, wherein driving maneuvers and/or a route are planned on the basis of the fusion of the sensor data with the digital map of the surroundings Computer program product which is designed to be loaded into a memory of a computer and which comprises software code sections with which the steps of the method for evaluating sensor data of a vehicle according to one of the preceding claims are carried out when the computer program product runs on the computer

Images