Search

EP-3914924-B1 - APPARATUS AND METHOD FOR DETECTING RADAR SENSOR BLOCKAGE USING MACHINE LEARNING

EP3914924B1EP 3914924 B1EP3914924 B1EP 3914924B1EP-3914924-B1

Inventors

  • FETTERMAN, MATTHEW
  • RU, JIFENG
  • CARLSEN, ARET
  • ZUO, Yifan

Dates

Publication Date
20260513
Application Date
20191211

Claims (10)

  1. A radar system, comprising: a radar sensor module for transmitting radar signals into a region, detecting reflected returning radar signals from the region, and converting the reflected returning radar signals into digital data signals; a memory storing a model defining a relationship between a condition of the radar sensor module and a plurality of features of radar detections, the model being generated by a machine learning approach in which, during a training operation, a plurality of training radar detections are received under known states of the condition of the radar sensor module, the model storing values of the plurality of features associated with the known states of the condition of the radar sensor module; and a processor for receiving the digital data signals and processing the digital data signals to generate actual radar detections, each of the actual radar detections being characterized by a plurality of the features of radar detections, the processor applying values of the features of the actual radar detections to the model to determine the state of the condition of the radar sensor module from the values of the features of the actual radar detections; wherein the model identifies a subset of features associated with the training radar detections which are correlated with the state of the condition of the radar sensor module wherein the subset of features is selected using analysis of histograms of features associated with the training radar detections; and the processor applies the identified features of the actual radar detections to the model to determine the state of the condition of the radar sensor module.
  2. The radar system of claim 1, wherein the radar system is an automotive radar system.
  3. The radar system of claim 1, wherein the condition is blockage of the radar sensor. and, optionally, wherein the state of the condition is blocked or wherein the state of the condition is partially blocked, or wherein the state of the condition is unblocked.
  4. The radar system of claim 1, wherein the machine learning approach comprises a neural network approach or a logistic regression approach, or a bagged trees approach.
  5. The radar system of claim 1, wherein the subset of features is selected using a Bagged Trees analysis of features associated with the training radar detections.
  6. A method for detecting a condition in a radar sensor module, comprising: storing in a memory a model defining a relationship between the condition of the radar sensor module and a plurality of features of radar detections, the model being generated by a machine learning approach in which, during a training operation, a plurality of training radar detections are received under known states of the condition of the radar sensor module, the model storing values of the plurality of features associated with the known states of the condition of the radar sensor module; transmitting radar signals into a region; detecting reflected returning radar signals from the region; converting the reflected returning radar signals into digital data signals; receiving the digital data signals with a processor; and processing the digital data signals with the processor to generate actual radar detections, each of the actual radar detections being characterized by a plurality of the features of radar detections, the processor applying values of the features of the actual radar detections to the model to determine the state of the condition of the radar sensor module from the values of the features of the actual radar detections, wherein the model identifies a subset of features associated with the training radar detections which are correlated with the state of the condition of the radar sensor module, wherein the subset of features is selected using analysis of histograms of features associated with the training radar detections; and the processor applies the identified features of the actual radar detections to the model to determine the state of the condition of the radar sensor module.
  7. The method of claim 6, wherein the radar sensor is an automotive radar sensor.
  8. The method of claim 6, wherein the condition is blockage of the radar sensor and wherein optionally wherein the state of the condition is blocked, partially blocked, or unblocked.
  9. The method of claim 6, wherein the machine learning approach comprises a neural network approach, a logistic regression approach, or a bagged trees approach.
  10. The method of claim 6, wherein the subset of features is selected using a bagged trees analysis of features associated with the training radar detections.

Description

BACKGROUND 1. Technical Field The present disclosure is related to automotive detection systems such as automotive radar systems and, in particular, to an apparatus and method for detecting and correcting for blockage of an automotive radar sensor. 2. Discussion of Related Art In automotive radar systems, it is desirable to detect when the radar sensor is blocked by debris, such as dirt, snow, ice, etc. Sensor blockage or radar blockage attenuates the transmitted and received signal such that objects in the field of view are no longer detectable. It is also important to alert the driver when the sensor is blocked so that the driver does not rely on the radar system while a sensor is blocked, and so that the driver can intervene and clear the debris from the sensor to restore performance of the system. Declaring a sensor blockage based on the absence of radar signal processing detections is a relatively straightforward means of determining sensor blockage with minimal additional processing time or resources. One drawback of this approach is that it is difficult to distinguish the blocked case from the case in which there are relatively few or no objects large enough to create detections in the field of view of a sensor that is not blocked and is functioning properly. This situation can occur, for example, when the automobile in which the system is operating is passing through a desert or along a bridge or causeway surrounded by water. DE 102017211816 A1 describes a method of calculating a radar distance sighting distance of a radar sensor (2), comprising the steps of: S1 creating a mathematical model and indicating a predicted value of a distance sighting distance from a previous cycle to a current cycle; S2 constructing a new histogram using the real distance of all objects (4, 5) from a field of view (3) of the radar sensor (2) and identifying a scenario; and S3 taking into account the mathematical model from the first method step (S1) and the identified scenario from the second method step (S2), and obtaining an estimated value of the distance sight distance of the radar sensor (2); and an apparatus for carrying out the method. US 2018/0143299 AI describes a method for determining a degree of blindness of a radar sensor in a motor vehicle on the basis of a measurement of the receive power level of a radar echo, including the following steps that are carried out when at least one object is located by the radar sensor: determining an expected value for the radar scatter cross-section of the object on the basis of known properties of objects to be located; estimating the radar scatter cross-section of the located object on the basis of the measured receive power level; and calculating an indicator for the degree of blindness of the radar sensor as a monotonically increasing function of the difference between the estimated radar scatter cross-section and the expected value. DE 10 2005 059 902 A1 describes a method involving producing sensor signals, which correlate with a distance of a motor vehicle (1) to a driveway limitation, by distance sensors (8a, 8b, 9a, 9b). A set of time and/or location dependent distance values are determined from the signals, and the values are stored. The stored distance values are statistically evaluated, and sensor condition signals, which correlate with the result of the evaluation, are produced. The following are also described: (1) a distance measuring device for a vehicle for measuring a distance of the vehicle from a driveway limitation (2) a parking assistance system of a vehicle for outputting parking indications. SUMMARY According to a first aspect, a radar sensor system according to the accompanying claims is provided. According to a second aspect, a method for detecting a condition in a radar sensor module according to the accompanying claims is provided. BRIEF DESCRIPTION OF THE DRAWINGS The present disclosure is further described in the detailed description which follows, in reference to the noted plurality of drawings by way of non-limiting examples of embodiments of the present disclosure, in which like reference numerals represent similar parts throughout the several views of the drawings. Fig. 1 A includes a schematic block diagram of an automotive detection system, such as an automotive radar system, according to some exemplary embodiments.Fig. 1B includes a schematic block diagram of an alternative automotive detection system, such as an automotive radar system, according to some exemplary embodiments.Fig. 2 includes a schematic top view of an automobile or vehicle equipped with an automotive detection system illustrated in Figs. 1 A and/or 1B, which includes one or more radar sensor modules, according to some exemplary embodiments.Fig. 3 includes a logical flow diagram illustrating steps in a process 100 for radar sensor blockage detection, according to some exemplary embodiments.Figs. 4A through 4C include exemplary histograms illustrating different degrees o