Method for diagnosing driver behavior in a motor vehicle and diagnostic system

Abstract

Method and system for diagnosing driver behavior in a motor vehicle comprising the steps of: capturing driving data using at least one sensor device, transmitting the data to an ECU, creating and acti

Description

FIELD OF THE INVENTION

[0001] The invention relates to the field of automobiles. More specifically, the present invention relates to a method for diagnosing driver behavior in a motor vehicle according to claim 1. Furthermore, the present invention relates to a diagnostic system, a corresponding computer program product, and a corresponding non-transitory computer-readable storage medium. BACKGROUND INFORMATION

[0002] The evaluation of driver behavior during real-world driving situations is needed for example for ensuring road safety and improving driver skills. Current methods rely heavily on human observation, which can introduce subjective bias and inconsistency in assessing driving performance. With the increasing adoption of advanced driver assistance systems (ADAS) in modern vehicles, there is a growing opportunity to leverage these systems for objective, data-driven evaluation of driver behavior. By utilizing onboard sensors and electronic computing units, it becomes possible to analyze various aspects of driver behavior in real-time, enabling the identification of potentially unsafe actions and assisting in post-event reporting or corrective feedback.

[0003] GB2589618A discloses a method for diagnosing driver behavior in a motor vehicle, involving the use of onboard sensors and an interior camera to identify reckless driving behavior. When such behavior is detected, a critical safety signal is activated, and the interior camera records the driver’s actions. The captured data, including the activation of the safety signal, is stored in a diagnostic database for further analysis. The method primarily focuses on monitoring the driver’s attentiveness and actions inside the vehicle, such as gaze tracking and hand position recognition, without involving advanced driver assistance systems for external driving context or comparison with predefined ideal driving behavior.

[0004] The objective of the invention is to provide a method to improve road safety and driver evaluation by offering a reliable, objective approach for detecting and analyzing driving behavior.

[0005] This objective is achieved by means of a method with the features of claim 1 and by means of a diagnostic system according to the invention. Advantageous embodiments and further developments can be inferred from the dependent claims and the description. SUMMARY OF THE INVENTION

[0006] One aspect of the invention relates to a method for diagnosing driver behavior in a motor vehicle, for example using a corresponding diagnostic system. This method involves initially capturing driving data using at least one sensor device that collects relevant information about the vehicle and its surroundings. The captured data is then transmitted to an electronic computing unit, which is responsible for analyzing the driver’s behavior. The computing unit processes the sensor data and generates a critical safety signal if reckless driving behavior is detected. The activation data of the critical safety signal is stored in a diagnostic database for later evaluation.

[0007] To solve the objective of the invention, which is to provide an objective evaluation of driver behavior, the invention proposes that the analysis of driver behavior is performed using an Advanced Driver Assistance System (ADAS). The ADAS is used to capture and process the driving data, comparing the driver’s behavior with a predefined ideal driving behavior. This comparison is carried out in real-time, enabling immediate identification of deviations from the ideal behavior. The ADAS combines sensor data from cameras, radar, and / or other onboard sources to conduct a comprehensive analysis. A significant advantage of this approach is that existing vehicle systems may be utilized, eliminating the need for additional hardware.

[0008] In an advantageous embodiment of the invention, it is provided that the ADAS system is used to determine deviations between the driver’s behavior and the predefined driving behavior. This enables even the smallest deviations, which may indicate potentially dangerous driving behavior, to be detected and documented.

[0009] In another advantageous embodiment of the invention, it is provided that the result of the analysis is made available in the form of an automatically generated report. This report may include detailed information on the identified deviations and their severity, thereby providing driving instructors or examiners with an objective basis for evaluating the driver.

[0010] In a further embodiment of the invention, it is provided that the ADAS system categorizes the identified dangerous driving behaviors by type and severity of deviation. This allows the report to be clearly structured and easy to understand, enhancing the traceability of the analysis.

[0011] In yet another advantageous embodiment of the invention, it is provided that the result of the analysis is used to evaluate the driver’s behavior by means of a point-based scoring system. The scoring system may be configured to objectively consider the degree of deviations, thereby ensuring a fair evaluation of the driver.

[0012] Another aspect of the invention concerns a diagnostic system for recording and assessing driving behavior in a vehicle. The diagnostic system includes at least one sensor device for capturing driving data, an electronic computing unit for processing the data and activating a safety signal, as well as a diagnostic database for storing the activation data. The diagnostic system enables comprehensive and reliable detection of safety-critical driving events. The diagnostic system is configured so that the analysis of the driving behavior is performed using the ADAS system. Therefore, the driver’s behavior is continuously compared with a predefined desired behavior, and a safety signal is activated when dangerous driving behavior is detected.

[0013] In other words, it is provided that the method and diagnostic system according to the invention offer an objective evaluation of the driver’s behavior by continuously capturing and analyzing driving data and generating reports on safety-critical events. By combining camera, radar, and environmental data with real-time analysis using an ADAS system, a high safety standard is achieved, making the invention particularly suitable for driving tests and long-term diagnostics.

[0014] Driving analysis is therefore conducted using sensor data from external cameras, radar, vehicle ego data (such as speed and steering), and the driver cabin camera. Analyzing applications (algorithms) are applied to this data to assess various aspects of driver behavior. Examples of the behaviors that may be analyzed include:

[0015] Analyzing Driving in the Middle of the Lane, wherein external camera data is used, and a lane detection algorithm is applied. The output of this algorithm determines the percentage of time a driver remains in the middle of the lane. Thresholds may be set by the Department of Motor Vehicles (DMV) to specify the required percentage of time the driver must stay in the lane to pass a driving test.

[0016] Analyzing Speed Limit Compliance, wherein vehicle ego motion data (e.g. speed) and mapping data listing speed limits for each road are fed into a speed reporting algorithm. This algorithm reports instances where the driver exceeded the speed limit and identifies dangerous acceleration or deceleration events based on thresholds set by the DMV.

[0017] Analyzing Traffic Light and Stop Sign Violations, wherein external camera data, mapping data, and vehicle ego motion data are used in a traffic stop violation algorithm. The algorithm outputs instances where the driver fails to stop at a red traffic light or a stop sign.

[0018] Analyzing Lane Changes, wherein when the driver initiates a lane change, a lane change violation algorithm checks whether the driver uses the turn signal, looks over their shoulder, and / or safely changes lanes when it is appropriate to do so. Radar data, external camera data, and / or internal cabin camera data may be used as inputs for this algorithm.

[0019] Checking Seat Belt Usage, wherein when the driver begins driving, internal camera data is used to check whether the driver is wearing a seat belt.

[0020] Analyzing Driving Behind a School Bus, wherein external camera data, radar data, and vehicle ego motion data are analyzed to assess how the driver behaves when following a school bus.

[0021] The discrepancies may be compared against a combination of predefined handbook rules, vehicle perception, and / or thresholds set for each driving behavior by the DMV. The point calculator mentioned in the analysis assigns a score to each detected discrepancy, contributing to the overall evaluation of the driver.

[0022] Regarding real-time accuracy, the diagnostic system may be configured for realtime analysis or offline evaluation, depending on DMV requirements. For real-time use, additional computing hardware capable of running the analysis algorithms is necessary. If used offline, the collected data can be processed on separate hardware. The analysis algorithms rely on traditional computer vision techniques and mathematical logic to achieve the required accuracy for driver behavior analysis.

[0023] Further advantages, features, and details of the invention derive from the following description of preferred embodiment as well as from the drawing. The features and feature combinations previously mentioned in the description as well as the features and feature combinations mentioned in the following description of the figure and / or shown in the figure alone can be employed not only in the respectively indicated combination but also in any other combination or taken alone without leaving the scope of the invention. BRIEF DESCRIPTION OF THE DRAWING

[0024] The novel features and characteristic of the disclosure are set forth in the appended claims. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and together with the description, serve to explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and / or methods in accordance with embodiments of the present subject matter are now described below, by way of example only, and with reference to the accompanying figures.

[0025] The drawing shows in:

[0026] Fig. 1 a diagram showing a possible implementation of a method for diagnosing driver behavior in a motor vehicle.

[0027] In the figure the same elements or elements having the same function are indicated by the same reference signs. DETAILED DESCRIPTION

[0028] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration". Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0029] While the disclosure is susceptible to various modifications and alternative forms, specific embodiments thereof have been shown by way of example in the drawing and will be described in detail below. It should be understood, however, that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.

[0030] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion so that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus preceded by “comprises” or “comprise” does not or do not, without more constraints, preclude the existence of other elements or additional elements in the system or method.

[0031] In the following detailed description of the embodiment of the disclosure, reference is made to the accompanying drawing that forms part hereof, and in which is shown by way of illustration a specific embodiment in which the disclosure may be practiced. This embodiment is described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0032] Fig. 1 shows a diagram showing a possible implementation of a method for diagnosing driver behavior in a motor vehicle by utilizing various sensor and processing components integrated into a diagnostic system 10. The diagnostic system 10 is divided into two main functional blocks: an upper block A and a bottom block B, each contributing specific elements essential for analyzing driver behavior.

[0033] The upper block A includes a sensor stack 11 comprising a standard set of sensors such as lidar, cameras, radar, and ultrasonic sensors, all of which are commonly installed in modern vehicles. The data from the sensor stack 11 is processed by a perception stack 12, which is responsible for interpreting sensor measurements to identify objects, predict movements, and generate a 3D environmental model and occupancy maps. The perception stack 12 produces both perception output 13a, which is structured for human readability, and latent vectors 13b, which contain raw neural network results that offer additional, non-transformed information.

[0034] The planning stack 15 therefore receives input from the perception stack 12 and the local driving handbook 14, enabling the diagnostic system 10 to generate an optimal driving plan. The planning stack 15 produces two outputs: ideal driving decisions 16a and tolerance levels, shown in Fig. 1 as ideal driving decisions and tolerance 17, as well as additional latent vectors 16b, 18. These outputs provide a comprehensive reference for comparing actual driving behavior with expected standards.

[0035] The bottom block B processes information from ego motion sensors, GPS, map data, and vehicle controls to determine the actual driving decisions made by the human driver. Therefore, human driving 21, ego motion, and map information 22 are input into a driving analyzer 23, which evaluates the driver's actions and generates driving decisions 24 as output. These outputs are then compared with the ideal driving decisions from the upper block A to identify discrepancies.

[0036] The combined outputs from blocks A and B are fed into a discrepancy analyzing network 31 in block C, representing the merging performed by the diagnostic system 10. This network identifies and categorizes discrepancies, generating a report 32a and a point-based evaluation 32b. An optional human evaluation 33 can be included to review the automated results. The outputs from the report generation 32a, point calculator 32b, and optional human evaluation 33 are collectively used as input for a final pass / fail decision 34 regarding the driver’s performance.

[0037] By integrating sensor data with real-time analysis and comparison against predefined driving standards, the diagnostic system 10 ensures an objective and consistent assessment of driver behavior, ultimately contributing to a fair and accurate evaluation process. sign’s list Diagnostic system Sensor stack Perception stack Perception output Latent vectors Local driving handbook Planning stack Ideal driving decisions Additional latent vectors Tolerance levels Additional latent vectors Human driving Ego motion and map information Driving analyzer Driving decisions Discrepancy analyzing network Report generation Point-based evaluation Optional human evaluation Final pass / fail decision Upper block Bottom block Discrepancy analysis block

Claims

1. Method for diagnosing driver behavior in a motor vehicle, comprising the steps of:- capturing driving data using at least one sensor device,- transmitting the captured sensor data to an electronic computing unit,- creating and activating a critical safety signal by the electronic computing unit based on at least one reckless driving behavior identified through an analysis, - storing the activation data of the critical safety signal in a diagnostic database, characterized in that- the analysis of the reckless driving behavior is performed using an ADAS system of the vehicle, where the driver’s behavior is compared with a predefined driving behavior.

2. Method according to claim 1, characterized in thatthe ADAS system is used to determine deviations between the driver’s behavior and the predefined driving behavior.

3. Method according to one of the preceding claims, characterized in thatthe result of the analysis is provided in the form of an automatically generated report.

4. Method according to one of the preceding claims, characterized in thatthe ADAS system is used to categorize the identified reckless driving behavior by type and severity of deviation.

5. Method according to one of the preceding claims, characterized in thatthe result of the analysis is used to evaluate the driver’s behavior using a scoring system.

6. Diagnostic system (10) for driver behavior in a motor vehicle, comprising:- at least one sensor device configured to capture driving data,- an electronic computing unit configured to receive the captured sensor data from the at least one sensor device,- the electronic computing unit being further configured to create and activate a critical safety signal based on at least one reckless driving behavior identified through an analysis,- a diagnostic database configured to store the activation data of the critical safety signal,characterized in thatthe analysis of the reckless driving behavior is performed using an ADAS system of the vehicle, and the driver’s behavior is comparable with a predefined driving behavior to carry out the analysis.

7. Computer program product comprising program code means for performing a method according to claim 1 to 5.

8. Non-transitory computer-readable storage medium comprising at least the computer program product according to claim 7.

Images