A method for evaluating a compliance driving of a driver of a motor vehicle, a computer program-product, a non-transitory computer-readable storage medium, as well as a support system

Abstract

A method for evaluating a compliance driving of a driver 18 of a motor vehicle 10 by a support system 16, comprising receiving a current driving behavior of the motor vehicle from at least one functi

Description

FIELD OF THE INVENTION

[0001] The invention relates to the field of automobiles. More specifically, the present invention relates to a method for evaluating a compliance driving of a driver of a motor vehicle by a support system of the motor vehicle. Furthermore, the present invention relates to a corresponding computer program product, a corresponding non-transitory computer-readable storage medium, as well as a corresponding support system. BACKGROUND INFORMATION

[0002] Many drivers have made their driver licenses, yet the driving tests are not comprehensive enough, consequently a driver frequently fails to realize when the driver is taking a wrong decision on the road. The absence of constant reminders about proper driving techniques leads the driver to repeat the same mistakes, and the driver may often remain oblivious until one day the driver encounters a major problem. Having well-educated drivers on the road is important for everyone's safety and should be given more consideration.

[0003] Therefore, there is a need in the art to provide a system that can remind people of what wrong decision they have been taken upon.

[0004] Currently, the state-of-the-art techniques implemented in production vehicles is a simple alert system that, for example, beeps when the motor vehicle exceeds a predetermined speed. However, the system is often insufficient as it only addresses speeding, neglecting other potential driving errors. SUMMARY OF THE INVENTION

[0005] It is an object of the present invention to provide a method, a corresponding computer program product, a corresponding non-transitory computer-readable storage medium, as well as a support system, by which the safety in road traffic is raised.

[0006] This object is solved by a method, a corresponding computer program product, a corresponding non-transitory computer-readable storage medium, as well as a corresponding support system according to the independent claims. Advantageous embodiments of the invention are provided in the dependent claims.

[0007] One aspect of the invention relates to a method for evaluating a compliance driving of a driver of a motor vehicle by a support system of the motor vehicle. A current driving behaviour of the motor vehicle is received from at least one functional device of the motor vehicle by an electronic computing device of the support system. Surroundings parameter are received by at least one capturing device of the motor vehicle by the electronic computing device. The surroundings parameter are analyzed and depending on the analyzation and provided laws and regulations, a target driving behaviour of the driver is determined. The laws and regulations are dependent on the road traffic. The target driving behaviour is compared with the current driving behaviour by the electronic computing device. The compliance driving is determined depending on the comparison by the electronic computing device and the determined compliance driving is outputted by an output device of the support system.

[0008] Therefore, the safety in road traffic can be raised as the driver gets the information, if the driving behaviour of the driver is a compliance driving or not.

[0009] Compliance driving is in particular a term that emphasizes adhering strictly to all traffic laws, regulations, and guidelines while operating the motor vehicle. Compliance driving is therefore more than just avoiding tickets, it's about understanding the rules of the road and consistently acting in a way that minimizes risks and promotes safety for the driver and others. Therefore, a thorough understanding of the relevant traffic laws, regulations, and road signs specific to the location is needed. This includes speed limits, right-off-way rules, signalling requirements, parking restrictions, and more. Consistently applying these rules in every driving situation is needed. This means obeying speed limits, stopping at red lights and stop signs, using turn signals appropriately, maintaining safe distance from other vehicles, and adhering to all other traffic control devices is needed. A driver must be aware of potential hazards and anticipating the actions of other drivers. This helps also to make informed decisions and avoid situations that could lead to violations or accidents. Therefore, a reduced risk of accidents, a legal protection, enhanced safety for the other road users and an improved driving habit may be provided.

[0010] Therefore, in particular, the solution of the problem as already stated is using, for example, the data's infrastructure available in the motor vehicle (Automatic Driving Assistance System - ADAS) to identify mistakes made by the driver when the motor vehicle is operated by the driver. Many times, most of non-safety related autonomous driving functions are not computed during the mode where the driver is driving the motor vehicle. Therefore, instead choosing to run the entire stack and use it to guide the driver to make them learn how to drive better. The support system clips the latent space of a core perception and planning networks as inputs to a language model. Based on the perception and planning latent information, in particular this large language model can be trained to only utter when a driver makes mistakes. The large language model can explain what mistakes have been made and how to fix them. It can also prepare and generate reports which the driver can later investigate from their connected application or the infotainment system to understand what happened.

[0011] In particular, as the functional device, for example an acceleration device, a deceleration device, a speedometer, and a steering wheel can be used. This is just for example only.

[0012] In particular, the invention has the advantage to increase education and safety in the road participants. Furthermore, new ways to drive can be unlocked as the large language model may show new tricks and tips on how to drive. Sharing knowledge from a lot of driven patterns that the large language model was trained from may further raise the safety. Furthermore, there is no additional cost involved as the hardware stack is already present in the car which is used when the motor vehicle is in autonomous mode.

[0013] According to an embodiment, if there is no compliance driving determined, generating a warning signal for the driver is provided.

[0014] According to another embodiment a correct driving behavior in the current driving situation is outputted.

[0015] In another embodiment, an identified mistake in the current driving situation is outputted.

[0016] According to another embodiment, the correct driving behavior and / or, the mistake is outputted as a text on a display device as the output device and / or, is acoustically outputted by a speaker device.

[0017] In another embodiment, the output is generated by a large language model.

[0018] In particular, the present invention is a computer-implemented method. Therefore, another aspect of the invention relates to a computer program product comprising program code means according to the preceding aspect.

[0019] A still further aspect of the invention relates to a non-transitory computer-readable storage medium comprising at least the computer program product according to the preceding aspect.

[0020] Furthermore, the present invention relates to a support system for evaluating a compliance driving of a driver of a motor vehicle, comprising at least one electronic computing device, and one output device, wherein the support system is configured for performing a method according to the preceding aspect. In particular, the method is performed by the support system.

[0021] Furthermore, the present invention relates to a motor vehicle comprising at least the support system according to the preceding aspect. In particular, the motor vehicle may further be configured for an at least in part autonomous driving operation.

[0022] Advantageous embodiments of the method are to be regarded as advantageous embodiments of the computer program product, the non-transitory computer-readable storage medium, the support system, as well as the motor vehicle. The support system, as well as the motor vehicle therefore comprises means for performing the method.

[0023] In particular, the computing unit / electronic computing device may include one or more computers, one or more microcontrollers, and / or one or more integrated circuits, for example, one or more application-specific integrated circuits, ASIC, one or more field-programmable gate arrays, FPGA, and / or one or more systems on a chip, SoC. The computing unit may also include one or more processors, for example one or more microprocessors, one or more central processing units, CPU, one or more graphics processing units, GPU, and / or one or more signal processors, in particular one or more digital signal processors, DSP. The computing unit may also include a physical or a virtual cluster of computers or other of said units.

[0024] In various embodiments, the computing unit includes one or more hardware and / or software interfaces and / or one or more memory units.

[0025] A memory unit may be implemented as a volatile data memory, for example a dynamic random access memory, DRAM, or a static random access memory, SRAM, or as a non-volatile data memory, for example a read-only memory, ROM, a programmable read-only memory, PROM, an erasable programmable read-only memory, EPROM, an electrically erasable programmable read-only memory, EEPROM, a flash memory or flash EEPROM, a ferroelectric random access memory, FRAM, a magnetoresistive random access memory, MRAM, or a phase-change random access memory, PCRAM.

[0026] Further advantages, features, and details of the invention derive from the following description of preferred embodiments as well as from the drawings. 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 figures and / or shown in the figures 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 DRAWINGS

[0027] 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. 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.

[0028] The drawings show in:

[0029] Fig 1 a schematic side view according to the embodiment of a motor vehicle comprising an embodiment of a support system,

[0030] Fig. 2 a schematic flowchart according to the embodiment of a method; and

[0031] Fig. 3 a schematic block diagram according to an embodiment of a support system.

[0032] In the figures the same elements or elements having the same function are indicated by the same reference signs. DETAILED DESCRIPTION

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] Fig. 1 shows a schematic side view according to an embodiment of a motor vehicle 10. The motor vehicle 10 may be for example at least in part autonomous and may provide also at least one operation mode, wherein in this operation mode a driver can operate the motor vehicle 10. The motor vehicle 10 may comprise at least one capturing device 12 as well as at least one functional device 14.

[0038] Furthermore, according to the present invention the motor vehicle 10 may comprise a support system 16 for evaluating a compliance driving of a driver 18 of the motor vehicle 10. The support system 16 may comprise at least one output device 20, 22 and at least one electronic computing device 24. A first output device 20 may be for example a display device and a second output device 22 may be for example a speaker device. Furthermore, as shown, the motor vehicle 10 may be operating in surroundings 26.

[0039] Fig. 2 shows a schematic flow chart according to an embodiment of the method. The method is for evaluating a compliance driving of the driver 18 of the motor vehicle 10 by the support system 16. Ina first step as S1 a current driving behaviour of the motor vehicle 10 is received from at least one functional device 14 of the motor vehicle 10 by the electronic computing device 24. In a second step S2 surroundings parameter are received by the at least one capturing device 12 of the motor vehicle 10 by the electronic computing device 24. Ina third step S3 the surroundings parameter are analyzed and a target driving behaviour of the driver 18 is determined depending on the analyzation and depending on provided laws and regulation 28 concerning a road traffic by the electronic computing device 24. Ina fourth step S4 the target driving behaviour is compared with the current driving behaviour by the electronic computing device 24. Ina fifth step S5 the compliance driving is determined depending on the comparison by the electronic computing device 24. Ina sixth step S6 the determined compliance driving is outputted by the output device 20, 22 of the support system 16.

[0040] According to the embodiment, if there is no compliance driving determined, a warning signal for the driver 18 is generated. Furthermore, a correct driving behaviour may be outputted in the current driving situation. Furthermore, an identified mistake in the current driving situation may be outputted. The correct driving behaviour and / or the mistake may be outputted as a text on the display device 20 as the output device 20, 22 and / or acoustic outputted by the speaker device 22 as the output device 20, 22. Furthermore, the output is generated by a large language model of the electronic computer device 24.

[0041] Fig. 3 shows a schematic block diagram according to an embodiment of the support system 16. In particular, at least in part the electronic computer device 24 is shown.

[0042] In Fig. 3 a sensor stack 30, a perception stack 32, a planning stack 34 and training data 36 are shown. Furthermore, a bottom block 38 is shown.

[0043] The sensor stack 30 includes raw sensor information from for example cameras, LiDAR, ultrasonics, radar and more, including ego motion data, GPS and map information. The sensor stack 30 may be in particular a so called standard set of sensors that is most modern in motor vehicles 10 and are already equipped with.

[0044] The perception stack 32 is a standard software system used in autonomous driving to process sensor measurements. It interprets data from sensors like LiDAR, cameras, radar, and ultrasonic sensors.

[0045] The system identifies for example objects, predicts their movements, and generates 3D surroundings and occupancy maps. This information is then used by downstream planning tasks to determine the vehicle's future actions. In addition to generating structured, neural monitoring output, the system may also utilize latent input. These latent inputs are the raw results from a neural network that haven't been transformed into neural monitoring data. Latent information encompasses more details than those directly captured by the neural network through labelled data. For example, even though a neural network might be trained for object detection, latent information is set to contain more than information needed for object detection.

[0046] Therefore, the perception stack 32 generates a perception output 40 as well as latent vectors 42. The perception output 40 is further processed by the planning analyzer 34. The planning analyzer 34, which may also be called planning stack, is a typical planning stack in an autonomous vehicle, which generates a safe and efficient path based on perception data. It considers obstacles, traffic rules, and dynamic changes in the environment to ensure the vehicle navigates safely and reaches its destination. In many systems, the core of the planning stack is a neural network. All neural networks output latent information, which can be intercepted before it is converted into human readable format. This information includes more than just the plan. As the output of the planning analyzer 34, planning output 44 as well as latent vectors 42 may be generated.

[0047] The training data 36 may comprise existing logs 46. These are the usual sensor information that are collected to train the perception and planning models in their ADAS stack. Furthermore, annotations during triages 48 may be provided, which describes when test engineers test the motor vehicles, that they usually leave a lot of voice and text information if the ADAS system is taking incorrect decisions, which can be used to identify mistake patterns by the network support. Furthermore, local driving handbooks 50 can be used. Some rules can also be fetched from local handbooks depending on the equal location of the motor vehicle 10 to understand what a mistake is and what is not as per local guidelines.

[0048] In particular, the latent vectors 42 as well as the training data 36 may then be used by the bottom block 38. The bottom block 38 may comprise a so-called clip 50 as well as a large language model 54. Furthermore, a structured report generator 56 is shown. The bottom block 38 may further comprise reports with graphs and statistic 58 and natural language alerts 60. From the reports with graphs and statistic 58 a mobile application 62 can be used to output these reports. The natural language alerts 60 may use the display device 20 as well as the speaker device 22 for output.

[0049] In particular, the bottom block 38 describes an embodiment of the method. Using ego motion, GPS, map information, and car controls, the electronic computing device 24 can determine all the drivers driving decisions. These driving decisions can be compared to the decisions against those from the for example autonomous system would make if the autonomous system may be active. The large language model 54 in the bottom block 38 also has the access to existing driving logs 46, the annotations during triage 48, and the local driving handbooks 50. Based on the discrepancies between the driver decisions, existing logs and ADAS decisions, the large language model 54 comes back with a natural language explanation of the discrepancy. If the discrepancy is a driver mistake, it alerts the driver 18 that's the mistake to report. To train a neural network like this, annotation and creating a new data set that has discrepancies as labels may be needed. The data can be collected and created by reports / statisties and graphs and can be shared with the driver / user 18 on their mobile application 62. This helps the driver 18 to identify their mistakes and help them fix them. Overall the method can improve road safety by educating drivers 18 from time to time even after they clear their driving set. Reference signs list 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38 40 42 44 46 48 50 52 54 56 58 60 62 motor vehicle capturing device functional device support system driver display device speaker device electronic computing device surroundings laws and regulations sensor stack perception stack planning analyzer training data bottom block perception output latent vectors planning output existing driving logs annotations during a triage local driving handbook clip large language model structured report generator reports with graphs and statistics natural language alerts mobile application

Claims

1. A method for evaluating a compliance driving of a driver (18) of a motor vehicle (10) by a support system (16) of the motor vehicle (10), comprising the steps of:- receiving a current driving behavior of the motor vehicle (10) from at least one functional device (14) of the motor vehicle (10) by an electronic computing device (24) of the support system (16); (S1)- receiving surroundings parameter by at least one capturing device (12) of the motor vehicle (10) by the electronic computing device (24); (S2)- analyzing the surroundings parameter and determining a target driving behavior of the driver (18) depending on the analyzation and depending on provided laws and regulations (28) concerning a road traffic by the electronic computing device (24);(S3)- comparing the target driving behavior with the current driving behavior by the electronic computing device (24); (S4)- determining the compliance driving depending on the comparison by the electronic computing device (24); (S5) and- outputting the determined compliance driving by an output device (20, 22) of the support system (16). (S6)2. The method according to claim 1, characterized in that,if there is no compliance driving determined, a warning signal for the driver (18) is generated.

3. The method to claim 1 or 2, characterized in thata correct driving behavior in the current driving situation is outputted.

4. The method according to any one of claims 1 to 3, characterized in thatan identified mistake in the current driving situation is outputted.

5. The method according to claim 3 or 4, characterized in thatthe correct driving behavior and / or the mistake is outputted as a text on a display device (20) as the output device (20, 22) and / or is acoustically outputted by a speaker device (22) as the output device (20, 22).

6. The method according to any one of claims 1 to 5, characterized in thatthe output is generated by a large language model (54).

7. A computer program product comprising program code means for performing a method according to any one of claims 1 to 6.

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

9. A support system (16) for evaluating a compliance driving of a driver (18) of a motor vehicle (10), comprising at least one electronic computing device (24), and one output device (20, 22), wherein the support system (16) is configured for performing a method according to any one of claims 1 to 6.

Images