Device, control unit, vehicle, method and computer program for fatigue detection in a vehicle
The integration of fatigue detection with a selectable driving profile in vehicles adjusts detection thresholds based on the driver's preferences, reducing false alarms by dynamically adapting to the selected driving mode, thus enhancing the accuracy of fatigue detection.
Patent Information
- Application Number
- DE102012018949
- Authority / Receiving Office
- DE · DE
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2012-09-26
- Publication Date
- 2026-05-28
- Estimated Expiration
- 2032-09-26
AI Technical Summary
Conventional vehicle fatigue detection systems rely on static recording of driving behavior statistics, leading to false alarms due to changes in driving style, such as transitioning from country roads to highways, as they fail to adapt to individual driver preferences and driving profiles.
A device that integrates fatigue detection with a selectable driving profile, adjusting thresholds for detecting driver fatigue based on the selected driving mode, such as Sport or Comfort, to reduce false alarms by considering the driver's individual preferences and driving conditions.
Reduces the occurrence of false fatigue warnings by dynamically adapting the detection criteria to the selected driving profile, ensuring more accurate fatigue detection tailored to the driver's specific driving habits and conditions.
Smart Images

Figure 00000000_0000_ABST
Abstract
Description
[0001] The present invention relates to a device according to claim 1, a control unit according to claim 10, a vehicle according to claim 12, a method according to claim 13 and a computer program according to claim 14.
[0002] Fatigue is a particular problem on long journeys. It is most commonly experienced by drivers who are on the road late at night. However, it affects drivers of all types of vehicles, as they all share the common experience of fatigue or inattentiveness after a more or less prolonged period of the attention required to drive. For this reason, several concepts already exist within conventional technology that use sensors to detect driver fatigue. Some of these concepts, for example, monitor the vehicle's steering sensors. Based on the characteristics of the steering movements, which become more rapid when fatigued, a state of fatigue in the driver can be detected and displayed.The display may include so-called fatigue alarms, which are intended to inform the driver acoustically, visually and also haptically about the detected fatigue.
[0003] More advanced systems, such as those shown in German patent application DE 10 2009 004 487 A1, evaluate signals from multiple sensors to detect driver fatigue. These systems also determine, for example, the data from a steering angle sensor in relation to a period of idling and subsequent steering action. Furthermore, certain driver preferences can be identified by evaluating a range of parameters, such as steering movements, acceleration behavior, speed, accelerations (both longitudinal and lateral), and so on.
[0004] DE 10 2011 114 655 A1 relates to a method and a device for detecting a driver's attention deficit, wherein at least one driver profile is determined and the vehicle's position on a lane it is traveling in is continuously monitored, wherein an impending lane departure is detected and, upon detection of the lane departure, active intervention in the vehicle's steering and / or braking system is initiated. According to the invention, the degree of attention deficit is determined based on the actively controlled interventions in the vehicle's steering and / or braking system.
[0005] US Patent 2007 / 0030157A1 discloses a method for controlling a driver assistance system that detects hazardous situations by comparing measured data with predefined threshold values and issues a warning signal upon detection of such a hazardous situation. An additional control module determines the driver's activity state based on at least one input value that allows inferences to be made about the driver's actions and can suppress the output of the warning signal depending on this activity state.
[0006] However, a potential drawback of these concepts is that they can only statically record statistics on driving behavior, i.e., the user behavior of the vehicle's individual controls, in order to detect deviations from parameters estimated based on habit or statistics. This estimation alone can lead to false alarms. For example, when a driver turns from a country road onto a highway, steering movements will generally decrease while speed increases. If the driver prefers a more sporty driving style on the country road, the larger steering movements there might trigger a fatigue detection even if no actual fatigue is present.
[0007] In adaptive systems, meaning those that learn from a driver's behavior, fatigue detection would be adjusted accordingly to the more pronounced steering movements on country roads. However, when the driver turns onto the highway, their driving behavior can change completely. For example, the speed might not be significantly higher than on the country road, but the steering movements will be considerably less frequent. In particular, a steering movement actually caused by fatigue will have a smaller impact. Since conventional systems might adapt to the driving behavior the driver exhibited on the country road that day, errors can occur.
[0008] Therefore, there is a need to create an improved concept for vehicle fatigue detection.
[0009] Exemplary embodiments of the present invention are based on the understanding that vehicles, particularly automobiles, already offer individual settings for the driver. For example, the driver can select driving profiles that correspond to their preferences or driving style. In particular, sporty and comfortable settings for the entire vehicle are possible. Such a driving profile can affect the chassis; for example, the shock absorbers and springs can be adjusted accordingly. Furthermore, the steering behavior can be influenced; for example, the feedback, i.e., the counter-pressure, of a power steering system can be adjusted. Finally, the transmission can also be influenced, insofar as, for example, an automatic transmission selects shift points later, i.e., at a higher engine speed, in sporty mode than in a comfortable mode. Finally, the acceleration characteristics, i.e.,The relationship between pressing the accelerator pedal and the vehicle's acceleration can be influenced. The same applies to the braking characteristics, i.e., how far or how firmly a brake pedal must be pressed to trigger a specific deceleration of the vehicle. Furthermore, there are many other parameters on a vehicle, especially an automobile, that can influence the vehicle's characteristics.
[0010] Further embodiments are based on the understanding that such a driver selection can be taken into account in the fatigue detection system. In this respect, these embodiments are based on the core idea of linking or combining the fatigue detection function with a driving profile selection in a vehicle.
[0011] Here and in the following, the term "vehicle" is generally used. This vehicle can be a car, a motorcycle, a truck, a ship, an airplane, a bus, etc. Wherever people are employed to drive a vehicle, the fatigue detection system described here can be used. Examples of its application are by no means limited to road vehicles like those mentioned above. Particularly in public transport, i.e., buses, commuter trains, subways, trams, etc., vehicles are driven by people who mostly work shifts. Here, drivers spend many hours at a time behind the wheel and can therefore be subject to periods of fatigue and inattention. Fatigue detection can be used to avert dangers to these individuals as well as to their passengers.Similar considerations apply to pilots, who are subject to the same phenomena, especially on long-haul flights. Such fatigue detection can also be used in shipping.
[0012] Exemplary embodiments therefore provide a device for detecting driver fatigue in a vehicle based on a predetermined driving profile. In other words, the device is designed to perform fatigue detection based on a predetermined driving profile. The device can be implemented, for example, as a circuit. The circuit can be composed of one or more electronic components that interact in such a way that fatigue detection is possible based on available information or signals. For example, the circuit can include electronic components that can execute corresponding computer programs. The driving profile is selectable by the driver. In other words, the driver selects a specific driving profile, for example, using a selector switch or via a central input device such as an on-board computer.These profiles can include, for example, Comfort, Sport, and / or Normal. However, implementation examples are not limited to these three driving profiles; any number of profiles, including customizable ones, are conceivable. For instance, each driver can make individual adjustments that influence the characteristics described above, which can be set within a driving profile. For example, a driving profile selection system can adapt the steering wheel characteristics, throttle response, engine performance, and / or the settings of the suspension units. Adapting the characteristics means tailoring the response to the individual driver, or giving the driver the option to adjust it according to their preferences. The driver can then choose between different profiles depending on their preferences or the intended driving situation.This gives the driver the opportunity to choose a profile that he considers most suitable for himself or the current driving task.
[0013] For example, the Comfort setting might be frequently used for long, relaxed drives on highways. In contrast, the Sport setting might be more suitable for fast, winding country roads.
[0014] Compared to conventional systems, exemplary embodiments of the invention can therefore offer the advantage that the fatigue detection can be adapted to the selected driving profile. Depending on the driving profile, the steering behavior can vary. In some exemplary embodiments, the steering behavior of a driver in a specific vehicle can be evaluated for fatigue detection. A sporty driving style, e.g., sharp steering maneuvers, might not trigger a fatigue alarm in a sport profile. In a comfort profile, however, such steering maneuvers could be interpreted as driver fatigue and thus trigger a fatigue alarm. Therefore, exemplary embodiments of the present invention can offer the advantage over conventional concepts that false alarms can be reduced depending on the selected driving profile. In other words, these exemplary embodiments can prevent drivers from receiving an increased number of unjustified fatigue warnings.In some implementation examples, the opposite case is also conceivable, namely that more justified warnings arise than is the case with conventional concepts.
[0015] In further embodiments, the driving profile can be influenced by recording the driver's driving characteristics. In other words, the driver can influence a driving profile, for example, by using a learning system. Generally, embodiments may include the option to save or reselect a driving profile for a specific driver. Furthermore, embodiments may include the option to reset a driver profile after a driver change. In other words, statistics can be recorded that, for example, allow conclusions to be drawn about how the driver typically behaves. For instance, it would be conceivable to determine steering characteristics, acceleration and braking characteristics—in principle, all operating characteristics of a driver—over a specific period.This period could, for example, be between 10 and 12 a.m., when the driver is assumed to be well-rested. In other embodiments, the driver could also pre-select specific times or periods to ensure they are in good condition. In still other embodiments, for example, the driver's pupil reactions and movements, or blinking, could be detected, allowing a conclusion to be drawn as to whether the driver is awake and alert.
[0016] In exemplary implementations, such situations can be used to record statistics, i.e., the aforementioned operating characteristics of the driver in relation to the vehicle, in order to better detect deviations. Apart from the driving profiles selectable by the driver, exemplary implementations can therefore also provide for the profile to be capable of learning or self-improvement.
[0017] In further embodiments, the driving profile can be influenced by the route and the vehicle's speed. For example, it is conceivable that the vehicle's navigation system is linked to the driver fatigue detection device. In this case, the route is characterized, and the driving profile is manipulated accordingly. For instance, if the route has tight switchbacks, large steering inputs are to be expected. If a long stretch of highway is detected, it is likely that the vehicle will make smaller steering inputs. Particularly when connected to modern GPS (Global Positioning System) devices, the consideration of numerous parameters is possible.From the coordinates, for example, longitudinal and lateral accelerations of the vehicle can be determined, which also allow conclusions to be drawn about a driver's driving characteristics and the driving profile can be adjusted accordingly.
[0018] In further embodiments, the driving profile can distinguish at least between a sport profile and a comfort profile. Generally, in these embodiments, the fatigue alarm can be triggered by driver maneuvers. In other words, driver maneuvers not included in the driving profile can trigger a fatigue alarm. For this purpose, the device can, for example, include a detection unit that can detect steering maneuvers, acceleration / braking maneuvers, and / or the speed of the steering maneuver. As already mentioned, certain steering angles and steering angle speeds can be evaluated here. Sharp steering maneuvers can still trigger a fatigue alarm in the comfort setting, whereas they do not trigger a fatigue alarm in the sport setting.
[0019] In some embodiments, fatigue detection can be achieved through threshold comparison. For example, a threshold for steering angle and steering speed can be determined based on a driving profile. If the detected steering angle or steering speed exceeds this threshold, a fatigue alarm can be triggered. In other words, exceeding the threshold can be interpreted as an indication of fatigue, and an alarm is triggered if these indications become frequent, for example, if the threshold is exceeded repeatedly within a certain time interval. In some embodiments, the threshold for this comparison can depend on the driving profile. Therefore, these embodiments offer the advantage that only one threshold for the comparison needs to be adjusted for different driving profiles.In other words, the threshold can then be assigned to the driving profile. In further embodiments, it is conceivable that the driver acknowledges false alarms, allowing the system to learn from them. For example, the threshold could then be raised in small increments after a false alarm.
[0020] In further embodiments, the device can be configured to distinguish at least one first threshold for the sport profile and a second threshold for the comfort profile, wherein the first threshold can be selected relative to the second threshold such that a fatigue alarm is triggered later. These embodiments are not limited to distinguishing between only two thresholds. Further profiles can be provided in these embodiments, and each profile can have its own threshold value independent of an early or late trigger time. As described above, this is because more aggressive or forceful steering maneuvers are to be expected with the sport profile setting than with a comfort profile. Therefore, fatigue detection should only be triggered at larger steering angles or higher steering speeds when the sport profile is selected.
[0021] Furthermore, some embodiments may include the ability to switch between driving profiles during the journey. This allows the corresponding thresholds for fatigue detection to be adjusted based on a newly selected driving profile. The thresholds can be adjusted by simply switching between profiles, resulting in abrupt changes. Other embodiments may involve a gradual transition of the thresholds, for example, a linear transition over a predetermined time interval.
[0022] Further embodiments include a control unit for a vehicle with a fatigue detection device as described above. The device or control unit can then include an input for a signal containing information about a driving profile, a steering maneuver, an acceleration / braking maneuver, and / or the speed of the steering maneuver, and an output for a signal containing information about a fatigue alarm. In addition, exemplary embodiments can provide an output for a signal containing information about a driving profile. For example, the driver's driving characteristics, as described above, can be taken into account and output for further processing. In exemplary embodiments, the input or output can also be on a bus, i.e., a data bus, as is already known from conventional technology.Therefore, buses are used in many different vehicles; in some embodiments, it may not be possible to assign a specific contact to a specific signal, since, for example, digital or binary signals are transmitted which can carry different information.
[0023] Furthermore, exemplary embodiments create a vehicle with a control unit according to the above description.
[0024] Further embodiments provide a method for detecting driver fatigue in a vehicle, taking into account the driver's driving profile. In addition, further embodiments provide a computer program with program code for carrying out one of the methods described above, when the program code is executed on a computer, a processor, or a programmable hardware component.
[0025] The following are examples of implementation described and explained in more detail with reference to the attached figures. Fig. Figure 1 shows an embodiment of a device for fatigue detection; and Fig. Figure 2 shows a block diagram of a flowchart of an embodiment of a method for fatigue detection.
[0026] In the following description of the accompanying figures, which show exemplary embodiments, identical reference numerals denote identical or comparable components. Furthermore, collective reference numerals are used for components and objects that appear multiple times in an exemplary embodiment or in a drawing, but are described jointly with respect to one or more features. Components or objects described with identical or collective reference numerals may be identical with respect to one, several, or all features, such as their dimensions, but may also differ, unless the description explicitly or implicitly indicates otherwise.
[0027] Furthermore, optional components are shown with dashed lines in the following figures. For example, the Fig. Figure 1 shows an embodiment of a device 10 for detecting driver fatigue in a vehicle based on a predetermined driving profile. In other words, to avoid or at least reduce the number of unwarranted fatigue warnings, the fatigue detection is linked to the driving profile selection. The driving profile can be selected by the driver. In further embodiments, the driving profile can be influenced by recording the driver's driving characteristics; the driving profile can also be determined by a route and / or the vehicle's speed, as described above. In other words, depending on the driving profile setting, the driver's fatigue can be detected differently.
[0028] In the exemplary embodiment under consideration, the driving profile should distinguish at least between a sport profile and a comfort profile. Specifically, the exemplary embodiment also considers a normal profile. The normal profile should be sportier than the comfort profile, but not as sporty as the sport profile. The fatigue alert itself can then be triggered by driving maneuvers performed by the driver.
[0029] As the Fig. Figure 1 shows that the device 10 further comprises a detection device 20 by which a driving maneuver can be detected. For example, a steering maneuver, an acceleration / braking maneuver, and / or the speed of the steering maneuver can be detected by the detection device 20. Furthermore, Figure 1 shows that... Fig. 1. A threshold comparison of 30, above which a fatigue alarm can be triggered. How the Fig. As further indicated in section 1, a threshold for the threshold comparison 30 is set via the driving profile. The threshold comparison 30 thus compares the output of the detection device 30, which represents a measure of a specific driving maneuver, with the threshold set via the driving profile.
[0030] In other words, the threshold for detecting driver fatigue is adjusted depending on the driving profile setting. These thresholds depend on the current driving profile; that is, the threshold parameters are adjusted according to the selected driving profile and then compared with the output of the detection device. In this example, it is assumed that the sporty driving profile, i.e., the Sport profile, has been selected. The thresholds are now less sensitive to steering maneuvers that indicate driver fatigue (also called events) and / or significantly more of these events are required to trigger a fatigue alarm.
[0031] In another embodiment, the driving profile is switched while driving. The threshold for fatigue detection is adjusted according to the new driving profile. This can be done either by a hard switch or by crossfading, i.e., by a smooth transition to the new threshold.
[0032] In exemplary embodiments, as described above, the fatigue detection thresholds can be adapted based on the driver's selection of driving profiles. In the specific exemplary embodiment, the device 10 is designed to distinguish at least a first threshold for the Sport profile and a second threshold for the Comfort profile. The first threshold is selected relative to the second threshold such that a fatigue alarm is triggered later; that is, more forceful steering movements are necessary to trigger a fatigue alarm in the Sport profile.
[0033] The Fig. Figure 1 further shows an embodiment of a control unit 100 for a vehicle with a fatigue detection device 10 as described above. In further embodiments, the control unit can have an input for a signal containing information about a driving profile, a steering maneuver, an acceleration / braking maneuver, and / or the speed of the steering maneuver, and an output for a signal containing information about a fatigue alarm. In a further embodiment, an additional output can be provided at which a signal containing information about an adapted driving profile is made available. The adapted driving profile can, for example, contain driver-specific characteristics or parameters that are adjusted based on a detected driving characteristic of the driver. Embodiments also include a vehicle with a control unit 100, in particular an automobile with a control unit 100.
[0034] The Fig. Figure 2 illustrates a block diagram of an embodiment of a method 50 for detecting driver fatigue in a vehicle, taking into account 40 a driving profile of the driver. Embodiments also provide a program with program code for carrying out one of the methods described above, when the program code is executed on a computer, a processor, or a programmable hardware component.
[0035] The features disclosed in the foregoing description, the following claims and the accompanying figures can be important and implemented individually or in any combination for the realization of an embodiment in its various configurations.
[0036] Although some aspects have been described in connection with a device, it is understood that these aspects also constitute a description of the corresponding process, so that a block or component of a device can also be understood as a corresponding process step or as a feature of a process step. Similarly, aspects described in connection with or as a process step also constitute a description of a corresponding block, detail, or feature of a corresponding device.
[0037] Depending on specific implementation requirements, embodiments of the invention can be implemented in hardware or in software. The implementation can be carried out using a digital storage medium, for example a floppy disk, DVD, Blu-ray disc, CD, ROM, PROM, EPROM, EEPROM or FLASH memory, hard disk or other magnetic or optical storage medium, on which electronically readable control signals are stored that can interact with, or interact with, a programmable hardware component in such a way that the respective method is carried out.
[0038] A programmable hardware component can be a processor, a computer processor (CPU = Central Processing Unit), a graphics processor (GPU = Graphics Processing Unit), a computer, a computer system, an application-specific integrated circuit (ASIC = Application-Specific Integrated Circuit), an integrated circuit (IC = Integrated Circuit), a system-on-a-chip (SOC = System on Chip), a programmable logic element, or a field-programmable gate array with a microprocessor (FPGA = Field Programmable Gate Array).
[0039] The digital storage medium can therefore be machine-readable or computer-readable. Some embodiments thus include a data carrier containing electronically readable control signals capable of interacting with a programmable computer system or programmable hardware component to execute one of the methods described herein. An embodiment is therefore a data carrier (or a digital storage medium or a computer-readable medium) on which the program for performing one of the methods described herein is recorded.
[0040] In general, embodiments of the present invention can be implemented as a program, firmware, computer program, or computer program product with program code or as data, wherein the program code or data is / are effective in carrying out one of the methods when the program runs on a processor or a programmable hardware component. The program code or data can, for example, also be stored on a machine-readable medium or data carrier. The program code or data can be in the form of, among other things, source code, machine code, bytecode, or other intermediate code.
[0041] Another embodiment is a data stream, a signal sequence, or a sequence of signals that represents the program for carrying out one of the methods described herein. The data stream, signal sequence, or sequence of signals can be configured, for example, to be transferred via a data communication link, such as the Internet or another network. Other embodiments include signal sequences representing data that are suitable for transmission via a network or data communication link, where the data represents the program.
[0042] A program according to one embodiment can implement one of the methods during its execution, for example, by reading memory locations or writing data to them, thereby potentially triggering switching operations or other processes in transistor structures, amplifier structures, or other electrical, optical, magnetic, or otherwise operating components. Similarly, by reading a memory location, a program can acquire, determine, or measure data, values, sensor values, or other information. Therefore, by reading from one or more memory locations, a program can acquire, determine, or measure quantities, values, measured values, and other information, and by writing to one or more memory locations, it can initiate, trigger, or execute an action, as well as control other devices, machines, and components.
[0043] The embodiments described above merely illustrate the principles of the present invention. It is understood that modifications and variations of the arrangements and details described herein will be obvious to other people skilled in the art. Therefore, it is intended that the invention be limited only by the scope of protection set forth in the following claims and not by the specific details presented herein by way of description and explanation of the embodiments.
Claims
[1] Device (10) for detecting fatigue in a driver of a vehicle, wherein the device (10) is designed to perform fatigue detection depending on a predetermined driving profile of the driver, wherein the driving profile is selectable by the driver. [2] Device (10) according to one of the preceding claims, wherein the driving profile can be influenced by detecting a driving characteristic of the driver. [3] Device (10) according to one of the preceding claims, wherein the driving profile can be determined by a route and a speed of the vehicle. [4] Device (10) according to one of the preceding claims, wherein the driving profile distinguishes at least a sport profile and a comfort profile. [5] Device (10) according to one of the preceding claims, wherein a fatigue alarm can be triggered by driving maneuvers of the driver. [6] Device (10) according to claim 5, which further comprises a detection device (20) by which a steering maneuver, a gas / brake maneuver and / or a speed of the steering maneuver can be detected and by which the driving maneuver can be detected. [7] Device (10) according to one of the preceding claims, wherein fatigue detection is detectable by a threshold comparison (30). [8] Device (10) according to claim 7, wherein a threshold for the threshold comparison (30) depends on the driving profile. [9] Device (10) according to claims 4 and 7, which is configured to distinguish at least a first threshold for the sport profile and a second threshold for the comfort profile, wherein the first threshold can be selected relative to the second threshold such that a fatigue alarm is triggered later. [10] Control unit (100) for a vehicle with a device (10) for fatigue detection according to one of the preceding claims. [11] Control unit (100) according to claim 10, comprising an input for a signal with information about a driving profile, a steering maneuver, a gas / brake maneuver and / or a speed of the steering maneuver and an output for a signal with information about a fatigue alarm. [12] Vehicle with a control unit (100) according to claim 10. [13] Method for detecting fatigue in a driver of a vehicle taking into account (40) a driving profile of the driver, wherein the driving profile is selectable by the driver. [14] Computer program comprising program code for performing the method according to claim 13, when the program code is executed on a computer, a processor or a programmable hardware component.
Citation Information
Patent Citations
Method for recognizing tiredness of driver of vehicle, involves constantly updating summation of weighed steering errors during averaging when current measured value for weighed steering error is added to past averaged association result
DE102009004487A1
Method for detecting attention deficit of driver of vehicle, involves performing active control of steering device engaged with braking device, according to recognition result of departure lane of vehicle
DE102011114655A1
Method of controlling a driver assistance system and an associated apparatus
US20070030157A1
