Method and assistance system for recognizing a riding characteristic of a rider of a single-track vehicle

Abstract

The present invention relates to a method for recognizing a riding characteristic of a rider of a single-track vehicle, wherein, for upcoming cornering through a road curve, a reference speed (106) is determined using at least one curve parameter (102) of the road curve and a stored correction variable (108), wherein, after the road curve has been ridden through, a comparison is carried out between the reference speed (106) and a speed (112) at which the rider rode in the road curve, and a result of the comparison is used to set and store the correction variable (108) for subsequent cornering through a subsequent road curve in order to replicate the riding characteristic.

Description

[0001] R. 415142

[0002] Description

[0003] title

[0004] Method and assistance system for recognizing the driving characteristics of a driver of a single-track vehicle

[0005] Field of invention

[0006] The invention relates to a method for recognizing the driving characteristics of a driver of a single-track vehicle, a corresponding assistance system, and a corresponding computer program product.

[0007] State of the art

[0008] A vehicle may have an assistance system that warns the driver, for example, if they approach an upcoming curve at an inappropriate speed.

[0009] DE 10 2014 225 625 A1 describes a method for assisting a driver of a single-track motor vehicle to safely navigate a curve.

[0010] Disclosure of the invention

[0011] Against this background, the approach presented here introduces a method for recognizing the driving characteristics of a driver of a single-track vehicle, a corresponding assistance system, and a corresponding computer program product according to the independent claims. Advantageous further developments and improvements of the approach presented here result from the description and are described in the dependent claims.

[0012] Advantages of the invention

[0013] KU:GR R. 415142

[0014] 2 -

[0015] A single-track vehicle cannot travel through a curve at an arbitrary speed due to the limitations of vehicle dynamics. In particular, the maximum friction between the tires of the single-track vehicle and the road surface limits the theoretically possible cornering speed. To achieve this theoretically possible cornering speed, it is necessary to utilize the available lane width to allow for the maximum possible curve radius, and often also to exploit the maximum lean angle of the single-track vehicle.

[0016] A rider of a single-track vehicle will generally never reach this theoretically possible cornering speed due to their individual riding characteristics. For example, the rider might not utilize the full lane width and / or might ride through the curve with insufficient lean angle. The rider may also sometimes simply not be interested in achieving the theoretically possible cornering speed. As a result, the rider will likely travel through the curve at a speed that is lower than the theoretically possible cornering speed.

[0017] The approach presented here learns the driver's individual driving characteristics, i.e., their driving style, using the actual speed driven through curves. This individual driving characteristic is learned from the speed in previously driven curves and taken into account when driving through future curves.

[0018] For this purpose, a predefined reference speed is determined for an upcoming curve and adjusted to the driving characteristics using a correction factor. The reference speed represents the speed at which the vehicle statistically travels through the curve. During or after the curve, the actual cornering speed is compared with the reference speed adjusted by the correction factor. The correction factor is then changed so that the adjusted reference speed for the next curve is higher if the driver traveled faster than the adjusted reference speed. Conversely, the correction factor is changed so that the reference speed for the next curve is lower if the driver traveled slower than the adjusted reference speed. R. 415142

[0019] 3 -

[0020] The approach presented here allows, for example, a curve warning function to be adapted to individual driving characteristics. A warning speed, at which the driver is warned that they are approaching the next curve too fast, can be derived from the adapted reference speed. The warning speed can be higher than the adapted reference speed.

[0021] A method for recognizing the driving characteristics of a driver of a single-track vehicle is presented, wherein a reference speed is determined for an upcoming curve through a road curve using at least one curve parameter of the road curve and a stored correction value, wherein after passing through the road curve a comparison is made between the reference speed and a speed driven by the driver in the road curve and the correction value for a subsequent curve through a subsequent road curve is set and stored using a result of the comparison in order to represent the driving characteristics in the correction value.

[0022] Ideas for embodiments of the present invention can be considered to be based, among other things, on the thoughts and findings described below.

[0023] A single-track vehicle can be, for example, a two-wheeler, especially a motorcycle. Unlike a multi-track vehicle, such as a car, a single-track vehicle can be driven at an angle. In particular, a single-track vehicle can be driven at an angle while cornering through a bend in the road. The maximum lean angle is mechanically limited by the vehicle's components that touch down. A rider of a single-track vehicle will most likely never intentionally reach the maximum lean angle. Therefore, they will probably always drive at a lesser lean angle than the maximum. How far the rider utilizes the maximum possible lean angle varies from person to person and significantly determines how fast the rider can drive through a bend in the road. R. 415142

[0024] 4 -

[0025] An expected average speed for a road curve can be determined from a curve parameter. This curve parameter could be, for example, the radius of curvature of the road curve. The curve parameter can be read from a stored database. Alternatively, the curve parameter can directly represent the expected average speed. The average speed is typically the lowest speed reached while cornering. It is reached particularly at or near the apex of the road curve. The average speed represents the average speed of different drivers negotiating the curve. The average speed is individualized for the driver of the single-track vehicle by applying a correction factor to the reference speed. This correction factor can be an absolute value or a factor.The reference speed can therefore be greater than, equal to, or less than the average speed. The correction value can be stored in a memory of the single-track vehicle.

[0026] A recorded speed can be the lowest speed reached in a curve. Alternatively, the recorded speed can be measured at or near the apex of the curve. The recorded speed can be extracted from a speed profile taken while traversing the curve. The recorded speed can be extracted at a minimum point in the speed profile.

[0027] The current speed can be compared to the reference speed. Depending on the result of the comparison, the correction value is adjusted or not. If the current speed is higher than the reference speed, the correction value is adjusted so that the reference speed is higher at the next bend in the road. If the current speed is lower than the reference speed, the correction value is adjusted so that the reference speed is lower at the next bend in the road. The adjusted or unchanged correction value is then saved.

[0028] The curve parameter can be determined using a stored processing rule and a geometric dimension of the road curve. A processing rule can be a mathematical formula or an algorithm. R. 415142

[0029] 5 - or it could be a calculation rule. The curve parameter can be calculated for any road curve.

[0030] The processing rule can represent a statistical relationship between the geometric dimension and an expected curve speed. The expected curve speed can correspond to the average speed. The processing rule can represent a Schimmelpfennig curve for single-track vehicles. The Schimmelpfennig curve can be expressed by a numerical equation. The numerical equation can, for example,

[0031] _ I 1. ' 34 r < 23m

[0032] ^'schiinmelptennig \

[0033] 41.3 r > 23m r: radius in in v: curve speed in km / h. Where v SC himmeipfennig is a predetermined reference velocity for the curve and r is the radius of the curve.

[0034] The geometric dimension can be extracted from a stored road map, for example. This road map might be stored in a navigation database. The geometric dimension could be the minimum curve radius of the road.

[0035] The correction quantity can be a correction factor. The reference speed can be determined using the expected curve speed for the road curve, based on the curve parameter, and the correction factor. In particular, the reference speed can be calculated based on a product of the two quantities mentioned. The correction factor can be increased or decreased. A correction factor can ensure that the reference speed is proportional to the expected curve speed. Alternatively, the correction quantity can be a speed offset that is applied the same way to every road curve. R. 415142

[0036] 6 -

[0037] The correction factor can be increased by a predefined increment if the driving speed is greater than the reference speed. The correction factor can be decreased by the same increment if the driving speed is less than the reference speed. A predefined increment prevents sudden changes in the correction factor. For example, the increment can be between 0.005 and 0.04. Specifically, the increment can be between 0.01 and 0.03.

[0038] The correction factor can be changed if the driving speed deviates from the reference speed by more than one speed tolerance. If the driving speed deviates from the reference speed by less than the speed tolerance, the correction factor can remain the same. The speed tolerance can be, for example, between 1 km / h and 20 km / h. In particular, the speed tolerance can be between 3 km / h and 10 km / h.

[0039] The correction value can be set to a predefined initial value before a journey begins. For example, the correction value can be set so that the reference speed corresponds to the average speed. By resetting to an initial value, the driving characteristics can be relearned for each journey.

[0040] The reference speed can also be determined using a preselected speed offset. For example, the driver can preselect a speed offset to reflect a desired driving style. The speed offset can represent a driver preference. Alternatively, the correction factor can be adjusted to the driver preference using a fixed offset.

[0041] The method is preferably computer-implemented and can be implemented, for example, in software or hardware, or in a hybrid form of software and hardware, for example, in an assistance system.

[0042] The approach presented here further creates an assistance system, whereby the assistance system is trained to perform the steps of a variant of the R. 415142 presented here.

[0043] 7 - provided procedures to be carried out, targeted or implemented in appropriate facilities.

[0044] The assistance system can be an electrical device, such as a control unit, with at least one processing unit for processing signals or data, at least one storage unit for storing signals or data, and at least one interface and / or a communication interface for reading or outputting data embedded in a communication protocol. The processing unit can be, for example, a signal processor, a so-called system ASIC, or a microcontroller for processing sensor signals and outputting data signals depending on the sensor signals. The storage unit can be, for example, flash memory, an EPROM, or a magnetic storage device. The interface can be configured as a sensor interface for reading sensor signals from a sensor and / or as an actuator interface for outputting data signals and / or control signals to an actuator.The communication interface can be configured to read or output data wirelessly and / or via a wired connection. The interfaces can also be software modules, such as those found on a microcontroller alongside other software modules.

[0045] Also advantageous is a computer program product or computer program with program code that can be stored on a machine-readable carrier or storage medium such as a semiconductor memory, a hard disk memory or an optical memory and is used to carry out, implement and / or control the steps of the method according to one of the embodiments described above, in particular if the program product or program is executed on a computer or device.

[0046] It is noted that some of the possible features and advantages of the invention are described herein with reference to different embodiments. A person skilled in the art will recognize that the features of the assistance system and the method can be suitably combined, adapted, or exchanged to arrive at further embodiments of the invention. R. 415142

[0047] 8 -

[0048] Brief description of the drawing

[0049] The following describes embodiments of the invention with reference to the accompanying drawing, whereby neither the drawing nor the description is to be interpreted as limiting the invention.

[0050] Fig. 1 shows a representation of a process flow according to an exemplary embodiment.

[0051] The figure is merely schematic and not to scale. Identical reference symbols denote identical or equivalent features.

[0052] Embodiments of the invention

[0053] Fig. 1 shows a representation of a process flow according to an exemplary embodiment. The process is executed while a single-track vehicle is in motion, using an assistance system of the single-track vehicle. In a first step 100, a curve parameter 102 of an upcoming road curve is determined. Then, in a second step 104, a reference speed 106 for the road curve is determined using a correction factor 108 and the curve parameter 102. In a third step 110, the reference speed 106 is compared with the actual speed 112 driven in the road curve. If the reference speed 106 is greater than the speed 112, the correction factor 108 is changed so that a lower reference speed 106 is determined for the next road curve in the second step 104.If the actual speed 112 is greater than the reference speed 106, the correction parameter 108 is adjusted so that a higher reference speed 106 is determined in the second step 104 at the next curve in the road. The adjusted correction parameter 108 is stored until the next curve in the road. After a certain number of curves, the correction parameter 108 reflects the driving characteristics of the driver of the single-track vehicle.

[0054] In one embodiment, in the first step 100, a geometric quantity 114, or a curve radius or maximum curvature of the next road curve, is determined as the curve parameter 102. (See R. 415142.)

[0055] 9 - in the second step 104, an expected speed 116 is derived from the geometric quantity 114 or the curve radius using a stored processing rule 118, and then the reference speed 106 is determined from the expected speed 116 using the correction quantity 108.

[0056] In one embodiment, processing instruction 116 depicts a Schimmelpfennig curve. The Schimmelpfennig curve describes how quickly a large number of different drivers of single-track vehicles statistically traverse a road curve as a function of the geometric parameter 114.

[0057] In one embodiment, in a fourth step 118, the correction parameter 108 is set to a predetermined initial value 120 at predetermined times. For example, the correction parameter 108 is a correction factor 122 and is set to the initial value 120 of one.

[0058] In one embodiment, the correction parameter 108 is changed by a predefined increment 124 each time the actual speed 112 deviates from the reference speed 106. If the correction parameter 108 is a correction factor 122, the correction factor 122 is increased by the increment 124 if the speed 112 is greater than the reference speed 106. Conversely, the correction factor 122 is decreased by the increment 124 if the speed 112 is less than the reference speed 106. Here, the increment 124 is, for example, 0.02.

[0059] In one embodiment, the geometric dimension 114 is read from a stored road map 126. The road map 126 can be used, for example, for route planning for the single-track vehicle.

[0060] In one embodiment, in a fifth step 128, a curve warning speed 130 is determined for the single-track vehicle using the currently determined reference speed 106 before the road curve. The curve warning speed 130 is used to issue a speed warning to the driver if they approach the road curve too fast. The curve warning speed 130 is higher than the reference speed 106 so that a warning is only issued if the driver actually exceeds the speed limit. R. 415142

[0061] 10 - enters the curve quickly. Since the reference speed of 106 is directly dependent on the learned driving characteristics, the curve warning speeds of 130 are automatically adjusted to these driving characteristics.

[0062] Possible embodiments of the invention are summarized below or presented using slightly different wording.

[0063] A curve velocity prediction using an adaptive Schimmelpfennig curve is presented.

[0064] The curve warning speed depends not only on the curve's characteristics and environmental influences, but also on the driver's driving style. To increase the acceptance of the curve warning system, the approach presented here adjusts the curve warning speed to the driver.

[0065] Traditionally, this individual setting can be adjusted by manually selecting driving modes (calm, normal, sporty). The approach described here involves automatically determining the curve warning speed using algorithms or software based on the driver's driving characteristics.

[0066] Driving characteristics are not constant for every driver. They can change over time. This article presents an algorithm that takes this characteristic into account.

[0067] The curve speed can be predicted using a Schimmelpfennig curve. This curve forms the basis of this algorithm and is further developed.

[0068] The curve warning speed used for the warning is predicted by an adaptive Schimmelpfennig curve. The curve is adjusted in the respective direction by comparing the prediction and the ground truth value (the actual speed driven). The adjustment is made by a factor a (Schimmelpfennig factor), which is multiplied by the raw prediction value of the Schimmelpfennig curve. R. 415142

[0069] 11 -

[0070] By individually adjusting the curve warning speed, the acceptance of the curve warning function is increased. This reduces the occurrence of the potential problem of ignoring the warnings and increases the safety benefit.

[0071] Conventional LSTM models only consider n seconds or n meters before the prediction period for their forecast. However, the parameter n cannot be chosen too high in real-world applications, as motorcycles lack significant computing power. This means that the forecast is conventionally based on only a short segment of the ride, which doesn't reveal much about the overall riding characteristics. The proposed approach of considering individual curves, however, uses only the critical and more informative data (from cornering) for the prediction.

[0072] Additionally, the rider's "riding aggressiveness" can be determined using the Schimmelpfennig factor a. This can be used for various motorcycle functions, such as ADAS, ABS, ACC, Bike Adaptive and / or Driver Recognition.

[0073] The prediction is performed for each curve individually. The system initializes the Schimmelpfennig factor a to one. After each curve is traversed, the predicted value is compared to the actual value, and the Schimmelpfennig factor a is adjusted. If the ground truth is greater than the prediction, a is increased by, for example, 0.02. If the ground truth is less than the prediction, a is decreased by, for example, 0.02. Here, 0.02 represents the adjustment factor, the increment by which the Schimmelpfennig factor a is changed.

[0074] If the driver consistently drives very slowly, the Schimmelpfennig factor a will decrease, and consequently, so will the warning speeds. As time progresses, the number of warnings will therefore increase. Conversely, if the driver drives faster, the number of warnings will decrease again over time. a < 1 means that the driver is driving slower than predicted by the Schimmelpfennig prediction; a > 1 means that the driver is driving faster. Therefore, considering this value already allows conclusions to be drawn about the driving characteristics. R. 415142

[0075] 12 -

[0076] Finally, it should be noted that terms such as "comprising," "encompassing," etc., do not exclude other elements or steps, and terms such as "a" or "an" do not exclude a plurality. Reference numerals in the claims are not to be considered as limitations.

Claims

R. 415142 13 - Claims 1. Method for recognizing a driving characteristic of a driver of a single-track vehicle, wherein a reference speed (106) is determined for an upcoming curve through a road curve using at least one curve parameter (102) of the road curve and a stored correction value (108), wherein after passing through the road curve a comparison is made between the reference speed (106) and a speed (112) driven by the driver in the road curve and the correction value (108) is set and stored for a subsequent curve through a subsequent road curve using a result of the comparison in order to represent the driving characteristic.

2. Method according to claim 1, wherein the curve parameter (102) is determined using a stored processing instruction (118) and a geometric dimension (114) of the road curve.

3. Method according to claim 2, wherein the processing instruction represents a statistical relationship between the geometric quantity (114) and an expected curve speed (116).

4. Method according to one of claims 2 to 3, wherein the geometric size (114) is read from a stored road map (126).

5. Method according to one of the preceding claims, wherein the correction quantity (108) is a correction factor (122) and the reference speed (106) is determined using an expected curve speed (116) for the road curve based on the curve parameter (102) and the correction factor (108). R. 415142 14 - 6. Method according to claim 5, wherein the correction factor (108) is increased by a predefined increment (124) when the speed driven (112) is greater than the reference speed (106) and decreased by the increment (124) when the speed driven (112) is less than the reference speed (106).

7. Method according to claim 6, wherein the correction factor (108) is changed when the speed driven (112) deviates from the reference speed (106) by more than one speed tolerance.

8. Method according to one of the preceding claims, wherein the correction parameter (108) is set to a predefined initial value (120) before the start of a journey.

9. Method according to one of the preceding claims, wherein the reference velocity (106) is further determined using a preselected velocity offset.

10. Assistance system, wherein the assistance system is configured to execute, implement and / or control the method according to one of the preceding claims in appropriate facilities.

11. Computer program product configured to instruct a processor, when the computer program product is executed, to execute, implement and / or control the method according to any one of claims 1 to 9.

12. Machine-readable storage medium on which the computer program product according to claim 11 is stored.

Images