SYSTEM AND METHOD FOR SETTING A VEHICLE'S SPEED LIMIT BASED ON ENVIRONMENTAL CONDITIONS

Abstract

The present disclosure provides a system 102 and a method 300 for setting a vehicle's speed limit based on environmental conditions. The method 300 comprises detecting parameters 302 and a friction level along a route. Furthermore, the method 300 comprises predicting a total rainfall amount 304 based on the parameters and the total rainfall amount. The method 300 also comprises determining a confidence level 306 for the prediction. Finally, the method 300 comprises setting a vehicle speed limit 308 based on the prediction.System 102 and Procedure 300 therefore overcome the limitations of existing systems that produce false positives by comparing predicted values ​​with individual sensor inputs, normalizing error values, and dynamically adjusting speed based on real-time environmental conditions. By predicting confidence levels from environmental data, this disclosure provides accurate speed settings to improve safety and efficiency compared to static or manual procedures.

Description

TECHNICAL AREA

[0001] The present disclosure relates to vehicle safety systems and in particular to a system and a method for setting a speed limit of a vehicle based on environmental conditions, such as road wetness and precipitation, in order to improve vehicle safety. BACKGROUND

[0002] Vehicle safety systems have become increasingly sophisticated in recent years, incorporating various sensors and control units to improve the safety of drivers and passengers. A particular concern is the impact of adverse weather conditions, especially rain, on vehicle performance and safety.

[0003] Rainfall can affect road conditions and reduce traction between tires and the road surface. This reduction in traction increases the risk of aquaplaning, in which a layer of water forms between the tires and the road, leading to a loss of steering control and braking effectiveness. The severity of this risk depends on factors such as rainfall intensity, road surface conditions, vehicle speed, and tire condition. Existing solutions primarily rely on optical sensors and the condition of windshield wipers to detect rain. These methods are prone to false alarms, which can trigger unnecessary speed limits. Some advanced systems incorporate cameras and additional sensors such as humidity, temperature, and pressure sensors.Camera-based methods, however, can lose performance when the field of view is obstructed or when computing demands are high. A crucial shortcoming of existing solutions is their inability to account for scenarios where it is not currently raining, but the road is wet and slippery due to previous rainfall. Conversely, existing systems cannot distinguish between situations where it is raining slightly, but there is only a negligible difference in friction and tire grip on the road. These nuanced scenarios are not adequately addressed by current technologies, leading to potential safety risks.

[0004] Furthermore, the speed limits considered in existing solutions are often fixed and do not account for constantly changing weather conditions and their impact on wetness and road friction. Existing systems typically consider either the aquaplaning speed or the critical speed limit, but not both, meaning that important safety thresholds may be overlooked. Another significant limitation of existing solutions is the lack of robust mechanisms for validating the data in these systems. Without effective means of preventing false sensor alarms, these existing systems can trigger sudden speed limits in situations where they are not needed, potentially endangering surrounding vehicles.

[0005] Many techniques have been developed to solve the aforementioned problems. For example, patent document US11535258B2 describes a method for determining and issuing a rain warning based on the evaluation of sensor data and the calculation of a confidence level for the weather conditions in a specified region. Another patent document, CN112884288B, describes a system for evaluating driving safety in rain and fog on highways. This system includes a module for estimating the coefficient of road friction, a speed limit model, a simulation platform, and a module for assessing the degree of safety. It determines road friction, limits speed, and classifies safety levels based on evaluation parameters.Another patent document, CN114360270B, describes a method and system for determining the permissible maximum speed on highways in adverse weather conditions using traffic meteorological data to analyze the visibility distance when parking, the visibility distance when making decisions, the sliding speed and driving stability, thereby improving traffic safety and applicability.

[0006] Conventional methods and systems lack a comprehensive approach to accurately predicting speed limits based on real-time environmental data and the dynamic response of multiple sensors. Furthermore, they do not consider factors such as road friction or aquaplaning risk, nor do they provide real-time speed adjustments based on immediate changes in rainfall intensity or vehicle stability. Conventional methods and systems also lack the integration of multiple sensor inputs to provide precise, context-aware speed recommendations. Therefore, they are limited to static evaluations and cannot effectively respond to rapid changes in road and weather conditions, potentially compromising safety and efficiency.

[0007] Therefore, there is a need for a more reliable and adaptable system that eliminates at least the aforementioned disadvantages and all other shortcomings, or at least provides a valuable alternative to existing procedures and systems. SUMMARY

[0008] A general objective of the present disclosure is to provide a system and a method for dynamically adjusting a vehicle's speed limit based on real-time detection of environmental factors, such as rain and road wetness, thereby ensuring improved vehicle safety.

[0009] One objective of the present disclosure is to eliminate discrepancies between sensor inputs and actual environmental and road conditions. Another objective of the present disclosure is to enable a safe speed estimation when individual sensor data are unreliable or prone to false positives. A further objective of the present disclosure is to estimate safe speed limits in various weather scenarios, including situations where the road remains wet after the rain stops or where the rain has minimal impact on road friction. A further objective of the present disclosure is to measure both the aquaplaning speed and the critical speed and to use these factors to dynamically set a speed limit for a vehicle based on real-time environmental data.

[0010] One aspect of the present disclosure relates to a method for setting a vehicle's speed limit. The method comprises detecting, by one or more processors associated with a system, one or more parameters associated with an environment and a friction level along a route. Furthermore, the method comprises the prediction of a total rainfall level by the one or more processors, based on the one or more parameters and the friction level, and the determination of a confidence level for the prediction by the one or more processors. The method also includes the setting of the vehicle's speed limit by the one or more processors based on the determination of the confidence level.

[0011] Another aspect of the present disclosure relates to a system for setting a vehicle's speed limit. The system comprises one or more processors and a memory operationally coupled to the one or more processors. The memory contains one or more instructions which, when executed, cause the processor to detect one or more parameters associated with an environment and a friction level. Furthermore, the one or more processors are configured to predict a total rainfall amount based on the one or more parameters and the friction level. In addition, the one or more processors can be configured to determine a confidence level for the prediction and to set the vehicle's speed limit based on this confidence level determination.

[0012] Various objects, features, aspects and advantages of the subject matter according to the invention will become clearer from the following detailed description of a preferred embodiment together with the accompanying drawing figures, in which the same numbers represent the same components. BRIEF DESCRIPTION OF THE DRAWINGS Fig. Figure 1 shows an exemplary block diagram of a system for setting a speed limit of a vehicle based on conditions in the environment, according to an embodiment of the present disclosure. Fig. Figure 2 shows an exemplary flowchart for estimating a safe maximum speed of the vehicle based on weather conditions according to an embodiment of the present disclosure. Fig.Figure 3 shows an exemplary flowchart of a method for setting the maximum speed of the vehicle based on the conditions in the environment according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] In the following, an embodiment of the disclosure, illustrated in the accompanying drawings, is described in detail. The embodiments are described in such detail that the disclosure becomes clearly understandable. However, the intention is not to limit the foreseeable variations of an embodiment with the necessary detail; rather, all modifications, equivalents, and alternatives that fall within the scope of the present disclosure, as defined by the accompanying claims, are to be covered.

[0014] One embodiment described here relates to the field of weather-dependent speed limits. In particular, the present disclosure provides a system and a method for setting a speed limit for a vehicle based on weather conditions in real time.

[0015] In one aspect, the present disclosure relates to the system and method for weather-dependent speed limiting using multiple sensor inputs. The method involves generating and processing real-time data from various sensors, including optical sensors, road wetness sensors, and friction sensors. The system aggregates and fuses this real-time sensor data to calculate rainfall and determine a confidence level for the calculated rainfall. This information about the rainfall and the confidence level is then used to determine safe speed limits based on aquaplaning and critical speeds. The system can generate a recommended speed limit that takes into account dynamic changes in road conditions and is set based on the calculated confidence level.

[0016] Various embodiments of the present disclosure are described with reference to Fig. 1 to 3 explained in more detail. 1-3.

[0017] Referring to block diagram 100 of Fig. 1 A system 102 for setting a speed limit of a vehicle using one or more environmental parameters (e.g., amount of precipitation and degree of wetness) is described according to an embodiment of the present disclosure. The vehicle may include, but is not limited to, two-wheeled vehicles, three-wheeled vehicles, four-wheeled vehicles, cars, vans, trucks, buses, and the like. In one embodiment, the vehicle may be an ego vehicle, i.e., a vehicle capable of perceiving its environment. In another embodiment, the vehicle may be a self-driving vehicle configured to perform autonomous navigation actions.

[0018] In an embodiment as shown in block diagram 100 of Fig.As shown in Figure 1, the system 102 can contain one or more processors 104, as shown in block diagram 100. The one or more processor(s) 104 can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and / or any devices that manipulate data based on operating instructions. Among other capabilities, the one or more processors 104 can be configured to retrieve and execute computer-readable instructions stored in a memory 106. The memory 106 can store one or more computer-readable instructions or routines that can be retrieved and executed to create or share the data units via a network service. The memory 106 can include any non-volatile storage device, such as a memory chip.volatile memory such as Random Access Memory (RAM) or non-volatile memory such as Erasable Programmable Read-Only Memory (EPROM), Flash memory, and the like.

[0019] In one embodiment, the system 102 may also include one or more interfaces 108. The interface(s) 108 may include a variety of interfaces, such as interfaces for data input and output devices, referred to as input / output (I / O) devices, storage devices, and the like. The interface(s) 108 may provide a communication path for one or more components of the system 102. Examples of such components include the processing machine(s) 110 and the database 126. In one embodiment, the database 126 may store data generated or received by the system 102.

[0020] In one embodiment, the processing machine(s) 110 can be implemented as a combination of hardware and programming (e.g., programmable instructions) to implement one or more functions of the processing machine(s) 110. In the examples described here, such combinations of hardware and programming can be implemented in various ways. For example, the programming for the processing machine(s) 110 can consist of processor-executable instructions stored on a non-volatile, machine-readable storage medium, and the hardware for the processing machine(s) 110 can include a processing resource (e.g., a control unit) to execute such instructions. In another embodiment, the processing machine(s) 110 can be implemented by electronic circuits.Database 126 can contain data that is either stored or generated as a result of functionalities implemented by one of the components of the processing machine(s) 110.

[0021] In one embodiment, the processing machine(s) 110 may comprise a machine for detecting environmental parameters 112, a data processing machine 114, a machine for predicting the total rainfall level and confidence level 116, a route analysis machine 118, a speed limit setting machine 120, a vehicle control machine 122, and other machine(s) 124. The other machine(s) 124 may implement functionalities that complement the applications / functions performed by the system 102.

[0022] In one embodiment, the environmental parameter detection machine 112 can be configured to detect one or more environmental parameters and a friction level during the vehicle's movement on the road using one or more sensors (not shown in the figures) associated with the system 102. These parameters may include, among others, the amount of precipitation and the degree of wetness on the road. In another embodiment, the environmental parameter detection machine 112 can work in conjunction with various sensors (not shown in the figures), such as optical sensors, road wetness sensors, and friction sensors, to collect data on environmental conditions. For example, the optical sensors can detect the presence and intensity of precipitation, and the road wetness sensors can measure the thickness of the water film on a road surface (e.g.,The sensors measure the surface of the road surface, and the friction sensors can measure the coefficient of friction between the vehicle's tires (e.g., wheels) and the road surface. The data that the detection machine 112 receives from the sensors includes data on rainfall level, wetness level, and friction.

[0023] In one embodiment, the processing machine 114 can be configured to process the data acquired by the detection machine 112 for environmental parameters. For example, the processing machine 114 can generate a weighting value corresponding to each of the parameters received from the sensors. The weighting values ​​can represent the relative importance or reliability of the individual sensor data. For instance, at low speed and in heavy rain, the data from the road wetness sensor can be weighted less than the data from the optical sensor. The processing machine 114 can also combine this sensor data, for example, using methods such as weighted averaging or more complex fusion techniques. The processing machine 114 can calculate the total rainfall, providing a consolidated representation of the environmental conditions.

[0024] In one embodiment, the machine for predicting total rainfall and confidence level 116 can be configured to predict an individual rainfall level based on the weighting value corresponding to each parameter. In another embodiment, the machine for predicting total rainfall and confidence level 116 can be configured to compare the total rainfall level determined by the data processing machine 114 with the individual rainfall level corresponding to each parameter. The machine for predicting total rainfall and confidence level 116 can then determine an error value between the total rainfall and the individual rainfall based on this comparison. For example, if all sensors are in good agreement, the error values ​​can be small, resulting in a high confidence level.The machine for predicting total rainfall and confidence level 116 can normalize the error value to determine the confidence level. In an exemplary embodiment, the weighting value for the parameters can be used to predict the total rainfall. For example, the error value for each sensor input can be calculated as the difference between the rainfall indicated by each input and the predicted total rainfall using the corresponding weighting value. The error value is then normalized to obtain a normalized error for each sensor input. The normalized errors are then averaged using a simple mean and then... 1−δ^¯l This is used to obtain the confidence level as a percentage. The confidence value indicates the error value as a percentage.

[0025] In one embodiment, the route analysis engine 118 can be configured to analyze the route the vehicle is traveling on. This can include determining a curvature profile of the route, which, in conjunction with environmental parameters and the confidence level, can be used to set the vehicle's maximum speed. The curvature profile can be obtained from map data, Global Positioning System (GPS) information, or real-time acquisition of the road ahead. For example, the route analysis engine 118 can determine factors such as the radius of curvature at various points along the route, which can be used to determine safe speeds, especially in wet or slippery conditions.

[0026] In one embodiment, the speed limit setting system 120 can be configured to set the vehicle's speed limit based on the outputs of other systems. For example, the speed limit setting machine 120 can estimate an aquaplaning speed and a critical speed based on the total rainfall level and estimate the speed limit based on the aquaplaning speed, the critical speed, and the confidence level. In one embodiment, the critical speed can be determined by considering the radius (e.g., the curvature profile) of the road curvature along with the rainfall amount, the amount of friction, and the road wetness.If the confidence level exceeds a predefined threshold, the speed limit setting machine 120 can set the safe maximum speed to ensure vehicle safety. The maximum speed is determined based on the aquaplaning speed and the critical speed to ensure the vehicle remains within a safe operating range.

[0027] Furthermore, the system 102 continuously monitors changes in speed limits (ΔV). L), where the current limit is set based on the previous limit and the confidence level (ε). The final safe speed limit is then determined based on the confidence-adjusted model, thus minimizing the risk of false alarms and enabling dynamic speed adjustment based on changing road conditions.

[0028] In one embodiment, the control unit 122 can be configured to control the vehicle's speed based on the set maximum speed. The vehicle control unit 122 can interface with the vehicle's speed control systems, such as the vehicle's electronic control unit (ECU), to ensure that the vehicle operates within the set safe maximum speed. For example, the vehicle control unit 122 can send commands via the ECU to the throttle control, the braking system, and potentially even the vehicle's steering systems in more advanced autonomous vehicles. The control unit 122 can make incremental speed changes to ensure occupant comfort and can also consider factors such as traffic conditions and legal speed limits when making its control decisions.

[0029] In one embodiment, the system 102 can be configured to adjust the vehicle's speed limit when the machine 116 predicts that the confidence level will exceed a predefined threshold based on the detected parameters. In this way, the system 102 can proactively adjust the vehicle's speed limit when a change in environmental conditions is detected, thereby improving safety and performance. In one embodiment, high confidence (above a predefined condition) can refer to certainty about the environmental conditions, and a new safe speed can be estimated, while low confidence (below a predefined threshold) refers to uncertainty and no updates to the set speed limit.

[0030] In one embodiment, the data stored in database 126 can be used as historical data for future predictions. Furthermore, in one example, database 126 can contain map data, which may include the curvature profile of the route. In exemplary embodiments, database 126 can be configured to store data corresponding to one or more parameters associated with the environment as the vehicle moves along the route. In exemplary embodiments, database 126 can contain data relating to confidence levels, weight values, estimated speeds, set speed limits, and the like.

[0031] Fig. Figure 2 shows a flowchart 200 for setting a speed limit for a vehicle according to an embodiment of the present disclosure.

[0032] In one embodiment, the system 102 receives rainfall data from a rain sensor 204 in step 202. For example, the rainfall data can be used to determine the current intensity of precipitation in the environment where the vehicle is traveling along a route. In one example, a value from the rain sensor 204 can be represented by x1 and provides a set of values ​​indicating the amount of rainfall. For instance, the rain sensor 204 can detect raindrops when they fall on the vehicle's windshield and output a signal with discrete values.

[0033] In one embodiment, the system 102 receives road moisture data from a moisture sensor 208 in step 206. In one example, the road moisture data indicates the moisture present on a road surface (e.g., a route surface), which can be influenced by factors such as rain, snowmelt, or standing water. In one example, the moisture sensor 208 can be represented by x2 and provides a set of continuous values ​​indicating the water film thickness on the road surface.

[0034] In one embodiment, the system 102 receives longitudinal friction data from a control unit 212 in step 210. For example, the friction value data can provide information about the coefficient of friction between the vehicle's tires (e.g., wheels) and the road surface, which can be affected by wet or slippery conditions. For example, the friction value can be represented by x3 and provides a set of values ​​indicating the degree of friction.

[0035] In one embodiment, system 102 calculates the total rainfall in step 214 based on the inputs obtained in steps 202, 206, and 210. This calculation can involve processing and combining the various sensor measurements to arrive at an assessment of the current rainfall and road conditions. In one example, the rainfall amount, which is represented as R iThis can be described as a prediction of the rainfall intensity for each given sensor with the value x. i As shown in Table 1, the range of rainfall, R i , as [R min , R max ] can be determined. The range of the value x i The individual sensor data can be represented as [X i,min , X i,max ] will be determined. Table 1 Variable symbol Area WBSL Rainfall Level R i [R min R max ] Optical rain sensor x 1 [x 1,min x 1,max ] Sensor for road wetness x 2 [x 2,min x 2,max ] Degree of friction x 3 [x 3,min x 3,max ] Rainfall forecast H [R min R max ]

[0036] In one example, a polynomial function n th -Order R i , as indicated below, can be derived individually to obtain the individual sensor data x i to convert into a rainfall amount. Ri(xi)=c0+c1xi+c2xi2+⋯+cnxin→[xi,minxi,max], where the coefficients c o , c1, ... c n can be determined using curve fitting methods.

[0037] In addition to the polynomial function, System 102 can use a generalized function R. iwhich contains the polynomial, logarithmic and exponential components, as shown below Ri(xi)=f(xi)=∑k=0nckxik+A.eB.xi+C.log(D.xi), where: f(x i ) the generalized function that uses the sensor data x i on the amount of rainfall R i The first term represents a polynomial function of order n. th A and B are coefficients for the exponential term, where e is the base of the natural logarithm. C and D are the coefficients for the logarithmic term. The logarithmic function is given by... i >0 is defined because the logarithm of zero or negative values ​​is undefined.

[0038] Therefore, for each sensor with data x1, x2, x3, a function for calculating the rainfall depth R1, R2, R3 can be estimated. For example, if the data x iIf one of the sensors has a limited resolution, it may be undesirable to estimate a continuous range of rainfall values. In such a situation, the function R can be used. i instead, it can be estimated as a piecewise function, which may include several polynomial functions and / or logarithmic and exponential functions that can interpolate the values ​​of the rainfall level for a finite range of sensor inputs. In one embodiment, the interpolation can also benefit from the use of one of the polynomial functions that is available for another sensor R. j (x j ) were estimated within finite intervals. For example: Ri(xi,xj)={Rj(xj),if g(xi,xj)=1c0+c1xi+c2xi2+⋯+cnxin,otherwise where g(x i , x j ) defines a function with a logical expression to determine the appropriate function for the interval.

[0039] In one example, a weighted average expression can be used to express the individual rainfall values ​​R1, R2 ... R n to combine into a single rainfall forecast h by using: h(x1,x2,…xn)=∑1npiRi∑1npi where the coefficients p1, p2 ... p n Weighting coefficients are values ​​that can be adjusted depending on the reliability and accuracy of an individual signal.

[0040] In one example, the error in the amount of rainfall R can be i (x i ) of each sensor compared to the total rainfall forecast h as δ i can be calculated, which can be given by: δi=|h−Ri|

[0041] In one example, the individual errors of the sensor in determining the rainfall depth R can be shown. i (x i ) normalized with respect to the corresponding coefficient p ifrom the weighted mean expression to be normalized δ^¯l which can be represented as follows: δ^¯l=piδi∑1npi

[0042] Therefore, System 102 calculates the rainfall prediction, which combines the various sensor inputs and provides an overall assessment of the current rainfall intensity in the vehicle. Furthermore, System 102 also calculates a confidence level for the prediction, which can be monitored using a threshold value to determine whether the predicted rainfall amount is reliable or unreliable.

[0043] Accordingly, in one embodiment, the system 102 determines the confidence level in step 216. For example, the confidence level can be derived from the sensor data and the calculated rainfall amount and represents the certainty of the system 102 in its assessment of the current weather conditions and road conditions.

[0044] In one embodiment, a weighted value can be generated to determine the total rainfall, corresponding to each parameter received from each sensor. Furthermore, a weighted average value is determined based on this weighted value. Finally, the total rainfall can be calculated based on this weighted average value.

[0045] In one embodiment, the confidence value is calculated by comparing the total rainfall value and the individual rainfall value corresponding to each parameter in order to determine the error value between the total rainfall value and the individual rainfall value based on the comparison, and the error value is normalized to determine the confidence value. In one embodiment, an average of the normalized errors of each sensor in determining the rainfall level R can be used. i (x i ) are taken as δ^¯l and then converted into a percentage error for determining the confidence level ε. ε=1−δ^¯l

[0046] In one embodiment, the system 102 can estimate an aquaplaning speed based on the total rainfall in step 218 and estimate a critical speed based on the total rainfall in step 220. In another embodiment, the system 102 evaluates in step 226 whether the determined confidence level is above the predefined threshold. In one example, the procedure returns to step 202 to collect new sensor data if the confidence level is not above the predefined range. In one example, an equation for the aquaplaning speed v is used. H The estimation of a speed limit when the vehicle is traveling in a straight line, using the value of the water film thickness, can be represented as follows: vH=508QB*t*Ci where Q is the wheel load in kilogram-force (KP), B represents the maximum width of the tire contact patch in mm, t stands for the thickness of the water film in mm, and C i represents the hydrodynamic buoyancy coefficient.

[0047] In another example, the water film thickness can be replaced by the predicted rainfall amount, resulting in a new equation for the aquaplaning speed, which can be represented as follows: vH=508QB*f1(h)*Ci where f1(h) is a function that estimates the water film thickness from the rainfall height; this function can be derived according to the specifications of the sensors.

[0048] In one embodiment, the system 102 estimates the critical speed in step 220. In one example, the estimation of the critical speed can take into account, in addition to the data on weather conditions and road condition, the data on road curvature shown in step 222.

[0049] In one example, an equation for the critical velocity v can be given. c , which estimates the speed at which the frictional force exceeds the centripetal force, can be represented: m(vc)2|r|≤μma

[0050] In one example, the coefficient of friction µ can be replaced by the predicted rainfall height and rearranged to obtain a new equation for the critical speed, which can be represented as follows: vc=μa|r|→vc=f2(h)a|r| where f2(h) is a function for estimating the coefficient of friction based on the predicted amount of rainfall, h is the level of rainfall intensity, a is the parameter for lateral acceleration, and r is the radius of curvature.

[0051] In one embodiment, the function f2(h) can be derived from the surface friction map data of the friction sensor, where f2(h) is a function that estimates the coefficient of friction based on the predicted amount of rainfall.

[0052] In one embodiment, the system 102 estimates a safe speed limit in step 224 based on the aquaplaning speed, the critical speed, and the confidence level.

[0053] In one embodiment, in step 228, the system 102 either sets a new speed limit or removes an existing speed limit, based on the safe speed limit estimated in step 224 and whether the confidence level exceeds the predefined threshold in step 226.

[0054] In one example, the minimum of the aquaplaning speed and the critical speed can be used to determine the safe maximum speed and can be represented as follows: VL=0.5*[vH+vC−|vH−vC|] where v H the aquaplaning speed and v C the critical speed.

[0055] In one example, the safe speed limit, V LThe confidence level and the previous speed limit are set to account for any uncertainties in calculating the rainfall level due to different inputs, and the setting can be represented as follows: ΔVL=VL−VL(n−1) Lm=VL−(K∗(1−ε)∗ΔVL) where V L the current speed limit is V L(n-1) where the previously differing speed limit is, ε is the confidence level of the rainfall value, and K is the confidence weighting factor.

[0056] In one example, the estimated safe maximum speed can be rounded to the nearest multiple of j by using the following equation. Lm=j⌊Lmj+12⌋

[0057] In one embodiment, system 102 can also be configured to apply the safe speed limit proposal only when the confidence level ε exceeds a specified threshold C1. The resulting safe speed limit can be given by: S(Lm)={No limit,if ε <C1Lm,if ε≥C1

[0058] In one example, the amount of rainfall can be calculated as shown below, where it is a normalized rainfall forecast that is a continuous value between 1 and 6, where 1 means "no rain" and 6 means "very heavy rain", with a mapping that corresponds to the values ​​of the rain sensor according to Table 2. Table 2 y n Rainfall amount x 1 Rain sensor x 2 Road wetness sensor 1 No rain (0) 0 2 Very little rainfall (1) 1 to 50 3 Low rainfall (2) 51 to 100 4 Average rainfall (3) 101 to 150 5 Heavy rain (4) 151 to 200 6 Very heavy rain (5) 201 to 250

[0059] As previously explained, the rain sensor (x1) detects raindrops on the windshield and outputs a signal with six discrete values ​​(range: no rain, very light rain, medium rain, heavy rain, very heavy rain). The road wetness sensor (x2) measures the water film thickness on the road and outputs a signal with a continuous range from 0 to 250. The rainfall amounts from x1 and x2 are calculated using functions y1 and y2, which can be specified as follows: y1(x1)=x1+1→[0,5] y2(x2)=0.02x2+1→[0,250]

[0060] For example: The longitudinal control unit (x3) measures the friction of the vehicle's tires (e.g., wheels) on the road and outputs a signal with three discrete values ​​(range: low, medium, high). Since the range of the friction signal is limited, the road wetness is also taken into account when calculating the amount of rain for this input x3, according to function y3. The consistency between friction and wetness is checked using function g1, and a logical value is returned. If the friction value and the road wetness match, the road wetness is calculated using function y2; otherwise, a statically mapped amount of rain is calculated according to function g2. In this case, g1(x3,x2)={1,if(x3=3)∧(0≤x2≤50)1,if(x3=2)∧(50 <x2≤150)1,if(x3=1)∧(150<x2≤250)0,otherwise g2(x3)=7−2x3→[1,3] y3(x3,x2)={y2(x2),if g(x3,x2)=1g2(x3),otherwise As previously explained, the confidence level can be calculated using the weighted average of the outputs of functions y1, y2, y3 with the weighting coefficients p1, p2, p3, which can be adjusted depending on the reliability / accuracy of the sensor. The discrepancy between the inputs can be quantified for the confidence level based on the errors between the rain forecasts. i is the error between a single rainfall forecast and the weighted average rainfall forecast, which can then be normalized to δl^. The average of these errors, δl^¯ is taken and converted into a percentage error for the prediction of the confidence level ε, where h(x1,x2,x3)=∑13piyi∑13pi δi=|h−yi| δl^=piδi∑13pi ε=1−δl^¯

[0061] In one embodiment, the confidence level ε can reach a peak when the sensor data matches the rainfall amount. In one example, the confidence level ε can range between 30% and 100%, but can vary depending on the configured sensor coefficients p1, p2, p3. In another example, the forecast is only trusted if the calculated confidence value is higher than a configurable threshold, e.g., 70%, to avoid false positives.

[0062] Accordingly, the System 102 can constantly monitor and react to changing weather conditions and road conditions to ensure that the vehicle's speed is always adapted to the current situation.

[0063] In Fig. Figure 3 shows a procedure 300 for setting a speed limit for a vehicle. Procedure 300 can be implemented by System 102 and / or the ECU in the vehicle.

[0064] In Block 302, Method 300 comprises the detection, by one or more processors (e.g., 104), such as the processor (e.g., 104) associated with the system (e.g., 102), of one or more parameters associated with an environment and a friction level during the movement of a vehicle along a route, via one or more sensors associated with the system (e.g., 102). In one example, the one or more parameters may include at least one of a precipitation level and a wetness level on the route. In another example, the one or more sensors may include an optical sensor configured to detect precipitation or snowfall, a road wetness sensor configured to measure the water film thickness on the road surface, and a friction sensor configured to measure the friction between a vehicle tire and the road surface.

[0065] In one embodiment, the optical sensor, the road wetness sensor, can be an electrical conductivity sensor or a capacitive sensor that measures the amount of water on the road surface. The friction sensor can be integrated into the tires or the wheel suspension system of the vehicle to continuously monitor the interaction between the tires and the road surface. In one embodiment, the method 300 comprises detecting the friction level between each wheel assigned to the vehicle and a surface of the road by one or more processors 104.

[0066] In block 304, the method 300 comprises the prediction of a total rainfall level by the one or more processors 104 based on the one or more parameters and the friction level. In one embodiment, the method 300 for predicting the total rainfall amount may include generating a weighting value corresponding to each parameter received from the sensors and determining a weighted average value based on the weighting value.

[0067] In 306, the method 300 comprises determining a confidence level for the prediction by the one or more processors 104. In one embodiment, the method 300 comprises predicting an individual rainfall level corresponding to each of the one or more parameters, based on the weighting value, and comparing the previously calculated average weighting value with each individual weighting value corresponding to the parameters. Furthermore, an error value is determined representing the differences between the total rainfall and the individual rainfall. These error values ​​can be normalized to determine the confidence value.

[0068] In one embodiment, the method 300 can include estimating an aquaplaning speed and a critical speed by the one or more processors 104 based on the determination of the total rainfall amount, and estimating the speed limit by the one or more processors 104 based on the aquaplaning speed, the critical speed, and the confidence level. In another embodiment, the method 300 can determine a curvature profile of the route by the one or more processors 104 and determine the critical speed based on the curvature profile of the route by the one or more processors 104.

[0069] In block 308, the method 300 comprises the setting of the vehicle's speed limit by the one or more processors 104. In one embodiment, the method 300 comprises the determination by the one or more processors 104 that the confidence level is above a predefined threshold based on the estimated speed limit, and the setting of the speed limit by the one or more processors 104 in response to the determination that the confidence level is above the predefined threshold.

[0070] The vehicle's ECU can then be configured to set the vehicle speed based on the predicted confidence level and the determined speed limit. Once the aquaplaning speed and critical speed are calculated, the maximum speed is set based on the confidence level. The confidence level reflects the uncertainty or reliability of the sensor inputs and helps fine-tune the speed limit to ensure safe operation under the current conditions and road characteristics. BENEFITS OF THE PRESENT DISCLOSURE

[0071] This disclosure provides a system and method for weather-based speed limiting using multiple sensor inputs and confidence level calculations.

[0072] This disclosure resolves discrepancies between different sensor inputs to allow for a more accurate assessment of the road's condition.

[0073] This disclosure estimates safe speed limits when individual sensor data may be noisy or unreliable due to environmental factors.

[0074] The present disclosure dynamically sets speed limits for vehicles based on real-time conditions in the environment, even if existing data on speed limits may be outdated or inaccurate.

[0075] This disclosure improves vehicle safety by taking into account both the aquaplaning speed and the critical speed based on the curvature of the road.

[0076] This disclosure improves the reliability of setting speed limits by calculating and using a confidence level for the calculated rainfall level.

[0077] This disclosure enables the individual setting of speed limits based on specific vehicle parameters, thereby improving applicability for different vehicle types. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] US 11535258B2

[0005] CN 112884288B

[0005] CN 114360270B

[0005]

Claims

[1] Method (300) for setting a speed limit of a vehicle based on environmental conditions, comprising: Detect (302), by one or more processors (104) assigned to a system (102), one or more parameters associated with an environment and a friction level along a route; Prediction (304) of a total rainfall level by the one or more processors (104), based on the one or more parameters and the friction level; Determination (306) by one or more processors (104) of a confidence level for the prediction; and Setting (308) the speed limit of the vehicle by the one or more processors (104) based on the determination of the confidence level. [2] Method (300) according to claim 1, wherein the one or more parameters are received from one or more sensors associated with the system (102), and wherein the one or more parameters include at least one of the following parameters: a precipitation level and a wetness level on the route. [3] Method (300) according to claim 1, wherein the prediction (304) of the total rainfall by the one or more processors (104) comprises: Generation, by the one or more processors (104), of a weighting value corresponding to each of the one or more parameters received from each of the one or more sensors associated with the system (102); Determination, by one or more processors (104), of a weighted average value based on the weighting value; and Determination of the total rainfall by the one or more processors (104) based on the weighted average. [4] Method (300) according to claim 3, wherein the determination (306) of the confidence level by the one or more processors (104) comprises: Prediction, by one or more processors (104), of an individual rainfall level corresponding to each of the one or more parameters, based on the weighting value; Comparing the total rainfall and the individual rainfall corresponding to each of the one or more parameters by the one or more processors (104); Determine, by one or more processors (104), an error value between the total rainfall level and the individual rainfall level based on the comparison; and Normalization of the error value by one or more processors (104) to determine the confidence value. [5] Method (300) according to claim 4, comprising: Estimating an aquaplaning speed and a critical speed by the one or more processors (104) based on the determination of the total rainfall; and Estimating the speed limit by the one or more processors (104) based on the aquaplaning speed, the critical speed and the confidence level. [6] Method (300) according to claim 5, comprising estimating the critical speed by the one or more processors (104): Determination of a curvature profile of the path by one or more processors (104); and Determination of the critical speed by one or more processors (104) based on the curvature profile of the track. [7] Method (300) according to claim 5, wherein the setting (308) of the speed limit by the one or more processors (104) comprises: Determination by one or more processors (104) that the confidence level is above a predefined threshold, based on the estimated speed limit; and Setting the speed limit by one or more processors (104) in response to the determination that the confidence level is greater than the predefined threshold. [8] Method (300) according to claim 1, comprising: Detecting the friction level between each wheel assigned to the vehicle and a surface of the track by one or more processors (104). [9] System (102) for setting a speed limit of a vehicle based on conditions in the environment, comprising: one or more processors (104); and a memory (106) that is operationally coupled to the one or more processors (104), wherein the memory (106) comprises one or more instructions which, when executed, cause the one or more processors (104) to: to detect one or more parameters that are associated with an environment and a degree of friction along a route; to predict a total rainfall amount based on one or more parameters and the amount of friction; to determine a confidence level for the prediction; and to set the maximum speed of the vehicle based on the determination of the confidence level. [10] System (102) according to claim 9, wherein for predicting the total rainfall amount, one or more processors (104) are configured such that they: generates a weighting value that corresponds to each of the one or more parameters received from each of the one or more sensors; a weighted average value is determined based on the weighting value; and the total rainfall amount is determined based on the weighted average value.

Images