WO2022071415A1 - Stop determining device - Google Patents

Stop determining device Download PDF

Info

Publication number
WO2022071415A1
WO2022071415A1 PCT/JP2021/035923 JP2021035923W WO2022071415A1 WO 2022071415 A1 WO2022071415 A1 WO 2022071415A1 JP 2021035923 W JP2021035923 W JP 2021035923W WO 2022071415 A1 WO2022071415 A1 WO 2022071415A1
Authority
WO
WIPO (PCT)
Prior art keywords
acceleration
value
vehicle
wheel speed
identification
Prior art date
Application number
PCT/JP2021/035923
Other languages
French (fr)
Japanese (ja)
Inventor
由多 伊藤
Original Assignee
いすゞ自動車株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by いすゞ自動車株式会社 filed Critical いすゞ自動車株式会社
Publication of WO2022071415A1 publication Critical patent/WO2022071415A1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/06—Road conditions
    • B60W40/076—Slope angle of the road
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B60W40/107—Longitudinal acceleration
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
    • G01P13/00—Indicating or recording presence, absence, or direction, of movement

Definitions

  • the present invention relates to a stop determination device for determining whether a vehicle is stopped.
  • Patent Document 1 the characteristics of each of the average value of the acceleration measured while the vehicle equipped with the acceleration sensor is running and the average value of the acceleration measured while the vehicle is stopped are learned.
  • a technique for determining whether a vehicle is running or stopped by using a support vector machine (SVM) is disclosed.
  • Patent Document 1 the characteristics of each of the average value of acceleration measured while the vehicle is running and the average value of acceleration measured while the vehicle is stopped are learned. Therefore, it may take some time for the characteristics of the average acceleration of the actually stopped vehicle to match the learned characteristics, and the timing at which the vehicle is determined to have stopped is the timing at which the vehicle actually stopped. It was out of alignment.
  • the present invention has been made in view of these points, and an object thereof is to reduce the difference between the timing when the vehicle is determined to be stopped and the timing when the vehicle is actually stopped.
  • the present invention is created by a pattern recognition model having an acceleration in the traveling direction of the vehicle and an integrated value obtained by integrating the accelerations while the wheel speed of the vehicle is equal to or less than a predetermined value.
  • a storage unit that stores the identification function, a wheel speed acquisition unit that sequentially acquires the wheel speed of the vehicle, an acceleration acquisition unit that sequentially acquires the acceleration in the traveling direction of the vehicle, and the wheel acquired by the wheel speed acquisition unit.
  • the integrated value calculation unit calculates the integrated value by integrating the acceleration acquired by the acceleration acquisition unit while the speed is continuously equal to or lower than the predetermined value, and the acceleration acquisition unit newly acquires the acceleration.
  • a stop determination device including a stop determination unit for determining that the vehicle is stopped when the identification value becomes equal to or higher than the predetermined determination threshold.
  • the stop determination unit determines that the vehicle is running while the identification value is less than the determination threshold value determined by the pattern recognition model, and when the identification value becomes equal to or greater than the determination threshold value, the said vehicle is described. It is determined that the vehicle is stopped.
  • the storage unit integrates the acceleration in the traveling direction calculated by using the output value of the acceleration sensor mounted on the vehicle, the gravitational acceleration, and the gradient of the road on which the vehicle travels, and the acceleration.
  • the discriminant function created by the pattern recognition model having a value as the feature amount is stored, and the discriminant value calculation unit substitutes the discriminant function stored in the storage unit to calculate the discriminant value. do.
  • the integral value calculation unit sets the integral value to zero when the wheel speed acquired by the wheel speed acquisition unit becomes larger than the predetermined value after the wheel speed becomes equal to or less than the predetermined value.
  • the integral value calculation unit has a plurality of acquisitions between the time when the wheel speed becomes equal to or less than the predetermined value and the time when the new acceleration is acquired.
  • the integrated value may be calculated by integrating the acceleration.
  • the time interval at which the acceleration acquisition unit acquires the acceleration and the time interval at which the wheel speed acquisition unit acquires the wheel speed may be the same.
  • the wheel speed acquisition unit detects the wheel speed detected by a sensor that outputs the predetermined value regardless of the actual rotation speed of the wheel from the time when the wheel speed becomes equal to or lower than the predetermined value until the wheel speed becomes zero. May be obtained.
  • FIG. 1 is a diagram schematically showing the configuration of the vehicle V.
  • the vehicle V includes a stop determination device 1, a wheel speed sensor 2, and an acceleration sensor 3.
  • the acceleration sensor 3 is a sensor that detects the acceleration of the vehicle V.
  • the acceleration sensor 3 may use a capacitance detection type sensor or a piezo resistance type sensor, but is not limited thereto.
  • the acceleration sensor 3 can detect acceleration in three axes of x-axis, y-axis, and z-axis.
  • the x-axis indicates the acceleration of the vehicle in the vehicle width direction.
  • the y-axis indicates the acceleration of the vehicle in the traveling direction.
  • the z-axis shows the acceleration in the direction of gravity.
  • the wheel speed sensor 2 is a sensor that detects the wheel speed of the vehicle V.
  • the wheel speed sensor 2 detects the wheel speed using a pulse signal proportional to the rotation speed of the wheel.
  • the wheel speed sensor 2 outputs a predetermined speed regardless of the actual rotation speed of the wheels from the time when the wheel speed becomes equal to or lower than the predetermined speed until the wheel speed is determined to be zero.
  • the predetermined speed is determined according to the specifications of the wheel speed sensor 2, and is, for example, 1 km / h. Therefore, if only the wheel speed at which the wheel speed sensor 2 detects the stop of the vehicle V is used, the timing at which the vehicle V is determined to have stopped is higher than the timing at which the wheel speed of the vehicle V becomes zero and the vehicle V actually stops. It may be later. Therefore, the stop determination device 1 determines whether or not the vehicle V has stopped based on the acceleration of the vehicle V acquired while the wheel speed is equal to or lower than the predetermined speed.
  • the configuration of the stop determination device 1 will be described.
  • the stop determination device 1 includes a storage unit 11 and a control unit 12.
  • the storage unit 11 is a storage medium including a ROM (Read Only Memory), a RAM (Random Access Memory), a hard disk, and the like.
  • the storage unit 11 stores a program executed by the control unit 12.
  • the storage unit 11 stores the identification function created by the pattern recognition model.
  • the pattern recognition model in the present embodiment is a soft margin SVM (Support Vector Machine), but the pattern recognition model is not limited to this.
  • the soft margin SVM of the present embodiment is characterized by an integrated value obtained by integrating the acceleration in the traveling direction of the vehicle V and the acceleration between the wheel speeds of the vehicle V at a predetermined speed K or less.
  • the soft margin SVM generates a discriminant function that classifies a set of integrated values obtained by integrating the acceleration of the vehicle V and the acceleration between the wheel speeds of a predetermined speed K or less into two classes of running and stopping.
  • the soft margin SVM learns a set of a plurality of accelerations and integral values of accelerations acquired in advance by experiments as training data to generate a discriminant function.
  • the distribution of the data while the vehicle V is running and the distribution of the data when the vehicle V is stopped may overlap, but the soft margin SVM has less misclassification for the distribution of the data overlapping in the two classes. It is possible to generate an identification function with adjusted parameters.
  • the acceleration in the traveling direction of the vehicle V is calculated using the output value of the acceleration sensor 3 mounted on the vehicle V, the gravitational acceleration, and the slope of the road on which the vehicle V travels.
  • the slope of the road on which the vehicle V travels is calculated using the output value of the acceleration sensor 3 and the gravitational acceleration.
  • the control unit 12 is a calculation resource including a processor such as a CPU (Central Processing Unit). By executing the program stored in the storage unit 11, the control unit 12 executes the wheel speed acquisition unit 121, the gradient estimation unit 122, the acceleration acquisition unit 123, the integral value calculation unit 124, the identification value calculation unit 125, and the stop determination unit. It realizes the function as 126.
  • a processor such as a CPU (Central Processing Unit).
  • the wheel speed acquisition unit 121 sequentially acquires the wheel speed of the vehicle V detected by the wheel speed sensor 2.
  • the time interval for the wheel speed acquisition unit 121 to acquire the wheel speed is determined according to, for example, the processing cycle of the control unit 12, and the specific value of the time interval is, for example, 100 milliseconds.
  • FIG. 2 is a diagram for explaining the time change of the wheel speed R when the vehicle V decelerates.
  • the horizontal axis of FIG. 2 indicates the time t.
  • the vertical axis shows the wheel speed R.
  • the broken line indicates a predetermined speed K.
  • the solid line U in FIG. 2 is a graph plotting the time change of the wheel speed R.
  • the wheel speed R is small from the origin to the time t1.
  • the time t1 is the time when the wheel speed R reaches the predetermined speed K.
  • the wheel speed sensor 2 outputs the predetermined speed K regardless of the actual rotation speed of the wheels. Therefore, the wheel speed R is the predetermined speed K from the time t1 to the time t2. It has become.
  • the acceleration acquisition unit 123 sequentially acquires the acceleration of the vehicle V in the traveling direction.
  • the time interval at which the acceleration acquisition unit 123 acquires the acceleration is the same as the time interval at which the wheel speed acquisition unit 121 acquires the wheel speed. Further, the acceleration acquisition unit 123 acquires the acceleration at the same timing as the wheel speed acquisition unit 121 acquires the wheel speed. By doing so, the acceleration acquisition unit 123 can acquire the acceleration and the wheel speed at the same time, so that, for example, the acceleration at the time when the wheel speed becomes equal to or lower than the predetermined speed can be acquired.
  • the acceleration acquisition unit 123 calculates the acceleration A in the traveling direction of the vehicle V using the first gradient estimated value ⁇ and the second gradient estimated value ⁇ . Specifically, the acceleration acquisition unit 123 calculates the acceleration A in the traveling direction using the following equation (3).
  • A g ⁇ sin ⁇ -g ⁇ sin ⁇ ... (3)
  • the integral value calculation unit 124 calculates the integrated value by integrating the acceleration A acquired while the wheel speed R acquired by the wheel speed acquisition unit 121 is continuously equal to or lower than the predetermined speed K. Specifically, the integral value calculation unit 124 acquires the integral value during the section L (see FIG. 2) from the time t1 when the wheel speed R becomes the predetermined speed K to the time t3 when the new acceleration A is acquired. The integrated value is calculated by integrating the plurality of accelerations A. More specifically, the integrated value calculation unit 124 calculates the integrated value of the acceleration A in the section L including the new acceleration A each time a new acceleration A is acquired. The section L is updated every time a new acceleration A is acquired. In this way, the integral value calculation unit 124 updates the integral value every time a new acceleration A is acquired, so that the identification value calculation unit 125, which will be described later, can calculate the identification value using the updated integral value. ..
  • the integrated value calculation unit 124 sets the integrated value to zero when the value of the wheel speed R increases and becomes larger than the predetermined speed K after the wheel speed R becomes equal to or less than the predetermined speed K. By doing so, the integral value calculation unit 124 can calculate the integral value of the acceleration A while the wheel speed R is continuously equal to or lower than the predetermined speed K.
  • the identification value calculation unit 125 calculates an identification value for determining whether or not the vehicle V is stopped.
  • the identification value calculation unit 125 calculates an identification value for classifying the set of the acceleration A of the vehicle V and the integrated value of the acceleration A into either of the two classes of running or stopping.
  • the discrimination value calculation unit 125 calculates the discrimination value by substituting the acceleration A and the integrated value obtained by integrating the acceleration A into the discrimination function stored in the storage unit 11.
  • the discriminant function is represented by, for example, the following equation (4).
  • ⁇ * p Optimal Lagrange multiplier, z p ⁇ ⁇ -1,1 ⁇ , K (x, x p ): Kernel function, x p : Sample point, b * : Optimal solution of minimization problem x is acceleration It is a vector whose component is the integrated value of A and the acceleration A.
  • the kernel function for example, a Gaussian kernel can be used, but the kernel function is not limited to this, and other kernel functions can be used.
  • the discrimination value calculation unit 125 calculates the discrimination value by substituting the vector x whose component is the acceleration A and the integrated value obtained by integrating the acceleration A into the equation (4). Each time the acceleration acquisition unit 123 newly acquires the acceleration A, the identification value calculation unit 125 substitutes the newly acquired acceleration and the integral value calculated by the integral value calculation unit 124 into the identification function to obtain the identification value. calculate. For example, when a sign function is used, the identification value calculation unit 125 calculates an identification value of -1 or less or +1 or more.
  • the stop determination unit 126 determines whether or not the vehicle V is stopped using the identification value calculated by the identification value calculation unit 125. Specifically, the stop determination unit 126 determines whether or not the vehicle is stopped every time the identification value is calculated (for example, every 100 milliseconds). The stop determination unit 126 determines that the vehicle V is traveling while the calculated identification value is less than the determination threshold value. When the discrimination value becomes equal to or higher than the determination threshold value, the stop determination unit 126 determines that the vehicle is stopped.
  • the determination threshold is a threshold for determining whether the calculated identification value is classified into running data or stopped data.
  • the determination threshold value is determined according to the discrimination value calculated by the discrimination function created by the pattern recognition model, for example. For example, when a sign function is used, an identification value of -1 or less or +1 or more is calculated, so that the determination threshold is the first determination threshold (minus 1) for classifying the identification value into running data. It includes a second determination threshold (plus 1) for classifying the identification value into the stopped data.
  • the determination threshold value may be determined by using, for example, a method of drawing a ROC curve (Receiver Operating Characteristic curve) and then using the point closest to the upper left corner, or using the Youden index.
  • ROC curve Receiveiver Operating Characteristic curve
  • the stop determination unit 126 determines that the vehicle V is running when the identification value is equal to or less than the first determination threshold value (minus 1). When the identification value is equal to or higher than the second determination threshold value (plus 1), the stop determination unit 126 determines that the vehicle V is stopped. In this way, the stop determination unit 126 determines whether or not the vehicle V is stopped by using the integrated values of the acceleration A and the acceleration A acquired at the current time. Therefore, the stop determination unit 126 does not take time for the characteristics of the acceleration A and the integrated value of the actually stopped vehicle V to match the learned characteristics, and the timing at which the vehicle V actually stopped and the timing when the vehicle V actually stopped, It is possible to reduce the deviation from the timing at which the vehicle V is determined to have stopped.
  • FIG. 3 is a flowchart showing an example of the flow of the stop determination process for determining whether or not the vehicle V has stopped.
  • the stop determination device 1 sequentially executes the stop determination process while the engine of the vehicle V is starting.
  • the interval for executing the processing may be appropriately determined, but it is the processing cycle of the control unit 12, and the specific value is, for example, 100 milliseconds.
  • the wheel speed acquisition unit 121 acquires the wheel speed R of the vehicle V from the wheel speed sensor 2 (step S1). Subsequently, the gradient estimation unit 122 estimates the gradient of the road on which the vehicle V travels (step S2). Specifically, the gradient estimation unit 122 uses an inverse sine function on the value obtained by dividing the gravitational acceleration component (Gx-a) obtained by subtracting the velocity differential value a from the acceleration Gx detected by the acceleration sensor 3 by the gravitational acceleration g. The first gradient estimated value ⁇ is estimated. Further, the gradient estimation unit 122 estimates the second gradient estimated value ⁇ by using an inverse trigonometric function on the value (Gx / g) obtained by dividing the acceleration Gx by the gravitational acceleration g. Note that step S2 may be executed before step S1 or may be executed in parallel with step S1 and step S2.
  • the acceleration acquisition unit 123 acquires the acceleration A in the traveling direction of the vehicle V using the first gradient estimated value ⁇ and the second gradient estimated value ⁇ (step S3). Specifically, the acceleration acquisition unit 123 calculates the acceleration A using the above equation (3).
  • the integral value calculation unit 124 determines whether or not the wheel speed R is equal to or less than the predetermined speed K (step S4).
  • the integrated value calculation unit 124 calculates the integrated value by integrating the acceleration A while the wheel speed R is continuously equal to or less than the predetermined speed K. (Step S5).
  • the integrated value calculation unit 124 calculates the integrated value by integrating the acceleration A from the time when the wheel speed R becomes the predetermined speed K or less to the present.
  • the discrimination value calculation unit 125 calculates the discrimination value by substituting the latest acceleration A and the integrated value including the latest acceleration A into the discrimination function (step S6).
  • the stop determination unit 126 determines whether or not the identification value is equal to or greater than the determination threshold value (step S7). When the discrimination value is equal to or higher than the determination threshold value (second determination threshold value) (Yes in step S7), the stop determination unit 126 determines that the vehicle V is stopped (step S8). When the identification value is equal to or less than the determination threshold value (first determination threshold value) (No in step S7), the stop determination unit 126 determines that the vehicle V is traveling (step S10).
  • the integral value calculation unit 124 changes the integral value of the acceleration A to zero (step S9), and determines that the vehicle V is traveling. (Step S10).
  • the stop determination unit 126 may determine that the vehicle is running while the discrimination value is equal to or higher than the predetermined threshold value according to the discrimination function, and may determine that the vehicle is stopped when the discrimination value becomes less than the predetermined threshold value. ..
  • the determination threshold includes two thresholds, a first determination threshold (minus 1) and a second determination threshold (plus 1).
  • the determination threshold value may be one.
  • one determination threshold value may be determined according to the discrimination value calculated by the discrimination function, and the specific value is, for example, zero.
  • the stop determination unit 126 determines that the vehicle V is running when the identification value is less than zero, and determines that the vehicle V is stopped when the identification value is zero or more.
  • the stop determination device 1 features pattern recognition having an integrated value obtained by integrating the acceleration A in the traveling direction of the vehicle V and the acceleration A while the wheel speed R of the vehicle V is equal to or less than a predetermined speed K.
  • the stop determination device 1 sequentially acquires the wheel speed R of the vehicle V and the acceleration A in the traveling direction of the vehicle V.
  • the stop determination device 1 calculates the integrated value by integrating the acquired acceleration A while the acquired wheel speed R is continuously equal to or lower than the predetermined speed K.
  • the stop determination device 1 determines that the vehicle V is traveling while the calculated identification value is less than the predetermined determination threshold value, and when the identification value becomes equal to or higher than the predetermined determination threshold value, the vehicle V stops. It is determined that it is.
  • the stop determination device 1 substitutes the newly acquired integrated values of the acceleration A and the acceleration A into the discrimination function created by the pattern recognition model having the integrated values of the acceleration A and the acceleration A as feature quantities. It is determined whether or not the vehicle V is stopped by using the identification value obtained in the above procedure. Therefore, in the stop determination device 1, it does not take time for the characteristics of the acceleration A and the integrated value of the actually stopped vehicle V to match the learned characteristics, and the timing at which the vehicle V actually stops and the timing at which the vehicle V actually stopped are determined. It is possible to reduce the deviation from the timing at which the vehicle V is determined to have stopped.
  • the stop determination device 1 still has the above-mentioned. As shown, it can be determined that the vehicle V has stopped at the timing when the vehicle V actually stopped.
  • Stop determination device 11 Storage unit 12 Control unit 121 Wheel speed acquisition unit 122 Gradient estimation unit 123 Accelerometer acquisition unit 124 Integral value calculation unit 125 Identification value calculation unit 126 Stop determination unit 2 Wheel speed sensor 3 Accelerometer

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Mathematical Physics (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Indicating Or Recording The Presence, Absence, Or Direction Of Movement (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

A stop determining device 1 is provided with: a storage unit 11 for storing an identification function created by a pattern recognition model which takes, as feature quantities, the acceleration of a vehicle V, and an integral value obtained by integrating the acceleration during an interval in which the wheel speed of the vehicle V is at most equal to a prescribed value; a wheel speed acquiring unit 121 for successively acquiring the wheel speed of the vehicle V; an acceleration acquiring unit 123 for successively acquiring the acceleration in the direction of travel of the vehicle V; an integral value calculating unit 124 for calculating the integral value by integrating the acceleration acquired during an interval in which the wheel speed is continuously at most equal to a prescribed value; an identification value calculating unit 125 for calculating an identification value for determining whether the vehicle V is stopped, by substituting the newly acquired acceleration and integral value into the identification function; and a stop determining unit 126 for determining that the vehicle V is traveling while the calculated identification value is less than a prescribed determination threshold, and determining that the vehicle V is stopped if the identification value is equal to or greater than the prescribed determination threshold.

Description

停止判定装置Stop judgment device
　本発明は、車両が停止しているかを判定する停止判定装置に関する。 The present invention relates to a stop determination device for determining whether a vehicle is stopped.
　特許文献１には、加速度センサが搭載された車両が走行している間に測定された加速度の平均値、及び停止している間に測定された加速度の平均値の各々が有する特徴を学習させたサポートベクトルマシン（ＳＶＭ：Support Vector Machine）を用いて、車両が走行中か停止中かを判定する技術が開示されている。 In Patent Document 1, the characteristics of each of the average value of the acceleration measured while the vehicle equipped with the acceleration sensor is running and the average value of the acceleration measured while the vehicle is stopped are learned. A technique for determining whether a vehicle is running or stopped by using a support vector machine (SVM) is disclosed.
特開２０１７－１５５４０号公報Japanese Unexamined Patent Publication No. 2017-15540
　特許文献１では、車両が走行している間に測定された加速度の平均値、及び停止している間に測定された加速度の平均値の各々が有する特徴を学習している。そのため、実際に停止した車両の加速度の平均値の有する特徴が、学習された特徴に一致するまでに時間がかかることがあり、車両が停止したと判定するタイミングが、実際に車両が停止したタイミングとずれてしまっていた。 In Patent Document 1, the characteristics of each of the average value of acceleration measured while the vehicle is running and the average value of acceleration measured while the vehicle is stopped are learned. Therefore, it may take some time for the characteristics of the average acceleration of the actually stopped vehicle to match the learned characteristics, and the timing at which the vehicle is determined to have stopped is the timing at which the vehicle actually stopped. It was out of alignment.
　そこで、本発明はこれらの点に鑑みてなされたものであり、車両が停止したと判定するタイミングと実際に車両が停止したタイミングとのずれを低減することを目的とする。 Therefore, the present invention has been made in view of these points, and an object thereof is to reduce the difference between the timing when the vehicle is determined to be stopped and the timing when the vehicle is actually stopped.
　本発明の第１の態様においては、車両の進行方向の加速度と、前記車両の車輪速が所定値以下の間の前記加速度を積分した積分値とを特徴量とするパターン認識モデルによって作成された識別関数を記憶する記憶部と、前記車両の車輪速を順次取得する車輪速取得部と、前記車両の進行方向の加速度を順次取得する加速度取得部と、前記車輪速取得部が取得した前記車輪速が継続して前記所定値以下である間に前記加速度取得部が取得した前記加速度を積分して積分値を算出する積分値算出部と、前記加速度取得部が前記加速度を新たに取得する毎に、前記加速度取得部が新たに取得した前記加速度と、前記積分値算出部が算出した前記積分値とを前記記憶部に記憶された前記識別関数に代入して前記車両が停止しているか否かを判定するための識別値を算出する識別値算出部と、前記識別値算出部が算出した前記識別値が所定の判定閾値未満である間、前記車両が走行していると判定し、前記識別値が前記所定の判定閾値以上になったら、前記車両が停止していると判定する停止判定部と、を備える停止判定装置を提供する。 In the first aspect of the present invention, it is created by a pattern recognition model having an acceleration in the traveling direction of the vehicle and an integrated value obtained by integrating the accelerations while the wheel speed of the vehicle is equal to or less than a predetermined value. A storage unit that stores the identification function, a wheel speed acquisition unit that sequentially acquires the wheel speed of the vehicle, an acceleration acquisition unit that sequentially acquires the acceleration in the traveling direction of the vehicle, and the wheel acquired by the wheel speed acquisition unit. Each time the integrated value calculation unit calculates the integrated value by integrating the acceleration acquired by the acceleration acquisition unit while the speed is continuously equal to or lower than the predetermined value, and the acceleration acquisition unit newly acquires the acceleration. Whether or not the vehicle is stopped by substituting the acceleration newly acquired by the acceleration acquisition unit and the integrated value calculated by the integrated value calculation unit into the identification function stored in the storage unit. While the identification value calculation unit that calculates the identification value for determining whether or not the identification value and the identification value calculated by the identification value calculation unit are less than a predetermined determination threshold value, it is determined that the vehicle is running, and the vehicle is determined to be running. Provided is a stop determination device including a stop determination unit for determining that the vehicle is stopped when the identification value becomes equal to or higher than the predetermined determination threshold.
　例えば、前記停止判定部は、前記識別値が前記パターン認識モデルにより定まる前記判定閾値未満である間、前記車両が走行していると判定し、前記識別値が前記判定閾値以上になったら、前記車両が停止していると判定する。 For example, the stop determination unit determines that the vehicle is running while the identification value is less than the determination threshold value determined by the pattern recognition model, and when the identification value becomes equal to or greater than the determination threshold value, the said vehicle is described. It is determined that the vehicle is stopped.
　例えば、前記記憶部は、前記車両に搭載された加速度センサの出力値と、重力加速度と、前記車両が走行する道路の勾配とを用いて算出された前記進行方向の加速度と、前記加速度の積分値とを前記特徴量とする前記パターン認識モデルによって作成された前記識別関数を記憶し、前記識別値算出部は、前記記憶部に記憶された前記識別関数に代入して、前記識別値を算出する。 For example, the storage unit integrates the acceleration in the traveling direction calculated by using the output value of the acceleration sensor mounted on the vehicle, the gravitational acceleration, and the gradient of the road on which the vehicle travels, and the acceleration. The discriminant function created by the pattern recognition model having a value as the feature amount is stored, and the discriminant value calculation unit substitutes the discriminant function stored in the storage unit to calculate the discriminant value. do.
　例えば、前記積分値算出部は、前記車輪速取得部が取得した前記車輪速が前記所定値以下になった後に、前記所定値よりも大きくなった場合、前記積分値をゼロにする。 For example, the integral value calculation unit sets the integral value to zero when the wheel speed acquired by the wheel speed acquisition unit becomes larger than the predetermined value after the wheel speed becomes equal to or less than the predetermined value.
　前記積分値算出部は、新たな前記加速度が取得される度に、前記車輪速が前記所定値以下になった時刻から前記新たな加速度が取得された時刻までの間に取得された複数の前記加速度を積分して前記積分値を算出してもよい。 Each time the new acceleration is acquired, the integral value calculation unit has a plurality of acquisitions between the time when the wheel speed becomes equal to or less than the predetermined value and the time when the new acceleration is acquired. The integrated value may be calculated by integrating the acceleration.
　前記加速度取得部が前記加速度を取得する時間間隔と、前記車輪速取得部が前記車輪速を取得する時間間隔とは、同じであってもよい。 The time interval at which the acceleration acquisition unit acquires the acceleration and the time interval at which the wheel speed acquisition unit acquires the wheel speed may be the same.
　前記車輪速取得部は、前記車輪速が前記所定値以下になってから前記車輪速がゼロになるまで、実際の車輪の回転速度に係わらず前記所定値を出力するセンサが検出した前記車輪速を取得してもよい。 The wheel speed acquisition unit detects the wheel speed detected by a sensor that outputs the predetermined value regardless of the actual rotation speed of the wheel from the time when the wheel speed becomes equal to or lower than the predetermined value until the wheel speed becomes zero. May be obtained.
　本発明によれば、車両が停止したと判定するタイミングと実際に車両が停止したタイミングとのずれを低減できるという効果を奏する。 According to the present invention, there is an effect that the difference between the timing when the vehicle is determined to be stopped and the timing when the vehicle actually stops can be reduced.
車両の構成を模式的に示す図である。It is a figure which shows the structure of a vehicle schematically. 車両が減速するときの車輪速の時間変化を説明するための図である。It is a figure for demonstrating the time change of a wheel speed when a vehicle decelerates. 車両が停止したか否かを判定する停止判定処理の流れの一例を示すフローチャートである。It is a flowchart which shows an example of the flow of the stop determination process which determines whether or not a vehicle has stopped.
［車両Ｖの構成］
　図１は、車両Ｖの構成を模式的に示す図である。車両Ｖは、停止判定装置１と、車輪速センサ２と、加速度センサ３とを備える。 [Vehicle V configuration]
FIG. 1 is a diagram schematically showing the configuration of the vehicle V. The vehicle V includes a stop determination device 1, a wheel speed sensor 2, and an acceleration sensor 3.
　加速度センサ３は、車両Ｖの加速度を検出するセンサである。加速度センサ３は、静電容量検出方式、又はピエゾ抵抗方式のセンサを用いればよいが、これに限定するものではない。加速度センサ３は、ｘ軸、ｙ軸、及びｚ軸の３軸における加速度を検出できる。本実施の形態において、ｘ軸は車両の車幅方向の加速度を示す。ｙ軸は車両の進行方向の加速度を示す。ｚ軸は重力方向の加速度を示す。 The acceleration sensor 3 is a sensor that detects the acceleration of the vehicle V. The acceleration sensor 3 may use a capacitance detection type sensor or a piezo resistance type sensor, but is not limited thereto. The acceleration sensor 3 can detect acceleration in three axes of x-axis, y-axis, and z-axis. In the present embodiment, the x-axis indicates the acceleration of the vehicle in the vehicle width direction. The y-axis indicates the acceleration of the vehicle in the traveling direction. The z-axis shows the acceleration in the direction of gravity.
車輪速センサ２は、車両Ｖの車輪速を検出するセンサである。例えば、車輪速センサ２は、車輪の回転速度に比例したパルス信号を用いて車輪速を検出する。車輪速センサ２は、車輪速が所定速度以下になってから車輪速がゼロと判定されるまで、実際の車輪の回転速度に係わらず所定速度を出力する。所定速度は、車輪速センサ２の仕様に応じて定まり、例えば時速１キロメートルである。そのため、車両Ｖの停止を車輪速センサ２が検出した車輪速のみでは、車両Ｖが停止したと判定するタイミングが、車両Ｖの車輪速がゼロになって車両Ｖが実際に停止したタイミングよりも後になってしまうおそれがある。そこで、停止判定装置１は、車輪速が所定速度以下の間に取得された車両Ｖの加速度に基づいて車両Ｖが停止したか否かを判定する。以下、停止判定装置１の構成を説明する。 The wheel speed sensor 2 is a sensor that detects the wheel speed of the vehicle V. For example, the wheel speed sensor 2 detects the wheel speed using a pulse signal proportional to the rotation speed of the wheel. The wheel speed sensor 2 outputs a predetermined speed regardless of the actual rotation speed of the wheels from the time when the wheel speed becomes equal to or lower than the predetermined speed until the wheel speed is determined to be zero. The predetermined speed is determined according to the specifications of the wheel speed sensor 2, and is, for example, 1 km / h. Therefore, if only the wheel speed at which the wheel speed sensor 2 detects the stop of the vehicle V is used, the timing at which the vehicle V is determined to have stopped is higher than the timing at which the wheel speed of the vehicle V becomes zero and the vehicle V actually stops. It may be later. Therefore, the stop determination device 1 determines whether or not the vehicle V has stopped based on the acceleration of the vehicle V acquired while the wheel speed is equal to or lower than the predetermined speed. Hereinafter, the configuration of the stop determination device 1 will be described.
［停止判定装置１の構成］
　停止判定装置１は、記憶部１１と、制御部１２とを備える。記憶部１１は、ＲＯＭ（Read Only Memory）、ＲＡＭ（Random Access Memory）及びハードディスク等を含む記憶媒体である。記憶部１１は、制御部１２が実行するプログラムを記憶する。 [Configuration of stop determination device 1]
The stop determination device 1 includes a storage unit 11 and a control unit 12. The storage unit 11 is a storage medium including a ROM (Read Only Memory), a RAM (Random Access Memory), a hard disk, and the like. The storage unit 11 stores a program executed by the control unit 12.
　記憶部１１は、パターン認識モデルによって作成された識別関数を記憶する。本実施の形態におけるパターン認識モデルは、ソフトマージンＳＶＭ（Support Vector Machine）であるが、これに限定するものではない。 The storage unit 11 stores the identification function created by the pattern recognition model. The pattern recognition model in the present embodiment is a soft margin SVM (Support Vector Machine), but the pattern recognition model is not limited to this.
　本実施の形態のソフトマージンＳＶＭは、車両Ｖの進行方向の加速度と、車両Ｖの車輪速が所定速度Ｋ以下の間の加速度を積分した積分値とを特徴量とする。ソフトマージンＳＶＭは、車両Ｖの加速度及び車輪速が所定速度Ｋ以下の間の加速度を積分した積分値の組を、走行中又は停止中の２つのクラスに分類する識別関数を生成する。ソフトマージンＳＶＭは、予め実験により取得された複数の加速度及び加速度の積分値の組をトレーニングデータとして学習して識別関数を生成する。ところで、車両Ｖが走行中のデータの分布と停止中のデータの分布とが重なり合うことがあるが、ソフトマージンＳＶＭは、２つのクラスに重なりのあるデータの分布に対して誤分類が少なくなるようにパラメータを調整した識別関数を生成することができる。 The soft margin SVM of the present embodiment is characterized by an integrated value obtained by integrating the acceleration in the traveling direction of the vehicle V and the acceleration between the wheel speeds of the vehicle V at a predetermined speed K or less. The soft margin SVM generates a discriminant function that classifies a set of integrated values obtained by integrating the acceleration of the vehicle V and the acceleration between the wheel speeds of a predetermined speed K or less into two classes of running and stopping. The soft margin SVM learns a set of a plurality of accelerations and integral values of accelerations acquired in advance by experiments as training data to generate a discriminant function. By the way, the distribution of the data while the vehicle V is running and the distribution of the data when the vehicle V is stopped may overlap, but the soft margin SVM has less misclassification for the distribution of the data overlapping in the two classes. It is possible to generate an identification function with adjusted parameters.
　車両Ｖの進行方向の加速度は、車両Ｖに搭載された加速度センサ３の出力値と、重力加速度と、車両Ｖが走行する道路の勾配とを用いて算出される。車両Ｖが走行する道路の勾配は、加速度センサ３の出力値と重力加速度とを用いて算出される。 The acceleration in the traveling direction of the vehicle V is calculated using the output value of the acceleration sensor 3 mounted on the vehicle V, the gravitational acceleration, and the slope of the road on which the vehicle V travels. The slope of the road on which the vehicle V travels is calculated using the output value of the acceleration sensor 3 and the gravitational acceleration.
　制御部１２は、例えばＣＰＵ（Central Processing Unit）等のプロセッサを含む計算リソースである。制御部１２は、記憶部１１に記憶されたプログラムを実行することにより、車輪速取得部１２１、勾配推定部１２２、加速度取得部１２３、積分値算出部１２４、識別値算出部１２５及び停止判定部１２６としての機能を実現する。 The control unit 12 is a calculation resource including a processor such as a CPU (Central Processing Unit). By executing the program stored in the storage unit 11, the control unit 12 executes the wheel speed acquisition unit 121, the gradient estimation unit 122, the acceleration acquisition unit 123, the integral value calculation unit 124, the identification value calculation unit 125, and the stop determination unit. It realizes the function as 126.
　車輪速取得部１２１は、車輪速センサ２が検出した車両Ｖの車輪速を順次取得する。車輪速取得部１２１が車輪速を取得する時間間隔は、例えば制御部１２の処理周期に応じて定まり、時間間隔の具体的な値は、例えば１００ミリ秒である。 The wheel speed acquisition unit 121 sequentially acquires the wheel speed of the vehicle V detected by the wheel speed sensor 2. The time interval for the wheel speed acquisition unit 121 to acquire the wheel speed is determined according to, for example, the processing cycle of the control unit 12, and the specific value of the time interval is, for example, 100 milliseconds.
　図２は、車両Ｖが減速するときの車輪速Ｒの時間変化を説明するための図である。図２の横軸は時刻ｔを示す。縦軸は車輪速Ｒを示す。破線は、所定速度Ｋを示す。図２の実線Ｕは、車輪速Ｒの時間変化をプロットしたグラフである。車両Ｖが減速すると、車輪速Ｒは小さくなる。図２において、車輪速Ｒは、原点から時刻ｔ１までの間、小さくなっている。時刻ｔ１は、車輪速Ｒが所定速度Ｋになった時刻である。車輪速Ｒが所定速度Ｋ以下になると、実際の車輪の回転速度に係わらず車輪速センサ２が所定速度Ｋを出力するため、車輪速Ｒは、時刻ｔ１から時刻ｔ２までの間、所定速度Ｋになっている。 FIG. 2 is a diagram for explaining the time change of the wheel speed R when the vehicle V decelerates. The horizontal axis of FIG. 2 indicates the time t. The vertical axis shows the wheel speed R. The broken line indicates a predetermined speed K. The solid line U in FIG. 2 is a graph plotting the time change of the wheel speed R. When the vehicle V decelerates, the wheel speed R decreases. In FIG. 2, the wheel speed R is small from the origin to the time t1. The time t1 is the time when the wheel speed R reaches the predetermined speed K. When the wheel speed R becomes the predetermined speed K or less, the wheel speed sensor 2 outputs the predetermined speed K regardless of the actual rotation speed of the wheels. Therefore, the wheel speed R is the predetermined speed K from the time t1 to the time t2. It has become.
　勾配推定部１２２は、車両が走行する道路の勾配を順次推定する。例えば、勾配推定部１２２は、２つの方法で２つの勾配推定値を算出する。具体的には、勾配推定部１２２は、加速度センサ３が検出した加速度Ｇｘから車両の速度を微分した速度微分値ａを減算した重力加速度成分（Ｇｘ－ａ）を、重力加速度ｇで除算した値に、逆正弦関数を用いて第１勾配推定値βを推定する。より具体的には、勾配推定部１２２は、下記式（１）を用いて第１勾配推定値βを算出する。
　β＝ｓｉｎ－１｛（Ｇｘ－ａ）／ｇ｝…（１） The gradient estimation unit 122 sequentially estimates the gradient of the road on which the vehicle travels. For example, the gradient estimation unit 122 calculates two gradient estimation values by two methods. Specifically, the gradient estimation unit 122 divides the gravity acceleration component (Gx-a) obtained by subtracting the velocity differential value a obtained by differentiating the vehicle speed from the acceleration Gx detected by the acceleration sensor 3 by the gravity acceleration g. In addition, the first gradient estimated value β is estimated using an inverse sine function. More specifically, the gradient estimation unit 122 calculates the first gradient estimated value β using the following equation (1).
β = sin -1 {(Gx-a) / g} ... (1)
　また、勾配推定部１２２は、加速度Ｇｘと重力加速度ｇとを用いて第２勾配推定値θを推定する。具体的には、勾配推定部１２２は、加速度Ｇｘを重力加速度ｇで除算した値に、逆正弦関数を用いて第２勾配推定値θを推定する。より具体的には、勾配推定部１２２は、下記式（２）を用いて第２勾配推定値θを算出する。
　θ＝ｓｉｎ－１（Ｇｘ／ｇ）…（２） Further, the gradient estimation unit 122 estimates the second gradient estimated value θ using the acceleration Gx and the gravitational acceleration g. Specifically, the gradient estimation unit 122 estimates the second gradient estimated value θ by using an inverse sine function on the value obtained by dividing the acceleration Gx by the gravitational acceleration g. More specifically, the gradient estimation unit 122 calculates the second gradient estimated value θ using the following equation (2).
θ = sin -1 (Gx / g) ... (2)
　加速度取得部１２３は、車両Ｖの進行方向の加速度を順次取得する。加速度取得部１２３が加速度を取得する時間間隔は、車輪速取得部１２１が車輪速を取得する時間間隔と同じである。また、加速度取得部１２３は、車輪速取得部１２１が車輪速を取得するタイミングと同じタイミングで加速度を取得する。このようにすることで、加速度取得部１２３は、同時期の加速度と車輪速を取得できるから、例えば車輪速が所定速度以下になった時点の加速度を取得できる。例えば、加速度取得部１２３は、第１勾配推定値β及び第２勾配推定値θを用いて車両Ｖの進行方向の加速度Ａを算出する。具体的には、加速度取得部１２３は、下記式（３）を用いて進行方向の加速度Ａを算出する。
　Ａ＝ｇ・ｓｉｎθ－ｇ・ｓｉｎβ…（３） The acceleration acquisition unit 123 sequentially acquires the acceleration of the vehicle V in the traveling direction. The time interval at which the acceleration acquisition unit 123 acquires the acceleration is the same as the time interval at which the wheel speed acquisition unit 121 acquires the wheel speed. Further, the acceleration acquisition unit 123 acquires the acceleration at the same timing as the wheel speed acquisition unit 121 acquires the wheel speed. By doing so, the acceleration acquisition unit 123 can acquire the acceleration and the wheel speed at the same time, so that, for example, the acceleration at the time when the wheel speed becomes equal to or lower than the predetermined speed can be acquired. For example, the acceleration acquisition unit 123 calculates the acceleration A in the traveling direction of the vehicle V using the first gradient estimated value β and the second gradient estimated value θ. Specifically, the acceleration acquisition unit 123 calculates the acceleration A in the traveling direction using the following equation (3).
A = g ・ sinθ－g ・ sinβ ... (3)
　積分値算出部１２４は、車輪速取得部１２１が取得した車輪速Ｒが継続して所定速度Ｋ以下である間に取得された加速度Ａを積分して積分値を算出する。具体的には、積分値算出部１２４は、車輪速Ｒが所定速度Ｋになった時刻ｔ１から、新たな加速度Ａが取得された時刻ｔ３までの区間Ｌ（図２を参照）の間に取得された複数の加速度Ａを積分して積分値を算出する。より具体的には、積分値算出部１２４は、新たな加速度Ａが取得される度に、新たな加速度Ａを含む区間Ｌ内の加速度Ａの積分値を算出する。なお、区間Ｌは、新たな加速度Ａが取得される毎に更新される。このように、積分値算出部１２４が、新たな加速度Ａが取得される度に積分値を更新するから、後述する識別値算出部１２５が、更新された積分値を用いて識別値を算出できる。 The integral value calculation unit 124 calculates the integrated value by integrating the acceleration A acquired while the wheel speed R acquired by the wheel speed acquisition unit 121 is continuously equal to or lower than the predetermined speed K. Specifically, the integral value calculation unit 124 acquires the integral value during the section L (see FIG. 2) from the time t1 when the wheel speed R becomes the predetermined speed K to the time t3 when the new acceleration A is acquired. The integrated value is calculated by integrating the plurality of accelerations A. More specifically, the integrated value calculation unit 124 calculates the integrated value of the acceleration A in the section L including the new acceleration A each time a new acceleration A is acquired. The section L is updated every time a new acceleration A is acquired. In this way, the integral value calculation unit 124 updates the integral value every time a new acceleration A is acquired, so that the identification value calculation unit 125, which will be described later, can calculate the identification value using the updated integral value. ..
　積分値算出部１２４は、車輪速Ｒが所定速度Ｋ以下になった後に、車輪速Ｒの値が増加して所定速度Ｋよりも大きくなった場合、積分値をゼロにする。このようにすることで、積分値算出部１２４は、車輪速Ｒが継続して所定速度Ｋ以下である間の加速度Ａの積分値を算出できる。 The integrated value calculation unit 124 sets the integrated value to zero when the value of the wheel speed R increases and becomes larger than the predetermined speed K after the wheel speed R becomes equal to or less than the predetermined speed K. By doing so, the integral value calculation unit 124 can calculate the integral value of the acceleration A while the wheel speed R is continuously equal to or lower than the predetermined speed K.
　識別値算出部１２５は、車両Ｖが停止しているか否かを判定するための識別値を算出する。識別値算出部１２５は、車両Ｖの加速度Ａと加速度Ａの積分値との組を、走行中又は停止中の２つのクラスのいずれかに分類するための識別値を算出する。具体的には、識別値算出部１２５は、加速度Ａと、加速度Ａを積分した積分値とを記憶部１１に記憶された識別関数に代入して識別値を算出する。識別関数は、例えば下記式（４）で表される。
Figure JPOXMLDOC01-appb-M000001
 　λ*ｐ：最適ラグランジュ乗数、ｚｐ∈｛－１，１｝、Ｋ（ｘ，ｘｐ）：カーネル関数、ｘｐ：サンプル点、ｂ＊：最小化問題の最適解
　なお、ｘは、加速度Ａ及び加速度Ａの積分値を成分とするベクトルである。また、カーネル関数は、例えばガウシアンカーネルを用いることができるが、これに限定するものではなく、他のカーネル関数を用いることができる。 The identification value calculation unit 125 calculates an identification value for determining whether or not the vehicle V is stopped. The identification value calculation unit 125 calculates an identification value for classifying the set of the acceleration A of the vehicle V and the integrated value of the acceleration A into either of the two classes of running or stopping. Specifically, the discrimination value calculation unit 125 calculates the discrimination value by substituting the acceleration A and the integrated value obtained by integrating the acceleration A into the discrimination function stored in the storage unit 11. The discriminant function is represented by, for example, the following equation (4).
Figure JPOXMLDOC01-appb-M000001
 λ * p : Optimal Lagrange multiplier, z p ∈ {-1,1}, K (x, x p ): Kernel function, x p : Sample point, b * : Optimal solution of minimization problem x is acceleration It is a vector whose component is the integrated value of A and the acceleration A. Further, as the kernel function, for example, a Gaussian kernel can be used, but the kernel function is not limited to this, and other kernel functions can be used.
　本実施の形態において、識別値算出部１２５は、加速度Ａと、加速度Ａを積分した積分値とを成分とするベクトルｘを式（４）に代入することにより、識別値を算出する。識別値算出部１２５は、加速度取得部１２３が加速度Ａを新たに取得する毎に、新たに取得した加速度と、積分値算出部１２４が算出した積分値とを識別関数に代入して識別値を算出する。例えば、符号関数を用いる場合、識別値算出部１２５は、マイナス１以下又はプラス１以上の識別値を算出する。 In the present embodiment, the discrimination value calculation unit 125 calculates the discrimination value by substituting the vector x whose component is the acceleration A and the integrated value obtained by integrating the acceleration A into the equation (4). Each time the acceleration acquisition unit 123 newly acquires the acceleration A, the identification value calculation unit 125 substitutes the newly acquired acceleration and the integral value calculated by the integral value calculation unit 124 into the identification function to obtain the identification value. calculate. For example, when a sign function is used, the identification value calculation unit 125 calculates an identification value of -1 or less or +1 or more.
　停止判定部１２６は、識別値算出部１２５が算出した識別値を用いて車両Ｖが停止しているか否かを判定する。具体的には、停止判定部１２６は、識別値が算出される毎（例えば１００ミリ秒毎）に、車両が停止しているか否かを判定する。停止判定部１２６は、算出された識別値が判定閾値未満である間、車両Ｖが走行していると判定する。停止判定部１２６は、識別値が判定閾値以上になったら、車両が停止していると判定する。 The stop determination unit 126 determines whether or not the vehicle V is stopped using the identification value calculated by the identification value calculation unit 125. Specifically, the stop determination unit 126 determines whether or not the vehicle is stopped every time the identification value is calculated (for example, every 100 milliseconds). The stop determination unit 126 determines that the vehicle V is traveling while the calculated identification value is less than the determination threshold value. When the discrimination value becomes equal to or higher than the determination threshold value, the stop determination unit 126 determines that the vehicle is stopped.
　判定閾値は、算出された識別値を走行中のデータに分類するか、停止中のデータに分類するかを判定する閾値である。判定閾値は、例えばパターン認識モデルによって作成された識別関数により算出される識別値に応じて定められる。例えば、符号関数を用いる場合、マイナス１以下又はプラス１以上の識別値が算出されるので、判定閾値は、識別値を走行中のデータに分類するための第１判定閾値（マイナス１）と、識別値を停止中のデータに分類するための第２判定閾値（プラス１）とを含む。なお、判定閾値は、例えばＲＯＣ曲線（Receiver Operating Characteristic curve）を描画した後に左上隅からの距離が最も近いポイントを利用する手法や、Youden indexを用いて定めてもよい。 The determination threshold is a threshold for determining whether the calculated identification value is classified into running data or stopped data. The determination threshold value is determined according to the discrimination value calculated by the discrimination function created by the pattern recognition model, for example. For example, when a sign function is used, an identification value of -1 or less or +1 or more is calculated, so that the determination threshold is the first determination threshold (minus 1) for classifying the identification value into running data. It includes a second determination threshold (plus 1) for classifying the identification value into the stopped data. The determination threshold value may be determined by using, for example, a method of drawing a ROC curve (Receiver Operating Characteristic curve) and then using the point closest to the upper left corner, or using the Youden index.
　停止判定部１２６は、符号関数を用いる場合、識別値が第１判定閾値（マイナス１）以下である場合、車両Ｖが走行中であると判定する。停止判定部１２６は、識別値が第２判定閾値（プラス１）以上の場合、車両Ｖが停止中と判定する。このように、停止判定部１２６は、現在の時刻において取得された加速度Ａ及び加速度Ａの積分値を用いて車両Ｖが停止しているか否かを判定する。そのため、停止判定部１２６は、実際に停止した車両Ｖの加速度Ａ及び積分値の特徴が、学習された特徴に一致するまでに時間がかかることがなく、実際に車両Ｖが停止したタイミングと、車両Ｖが停止したと判定するタイミングとのずれを低減することができる。 When the sign function is used, the stop determination unit 126 determines that the vehicle V is running when the identification value is equal to or less than the first determination threshold value (minus 1). When the identification value is equal to or higher than the second determination threshold value (plus 1), the stop determination unit 126 determines that the vehicle V is stopped. In this way, the stop determination unit 126 determines whether or not the vehicle V is stopped by using the integrated values of the acceleration A and the acceleration A acquired at the current time. Therefore, the stop determination unit 126 does not take time for the characteristics of the acceleration A and the integrated value of the actually stopped vehicle V to match the learned characteristics, and the timing at which the vehicle V actually stopped and the timing when the vehicle V actually stopped, It is possible to reduce the deviation from the timing at which the vehicle V is determined to have stopped.
［停止判定装置１が実行する停止判定処理の流れ］
　図３は、車両Ｖが停止したか否かを判定する停止判定処理の流れの一例を示すフローチャートである。停止判定装置１は、停止判定処理を車両Ｖのエンジンが始動している間、順次実行する。処理を実行する間隔は適宜定めればよいが、制御部１２の処理周期であり、具体的な値は例えば１００ミリ秒である。 [Flow of stop determination process executed by stop determination device 1]
FIG. 3 is a flowchart showing an example of the flow of the stop determination process for determining whether or not the vehicle V has stopped. The stop determination device 1 sequentially executes the stop determination process while the engine of the vehicle V is starting. The interval for executing the processing may be appropriately determined, but it is the processing cycle of the control unit 12, and the specific value is, for example, 100 milliseconds.
　まず、車輪速取得部１２１は、車両Ｖの車輪速Ｒを車輪速センサ２から取得する（ステップＳ１）。続いて、勾配推定部１２２は、車両Ｖが走行する道路の勾配を推定する（ステップＳ２）。具体的には、勾配推定部１２２は、加速度センサ３が検出した加速度Ｇｘから速度微分値ａを減算した重力加速度成分（Ｇｘ－ａ）を、重力加速度ｇで除算した値に逆正弦関数を用いて第１勾配推定値βを推定する。また、勾配推定部１２２は、加速度Ｇｘを重力加速度ｇで除算した値（Ｇｘ／ｇ）に逆三角関数を用いて第２勾配推定値θを推定する。なお、ステップＳ２は、ステップＳ１よりも前に実行してもよく、ステップＳ１とステップＳ２とを並列に実行してもよい。 First, the wheel speed acquisition unit 121 acquires the wheel speed R of the vehicle V from the wheel speed sensor 2 (step S1). Subsequently, the gradient estimation unit 122 estimates the gradient of the road on which the vehicle V travels (step S2). Specifically, the gradient estimation unit 122 uses an inverse sine function on the value obtained by dividing the gravitational acceleration component (Gx-a) obtained by subtracting the velocity differential value a from the acceleration Gx detected by the acceleration sensor 3 by the gravitational acceleration g. The first gradient estimated value β is estimated. Further, the gradient estimation unit 122 estimates the second gradient estimated value θ by using an inverse trigonometric function on the value (Gx / g) obtained by dividing the acceleration Gx by the gravitational acceleration g. Note that step S2 may be executed before step S1 or may be executed in parallel with step S1 and step S2.
　次に、加速度取得部１２３は、第１勾配推定値β及び第２勾配推定値θを用いて車両Ｖの進行方向の加速度Ａを取得する（ステップＳ３）。具体的には、加速度取得部１２３は、上記の式（３）を用いて加速度Ａを算出する。 Next, the acceleration acquisition unit 123 acquires the acceleration A in the traveling direction of the vehicle V using the first gradient estimated value β and the second gradient estimated value θ (step S3). Specifically, the acceleration acquisition unit 123 calculates the acceleration A using the above equation (3).
　積分値算出部１２４は、車輪速Ｒが所定速度Ｋ以下か否かを判定する（ステップＳ４）。積分値算出部１２４は、車輪速Ｒが所定速度Ｋ以下である場合（ステップＳ４でＹｅｓ）、車輪速Ｒが継続して所定速度Ｋ以下の間の加速度Ａを積分して積分値を算出する（ステップＳ５）。具体的には、積分値算出部１２４は、車輪速Ｒが所定速度Ｋ以下になった時点から現在まで間の加速度Ａを積分して積分値を算出する。そして、識別値算出部１２５は、最新の加速度Ａと、最新の加速度Ａを含む積分値とを識別関数に代入して識別値を算出する（ステップＳ６）。 The integral value calculation unit 124 determines whether or not the wheel speed R is equal to or less than the predetermined speed K (step S4). When the wheel speed R is equal to or less than the predetermined speed K (Yes in step S4), the integrated value calculation unit 124 calculates the integrated value by integrating the acceleration A while the wheel speed R is continuously equal to or less than the predetermined speed K. (Step S5). Specifically, the integrated value calculation unit 124 calculates the integrated value by integrating the acceleration A from the time when the wheel speed R becomes the predetermined speed K or less to the present. Then, the discrimination value calculation unit 125 calculates the discrimination value by substituting the latest acceleration A and the integrated value including the latest acceleration A into the discrimination function (step S6).
　停止判定部１２６は、識別値が判定閾値以上か否かを判定する（ステップＳ７）。停止判定部１２６は、識別値が判定閾値（第２判定閾値）以上である場合（ステップＳ７でＹｅｓ）、車両Ｖが停止していると判定する（ステップＳ８）。停止判定部１２６は、識別値が判定閾値（第１判定閾値）以下である場合（ステップＳ７でＮｏ）、車両Ｖが走行していると判定する（ステップＳ１０）。 The stop determination unit 126 determines whether or not the identification value is equal to or greater than the determination threshold value (step S7). When the discrimination value is equal to or higher than the determination threshold value (second determination threshold value) (Yes in step S7), the stop determination unit 126 determines that the vehicle V is stopped (step S8). When the identification value is equal to or less than the determination threshold value (first determination threshold value) (No in step S7), the stop determination unit 126 determines that the vehicle V is traveling (step S10).
　積分値算出部１２４は、車輪速Ｒが所定速度Ｋよりも大きい場合（ステップＳ４でＮｏ）、加速度Ａの積分値をゼロに変更し（ステップＳ９）、車両Ｖが走行していると判定する（ステップＳ１０）。 When the wheel speed R is larger than the predetermined speed K (No in step S4), the integral value calculation unit 124 changes the integral value of the acceleration A to zero (step S9), and determines that the vehicle V is traveling. (Step S10).
（変形例１）
　識別関数を作成するためのパターン認識モデルや、作成された識別関数により、識別値の正負の符号が反転することがある。そのため、停止判定部１２６は、識別関数に応じて、識別値が所定閾値以上の間車両が走行していると判定し、所定閾値未満になったら車両が停止していると判定してもよい。 (Modification 1)
Depending on the pattern recognition model for creating the discriminant function and the created discriminant function, the positive and negative signs of the discriminant value may be reversed. Therefore, the stop determination unit 126 may determine that the vehicle is running while the discrimination value is equal to or higher than the predetermined threshold value according to the discrimination function, and may determine that the vehicle is stopped when the discrimination value becomes less than the predetermined threshold value. ..
（変形例２）
　上記の実施の形態において、判定閾値は、第１判定閾値（マイナス１）と、第２判定閾値（プラス１）との２つの閾値を含んだ。なお、これに限らず、判定閾値は、１つであってもよい。例えば、１つの判定閾値は、識別関数により算出される識別値に応じて定めればよく、具体的な値は、例えばゼロである。この場合、停止判定部１２６は、識別値がゼロ未満の場合、車両Ｖが走行中と判定し、識別値がゼロ以上の場合、車両Ｖが停止中と判定する。 (Modification 2)
In the above embodiment, the determination threshold includes two thresholds, a first determination threshold (minus 1) and a second determination threshold (plus 1). Not limited to this, the determination threshold value may be one. For example, one determination threshold value may be determined according to the discrimination value calculated by the discrimination function, and the specific value is, for example, zero. In this case, the stop determination unit 126 determines that the vehicle V is running when the identification value is less than zero, and determines that the vehicle V is stopped when the identification value is zero or more.
［実施の形態に係る停止判定装置１の効果］
　以上説明したとおり、停止判定装置１は、車両Ｖの進行方向の加速度Ａと、車両Ｖの車輪速Ｒが所定速度Ｋ以下の間の加速度Ａを積分した積分値とを特徴量とするパターン認識モデルによって作成された識別関数を記憶している。停止判定装置１は、車両Ｖの車輪速Ｒと、車両Ｖの進行方向の加速度Ａとを順次取得する。次に、停止判定装置１は、取得した車輪速Ｒが継続して所定速度Ｋ以下である間に取得した加速度Ａを積分して積分値を算出する。続いて、停止判定装置１は、加速度Ａを新たに取得する毎に、加速度Ａ取得部が新たに取得した加速度Ａと、算出した積分値とを識別関数に代入して車両Ｖが停止しているか否かを判定するための識別値を算出する。そして、停止判定装置１は、算出した識別値が所定の判定閾値未満である間、車両Ｖが走行していると判定し、識別値が所定の判定閾値以上になったら、車両Ｖが停止していると判定する。 [Effect of stop determination device 1 according to the embodiment]
As described above, the stop determination device 1 features pattern recognition having an integrated value obtained by integrating the acceleration A in the traveling direction of the vehicle V and the acceleration A while the wheel speed R of the vehicle V is equal to or less than a predetermined speed K. Remembers the discriminant function created by the model. The stop determination device 1 sequentially acquires the wheel speed R of the vehicle V and the acceleration A in the traveling direction of the vehicle V. Next, the stop determination device 1 calculates the integrated value by integrating the acquired acceleration A while the acquired wheel speed R is continuously equal to or lower than the predetermined speed K. Subsequently, every time the stop determination device 1 newly acquires the acceleration A, the vehicle V stops by substituting the newly acquired acceleration A and the calculated integral value into the discrimination function. The identification value for determining whether or not it is present is calculated. Then, the stop determination device 1 determines that the vehicle V is traveling while the calculated identification value is less than the predetermined determination threshold value, and when the identification value becomes equal to or higher than the predetermined determination threshold value, the vehicle V stops. It is determined that it is.
　このように、停止判定装置１は、新たに取得された加速度Ａ及び加速度Ａの積分値を、加速度Ａと加速度Ａの積分値とを特徴量とするパターン認識モデルにより作成された識別関数に代入して得られた識別値を用いて車両Ｖが停止しているか否かを判定する。そのため、停止判定装置１は、実際に停止した車両Ｖの加速度Ａ及び積分値の特徴が、学習された特徴に一致するまでに時間がかかることがなく、実際に車両Ｖが停止したタイミングと、車両Ｖが停止したと判定するタイミングとのずれを低減することができる。 In this way, the stop determination device 1 substitutes the newly acquired integrated values of the acceleration A and the acceleration A into the discrimination function created by the pattern recognition model having the integrated values of the acceleration A and the acceleration A as feature quantities. It is determined whether or not the vehicle V is stopped by using the identification value obtained in the above procedure. Therefore, in the stop determination device 1, it does not take time for the characteristics of the acceleration A and the integrated value of the actually stopped vehicle V to match the learned characteristics, and the timing at which the vehicle V actually stops and the timing at which the vehicle V actually stopped are determined. It is possible to reduce the deviation from the timing at which the vehicle V is determined to have stopped.
　また、車輪速が所定速度以下になってからゼロになるまで実際の車輪の回転速度に係わらず所定速度を出力する車輪速センサ２を用いる場合であっても、停止判定装置１は、上記のとおり、実際に車両Ｖが停止したタイミングで、車両Ｖが停止したことを判定できる。 Further, even when the wheel speed sensor 2 that outputs a predetermined speed regardless of the actual rotation speed of the wheels is used from the time when the wheel speed becomes equal to or less than the predetermined speed to zero, the stop determination device 1 still has the above-mentioned. As shown, it can be determined that the vehicle V has stopped at the timing when the vehicle V actually stopped.
　以上、本発明を実施の形態を用いて説明したが、本発明の技術的範囲は上記実施の形態に記載の範囲には限定されず、その要旨の範囲内で種々の変形及び変更が可能である。例えば、装置の全部又は一部は、任意の単位で機能的又は物理的に分散・統合して構成することができる。また、複数の実施の形態の任意の組み合わせによって生じる新たな実施の形態も、本発明の実施の形態に含まれる。組み合わせによって生じる新たな実施の形態の効果は、もとの実施の形態の効果を併せ持つ。 Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes can be made within the scope of the gist. be. For example, all or part of the device can be functionally or physically distributed / integrated in any unit. Also included in the embodiments of the present invention are new embodiments resulting from any combination of the plurality of embodiments. The effect of the new embodiment produced by the combination has the effect of the original embodiment together.
１　停止判定装置
１１　記憶部
１２　制御部
１２１　車輪速取得部
１２２　勾配推定部
１２３　加速度取得部
１２４　積分値算出部
１２５　識別値算出部
１２６　停止判定部
２　車輪速センサ
３　加速度センサ 1 Stop determination device 11 Storage unit 12 Control unit 121 Wheel speed acquisition unit 122 Gradient estimation unit 123 Accelerometer acquisition unit 124 Integral value calculation unit 125 Identification value calculation unit 126 Stop determination unit 2 Wheel speed sensor 3 Accelerometer

Claims (7)

  1. 　車両の進行方向の加速度と、前記車両の車輪速が所定値以下の間の前記加速度を積分した積分値とを特徴量とするパターン認識モデルによって作成された識別関数を記憶する記憶部と、
    　前記車両の車輪速を順次取得する車輪速取得部と、
    　前記車両の進行方向の加速度を順次取得する加速度取得部と、
    　前記車輪速取得部が取得した前記車輪速が継続して前記所定値以下である間に前記加速度取得部が取得した前記加速度を積分して積分値を算出する積分値算出部と、
    　前記加速度取得部が前記加速度を新たに取得する毎に、前記加速度取得部が新たに取得した前記加速度と、前記積分値算出部が算出した前記積分値とを前記記憶部に記憶された前記識別関数に代入して前記車両が停止しているか否かを判定するための識別値を算出する識別値算出部と、
    　前記識別値算出部が算出した前記識別値が所定の判定閾値未満である間、前記車両が走行していると判定し、前記識別値が前記所定の判定閾値以上になったら、前記車両が停止していると判定する停止判定部と、
    　を備える停止判定装置。     A storage unit that stores an identification function created by a pattern recognition model having an acceleration in the traveling direction of the vehicle and an integral value obtained by integrating the accelerations while the wheel speed of the vehicle is equal to or less than a predetermined value.
    A wheel speed acquisition unit that sequentially acquires the wheel speed of the vehicle,
    An acceleration acquisition unit that sequentially acquires acceleration in the traveling direction of the vehicle,
    An integral value calculation unit that calculates an integral value by integrating the acceleration acquired by the acceleration acquisition unit while the wheel speed acquired by the wheel speed acquisition unit is continuously equal to or lower than the predetermined value.
    Each time the acceleration acquisition unit newly acquires the acceleration, the identification in which the acceleration newly acquired by the acceleration acquisition unit and the integral value calculated by the integral value calculation unit are stored in the storage unit. An identification value calculation unit that calculates an identification value for determining whether or not the vehicle is stopped by substituting it into a function.
    While the identification value calculated by the identification value calculation unit is less than the predetermined determination threshold value, it is determined that the vehicle is running, and when the identification value becomes equal to or more than the predetermined determination threshold value, the vehicle stops. The stop determination unit that determines that the product is running, and
    A stop determination device.
  2. 　前記停止判定部は、前記識別値が前記パターン認識モデルにより定まる前記判定閾値未満である間、前記車両が走行していると判定し、前記識別値が前記判定閾値以上になったら、前記車両が停止していると判定する、
    　請求項１に記載の停止判定装置。     The stop determination unit determines that the vehicle is running while the identification value is less than the determination threshold value determined by the pattern recognition model, and when the identification value becomes equal to or greater than the determination threshold value, the vehicle is moved. Judge that it is stopped,
    The stop determination device according to claim 1.
  3. 　前記記憶部は、前記車両に搭載された加速度センサの出力値と、重力加速度と、前記車両が走行する道路の勾配とを用いて算出された前記進行方向の加速度と、前記加速度の積分値とを前記特徴量とする前記パターン認識モデルによって作成された前記識別関数を記憶し、
    　前記識別値算出部は、前記記憶部に記憶された前記識別関数に代入して、前記識別値を算出する、
    　請求項１又は２に記載の停止判定装置。     The storage unit includes the output value of the acceleration sensor mounted on the vehicle, the gravitational acceleration, the acceleration in the traveling direction calculated using the gradient of the road on which the vehicle travels, and the integrated value of the acceleration. The discriminant function created by the pattern recognition model having the feature quantity of
    The identification value calculation unit calculates the identification value by substituting it into the identification function stored in the storage unit.
    The stop determination device according to claim 1 or 2.
  4. 　前記積分値算出部は、前記車輪速取得部が取得した前記車輪速が前記所定値以下になった後に、前記所定値よりも大きくなった場合、前記積分値をゼロにする、
    　請求項１から３のいずれか一項に記載の停止判定装置。     The integral value calculation unit sets the integral value to zero when the wheel speed acquired by the wheel speed acquisition unit becomes larger than the predetermined value after the wheel speed becomes equal to or less than the predetermined value.
    The stop determination device according to any one of claims 1 to 3.
  5. 　前記積分値算出部は、新たな前記加速度が取得される度に、前記車輪速が前記所定値以下になった時刻から前記新たな加速度が取得された時刻までの間に取得された複数の前記加速度を積分して前記積分値を算出する、
    　請求項１から４のいずれか一項に記載の停止判定装置。     Each time the new acceleration is acquired, the integral value calculation unit has a plurality of acquisitions between the time when the wheel speed becomes equal to or less than the predetermined value and the time when the new acceleration is acquired. Calculate the integrated value by integrating the acceleration,
    The stop determination device according to any one of claims 1 to 4.
  6. 　前記加速度取得部が前記加速度を取得する時間間隔と、前記車輪速取得部が前記車輪速を取得する時間間隔とは、同じである、
    　請求項１から５のいずれか一項に記載の停止判定装置。     The time interval at which the acceleration acquisition unit acquires the acceleration and the time interval at which the wheel speed acquisition unit acquires the wheel speed are the same.
    The stop determination device according to any one of claims 1 to 5.
  7. 　前記車輪速取得部は、前記車輪速が前記所定値以下になってから前記車輪速がゼロになるまで、実際の車輪の回転速度に係わらず前記所定値を出力するセンサが検出した前記車輪速を取得する、
    　請求項１から６のいずれか一項に記載の停止判定装置。     The wheel speed acquisition unit detects the wheel speed detected by a sensor that outputs the predetermined value regardless of the actual rotation speed of the wheel from the time when the wheel speed becomes equal to or lower than the predetermined value until the wheel speed becomes zero. To get,
    The stop determination device according to any one of claims 1 to 6.
PCT/JP2021/035923 2020-09-30 2021-09-29 Stop determining device WO2022071415A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020-166171 2020-09-30
JP2020166171A JP7310773B2 (en) 2020-09-30 2020-09-30 Stop judgment device

Publications (1)

Publication Number Publication Date
WO2022071415A1 true WO2022071415A1 (en) 2022-04-07

Family

ID=80950636

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/035923 WO2022071415A1 (en) 2020-09-30 2021-09-29 Stop determining device

Country Status (2)

Country Link
JP (1) JP7310773B2 (en)
WO (1) WO2022071415A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002040040A (en) * 2000-07-21 2002-02-06 Denso Corp Processing device using acceleration
JP2007170882A (en) * 2005-12-20 2007-07-05 Furuno Electric Co Ltd Moving state detecting apparatus
JP2013250064A (en) * 2012-05-30 2013-12-12 Seiko Epson Corp Stop determination method, program performing stop determination and stop determination device
JP2017146279A (en) * 2016-02-19 2017-08-24 ヤフー株式会社 Estimation device, estimation method, and estimation program
US20200088756A1 (en) * 2018-09-14 2020-03-19 Hyundai Motor Company System and method for estimating wheel speed of vehicle

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002040040A (en) * 2000-07-21 2002-02-06 Denso Corp Processing device using acceleration
JP2007170882A (en) * 2005-12-20 2007-07-05 Furuno Electric Co Ltd Moving state detecting apparatus
JP2013250064A (en) * 2012-05-30 2013-12-12 Seiko Epson Corp Stop determination method, program performing stop determination and stop determination device
JP2017146279A (en) * 2016-02-19 2017-08-24 ヤフー株式会社 Estimation device, estimation method, and estimation program
US20200088756A1 (en) * 2018-09-14 2020-03-19 Hyundai Motor Company System and method for estimating wheel speed of vehicle

Also Published As

Publication number Publication date
JP2022057760A (en) 2022-04-11
JP7310773B2 (en) 2023-07-19

Similar Documents

Publication Publication Date Title
US10370004B2 (en) System and method for determining state of stiffness of tires of vehicle
CN107074241B (en) Method for estimating the side-slip angle of four-wheel car
JP7068770B2 (en) Methods, systems, and vehicles for analyzing rider abilities
CN103502075B (en) The estimation of road inclination
CN107933563A (en) For determining the method and system to rub between ground and vehicle tyre
CN111879957A (en) Vehicle dynamics determination based on fuzzy logic and enhanced machine learning
WO2016020834A1 (en) A method for estimating variables affecting the vehicle dynamics and corresponding virtual sensor
CN111114551B (en) Vehicle ramp gradient identification method and device
CN110217239A (en) A kind of vehicle yaw velocity measurement method and apparatus
BR112013033123B1 (en) process for determining whether a vehicle is swaying, vehicle and computer readable medium
US20210070308A1 (en) Apparatus and method for controlling autonomous driving
CN108304594B (en) Method for judging driving stability of automobile based on speed and gyroscope data
JP2024531274A (en) Method and apparatus for calculating and characterizing road surface unevenness - Patents.com
CN115315622A (en) Tire wear estimation method and tire wear shape determination method
CN111094099A (en) Method for determining the position of the center of gravity of a vehicle
CN114084199B (en) Train stability evaluation method and system based on recursive graph analysis
JP2024531272A (en) Method and apparatus for calculating and characterizing road surface unevenness - Patents.com
KR101827152B1 (en) Method for deciding a road surface using vehicle data
WO2022071415A1 (en) Stop determining device
Alshawi et al. An adaptive unscented kalman filter for the estimation of the vehicle velocity components, slip angles, and slip ratios in extreme driving manoeuvres
CN111645670B (en) Heavy-duty vehicle roll state detection method based on support vector machine
KR102570295B1 (en) Vehicle and control method thereof
JP5404062B2 (en) Tire pressure drop detection device and method, and tire pressure drop detection program
JP4915326B2 (en) In-vehicle control device
CN115284809B (en) Intelligent internet fleet active suspension control method and system and computer equipment

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21875713

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21875713

Country of ref document: EP

Kind code of ref document: A1