JP2017187506A - Estimation device, movement direction estimation method, and movement direction estimation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To easily identify an installation posture and accurately estimate a vehicle travel direction.SOLUTION: An estimation device comprises a detection unit for detecting acceleration speed, an identification unit for identifying a gravity direction using an average of the acceleration speed detected by the detection unit in a predetermined state and an estimation unit for, from the acceleration speed detected by the detection unit, calculating variation of the acceleration speed on a flat surface perpendicular to the gravity direction identified by the identification unit and, on the basis of the calculated variation, estimating a movement direction of a terminal device.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an estimation device, a movement direction estimation method, and a movement direction estimation program.

  2. Description of the Related Art Conventionally, a car navigation technology (hereinafter also referred to as “guidance”) that guides a vehicle on which a user is boarding to a destination using a portable terminal device such as a smartphone is known. A terminal device that performs such guidance uses a satellite positioning system such as GPS (Global Positioning System) to identify the current location of the vehicle, and displays a map or guidance route screen and the identified current location in an overlapping manner. .

  On the other hand, the terminal device cannot display the current location in a place where it is difficult to receive a signal from a satellite such as in a tunnel. The same problem is not limited to GPS, but is common to all positioning using external signals (for example, radio waves from mobile phone (cellular) base stations, wireless LAN radio waves, etc.). Therefore, a method of estimating the current location of the vehicle based on the moving direction and speed of the vehicle can be considered. For example, a method has been proposed in which a device having an accelerometer is fixed in a vehicle in a predetermined posture, and a traveling direction of the vehicle is specified from acceleration detected by the device.

JP 11-248455 A

  However, the terminal device such as a smartphone easily changes the direction in which the vehicle has moved because the installation posture in the vehicle varies depending on the type of the vehicle on which the user gets on, the usage status of the holder that holds the terminal device, etc. There is a problem that cannot be estimated.

  For example, since the terminal device has an accelerometer that detects axial acceleration with respect to the terminal device, the direction of the detected acceleration is based on the moving direction of the vehicle based on the installation posture of the terminal device. Convert to And a terminal device specifies the advancing direction and speed of a vehicle using the acceleration which changed the direction, and specifies the present location of a vehicle from the specified advancing direction and speed. However, when the installation posture is unknown, the terminal device cannot change the direction of acceleration and cannot specify the traveling direction of the vehicle.

  The present application has been made in view of the above, and an object thereof is to provide an estimation apparatus, a movement direction estimation method, and a movement direction estimation program that can easily specify the installation posture and accurately estimate the traveling direction of the vehicle. To do.

  The estimation apparatus according to the present application includes a detection unit that detects acceleration, a specifying unit that specifies a gravitational direction using an average value of acceleration detected by the detection unit in a predetermined state, and an acceleration detected by the detection unit. And an estimation unit that calculates variation in acceleration on a plane perpendicular to the direction of gravity specified by the specifying unit, and estimates a moving direction of the terminal device based on the calculated variation.

  According to one aspect of the embodiment, it is possible to easily specify the installation posture and accurately estimate the traveling direction of the vehicle.

Drawing 1 is a figure for explaining an example of an operation effect which a terminal unit concerning an embodiment exhibits. FIG. 2 is a diagram illustrating an example of a functional configuration of the terminal device according to the embodiment. FIG. 3 is a flowchart illustrating an example of a flow of guidance processing executed by the terminal device according to the embodiment. FIG. 4 is a flowchart illustrating an example of a flow of estimation processing executed by the terminal device according to the embodiment. FIG. 5 is a diagram for explaining an example of acceleration generated when the vehicle moves. FIG. 6 is a diagram illustrating an example of a process in which the terminal device according to the embodiment calculates the speed of the vehicle.

  Hereinafter, an embodiment (hereinafter referred to as “embodiment”) for carrying out the estimation apparatus, the movement direction estimation method, and the movement direction estimation program according to the present application will be described in detail with reference to the drawings. In addition, the estimation apparatus, the movement direction estimation method, and the movement direction estimation program according to the present application are not limited by this embodiment. Further, in the following embodiments, the same parts and processes are denoted by the same reference numerals, and redundant description is omitted.

  In the following description, an example of car navigation that guides a vehicle on which a user has boarded to a destination will be described as processing executed by the estimation device, but the embodiment is not limited thereto. For example, the estimation device performs processing described below and guides the user to a destination even when the user is walking or when using a transportation means other than a vehicle such as a train. May be executed.

[1. (Overview of effects)
First, the concept of the effect which the terminal device 100 which is an example of an estimation apparatus exhibits is demonstrated using FIG. Drawing 1 is a figure for explaining an example of an operation effect which a terminal unit concerning an embodiment exhibits. For example, the terminal device 100 is a mobile terminal such as a smartphone, a tablet terminal or a PDA (Personal Digital Assistant), or a terminal device such as a notebook PC (Personal Computer), such as a mobile communication network or a wireless LAN (Local Area Network). The terminal device can communicate with an arbitrary server via the network N.

  In addition, the terminal device 100 has a car navigation function for guiding a vehicle on which a user gets to a destination. For example, when receiving the input of the destination from the user, the terminal device 100 acquires route information for guiding the user to the destination from a server or the like not shown. For example, the route information includes the route to the destination where the vehicle can be used, the information on the expressway included in the route, the traffic jam information on the route, the facility serving as a guide for guidance, the information on the map displayed on the screen, the guidance Data such as images such as voices and maps that are sometimes output are included.

  Further, the terminal device 100 has a positioning function for specifying the position of the terminal device 100 (hereinafter referred to as “current location”) at predetermined time intervals using a satellite positioning system such as GPS (Global Positioning System). . Then, the terminal device 100 displays an image such as a map included in the route information on a liquid crystal screen, electroluminescence, an LED (Light Emitting Diode) screen or the like (hereinafter simply referred to as “screen”) and specifies the image. The current location is displayed on the map each time. In addition, the terminal device 100 displays a left turn, a right turn, a change in the lane to be used, an estimated arrival time at the destination, or the like according to the specified current location, or outputs by voice from the terminal device 100, a vehicle speaker, or the like. .

  Here, in the satellite positioning system, signals transmitted from a plurality of satellites are received, and the current location of the terminal device 100 is specified using the received signals. For this reason, the terminal device 100 cannot identify the current location when it cannot properly receive a signal transmitted from a satellite such as a place in a tunnel or a building group. Moreover, the application etc. which make the terminal device 100 implement | achieve guidance do not have a function which acquires information, such as a speed and a moving direction, from a vehicle. For this reason, the method of installing the acceleration sensor which measures an acceleration in the terminal device 100, and estimating the position of the terminal device 100 based on the acceleration which the acceleration sensor measured can be considered.

  For example, as shown in FIG. 1A, the terminal device 100 uses the short direction of the screen as the x axis, the long direction of the screen as the y axis, and the direction perpendicular to the screen as the z axis. The acceleration in the xyz axis direction is measured. For example, when the terminal device 100 has the screen as the front, the front side is the + z axis direction, the back side is the −z axis direction, and when the terminal device 100 is used, the upper side of the screen is the + x axis direction, and the lower side of the screen is − The acceleration in the terminal coordinate system is measured with the x-axis direction, the left side of the screen as the + y-axis direction, and the right side of the screen as the -y-axis direction.

  On the other hand, as shown in FIG. 1B, the moving direction and speed of the vehicle C10 used by the user is such that the vehicle travels on a plane perpendicular to the Z axis, with the direction in which the vehicle travels being the Z axis. The direction of turning left or right when traveling is represented by a vehicle coordinate system in which the Y-axis direction is the Y-axis direction and the vertical direction of the vehicle is the X-axis direction. For example, the moving direction and speed of the vehicle C10 are the + X axis direction for the upward direction of the vehicle, the −X axis direction for the downward direction (that is, the ground side), the + Y axis direction for the left turn direction, and the −Y axis direction for the right turn direction. The vehicle rear direction is represented by a vehicle coordinate system in which the rear direction of the vehicle is the + Z-axis direction and the front direction is the -Z-axis direction.

  For this reason, the terminal device 100 converts the acceleration measured in the terminal coordinate system into the vehicle coordinate system, and measures the moving direction and speed of the vehicle using the converted acceleration. However, the terminal device 100 is, for example, held by the passenger in the passenger seat by hand, or held by the holder, the angle at which the holder holds the terminal device 100, the vehicle type of the vehicle on which the user is riding, etc. Depending on the situation, the installation posture is different each time. For this reason, when the installation posture is unknown, even if the acceleration is measured, the terminal coordinate system cannot be converted into the vehicle coordinate system.

  Therefore, the terminal device 100 executes an estimation process. First, the terminal device 100 includes an acceleration sensor that detects acceleration with respect to the terminal device 100. Moreover, the terminal device 100 specifies the direction of gravity in the vehicle coordinate system using the average value of acceleration detected in a predetermined state. And the terminal device 100 estimates the moving direction based on the specified gravity direction from the acceleration detected by the acceleration sensor, that is, the moving direction of the vehicle C10 in the vehicle coordinate system.

  Hereinafter, an example of a functional configuration and an effect of the terminal device 100 that realizes the estimation process described above will be described with reference to the drawings.

[2. Example of functional configuration)
FIG. 2 is a diagram illustrating an example of a functional configuration of the terminal device according to the embodiment. As illustrated in FIG. 2, the terminal device 100 includes a communication unit 11, a storage unit 12, a plurality of acceleration sensors 13 a to 13 c (hereinafter, may be collectively referred to as “acceleration sensor 13”), and a GPS receiving antenna. 14, an output unit 15, and a control unit 16. The communication unit 11 is realized by, for example, a NIC (Network Interface Card). The communication unit 11 is connected to the network N in a wired or wireless manner. When the communication unit 11 receives a destination from the terminal device 100 and the terminal device 100, the communication unit 11 distributes route information indicating a route to the destination. Send and receive information.

  The storage unit 12 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 12 has a guidance information database 12a that is various data used for executing guidance. For example, route information to a destination received from a server or the like (not shown) is stored in the guidance information database 12a.

  The acceleration sensor 13 measures the magnitude and direction of acceleration related to the terminal device 100 at a predetermined time interval (for example, 5 milliseconds). For example, the acceleration sensor 13a measures the acceleration in the x-axis direction in the terminal coordinate system. The acceleration sensor 13b measures acceleration in the y-axis direction in the terminal coordinate system. The acceleration sensor 13c measures the acceleration in the z-axis direction in the terminal coordinate system. That is, the terminal device 100 can obtain a vector indicating the direction and magnitude of the acceleration with respect to the terminal device 100 by using the acceleration measured by each of the acceleration sensors 13a to 13c as the acceleration in each axial direction of the terminal coordinate system. it can.

  The GPS receiving antenna 14 is an antenna for receiving signals used in a satellite positioning system such as GPS from a satellite. The output unit 15 is a screen for displaying a map and a current location when performing guidance, and a speaker for outputting sound.

  The control unit 13 is stored in a storage device inside the terminal device 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like. The various programs are executed by using a storage area such as a RAM as a work area. In the example illustrated in FIG. 2, the control unit 13 may be described as a guidance execution unit 17, a voice output unit 18, an image output unit 19, and a direction estimation unit 20 (hereinafter collectively referred to as the processing units 17 to 20). ). In addition, the direction estimation unit 20 includes a detection unit 21, a specification unit 22, a determination unit 23, an estimation unit 24, and a calculation unit 25.

  The connection relationship between the processing units 17 to 20 included in the control unit 13 is not limited to the connection relationship illustrated in FIG. 2, and may be another connection relationship. Each of the processing units 17 to 20 realizes / executes the function / action (for example, FIG. 1) of the guidance process as described below, but these are functional units arranged for explanation, The actual hardware elements and software modules may be matched. That is, the terminal device 100 may realize and execute the guidance process in arbitrary functional units as long as the following functions and actions of the guidance process can be realized and executed.

[3. Example of effects in guidance processing]
Hereinafter, the content of the guidance process executed and realized by each of the processing units 17 to 20 will be described using the flowchart shown in FIG. FIG. 3 is a flowchart illustrating an example of a flow of guidance processing executed by the terminal device according to the embodiment.

  First, the guidance execution unit 17 determines whether or not a destination is input from the user (step S101). When the destination is input (step S101: Yes), the guidance execution unit 17 acquires route information from an external server (not shown) (step S102). Here, the guidance execution unit 17 determines whether or not the GPS can be used (step S103).

  For example, the guidance execution unit 17 determines that the GPS cannot be used when the GPS receiving antenna 14 cannot receive a signal from a satellite or when the number of satellites that can receive the signal is smaller than a predetermined threshold. (Step S103: Yes), the current location is acquired from the moving direction and speed of the vehicle C10 estimated by the direction estimating unit 20 (Step S104). For example, the guidance execution unit 17 estimates the location when moving at the estimated speed in the movement direction estimated by the direction estimation unit 20 as the new location, starting from the location specified or estimated from the previous GPS as the current location. To do. In addition, the specific content of the estimation process in which the direction estimation part 20 estimates the moving direction and speed of the vehicle C10 is mentioned later.

  On the other hand, when it is determined that the GPS can be used (step S103: No), the guidance execution unit 17 specifies the current location using the GPS (step S105). Then, the guidance execution unit 17 controls the voice output unit 18 and the image output unit 19 to output guidance using the current location using GPS or the estimated current location (step S106). For example, the voice output unit 18 outputs, from the output unit 15, voice indicating the current location, the direction in which the vehicle C <b> 10 should travel, and the like according to control from the guidance execution unit 17. Further, the image output unit 19 outputs, from the output unit 15, an image in which the current location and the surrounding map are overlaid, an image indicating the direction in which the vehicle C <b> 10 should travel, etc.

  Subsequently, the guidance execution unit 17 determines whether or not the current position is around the destination (step S107). If the guidance execution unit 17 determines that the current location is around the destination (step S107: Yes), the guidance execution unit 17 controls the audio output unit 18 and the image output unit 19 to output end guidance indicating the end of the guidance. (Step S108), and the process ends. On the other hand, when the guidance execution unit 17 determines that the current location is not around the destination (step S107: No), it executes step S103. In addition, when the destination is not input (step S101: No), the guidance execution part 17 waits until it is input.

[4. Example of effects in estimation process)
Next, the contents of the guidance process executed and realized by the detection unit 21, the identification unit 22, the determination unit 23, the estimation unit 24, and the calculation unit 25 included in the direction estimation unit 20 will be described using the flowchart illustrated in FIG. FIG. 4 is a flowchart illustrating an example of a flow of estimation processing executed by the terminal device according to the embodiment.

  First, the detection unit 21 acquires acceleration from the acceleration sensor 13 (step S201). Here, it is considered that the acceleration value measured by the acceleration sensor 13 includes noise. Therefore, the detection unit 21 calculates an average value of measured accelerations for each of the acceleration sensors 13a to 13c using a moving average method which is a kind of low-pass filter (step S202). Here, the moving average method is a method of calculating an average of a plurality of data measured most recently when data continuously measured exist.

  Specifically, the detection unit 21 calculates an average value of a plurality of acceleration values detected until a predetermined time elapses, or an average value of a predetermined number of acceleration values detected continuously. Is output as the average value of the detected accelerations. For example, the detection unit 21 sets the average value of the acceleration values measured by the acceleration sensor 13a from time t-n to time t as the acceleration value measured by the acceleration sensor 13a at time t, and sets the time t-n + 1. The average value of the acceleration values measured by the acceleration sensor 13a from the time t + 1 to the time t + 1 is defined as the acceleration value measured by the acceleration sensor 13a at the time t + 1.

  Subsequently, the determination unit 23 determines whether or not the terminal device 100 is moving based on the characteristics of the acceleration value (step S203). For example, the determination unit 23 uses a support vector machine (SVM) that has learned features of acceleration values measured while the terminal device 100 is moving and not moving. Then, it is determined whether or not the terminal device 100 is moving.

  Here, the support vector machine is a kind of learning model (that is, a model generated by supervised learning) that learns features of teacher data. For example, the SVM used by the determination unit 23 indicates stop data indicating acceleration in three axes when a certain vehicle is stopped, and acceleration in three axes measured during acceleration or movement. This is a learning model in which feature data has been learned so that stop data and travel data can be accurately separated using travel data as teacher data. For example, the SVM has an amplitude, a standard deviation, a frequency, an average value, a maximum value, and a minimum value included in a certain time (for example, 1 second) of measured acceleration values for each axial direction. Learn value features.

  The SVM that has learned the characteristics of the travel data and the stop data in this way is measured during travel based on the characteristics of the acceleration in each axis direction when newly measured accelerations in the three axis directions are input. It is possible to specify with high accuracy whether the acceleration is a measured acceleration or an acceleration measured at the time of stopping. Therefore, the determination unit 23 inputs the acceleration in each axis direction detected by the detection unit 21 to the SVM learned in advance, and when the SVM determines that the acceleration value is the acceleration measured at the time of stoppage. It is determined that the vehicle C10 is stopped.

  Note that the terminal device 100 may use an SVM that has been learned using teacher data measured by the terminal device 100 itself or a terminal device of the same type as the terminal device 100 in order to realize accurate determination. Further, the terminal device 100 may use an SVM that has been learned using teacher data measured by various types of terminal devices including the same type of terminal device as the terminal device 100 in order to achieve robust determination.

  Further, the SVM teacher data may remain in the coordinate system (for example, the terminal coordinate system) of the apparatus for measuring acceleration, or may be data converted into the vehicle coordinate system (for example, the vehicle coordinate system). Good. In order to make an accurate determination, it is desirable that the teacher data of the SVM is acceleration measured in the same posture as when the terminal device 100 performs guidance by a terminal device of the same type as the terminal device 100.

  Subsequently, when the determination unit 23 determines that the determination unit 23 is in a stopped state (step S203: Yes), the specifying unit 22 specifies the gravity direction using the average value of acceleration (step S204). For example, as shown in FIG. 1C, the acceleration sensor 13 of the terminal device 100 constantly detects not only the acceleration according to the acceleration / deceleration of the vehicle C10 but also the gravitational acceleration G acting on the terminal device 100. It becomes. Here, considering the operation of the vehicle C10, it is considered that the acceleration detected by the terminal device 100 by the acceleration / deceleration of the vehicle C10 almost cancels when viewed within a sufficient period.

  For this reason, it is estimated that the average value and direction of the detected acceleration are substantially the same as the value and direction of the gravitational acceleration G. Therefore, the terminal device 100 can specify the direction of the gravitational acceleration G in the terminal coordinate system (hereinafter referred to as “gravity direction”) by calculating the average value of the measured accelerations. Further, since the gravity direction in the terminal coordinate system coincides with the gravity direction in the vehicle coordinate system, that is, the -X axis direction, it serves as a guideline for specifying the installation posture of the terminal device 100 and, consequently, the moving direction of the vehicle C10.

  Therefore, the estimation unit 24 estimates the moving direction based on the direction of gravity specified by the specifying unit 22 from the detected acceleration by executing the processing shown in steps S205 to 208 shown in FIG. First, the estimation unit 24 specifies a rotation angle around the Y axis and a rotation angle around the Z axis from the estimated direction of gravity (step S205).

  For example, as shown in FIG. 1D, when the origins of the terminal coordinate system and the vehicle coordinate system are overlapped and the Y axis and the y axis coincide with each other, the x about the Y axis direction is the center. The angle β between the axis and the X-axis can specify how much the terminal device 100 is inclined in the back direction of the screen. If the Z-axis and the z-axis coincide with each other, the angle γ between the y-axis and the Y-axis centering on the Z-axis direction will cause the terminal device 100 to move left or right when the screen is on the front side. You can only identify if you are leaning. A more general identification method will be described using mathematical expressions in the description to be described later.

  Here, the gravitational acceleration G is a force in the −X axis direction. The magnitude of the gravitational acceleration G can be represented by the square root of the sum of squares of accelerations in the respective axis directions in the terminal coordinate system. Then, the estimation unit 24 can calculate the angle β using a trigonometric function from the detected acceleration magnitude in the −x-axis direction and the magnitude of the gravitational acceleration G. Similarly, the estimation unit 24 can calculate the angle γ using a trigonometric function from the detected magnitude of the acceleration in the + y-axis direction and the magnitude of the gravitational acceleration G. As a result, the estimation unit 24 can specify the YZ plane perpendicular to the specified gravity direction. In addition, the estimation part 24 should just specify a YZ plane based on the gravity direction specified last time, when it determines with it not being a stop state (step S203: No).

  Subsequently, the estimation unit 24 calculates the variation in acceleration in the plane direction perpendicular to the specified gravity direction, that is, the variance, and sets the direction in which the variance is greatest as the traveling direction of the vehicle C10, that is, the -Z axis direction. (Step S206). For example, FIG. 5 is a diagram illustrating an example of acceleration generated when the vehicle moves. For example, the YZ plane in the vehicle coordinate system is a plane perpendicular to the X-axis direction, and can be divided into a Z-axis direction that is the traveling direction of the vehicle C10 and a Y-axis direction that is perpendicular to the Z-axis. Here, considering the behavior of the vehicle C10, as shown by the dotted straight line in FIG. 5, among the accelerations generated by acceleration / deceleration of the vehicle C10, the acceleration when moving straight from the stop state to the departure state is Presumed to be the strongest acceleration. Further, as shown by the dotted curve in FIG. 5, even if the vehicle C10 is bent in the Y-axis direction, the vehicle C10 moves forward (−Z-axis direction).

  As a result, when the acceleration measured by the terminal device 100 is projected onto the YZ plane, the direction in which the measured acceleration spreads the most, that is, the direction with the largest variance is the longitudinal direction of the vehicle C10, that is, the −Z axis or It is predicted to be in the + Z-axis direction. At this stage, either the + Z-axis direction or the −Z-axis direction has an indeterminate direction of travel, but the method for specifying the direction of travel will be described using mathematical formulas in the following description. In the following description, A description will be given assuming that the direction in which the variance is greatest is the −Z-axis direction.

  For example, the estimation unit 24 projects the measured acceleration on the YZ plane perpendicular to the direction of gravity as shown in FIG. The moving direction of the vehicle C10, that is, the −Z axis direction is used. As shown in FIG. 1F, when the direction P is estimated to be the −Z-axis direction, the terminal device 100 is determined by the angle α between the Z-axis and the z-axis centered on the X-axis direction. It is possible to specify how much it rotates about the vertical direction.

  Thereafter, as shown in FIG. 1G, the terminal device 100 performs coordinate conversion of the measured acceleration using a rotation matrix that converts the measured gravity direction into the X-axis direction of the vehicle coordinate system, and moves Calculate direction and speed. More specifically, as shown in FIG. 4, when the estimation unit 24 identifies the angles α, β, and γ, the estimation unit 24 converts the terminal coordinate system to the vehicle coordinate system using the identified angles α, β, and γ. A rotation matrix is calculated (step S207).

  For example, the estimation unit 24 rotates the vector of the terminal coordinate system by an angle −α around the x axis, the angle −β around the y axis, and the angle −γ around the z axis. Generate a matrix. And the estimation part 24 converts the acceleration of the detected terminal coordinate system into a vehicle coordinate system using a rotation matrix, and estimates the advancing direction of the vehicle C10 using the converted acceleration (step S208). . That is, the estimation unit 24 uses the rotation matrix that matches the gravitational acceleration direction measured in the terminal coordinate system with the X-axis direction in the vehicle coordinate system, and converts the detected acceleration into an acceleration in the moving direction based on the gravitational direction. The direction of movement is estimated by converting and analyzing the converted acceleration.

  For example, the estimation unit 24 estimates the movement direction of the vehicle C10 and a change in the movement direction using acceleration on the YZ plane perpendicular to the X axis, that is, acceleration in the Y axis direction and the Z axis direction. More specifically, the estimation unit 24 determines that the vehicle C10 is accelerating when acceleration in the + Z-axis direction is measured, and decelerates the vehicle when acceleration in the -Z-axis direction is detected. It is determined that Further, when the acceleration in the + Y-axis direction perpendicular to the −Z-axis direction, which is the traveling direction, is measured, the estimation unit 24 determines that the vehicle C10 has turned to the right, and the acceleration in the −Y-axis direction is measured. In this case, it is determined that the vehicle C10 has made a left turn.

  Subsequently, the calculation unit 25 calculates the moving speed of the vehicle C10 using the converted acceleration (step S209). Specifically, the calculation unit 25 uses the average value of the Z-axis component of acceleration when the vehicle C10 is stopped as the origin (0), and uses the integrated value of the Z-axis component of acceleration as the moving speed of the vehicle C10.

  For example, FIG. 6 is a diagram illustrating an example of processing in which the terminal device according to the embodiment calculates the speed of the vehicle. In the example shown in FIG. 6, the time lapse of the speed is plotted by taking the speed value in the −Z-axis direction on the vertical axis and the time on the horizontal axis. For example, when the vehicle C10 accelerates forward between time T1 and time T2, since the acceleration in the + Z-axis direction is detected, the calculation unit 25 determines that the speed gradually increases as shown in FIG. To do. Further, when the vehicle C10 decelerates between time T2 and time T3, acceleration in the −Z-axis direction is detected, so the speed shown in FIG. 6A is set to the maximum speed and the speed of the vehicle C10 is gradually increased. To slow down.

  Here, even if the vehicle C10 stops at time T3, depending on the setting of the origin, the accuracy of the acceleration that can be detected by the terminal device 100, and the like, as shown in FIG. May be positive after time T3. If such an integrated value is continuously used, the error is gradually increased because the error is accumulated.

  Therefore, when the determination unit 23 determines that the vehicle C10 is not moving, the calculation unit 25 corrects the integral value to 0 as shown in (C) of FIG. Similarly, when the vehicle accelerates from time T4, the calculation unit 25 calculates the speed by integrating the acceleration of the acceleration. Then, even when the integral value of the actually measured acceleration transitions as shown in (D) of FIG. 6, the calculation unit 25 determines that the vehicle C10 has stopped at time T5. As shown in the middle (E), the integral value is corrected to zero.

[5. Example of mathematical expression in estimation process)
Next, an example of processing in which the estimation unit 24 calculates a rotation matrix for converting the terminal coordinate system into the vehicle coordinate system will be described using mathematical expressions. In addition, the process which the estimation part 24 performs is not limited to the process which the following numerical formula shows. For example, the estimation unit 24 may perform coordinate conversion from the terminal coordinate system to the vehicle coordinate system using a mathematical expression expressing the primary conversion.

For example, each axis of the terminal coordinate system is an xyz axis, and each axis of the vehicle coordinate system is an XYZ axis. In such a case, the process of converting the vehicle coordinate system to the terminal coordinate system is expressed by the following equation (1). In equation (1), the rotation angle around the x axis is α, the rotation angle around the y axis is β, the rotation angle around the z axis is γ, and the coordinates by rotation around the x axis R _x (α) is a rotation matrix that performs transformation, R _y (β) is a rotation matrix that performs coordinate transformation by rotation around the y axis, and R _z is a rotation matrix that performs coordinate transformation by rotation around the z axis. (Γ).

Further, the rotation matrix R _x (α), the rotation matrix R _y (β), and the rotation matrix R _z (γ) (hereinafter, may be collectively referred to as “each rotation matrix”) are expressed by the following equations. (2) to (4).

  Here, since the gravitational acceleration is acceleration in the −X axis direction, it can be expressed by the following expression (5) in the vehicle coordinate system.

On the other hand, the gravitational acceleration in each axial direction detected in the terminal coordinate system is described as a _x , a _y , and a _z . In such a case, since the gravitational accelerations a _x , a _y , and a _z in the terminal coordinate system are values obtained by converting the gravitational acceleration expressed by the equation (5) by each rotation matrix, the following equation (6) is established.

  As a result, Expression (7) is obtained from the value in the z-axis direction in Expression (6).

  Also, considering the magnitude of gravitational acceleration, equation (8) holds, and therefore equation (9) is obtained from the values in the x-axis and y-axis directions in equation (6). As a result, the terminal device 100 can specify the rotation angle β around the y axis from the equations (7) and (9).

  Here, a positive value is selected as a solution among the values shown in Expression (9). Then, Expression (10) and Expression (11) are obtained from the values in the x-axis and y-axis directions in Expression (6). As a result, the terminal device 100 can specify the rotation angle γ around the z-axis from the equations (10) and (11).

  On the other hand, the process of converting the terminal coordinate system to the vehicle coordinate system is the inverse conversion of the coordinate conversion shown in Expression (1), and is expressed by Expression (12) below.

The value of β and γ the formula (7), (9), (10), can be calculated from (11), sample _a x of the acceleration of the terminal coordinate _system, a y, y-axis of _{a z} and z When only the shaft is rotated and converted into the vehicle coordinate system, Expression (13) is obtained.

  Next, consider a process in which a sample of acceleration is projected on a plane perpendicular to the gravitational acceleration G (that is, on the YZ plane) and the direction P having the largest variance is obtained. If the acceleration sample in the y-axis direction is y, the acceleration sample in the z-axis direction is z, and the components of the acceleration sample projected on the YZ plane are y ′ and z ′, Expression (14) is obtained.

  Here, when z ′ is extracted from Expression (14), Expression (15) is obtained.

Here, the direction in which the information amount of z ′ is maximized, that is, the direction P in which the variance is greatest is the traveling direction of the vehicle C10. Therefore, consider the sum of squares of the residual of z ′. If the Z-axis components of N accelerations projected on the YZ plane are z ₁ ′ to z _N ′, the sum of squares of the residual is expressed by the following equation (16).

  Here, z ′ with an overline in the equation (16) is a value satisfying the following equation (17).

Considering that the partial differential of L with respect to the angle α is 0, the equation (16) is transformed into the following equation (18). Here, S _y , S _z , and S _yz shown in the equation (18) are _values shown in the following equations (19) to (21).

  Here, when Expression (18) is divided into an α variable and a coordinate variable, Expression (22) can be derived.

  Here, when the tangent function (tan α) of α is t and the left side of the equation (22) is s, the equation (22) can be expressed by a quadratic function of t as shown in the equation (23). Therefore, t can be expressed by Expression (24). In other words, the variable t of α can be represented by the variable s of coordinates.

  Here, the sine function (sin α) and the cosine function (cos α) of α are expressed by equations (25) and (26) from equation (24).

  On the other hand, when the value of Expression (24) is divided into a positive value and a negative value, it can be expressed by the following Expression (27) and Expression (28), and the solution of t is expressed by Expression (27) or Expression (28). ).

  Here, one of the equations (27) or (28) may be a solution indicating a direction in which the variance is minimized. Therefore, consider the second-order partial differentiation of L. The second-order partial differentiation of L can be expressed by Equation (29).

  Here, considering the purpose of maximizing the information amount of z ′, since L is a convex function, a condition satisfying Expression (30) is considered.

Then, when S _yz is larger than 0, the value of t must be smaller than 0 in order to satisfy the equation (30), so the equation (28) becomes a solution. On the other hand, when S _yz is less than 0, the value of t must be greater than 0 in order to satisfy Equation (30), so Equation (27) is the solution. Therefore, the terminal device 100 substitutes the value of t obtained according to the value of S _yz into Equation (25) and Equation (26), and calculates the value of the rotation angle α.

In addition, when the value of S _yz is 0, the second-order partial differentiation of L is expressed by Expression (31). For this reason, when S _z -S _y is larger than 0, the expressions (32) and (33) are _satisfied , and when S _z -S _y is smaller than 0, the expressions (34) and (35) are satisfied. . Therefore, the terminal device 100 calculates the value of α using Expression (32) and Expression (33) or Expression (34) and Expression (35) based on the value of S _z −S _y .

  Here, when the value of α is calculated, it is unclear which direction of the vehicle C10 the Z axis is forward (the traveling direction or the −Z axis direction). Therefore, the terminal device 100 identifies the forward direction of the vehicle C10 based on the sign of acceleration measured when the vehicle C10 starts moving or the sign of the integrated speed, and the identified direction is set as the −Z-axis direction. . For example, the terminal device 100 sets the direction opposite to the direction of acceleration measured when the vehicle C10 starts moving as the −Z axis direction. In addition, the terminal device 100 specifies the −Z axis direction so that the sign of the integrated speed is positive.

  In summary, the coordinate conversion for rotating the acceleration of the terminal coordinate system around the y-axis and the z-axis can be expressed by the following equation (36). Further, the coordinate conversion for converting into the vehicle coordinate system by rotating the acceleration converted by the expression (36) about the x-axis can be expressed by the following expression (37). For this reason, the terminal device 100 converts the terminal coordinate system into the vehicle coordinate system using the above-described equations (36) and (37).

[6. About correction of estimated speed)
The terminal device 100 described above corrects the integral value of acceleration to 0 when it is determined that the vehicle has stopped. However, the embodiment is not limited to this. For example, the terminal device 100 integrates the acceleration value or the acceleration so as to obtain an integrated value so that the integrated value from when it is determined that the vehicle C10 has stopped until it is determined that the vehicle C10 has stopped again becomes zero. An appropriate coefficient may be corrected. For example, the calculation unit 25 may correct the setting of the origin so that the integrated value of the acceleration values measured from time T3 to time T5 shown in FIG.

  The terminal device 100 may correct the integral value of acceleration using GPS. For example, the terminal device 100 executes the estimation process described above, specifies the position of the terminal device 100 based on a signal from a satellite, and calculates the moving speed of the terminal device 100 from the amount of change in the specified position. Then, the terminal device 100 corrects the detected acceleration value so that the estimated speed, that is, the integrated value of the detected acceleration becomes the same value as the calculated moving speed (for example, a value that is set as the origin). Correction).

[7. (Regarding direction correction)
In the terminal device 100 described above, the direction in which the dispersion of acceleration is large is the front of the vehicle C10 (−Z axis direction). However, the embodiment is not limited to this. For example, the terminal device 100 determines whether or not the vehicle C10 is traveling straight using GPS, and when the vehicle C10 is traveling straight, the direction of acceleration detected at this time is set to the Z-axis direction. It may be set. Further, when the terminal device 100 uses GPS to identify the transition of the current location of the vehicle C10 and determines that the vehicle C10 is accelerating while traveling straight, the direction of acceleration detected on the YZ plane is A rotation determinant such as that behind the vehicle C10 (+ Z axis direction) may be calculated, and acceleration may be converted from the terminal coordinate system to the terminal coordinate system using the rotation determinant.

[8. Other embodiments]
In addition, the said embodiment is only an illustration and this invention includes what is illustrated below and other embodiment other than that. For example, the functional configuration, data structure, processing order and contents shown in the flowchart in the present application are merely examples, and the presence / absence of each element, the order of arrangement and processing execution, and specific contents can be changed as appropriate. . For example, the above-described guidance processing and estimation processing can be realized as a device, a method, and a program in a terminal realized by a smartphone application or the like in addition to the terminal device 100 as exemplified in the above embodiment.

  Moreover, the structure which implement | achieves each process part 17-20 which comprises the terminal device 100 with a further independent apparatus is also common. Moreover, the structure which implement | achieves each part 21-25 which comprises the direction estimation part 20 with an respectively independent apparatus may be sufficient. Similarly, the configuration of the present invention is flexible, such as by realizing each means shown in the above embodiment by calling an external platform or the like with an API (application program interface) or network computing (so-called cloud). Can be changed. Furthermore, each element such as means relating to the present invention may be realized by other information processing mechanisms such as a physical electronic circuit as well as a computer control unit.

  For example, the terminal device 100 may execute the guidance process described above in cooperation with a distribution server that can communicate with the terminal device 100. For example, the distribution server includes the specifying unit 22, the estimation unit 24, and the calculation unit 25, and estimates the gravity direction, the moving direction and the moving speed of the terminal device 100 from the acceleration detected by the terminal device 100. Then, the distribution server may distribute the estimated moving direction and moving speed to the terminal device 100 to execute user guidance. Further, the distribution server may cause the terminal device 100 to execute the guidance process by executing the estimation process described above instead of the terminal device 100 and transmitting the execution result to the terminal device 100.

  Further, the distribution server may include a determination unit 23 and determine whether or not the terminal device 100 is moving. When there are a plurality of terminal devices that perform guidance processing and estimation processing in cooperation with the distribution server, the distribution server uses different SVMs for each terminal device to determine whether each terminal device is moving. You may judge. In addition, the distribution server collects position information acquired by each terminal device using GPS, determines whether each terminal device is moving from the collected position information, and collects the determination result and each terminal device. SVM learning may be realized using the acceleration value.

[9. effect〕
As described above, the terminal device 100 specifies the direction of gravity using the average value of acceleration detected in a predetermined state. And the terminal device 100 estimates the moving direction based on the identified gravity direction from the detected acceleration. Thus, the terminal device 100 specifies the weight direction from the average value of the measured accelerations without performing complicated processing, and estimates the moving direction based on the specified gravity direction from the measured accelerations. As a result, the terminal device 100 has an effect that the installation posture can be easily specified and the traveling direction of the vehicle C10 can be accurately estimated.

  In addition, the terminal device 100 specifies the direction of gravity using the average value of acceleration detected when the terminal device 100 is not moving. For this reason, since the terminal device 100 can specify the gravity direction with high accuracy without executing complicated processing, the installation posture can be easily specified and the traveling direction of the vehicle C10 can be estimated with high accuracy. .

  In addition, the terminal device 100 uses a rotation determinant that matches the direction of the terminal coordinate system in which the gravitational acceleration is detected with a predetermined axis direction of the vehicle coordinate system, and the detected acceleration is a moving direction based on the direction of the gravitational acceleration, That is, the acceleration is converted into an acceleration on the YZ plane perpendicular to the gravitational acceleration, and the moving direction is estimated using the converted acceleration. For this reason, the terminal device 100 can identify the direction in which the vehicle C10 moves from the detected acceleration without fixing the installation posture of the terminal device 100.

  Here, in a normal mode, since the vehicle C10 moves on the YZ plane, acceleration caused by the movement also occurs on the YZ plane. Therefore, the terminal device 100 estimates the moving direction with reference to the YZ plane perpendicular to the direction of gravity.

  More specifically, the terminal device 100 estimates the moving direction using the acceleration on the YZ plane perpendicular to the gravity direction among the detected accelerations. Further, the terminal device 100 detects a change in the moving direction of the terminal device 100 based on the acceleration in the direction on the YZ plane perpendicular to the gravity direction and perpendicular to the moving direction. For this reason, the terminal device 100 can estimate the moving direction and moving speed of the vehicle C10 with high accuracy.

  Further, the terminal device 100 calculates the variation in acceleration on the YZ plane perpendicular to the direction of gravity, and the direction in which the calculated variation is maximum, that is, the direction in which the variance is maximum is the −Z axis. The direction. For this reason, the terminal device 100 can specify the moving direction of the vehicle C10 easily and accurately.

  Further, the terminal device 100 calculates an average value of a plurality of acceleration values detected until a predetermined time elapses or an average value of a predetermined number of acceleration values detected continuously. The calculated average value is set as the average value of the detected acceleration. That is, the terminal device 100 smoothes the acceleration value detected by the acceleration sensor 13 using the moving average method, and reduces noise. For this reason, the terminal device 100 can improve the estimation accuracy of the moving direction and the moving speed.

  Further, the terminal device 100 determines whether or not the terminal device 100, and thus the vehicle C10, is moving based on the characteristics of the detected acceleration value, and determines that the terminal device 100 is not moving. The direction of gravity is specified using the average value of the detected accelerations. For this reason, the terminal device 100 can improve the estimation accuracy of the moving direction and the moving speed as a result of being able to accurately specify the direction of gravity.

  Further, the terminal device 100 uses the SVM that has learned the characteristics of the acceleration values measured while the terminal device 100 is moving and not, whether or not the terminal device 100 is moving. Determine whether. Therefore, the terminal device 100 can accurately determine whether or not the terminal device 100 is moving.

  Further, the terminal device 100 calculates a moving speed in the estimated moving direction. More specifically, the terminal device 100 sets the integral value of acceleration in the estimated moving direction as the moving speed in this direction. For this reason, the terminal device 100 can estimate the moving speed of the vehicle C10.

  Further, the terminal device 100 corrects the integral value of acceleration to zero when the terminal device 100 is not moving. Further, the terminal device 100 corrects the detected acceleration value so that the integrated value of the detected acceleration from the start to the stop of the movement becomes zero. Further, when the terminal device 100 calculates the moving speed of the terminal device 100 calculated based on the signal from the satellite, the terminal device 100 corrects the detected acceleration value so that the integrated value of the acceleration becomes the calculated moving speed. To do. As a result of these processes, the terminal device 100 can improve the estimation accuracy of the moving speed.

  As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to implement the present invention in other forms with improvements.

  Moreover, the above-mentioned “section (module, unit)” can be read as “means”, “circuit”, and the like. For example, the direction estimation unit can be read as direction estimation means or a direction circuit.

DESCRIPTION OF SYMBOLS 11 Communication part 12 Memory | storage part 13 Acceleration sensor 14 GPS receiving antenna 15 Output part 16 Control part 17 Guidance execution part 18 Audio | voice output part 19 Image output part 20 Direction estimation part 21 Detection part 22 Identification part 23 Determination part 24 Estimation part 25 Calculation part 100 terminal device

Claims (17)

A detection unit for detecting acceleration;
A specifying unit for specifying the direction of gravity using an average value of acceleration detected by the detecting unit in a predetermined state;
An estimation unit that calculates a variation in acceleration on a plane perpendicular to the direction of gravity specified by the specifying unit from the acceleration detected by the detection unit, and estimates a moving direction of the terminal device based on the calculated variation; The estimation apparatus characterized by having.   The said specific | specification part specifies the said gravitational direction using the average value of the acceleration which the said detection part detected in the state which the said terminal device is not moving as said predetermined | prescribed state. The estimation device described.   The estimation unit converts the acceleration detected by the detection unit into an acceleration in a moving direction based on the direction of the gravitational acceleration by using a rotation type that matches a direction in which the detection unit detects the gravitational acceleration with a predetermined axial direction. The estimation apparatus according to claim 1, wherein the moving direction is estimated using the converted acceleration.   The estimation device according to claim 1, wherein the estimation unit estimates a moving direction based on a plane perpendicular to the gravity direction.   The estimation apparatus according to claim 4, wherein the estimation unit estimates the moving direction using an acceleration on a plane perpendicular to the gravity direction among the accelerations detected by the detection unit. .   The estimation unit detects a change in the movement direction of the terminal device based on acceleration in a direction perpendicular to the gravity direction and perpendicular to the movement direction. The estimation apparatus according to claim 5.   The said estimation part calculates the dispersion | variation in the acceleration on a plane perpendicular | vertical with respect to the said gravitational direction, and estimates the direction where the calculated dispersion | variation becomes the maximum as the said moving direction. The estimation apparatus as described in any one.   The detection unit calculates an average value of a plurality of acceleration values detected until a predetermined time elapses, or an average value of a predetermined number of acceleration values detected continuously, and 8. The estimation device according to claim 1, wherein the calculated average value is output as a value of the detected average value of acceleration. A determination unit for determining whether or not the terminal device is moving based on a characteristic of an acceleration value detected by the detection unit;
The said specific | specification part specifies the said gravitational direction using the average value of the acceleration which the said detection part detected when the said determination part determined that the said terminal device was not moving. The estimation apparatus as described in any one of -8.   The determination unit determines whether or not the terminal device is moving using a support vector machine that has learned features of acceleration values measured while the terminal device is moving and not moving. The estimation apparatus according to claim 9, wherein: The estimation apparatus according to claim 1, further comprising: a calculation unit that calculates a movement speed in the movement direction estimated by the estimation unit.   The estimation device according to claim 11, wherein the calculation unit uses an integral value of acceleration in the movement direction estimated by the estimation unit as a movement speed in the movement direction.   The estimation device according to claim 12, wherein the calculation unit corrects an integral value of the acceleration to zero when the terminal device is not moving.   The calculation unit corrects the acceleration value detected by the detection unit so that an integral value of acceleration detected from when the terminal device starts moving until it stops is zero. The estimation apparatus according to any one of claims 11 to 13.   The calculation unit corrects the acceleration value detected by the detection unit so that an integral value of the acceleration matches a moving speed of the terminal device calculated based on a signal from a satellite. The estimation apparatus according to any one of claims 11 to 14. A moving direction estimation method executed by a terminal device,
A specific step of specifying the direction of gravity using an average value of acceleration detected in a predetermined state;
An estimation step of calculating a variation in acceleration on a plane perpendicular to the direction of gravity specified in the specifying step from the detected acceleration, and estimating a moving direction of the terminal device based on the calculated variation. A moving direction estimation method comprising: On the computer,
A specific procedure for specifying the direction of gravity using the average value of acceleration detected in a predetermined state,
An estimation procedure for calculating a variation in acceleration on a plane perpendicular to the direction of gravity specified in the specific procedure from the detected acceleration, and estimating a moving direction of the terminal device based on the calculated variation. A moving direction estimation program characterized by being executed.

Images