Control device

Abstract

To provide a control device capable of determining whether misregistration has occurred in an estimation result of a self-position.SOLUTION: A control device 100 comprises an obtaining unit 111, a self-position estimation unit 112, a calculation unit 113; and a determination unit 114. The obtaining unit 111 obtains information indicating speed of a vehicle M from a vehicle sensor 15. The self-position estimation unit 112 estimates a self-position of the vehicle M based on a recognition result of an object recognition device 14 which recognizes the surroundings of the vehicle M. The calculation unit 113 calculates an average vehicle speed of the vehicle M during a predetermined period based on the obtained speed of the vehicle M. The calculation unit 113 calculates an average estimated speed as the average vehicle speed of the vehicle M during the predetermined period based on an estimation result of the self-position of the vehicle M estimated by the self-position estimation unit 112. The determination unit 114 determines that misregistration has occurred in the estimation result of the self-position by the self-position estimation unit 112 when a difference between the average vehicle speed and the average estimated vehicle speed is equal to or more than a threshold.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a control device. [Background technology]

[0002] BACKGROUND ART Conventionally, there is known a technique for estimating the self-position of a moving object such as a vehicle based on an image captured and generated by an imaging unit provided in the moving object (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2009-074861 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the method disclosed in Patent Document 1, when a moving object is traveling in a place where there is little change in the feature amount, such as a tunnel, it is sometimes difficult to estimate the self-position with high accuracy. Also, there is a new demand for determining whether the self-position cannot be detected with high accuracy and a position deviation has occurred in the estimation result. [Means for solving the problem]

[0005] A control device that achieves the above-mentioned object is characterized by comprising an acquisition unit that acquires information indicating the speed of a moving body, a self-position estimation unit that estimates the self-position of the moving body based on the recognition result of a recognition unit that recognizes the surroundings of the moving body, a calculation unit that calculates the average speed of the moving body within the specified period based on the acquired speed of the moving body and calculates an average estimated speed as the average speed of the moving body within the specified period based on the estimation result of the self-position, and a determination unit that determines that a position shift has occurred if the difference between the average speed and the average estimated speed is equal to or greater than a threshold value.

[0006] According to this configuration, it is possible to determine whether a position deviation has occurred in the estimation result of the self-position. In a control device that achieves the above-mentioned object, the acquisition unit may acquire the detection results of a vehicle speed sensor that detects the vehicle speed of the moving body as information indicating the speed of the moving body, and the calculation unit may calculate the average vehicle speed of the moving body as the average speed.

[0007] According to this configuration, the positional deviation of the moving body can be determined with high accuracy. In a control device that achieves the above-mentioned object, the acquisition unit may acquire the detection results of an angular velocity sensor that detects the angular velocity of the moving body as information indicating the velocity of the moving body, and the calculation unit may calculate an average angular velocity of the moving body as the average velocity.

[0008] According to this configuration, it is possible to determine the deviation in the orientation of the moving body with high accuracy. In a control device that achieves the above-mentioned object, the calculation unit may calculate the average speed based on the speed of the moving body acquired within the specified period from the time when the speed of the moving body was last acquired until a specified time before, and may calculate the average estimated speed based on the self-position estimated within the specified period from the time when the self-position was last estimated until the specified time before.

[0009] According to this configuration, it is possible to determine the deviation of the estimation result of the self-position based on appropriate data among the data acquired within a predetermined period. [Effects of the Invention]

[0010] According to the present invention, it is possible to determine whether a position deviation has occurred in the estimation result of the self-position. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram used to explain the control device. [Figure 2]FIG. 2 is a diagram used to explain how to estimate the vehicle's own position on a route with a large amount of features. [Figure 3] FIG. 3 is a diagram used to explain the positional deviation of the self-position based on the actual vehicle speed and the estimated vehicle speed. [Figure 4] FIG. 4 is a flowchart illustrating an example of processing executed by the control device. [Figure 5] FIG. 5 is a flowchart illustrating an example of processing executed by the control device. DETAILED DESCRIPTION OF THE INVENTION

[0012] <Embodiment> Hereinafter, an embodiment embodying a control device will be described with reference to the drawings. [Overall configuration] 1 is a diagram showing an example of a vehicle system 1. The vehicle (hereinafter referred to as vehicle M) on which the vehicle system 1 is mounted is, for example, a two-wheeled, three-wheeled, or four-wheeled vehicle, and its driving source is an internal combustion engine such as a diesel engine or a gasoline engine, a secondary battery, a fuel cell, an electric motor, or a combination of these. The electric motor operates using power generated by a generator connected to the internal combustion engine, or power discharged from the secondary battery or fuel cell.

[0013] The vehicle system 1 includes, for example, a camera 10, a radar device 12, an object recognition device 14, a vehicle sensor 15, an HMI (Human Machine Interface) 16, and a control device 100. These devices and equipment are connected to each other via multiplex communication lines such as a CAN (Controller Area Network) communication line, serial communication lines, a wireless communication network, etc. Note that the configuration shown in Fig. 1 is merely an example, and some of the configuration may be omitted, or other configurations may be added.

[0014] The camera 10 is a digital camera that uses a solid-state imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). The camera 10 is attached to any location on the vehicle M. For example, when capturing an image in front of the vehicle M, the camera 10 is attached to the top of the front windshield or the back of the rearview mirror. When capturing an image behind the vehicle M, the camera 10 is attached to the top of the rear windshield or the back door. When capturing an image of the sides and rear of the vehicle M, the camera 10 is attached to a door mirror or the like. The camera 10 periodically and repeatedly captures images of the surroundings of the vehicle M, for example.

[0015] The radar device 12 emits radio waves such as millimeter waves around the vehicle M and detects radio waves reflected by an object (reflected waves) to detect at least the position (distance and direction) of the object. The radar device 12 is attached to any location on the vehicle M. The radar device 12 may detect the position and speed of an object using an FM-CW (Frequency Modulated Continuous Wave) method.

[0016] The object recognition device 14 performs sensor fusion processing on the detection results from some or all of the camera 10 and the radar device 12 to recognize the position, type, speed, etc. of the object. The object recognition device 14 outputs the recognition result to the control device 100. The object recognition device 14 is an example of a recognition unit.

[0017] The vehicle sensor 15 includes a vehicle speed sensor that detects the speed of the vehicle M, and a yaw rate sensor that detects the angular velocity around a vertical axis. The HMI 16 presents various information to the occupants of the vehicle M under the control of the control device 100, and accepts input operations by the occupants. The HMI 16 includes, for example, various display devices, speakers, switches, a microphone, a buzzer, a touch panel, keys, etc. The various display devices are, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display device. The display device is provided, for example, near the front of the driver's seat (the seat closest to the steering wheel) on the instrument panel, and is installed in a position where the occupant can see it through the gap in the steering wheel or over the steering wheel. The display device may also be installed in the center of the instrument panel.

[0018] The control device 100 includes, for example, a control unit 110 and a storage unit 150. The control unit 110 is realized by, for example, a hardware processor such as a CPU (Central Processing Unit) executing a program (software). Some or all of these components may be realized by hardware (including circuitry) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be realized by a combination of software and hardware. The program may be stored in advance in a storage device (a storage device having a non-transitory storage medium) such as an HDD or flash memory serving as the storage unit 150, or may be stored in a removable storage medium such as a DVD or CD-ROM, and installed in the HDD or flash memory of the control device 100 by inserting the storage medium (non-transitory storage medium) into a drive device.

[0019] The storage unit 150 may be realized by the above-mentioned various storage devices, or a solid state drive (SSD), an electrically erasable programmable read only memory (EEPROM), a read only memory (ROM), or a random access memory (RAM). The storage unit 150 stores, for example, map information 151. The map information 151 is, for example, information that represents road shapes using links indicating roads and nodes connected by the links. The map information 151 may include road curvature, point of interest (POI) information, and the like.

[0020] The control unit 110 includes, for example, an acquisition unit 111, a self-position estimation unit 112, a calculation unit 113, a determination unit 114, and a notification unit 115. The acquisition unit 111 acquires, for example, information indicating the vehicle speed of the vehicle M from a vehicle speed sensor included in the vehicle sensor 15. The acquisition unit 111 acquires, for example, the information indicating the vehicle speed of the vehicle M at predetermined time intervals. The information indicating the vehicle speed of the vehicle M is an example of information indicating the speed of the vehicle M.

[0021] The self-position estimation unit 112 estimates the self-position of the vehicle M based on the recognition result of the object recognition device 14 and the map information 151. Specifically, the self-position estimation unit 112 estimates, based on the recognition result of the object recognition device 14 and the characteristics of the route shown in the map information 151, a position where the recognition result matches the characteristics as the self-position of the vehicle M. Hereinafter, it is assumed that the self-position of the vehicle M is indicated by a coordinate system indicating latitude and longitude. The self-position estimation unit 112 estimates the self-position of the vehicle M at predetermined time intervals.

[0022] The self-position estimation unit 112 may auxiliary use the detection result of a position sensor that acquires the position of the vehicle M as the vehicle sensor 15 in the process of estimating the self-position. The position sensor is, for example, a sensor that acquires position information (longitude and latitude information) from a GPS (Global Positioning System) device. The position sensor may also be a sensor that acquires position information using a GNSS (Global Navigation Satellite System) receiver. The self-position estimation unit 112 may also estimate the self-position by odometry that estimates the self-movement amount based on the detection result of the vehicle sensor 15.

[0023] The calculation unit 113 calculates the average vehicle speed of the vehicle M within a predetermined period based on the vehicle speed of the vehicle M acquired by the acquisition unit 111. The calculation unit 113 calculates the average vehicle speed of the vehicle M for each predetermined period, for example. Therefore, the predetermined period is a period from the timing at which the speed of the vehicle M is acquired by the acquisition unit 111 immediately before the timing at which the average vehicle speed is calculated to a predetermined time before that. Specifically, the acquisition unit 111 acquires information indicating the speeds of three or more vehicles M from the vehicle sensor 15 within the predetermined period. The calculation unit 113 calculates the average vehicle speed of the vehicle M based on the information indicating the speeds of the multiple vehicles M acquired within the predetermined period and the following equation (1). In equation (1), n ​​is the number of pieces of information indicating the speed of the vehicle M acquired within the predetermined period. Furthermore, v is the vehicle speed of the vehicle M acquired by the acquisition unit 111.

[0024]

number

[0025] Furthermore, the calculation unit 113 calculates an average estimated vehicle speed as the average vehicle speed of the vehicle M within a predetermined period based on the estimation result of the vehicle's own position. For example, the calculation unit 113 calculates the average estimated vehicle speed based on the information used to calculate the average vehicle speed of the vehicle M, based on the own position of the vehicle M estimated by the own position estimation unit 112 during a predetermined period that coincides with the predetermined period acquired by the acquisition unit 111. The calculation unit 113 calculates the average estimated vehicle speed of the vehicle M based on the own position of the vehicle M estimated during the predetermined period and the following equation (2). First, the calculation unit 113 calculates the difference in position between adjacent data of the own positions of the vehicle M that are consecutive in time series as the inter-data movement distance T. Specifically, when the self-position estimation unit 112 estimates a self-position at a first timing, a self-position at a second timing, ..., a self-position at a fifth timing within the predetermined period, the self-position estimation unit 112 calculates the difference in position between adjacent data of each of the self positions as the inter-data movement distance T. More specifically, the calculation unit 113 calculates the difference obtained by subtracting the self-position at the first timing from the self-position at the second timing as the inter-data movement distance T, calculates the difference obtained by subtracting the self-position at the second timing from the self-position at the third timing as the inter-data movement distance T, ..., calculates the difference obtained by subtracting the self-position at the fourth timing from the self-position at the fifth timing as the inter-data movement distance T. In other words, the inter-data movement distance T is the distance from the self-position of the vehicle M at a certain estimated timing to the self-position at the next estimated timing.

[0026] Furthermore, the calculation unit 113 acquires, as a data interval V, the difference in time at which the original data of the inter-data movement distance T was acquired by the object recognition device 14. In general, the data interval V is always a constant time interval.

[0027] In equation (2), T is the inter-data movement distance T. V is the data interval V. n is the number of inter-data movement distances T calculated based on data acquired within a predetermined period. Specifically, n in equation (2) is a number that is one less than the number of pieces of information indicating the self-location acquired within the predetermined period.

[0028]

number

[0029] If the difference between the average vehicle speed calculated by the calculation unit 113 and the average estimated vehicle speed is equal to or greater than the threshold, the determination unit 114 determines that a position deviation has occurred in the estimation result of the self-position by the self-position estimation unit 112. On the other hand, if the difference between the average vehicle speed and the average estimated vehicle speed is less than the threshold, the determination unit 114 determines that a position deviation has not occurred in the estimation result of the self-position by the self-position estimation unit 112. Details of the determination method will be described later.

[0030] The notification unit 115 notifies the occupant of the vehicle M that a positional deviation has occurred, via the HMI 16, by the determination unit 114 determining that a positional deviation has occurred in the estimation result of the self-position by the self-position estimation unit 112. The notification unit 115 notifies the occupant of the vehicle M that a positional deviation has occurred, for example, by outputting an alarm sound indicating that a positional deviation has occurred via the HMI 16. Note that the notification method of the notification unit 115 is just one example and is not limited thereto, and the notification unit 115 may notify the occupant of the vehicle M that a positional deviation has occurred by displaying an image indicating that a positional deviation has occurred on the display device of the HMI 16.

[0031] [Details of the judgment method] Here, the travel route of the vehicle M includes routes with large feature amounts and routes with small feature amounts. FIG. 2 shows an example of a route with large feature amounts, and FIG. 3 shows an example of a route with small feature amounts. A route with large feature amounts is, for example, a route with high curvature or a route with a special shape such as an intersection. On the other hand, a route with small feature amounts is, for example, a straight route with low curvature, or a route with a continuous constant curvature, and a route such as a tunnel where no change is observed in the surrounding environment of the vehicle M.

[0032] On a route with a large amount of features, the object recognition device 14 can appropriately recognize the surroundings of the vehicle M based on the peripheral image of the vehicle M generated by the camera 10 and the detection results of the radar device 12. Therefore, the self-position estimation unit 112 can appropriately estimate the self-position of the vehicle M based on the recognition results. Specifically, at a three-way intersection as shown in FIG. 2, the detection results of the radar device 12 have a feature in that the detection results are partially missing for routes other than those ahead of the vehicle M (in this case, the route in the left turn direction). The self-position estimation unit 112 appropriately estimates the self-position of the vehicle M based on the features of such detection results.

[0033] On the other hand, on a route with a small amount of features, the object recognition device 14 cannot appropriately recognize the surroundings of the vehicle M based on the peripheral image of the vehicle M generated by the camera 10 or the detection results of the radar device 12. Therefore, the self-position estimation unit 112 may cause a position deviation in the estimation result of the self-position of the vehicle M based on the recognition results. Specifically, on a straight route such as a tunnel as shown in FIG. 3, it is difficult to find features in the image generated by the camera 10 or the detection results of the radar device 12. For this reason, the object recognition device 14 may produce similar images and detection results for the actual position of the vehicle M and for a position ahead (or behind) the actual vehicle M. Therefore, it is difficult for the self-position estimation unit 112 to appropriately estimate the self-position of the vehicle M based on the detection results of the camera 10 and the radar device 12.

[0034] However, when the self-position estimation unit 112 estimates a position ahead of the actual position of the vehicle M in the traveling direction as the self-position of the vehicle M, the average estimated vehicle speed based on the estimation result should be faster than the average vehicle speed based on the detection result of the vehicle sensor 15. Similarly, when the self-position estimation unit 112 estimates a position behind the actual position of the vehicle M in the traveling direction as the self-position of the vehicle M, the average estimated vehicle speed based on the estimation result should be slower than the average vehicle speed based on the detection result of the vehicle sensor 15.

[0035] The determination unit 114 compares the average estimated vehicle speed, including the positional deviation as described above, with the average vehicle speed, and determines whether or not a positional deviation has occurred in the result of the self-position estimation by the self-position estimation unit 112.

[0036] [Processing of the control unit 110] A series of processes executed by the control unit 110 will be described below with reference to Fig. 4. The process of the flowchart shown in Fig. 4 is repeatedly executed at predetermined time intervals.

[0037] First, the acquisition unit 111 acquires information indicating the vehicle speed of the vehicle M from the vehicle sensor 15 (step S100). Next, the self-position estimation unit 112 estimates the self-position of the vehicle M based on the recognition result of the object recognition device 14 and the map information 151 (step S102). Next, the calculation unit 113 calculates the average vehicle speed of the vehicle M within a predetermined period based on the acquired speed of the vehicle M (step S104). Next, the calculation unit 113 calculates an average estimated vehicle speed as the average vehicle speed of the vehicle M within the predetermined period based on the estimation result of the self-position (step S106). The determination unit 114 determines whether or not the difference between the average vehicle speed calculated by the calculation unit 113 and the average estimated vehicle speed is equal to or greater than a threshold (step S108). If the difference is less than the threshold (step S108; NO), the determination unit 114 determines that no positional deviation has occurred in the self-position estimated by the self-position estimation unit 112, and ends the series of processes. If the judgment unit 114 determines that the difference is greater than or equal to the threshold (step S108; YES), the notification unit 115 notifies the HMI 16 that a position shift has occurred in the self-position estimated by the self-position estimation unit 112 (step S110), and terminates the series of processes.

[0038] [Effects of the embodiment] According to the above embodiment, the following effects can be obtained. (1) The control device 100 includes an acquisition unit 111, a self-position estimation unit 112, a calculation unit 113, and a determination unit 114. The acquisition unit 111 acquires information indicating the speed of the vehicle M from the vehicle sensor 15. The self-position estimation unit 112 estimates the self-position of the vehicle M based on the recognition result of the object recognition device 14 that recognizes the surroundings of the vehicle M. The calculation unit 113 calculates the average vehicle speed of the vehicle M within a predetermined period based on the acquired speed of the vehicle M. Furthermore, the calculation unit 113 calculates an average estimated speed as the average vehicle speed of the vehicle M within the predetermined period based on the estimation result of the self-position of the vehicle M estimated by the self-position estimation unit 112. If the difference between the average vehicle speed and the average estimated vehicle speed is equal to or greater than a threshold, the determination unit 114 determines that a position deviation has occurred in the estimation result of the self-position by the self-position estimation unit 112.

[0039] As described above, the average vehicle speed and the average estimated vehicle speed deviate from each other when a position deviation occurs in the estimation result of the self-position by the self-position estimation unit 112. With this configuration, the determination unit 114 can determine the deviation of the estimation result of the self-position by the self-position estimation unit 112 based on the average speed and the average estimated vehicle speed.

[0040] (2) The notification unit 115 notifies the occupant of the vehicle M via the HMI 16 that the determination unit 114 has determined that a position deviation has occurred in the estimation result of the self-position by the self-position estimation unit 112. The notification unit 115 notifies the occupant of the vehicle M that a position deviation has occurred, for example, by outputting an alarm sound indicating that a position deviation has occurred via the HMI 16. With this configuration, the occupant of the vehicle M can understand that a position deviation has occurred in the estimation result of the self-position by the self-position estimation unit 112. Specifically, based on the notification by the notification unit 115, the occupant of the vehicle M can assume that there may be an error in the guidance or disable an assist function that assists in driving the vehicle M.

[0041] The above-described embodiments may be modified as follows: The above-described embodiments and the following modifications may be combined with each other within the scope of technical compatibility. In the above description, the determination unit 114 determines whether or not a position deviation has occurred in the estimation result of the vehicle's own position based on the average vehicle speed and the average estimated vehicle speed, but this is not limiting. The determination unit 114 may perform a determination process based on the angular velocity of the vehicle M in addition to the determination process based on the vehicle speed of the vehicle M.

[0042] In this case, the acquisition unit 111 acquires information indicating the angular velocity of the vehicle M from a yaw rate sensor included in the vehicle sensor 15. The acquisition unit 111 acquires the information indicating the angular velocity of the vehicle M, for example, at predetermined time intervals. The information indicating the angular velocity of the vehicle M is an example of information indicating the speed of the vehicle M.

[0043] The calculation unit 113 calculates the average angular velocity of the vehicle M within a predetermined period based on the angular velocity of the vehicle M acquired by the acquisition unit 111. The calculation unit 113 calculates the average angular velocity of the vehicle M for each predetermined period, for example. Therefore, the predetermined period is a period from the timing at which the velocity of the vehicle M is acquired by the acquisition unit 111 immediately before the timing at which the average angular velocity is calculated to a predetermined time before that. Specifically, the acquisition unit 111 acquires information indicating the velocities of three or more vehicles M from the vehicle sensor 15 within the predetermined period. The calculation unit 113 calculates the average angular velocity of the vehicle M based on the information indicating the velocities of the multiple vehicles M acquired within the predetermined period and the following equation (3). In equation (3), n is the number of pieces of information indicating the angular velocity of the vehicle M acquired within the predetermined period. Furthermore, ω is the angular velocity of the vehicle M acquired by the acquisition unit 111.

[0044]

number

[0045] Furthermore, the calculation unit 113 calculates an average estimated angular velocity as the average angular velocity of the vehicle M within a predetermined period based on the estimation result of the vehicle's own position. For example, the calculation unit 113 calculates the average estimated angular velocity based on the vehicle's own position estimated by the self-position estimation unit 112 during a predetermined period that coincides with the predetermined period for which the acquisition unit 111 acquired information used to calculate the average angular velocity of the vehicle M. The calculation unit 113 calculates the average estimated angular velocity of the vehicle M based on the vehicle's own position estimated during the predetermined period and the following equation (4). First, the calculation unit 113 calculates the angular difference between the movement vectors of adjacent data of the vehicle's own positions that are consecutive in time series as the inter-data attitude difference A. Specifically, when the self-position estimation unit 112 estimates a self-position at a first timing, a self-position at a second timing, ..., a self-position at a fifth timing within the predetermined period, the self-position estimation unit 112 calculates the difference between the positions of the adjacent data as the inter-data attitude difference A. More specifically, calculation unit 113 calculates the difference obtained by subtracting the self-position at the first timing from the self-position at the second timing as inter-data attitude difference A, calculates the difference obtained by subtracting the self-position at the second timing from the self-position at the third timing as inter-data attitude difference A, ..., calculates the difference obtained by subtracting the self-position at the fourth timing from the self-position at the fifth timing as inter-data attitude difference A. In other words, inter-data attitude difference A is the distance from the self-position of vehicle M at a certain estimated timing to the self-position at the next estimated timing.

[0046] Furthermore, the calculation unit 113 acquires the difference in time at which the original data of the inter-data posture difference A was acquired by the object recognition device 14 as the data interval V. In general, the data interval V is always a constant time interval.

[0047] In equation (4), A is the inter-data attitude difference A. V is the data interval V. n is the number of inter-data attitude differences A calculated based on data acquired within a predetermined period. Specifically, n in equation (4) is a number that is one less than the number of pieces of information indicating the self-position acquired within the predetermined period.

[0048]

number

[0049] If the difference between the average angular velocity calculated by the calculation unit 113 and the average estimated angular velocity is equal to or greater than the threshold, the determination unit 114 determines that a position shift has occurred in the estimation result of the self-position by the self-position estimation unit 112. On the other hand, if the difference between the average angular velocity and the average estimated angular velocity is less than the threshold, the determination unit 114 determines that a position shift has not occurred in the estimation result of the self-position by the self-position estimation unit 112.

[0050] A series of processes executed by the control unit 110 in this example will be described below with reference to Fig. 5. The process of the flowchart shown in Fig. 5 includes steps S200 to S206 in addition to the process of the flowchart shown in Fig. 4. Furthermore, in the process of the flowchart shown in Fig. 5, information indicating the angular velocity of the vehicle M is acquired in step S100.

[0051] After the determination process of step S108 or the process of step S110, the calculation unit 113 calculates the average angular velocity of the vehicle M within a predetermined period based on the acquired angular velocity of the vehicle M (step S200). Next, the calculation unit 113 calculates an average estimated angular velocity as the average angular velocity of the vehicle M within the predetermined period based on the estimation result of the vehicle's own position (step S202). The determination unit 114 determines whether or not the difference between the average angular velocity calculated by the calculation unit 113 and the average estimated angular velocity is equal to or greater than a threshold (step S204). If the difference is less than the threshold (step S204; NO), the determination unit 114 determines that no deviation has occurred in the vehicle's own position estimated by the vehicle's own position estimation unit 112, and ends the series of processes. If the judgment unit 114 determines that the difference is greater than or equal to the threshold (step S108; YES), the notification unit 115 notifies the HMI 16 that a position shift has occurred in the self-position estimated by the self-position estimation unit 112 (step S206), and terminates the series of processes.

[0052] The acquisition unit 111 acquires information indicating the angular velocity of the vehicle M from the vehicle sensor 15. The calculation unit 113 calculates an average angular velocity of the vehicle M within a predetermined period based on the acquired angular velocity of the vehicle M. The calculation unit 113 also calculates an average estimated angular velocity as the average angular velocity of the vehicle M within the predetermined period based on the estimation result of the self-position of the vehicle M estimated by the self-position estimation unit 112. If the difference between the average angular velocity and the average estimated vehicle speed is equal to or greater than a threshold, the determination unit 114 determines that a position deviation has occurred in the estimation result of the self-position by the self-position estimation unit 112.

[0053] Here, the positional deviation of the self-position estimated by the self-position estimation unit 112 includes the above-mentioned deviation of the coordinates of the vehicle M and the deviation of the orientation of the vehicle M. Therefore, even if the coordinates of the vehicle M match, the orientation of the vehicle M may differ in the self-position estimated by the self-position estimation unit 112. With this configuration, the determination unit 114 can determine that a deviation in orientation as a positional deviation has occurred in the estimation result of the self-position by the self-position estimation unit 112.

[0054] In the above description, the calculation unit 113 calculates the average speed of the vehicle M within a predetermined period based on the vehicle speed of the vehicle M acquired by the acquisition unit 111. However, this is not limiting. The calculation unit 113 may select appropriate information from multiple pieces of information indicating the vehicle speed of the vehicle M acquired by the acquisition unit 111, and calculate the average vehicle speed of the vehicle M based on the selected information. In this case, the calculation unit 113 may calculate the average vehicle speed of the vehicle M based on the speed of the vehicle M acquired during a predetermined time period from the timing at which the most recent speed of the vehicle M was acquired, among the multiple pieces of information acquired by the acquisition unit 111 at predetermined time intervals. The predetermined time period is shorter than the predetermined time interval. Furthermore, the calculation unit 113 calculates the average estimated vehicle speed based on the self-position of the vehicle M estimated by the self-position estimation unit 112 during a predetermined period that coincides with the predetermined period during which the acquisition unit 111 acquired information used to calculate the average vehicle speed of the vehicle M. According to this configuration, the determination unit 114 can determine the deviation of the estimation result of the self-position based on the appropriate data that is closer to the determination timing (i.e., closer to the actual state) among the data acquired within a predetermined period.

[0055] The above-described selection of information may be applied to the process of calculating the average angular velocity and the average estimated angular velocity by the calculation unit 113. In this case, in the above description, the average vehicle speed may be read as the average angular velocity, and the average angular velocity may be read as the average estimated angular velocity.

[0056] The control unit 110 may determine the position deviation of the estimation result of the self-position by the self-position estimation unit 112 based only on the angular velocity of the vehicle M. In this case, the control unit 110 omits steps S104 to S110 from the processing shown in FIG.

[0057] The vehicle system 1 may include a LIDAR (Light Detection and Ranging) device instead of (or in addition to) the radar device 12. The object recognition device 14 may output the detection results of the camera 10 and the radar device 12 directly to the control device 100. In this case, the object recognition device 14 may be omitted from the vehicle system 1. In this case, the self-position estimation unit 112 performs sensor fusion processing on the detection results of some or all of the camera 10 and the radar device 12 to recognize the position, type, speed, etc. of the object.

[0058] The acquisition unit 111 may acquire information indicating the vehicle speed or angular velocity of the vehicle M from the object recognition device 14. In this case, the vehicle sensor 15 may be omitted from the vehicle system 1.

[0059] The display device included in the HMI 16 may be a HUD (Head Up Display). The HUD projects an image onto a portion of the front windshield in front of the driver's seat, allowing the driver sitting in the driver's seat to see a virtual image.

[0060] The vehicle M may be an autonomous vehicle. In this case, the control device 100 or a vehicle control device different from the control device 100 executes various controls related to autonomous driving. Autonomous driving refers to, for example, automatically controlling one or both of the steering and speed (acceleration / deceleration) of the vehicle M to execute driving control. The driving control of the vehicle M may include various driving assistance such as a lane-keeping assistance system (LKAS), an auto lane-changing system (ALC), an adaptive cruise control (ACC), an auto lane-changing assist (ALCA), deceleration control before a curve, curving road departure prevention, and merging assistance (yielding to a merging vehicle). Some or all of the driving of an autonomous vehicle may be manually controlled by an occupant (driver). In this case, the determination result of the determination unit 114 that a position deviation has occurred in the self-position estimated by the self-position estimation unit 112 may be used for various controls related to autonomous driving of the vehicle M. Specifically, the control device 100, or a vehicle control device different from the control device 100, may modify the control variables of various controls related to the automatic driving of the vehicle M based on the difference between the average vehicle speed and the average estimated vehicle speed, or the difference between the average angular velocity and the average estimated angular velocity.

[0061] The technical ideas that can be understood from the above-described embodiment and modified examples will be described. [Mode 1] The control device includes an acquisition unit that acquires information indicating the speed of a moving body, a self-position estimation unit that estimates the self-position of the moving body based on the recognition result of a recognition unit that recognizes the surroundings of the moving body, a calculation unit that calculates the average speed of the moving body within the specified period based on the acquired speed of the moving body and calculates an average estimated speed as the average speed of the moving body within the specified period based on the estimation result of the self-position, and a determination unit that determines that a position shift has occurred if the difference between the average speed and the average estimated speed is equal to or greater than a threshold value.

[0062] [Aspect 2] The control device described in [Aspect 1], wherein the acquisition unit acquires the detection result of a vehicle speed sensor that detects the vehicle speed of the moving body as information indicating the speed of the moving body, and the calculation unit calculates the average vehicle speed of the moving body as the average speed.

[0063] [Aspect 3] A control device as described in [Aspect 1] or [Aspect 2], wherein the acquisition unit acquires the detection result of an angular velocity sensor that detects the angular velocity of the moving body as information indicating the velocity of the moving body, and the calculation unit calculates the average angular velocity of the moving body as the average velocity.

[0064] [Aspect 4] A control device described in any one of [Aspect 1] to [Aspect 3], wherein the calculation unit calculates the average speed based on the speed of the moving body acquired during the specified period from the time when the speed of the moving body was most recently acquired until a specified time before, and calculates the average estimated speed based on the self-position estimated during the specified period from the time when the self-position was last estimated until the specified time before. [Explanation of symbols]

[0065] 1...vehicle system, 10...camera, 12...radar device, 14...object recognition device, 15...vehicle sensor, 16...HMI, 100...control device, 110...control unit, 111...acquisition unit, 112...self-position estimation unit, 113...calculation unit, 114...determination unit, 115...notification unit, 150...memory unit, 151...map information, A...posture difference between data, M...vehicle, T...travel distance between data, V...data interval.

Claims

1. an acquisition unit that acquires information indicating the speed of a moving object; a self-position estimation unit that estimates a self-position of the moving object based on a recognition result of a recognition unit that recognizes the surroundings of the moving object; a calculation unit that calculates an average speed of the moving body within the predetermined period based on the acquired speed of the moving body, and calculates an average estimated speed as an average speed of the moving body within the predetermined period based on the estimation result of the self-position; a determination unit that determines that a positional deviation has occurred when the difference between the average velocity and the average estimated velocity is equal to or greater than a threshold value; A control device comprising:

2. the acquisition unit acquires a detection result of a vehicle speed sensor that detects a vehicle speed of the moving object as information indicating the speed of the moving object; the calculation unit calculates an average vehicle speed of the moving object as the average speed. The control device according to claim 1 .

3. the acquisition unit acquires a detection result of an angular velocity sensor that detects an angular velocity of the moving body as information indicating the velocity of the moving body; the calculation unit calculates an average angular velocity of the moving object as the average velocity. The control device according to claim 1 .

4. the calculation unit calculates the average speed based on speeds of the moving body acquired during a predetermined time period from a timing at which the speed of the moving body was last acquired, and calculates the average estimated speed based on the self-position estimated during a predetermined time period from a timing at which the self-position was last estimated, The control device according to claim 1 .

Images