Position accuracy determination device, position accuracy determination computer program, and position accuracy determination method
The position accuracy determination device addresses inaccuracies in vehicle positioning by using road features and prediction filters to ensure safe and reliable navigation by adjusting control modes based on accuracy thresholds.
Patent Information
- Application Number
- JP2021197958
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2021-12-06
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2041-12-06
AI Technical Summary
Existing automatic control systems in vehicles face inaccuracies in estimating the current position due to factors such as road feature conditions, movement errors, and vehicle skidding, leading to potential safety risks during navigation.
A position accuracy determination device that estimates the vehicle's position using road features and a prediction filter, determining the accuracy state by comparing estimated positions and calculating differences, and notifying the driver or changing control modes based on accuracy thresholds.
The device ensures safe and accurate vehicle navigation by determining the accuracy of the estimated position, allowing for safe automatic control or manual intervention when necessary, thereby enhancing safety and reliability.
Smart Images

Figure 0007593306000001 
Figure 0007593306000002 
Figure 0007593306000003
Abstract
Description
[Technical field]
[0001] The present disclosure relates to a position accuracy determination device, a position accuracy determination computer program, and a position accuracy determination method. [Background technology]
[0002] An automatic control system installed in a vehicle generates a navigation route for the vehicle based on the current position of the vehicle, the destination position of the vehicle, and a navigation map. The automatic control system estimates the current position of the vehicle using the map information and drives the vehicle along the navigation route.
[0003] It is preferable that the automatic control system can accurately estimate the current position of the vehicle. For example, the automatic control system estimates a first estimated position based on an image showing road features on the road surface around the vehicle and position information of the road features on a map. The automatic control system also estimates a second estimated position based on the position of the vehicle at a previous time and the amount of movement and azimuth angle change of the vehicle from the previous time to the current time. Then, the automatic control system estimates the current position of the vehicle based on the first estimated position and the second estimated position (for example, see Patent Document 1). [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2016-224802 A Summary of the Invention [Problem to be solved by the invention]
[0005] The current position of the vehicle estimated based on the first estimated position and the second estimated position is not necessarily correct due to factors such as the state of road features shown in the image, errors in the amount of movement or change in azimuth angle of the vehicle, or occurrence of skidding of the vehicle. Since the automatic control system drives the vehicle based on the current position of the vehicle, if the current position of the vehicle is incorrect, there is a risk that the vehicle cannot be driven safely.
[0006] Therefore, an object of the present disclosure is to provide a position accuracy determination device that can determine the state of accuracy of an estimated current position of a vehicle. [Means for solving the problem]
[0007] According to one embodiment, a position accuracy determination device is provided, which includes a first position estimation unit that estimates a first position of a moving object at a first time based on an image showing road features on a road surface around the moving object at a first time and position information of the road features on the road surface, a second position estimation unit that estimates a second position of the moving object at the first time based on a position of the moving object at a second time before the first time and a movement amount and an azimuth angle change amount of the moving object from the second time to the first time, a calculation unit that inputs the first position and the second position at the first time to a prediction filter to calculate a current position of the moving object at the first time, and a determination unit that determines a state of accuracy of the current position of the moving object based on a first difference amount between the current position of the moving object at the first time, the position of the moving object at a time before the first time, and a position estimated based on the movement amount and the azimuth angle change amount of the moving object from the previous time to the first time.
[0008] In addition, in this position accuracy determination device, it is preferable that the determination unit calculates a second difference amount between the first position and the second position of the moving object at the first time, and the determination unit determines the state of accuracy of the current position of the moving object based on the first difference amount and the second difference amount.
[0009] In addition, in this position accuracy determination device, it is preferable that the determination unit uses different criteria when determining that the accuracy of the current position of a moving object should be changed from a good state to a bad state and when determining that the accuracy of the current position of a moving object should be changed from a bad state to a good state.
[0010] In the position accuracy determination device, it is preferable that the determination unit compares the second difference amount with a predetermined reference threshold value to determine the state of estimation accuracy of the position of the moving object.
[0011] In addition, in this position accuracy determination device, it is preferable that the determination unit notifies the driver of a request for involvement in driving the moving object via the notification unit based on the state of estimation accuracy of the position of the moving object.
[0012] In the position accuracy determination device, it is preferable that the determination unit uses the second time as the previous time.
[0013] According to another embodiment, there is provided a computer program for determining position accuracy, which causes a processor to execute the following steps: estimating a first position of a moving object at a first time based on an image showing road features on a road surface around the moving object at a first time and position information of the road features on the road surface; estimating a second position of the moving object at the first time based on a position of the moving object at a second time prior to the first time and a movement amount and an azimuth angle change amount of the moving object from the second time to the first time; inputting the first position and the second position at the first time to a prediction filter to calculate a current position of the moving object at the first time; and determining a state of accuracy of the current position of the moving object based on a first difference amount between the current position of the moving object at the first time, the position of the moving object at a time prior to the first time, and a position estimated based on the movement amount and the azimuth angle change amount of the moving object from the previous time to the first time.
[0014] According to another embodiment, there is provided a position accuracy determination method, which is characterized in that a position accuracy determination device executes the following steps: estimating a first position of a moving object at a first time based on an image showing road features on a road surface around the moving object at a first time and position information of the road features on the road surface; estimating a second position of the moving object at the first time based on a position of the moving object at a second time before the first time and a movement amount and an azimuth angle change amount of the moving object from the second time to the first time; inputting the first position and the second position at the first time to a prediction filter to calculate a current position of the moving object at the first time; and determining a state of accuracy of the current position of the moving object based on a first difference amount between the current position of the moving object at the first time, the position of the moving object at a time before the first time, and a position estimated based on the movement amount and the azimuth angle change amount of the moving object from the previous time to the first time. Effect of the Invention
[0015] The position accuracy determination device according to the present disclosure can determine the state of accuracy of the estimated current position of the vehicle. [Brief description of the drawings]
[0016] [Figure 1] 2 is a diagram for explaining an outline of the operation of the position accuracy determination device according to the present embodiment. FIG. [Diagram 2] 1 is a schematic configuration diagram of a vehicle in which a vehicle control system including a position accuracy determination device according to an embodiment of the present invention is implemented. [Diagram 3] FIG. 2 is a diagram illustrating a prediction filter. [Figure 4] 5 is an example of an operational flowchart relating to a position accuracy determination process of the position estimation device according to the present embodiment. [Diagram 5] FIG. 4 is a diagram illustrating an example of a first difference amount. [Figure 6] FIG. 11 is a diagram illustrating an example of a second difference amount. [Figure 7] FIG. 11 is a diagram illustrating an example of a determination process. [Figure 8]5 is an example of an operational flowchart relating to a determination process of the position estimation device according to the present embodiment. [Figure 9] FIG. 1 is a diagram (part 1) for explaining the concept of determining a worsening condition and an improving condition. [Figure 10] FIG. 2 is a diagram (part 2) for explaining the concept of determining the condition worsening condition and the condition improving condition. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0017] 1 is a diagram for explaining an overview of the operation of the position accuracy determination device of this embodiment. Hereinafter, an overview of the operation related to the position accuracy determination process of the position estimation device 12, which is an example of the position accuracy determination device disclosed in this specification, will be described with reference to FIG.
[0018] The vehicle 10 travels while estimating its current position at a predetermined period using the position estimation device 12. The vehicle 10 is an example of a moving object.
[0019] 1(A), the position estimation device 12 estimates the position of the vehicle 10 at time t1 based on an image showing road features (e.g., lane markings) on the road surface around the vehicle 10 at time t1 and position information (e.g., map information) of the road features on the road surface. Similarly, the position estimation device 12 estimates the position P1 of the vehicle 10 at time t2 (an estimated position based on road features) at time t2, which is a predetermined period after time t1.
[0020] Furthermore, the position estimation device 12 estimates a position P2 of the vehicle 10 at time t2 (a position estimated by dead reckoning) based on the position of the vehicle 10 at time t1 and the amount of movement and amount of change in azimuth angle of the vehicle 10 from time t1 to time t2.
[0021] Then, the position estimation device 12 inputs the positions P1 and P2 of the vehicle 10 at time t2 to a prediction filter (e.g., a Kalman filter) to calculate a current position P0 of the vehicle 10 at time t2 (a position estimated by the prediction filter). This current position P0 is used to control the driving of the vehicle 10. The current position P0 is also used to obtain a next second estimated position (a position estimated by dead reckoning).
[0022] The position estimation device 12 obtains a discrepancy D between the estimated position P2 of the vehicle 10 at time t2 and the current position P0. In the example shown in Fig. 1(A), the discrepancy D is a lateral discrepancy in a lateral direction perpendicular to the traveling direction of the vehicle 10.
[0023] Examples of factors that may cause the discrepancy D include the following: (1) an abnormality in a camera that captures an image showing road features on the road surface around the vehicle 10, (2) road features on the road surface around the vehicle 10 being unclear (e.g., blurred lane markings), (3) a mismatch between a high-precision map showing the position information of road features on the road surface and the current topography, (4) an abnormality in a speed sensor used to determine the amount of movement of the vehicle 10, (5) an abnormality in a yaw rate sensor used to determine the amount of change in the azimuth angle of the vehicle 10, (6) a sideways skid of the vehicle 10, etc.
[0024] The position estimation device 12 determines the state of accuracy of the current position of the vehicle 10 based on the difference amount D. In the example shown in Fig. 1(C), the state of accuracy of the current position of the vehicle 10 is determined as normal 1 (normal), normal 2 (hands-off), poor condition 1 (hands-on), and poor condition 2 (Transition Demand: TD). The state of accuracy of the current position of the vehicle 10 is best with normal 1 (normal), followed by normal 2 (hands-off), poor condition 1 (hands-on), and poor condition 2 (TD), in that order.
[0025] When the state of accuracy of the current position of the vehicle 10 is determined to be normal 1 or normal 2, the driving of the vehicle 10 is automatically controlled safely based on the current position of the vehicle 10 estimated by the position estimation device 12.
[0026] On the other hand, if the accuracy state of the current position of the vehicle 10 is determined to be malfunction 1 or malfunction 2, there is a risk that the operation of the vehicle 10 will no longer be safely automatically controlled based on the current position of the vehicle 10 estimated by the position estimation device 12.
[0027] Therefore, when the position estimation device 12 determines that the state of accuracy of the current position of the vehicle 10 is poor condition 1 (hands-on), it notifies the driver of a gripping request to grip the steering wheel. Also, when the position estimation device 12 determines that the state of accuracy of the current position of the vehicle 10 is poor condition 2 (TD), it notifies the driver of a control change request to change the driving of the vehicle 10 from automatic control to manual control.
[0028] For example, if lane markings, which are an example of road features, are not correctly displayed in an image due to a camera malfunction, the accuracy state of the current position of vehicle 10 may be determined as poor 1 or 2. Also, if the lane markings are blurred and cannot be correctly identified from an image, the accuracy state of the current position of vehicle 10 may be determined as poor 1 or 2. Thus, the accuracy state of the current position of vehicle 10 is affected by factors other than hardware, as well as hardware such as sensors.
[0029] In this way, the position estimation device 12 can determine the accuracy of the estimated current position of the vehicle 10, and the determination results can be used as information for safely driving the vehicle 10.
[0030] 2 is a schematic configuration diagram of a vehicle in which a vehicle control system 1 including a position estimation device 12 of the present embodiment is implemented. The vehicle 10 includes a camera 2, a positioning information receiver 3, a navigation device 4, a user interface (UI) 5, a vehicle speed sensor 6, a yaw rate sensor 7, a map information storage device 11, a position estimation device 12, an object detection device 13, a driving lane planning device 14, a driving planning device 15, a vehicle control device 16, and the like. Furthermore, the vehicle 10 may include a distance measurement sensor (not shown) such as a LiDAR sensor for measuring distances to objects around the vehicle 10.
[0031] The camera 2, positioning information receiver 3, navigation device 4, UI 5, vehicle speed sensor 6, yaw rate sensor 7, map information storage device 11, position estimation device 12, object detection device 13, driving lane planning device 14, driving planning device 15, and vehicle control device 16 are communicatively connected via an in-vehicle network 17 that complies with a standard such as a controller area network.
[0032] The camera 2 is an example of an imaging unit provided on the vehicle 10. The camera 2 is attached to the vehicle 10 so as to face forward of the vehicle 10. The camera 2 captures camera images showing the environment of a predetermined area ahead of the vehicle 10, for example, at a predetermined period. The camera images may show the road included in the predetermined area ahead of the vehicle 10 and road features such as lane markings on the road surface. The camera 2 has a two-dimensional detector composed of an array of photoelectric conversion elements sensitive to visible light, such as a CCD or C-MOS, and an imaging optical system that forms an image of the area to be captured on the two-dimensional detector.
[0033] Every time the camera 2 captures a camera image, it outputs the camera image and the camera image capture time at which the camera image was captured to the position estimation device 12, the object detection device 13, etc. via the in-vehicle network 17. The camera image is used by the position estimation device 12 in a process of estimating the position of the vehicle 10. The camera image is also used by the object detection device 13 in a process of detecting other objects around the vehicle 10.
[0034] The positioning information receiver 3 outputs positioning information indicating the current position of the vehicle 10. For example, the positioning information receiver 3 may be a GNSS receiver. Every time the positioning information receiver 3 acquires positioning information at a predetermined reception cycle, the positioning information receiver 3 outputs the positioning information and the positioning information acquisition time when the positioning information was acquired to the navigation device 4, the map information storage device 11, etc.
[0035] The navigation device 4 generates a navigation route from the current position of the vehicle 10 to the destination position in response to a request from the driver, based on the navigation map information, the destination position of the vehicle 10 input from the UI 5, and the positioning information indicating the current position of the vehicle 10 input from the positioning information receiver 3. The navigation route includes information regarding the positions of right turns, left turns, merging, and branching. The navigation device 4 generates a new navigation route for the vehicle 10 when a new destination position is set, or when the current position of the vehicle 10 deviates from the navigation route, etc. Every time the navigation device 4 generates a navigation route, it outputs the navigation route to the position estimation device 12, the driving lane planning device 14, etc. via the in-vehicle network 17.
[0036] The UI 5 is an example of a notification unit. The UI 5 is controlled by the navigation device 4 and the position estimation device 12, etc., and notifies the driver of the vehicle 10 of driving information, a gripping request, a control change request, etc. The driving information of the vehicle 10 includes information on the current and future routes of the vehicle, such as the current position of the vehicle and a navigation route. The gripping request requests the driver to grip the steering wheel. The control change request requests the driver to change the driving of the vehicle 10 from automatic control to manual control. The UI 5 also generates an operation signal according to an operation from the driver to the vehicle 10. The UI 5 has a display device 5a such as a liquid crystal display or a touch panel to display the driving information, etc. The UI 5 may also have an audio output device (not shown) to notify the driver of the driving information, etc. The UI 5 also has, for example, a touch panel or an operation button as an input device for inputting operation information from the driver to the vehicle 10. Examples of the operation information include a destination position, a waypoint, a vehicle speed, and other control information of the vehicle 10. The UI 5 outputs the input operation information to the navigation device 4, the vehicle control device 16, etc. via the in-vehicle network 17.
[0037] The vehicle speed sensor 6 detects vehicle speed information of the vehicle 10, and outputs the vehicle speed information and the speed information acquisition time when the vehicle speed information was acquired to the position estimation device 12 and the like via the in-vehicle network 17. The vehicle speed sensor 6 is attached to, for example, an axle (not shown), detects the rotation speed of the axle, and outputs a pulse signal proportional to the rotation speed.
[0038] The yaw rate sensor 7 detects the yaw rate of the vehicle 10 and outputs the yaw rate and the yaw rate information acquisition time when the yaw rate was acquired to the position estimation device 12, etc., via the in-vehicle network 17. As the yaw rate sensor 7, for example, an acceleration sensor such as a gyroscope can be used.
[0039] The map information storage device 11 stores map information of a relatively wide area (for example, a range of 10 to 30 km square) including the current position of the vehicle 10. This map information has three-dimensional information of the road surface, information representing the types and positions of road features and structures such as lane markings on the road surface, and high-precision map information including the legal speed limit of the road. The map information storage device 11 receives wide-area map information from an external server via a base station by wireless communication via a wireless communication device (not shown) mounted on the vehicle 10 according to the current position of the vehicle 10, and stores the received map information in the storage device. Each time positioning information is input from the positioning information receiver 3, the map information storage device 11 refers to the stored wide-area map information, and outputs map information of a relatively small area (for example, a range of 100 m to 10 km square) including the current position represented by the positioning information to the position estimation device 12, the object detection device 13, the driving lane planning device 14, the driving planning device 15, the vehicle control device 16, and the like via the in-vehicle network 17.
[0040] The position estimation device 12 executes a position estimation process, a calculation process, and a determination process. To this end, the position estimation device 12 has a communication interface (IF) 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 are connected via a signal line 24. The communication interface 21 has an interface circuit for connecting the position estimation device 12 to the in-vehicle network 17.
[0041] All or part of the functions of the position estimation device 12 are functional modules realized by a computer program running on the processor 23, for example. The processor 23 has a position estimation unit 230, a calculation unit 231, and a determination unit 232. Alternatively, the functional modules of the processor 23 may be dedicated arithmetic circuits provided in the processor 23. The processor 23 has one or more central processing units (CPUs) and their peripheral circuits. The processor 23 may further have other arithmetic circuits such as a logic arithmetic unit, a numerical arithmetic unit, or a graphic processing unit. The memory 22 is an example of a storage unit, and has, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 22 stores computer programs of applications and various data used in information processing executed by the processor 23.
[0042] Every time the position estimation device 12 determines the current position of the vehicle 10 at the time an image is captured by the camera, it outputs the current position to the object detection device 13, the traffic lane planning device 14, the operation planning device 15, the vehicle control device 16, etc. The operation of the position estimation device 12 will be described in detail later.
[0043] The object detection device 13 detects other objects and their types (e.g., vehicles) around the vehicle 10 based on camera images, etc. The other objects include other vehicles traveling around the vehicle 10. The object detection device 13 tracks the detected other objects to obtain the trajectory of the other objects. The object detection device 13 identifies the driving lane in which the other objects are traveling based on the lane dividing lines shown in the map information and the positions of the other objects. The object detection device 13 outputs object detection information including information indicating the type of the detected other objects, information indicating their positions, and information indicating the driving lane to the driving lane planning device 14, the driving planning device 15, etc.
[0044] The driving lane planning device 14 generates a driving lane plan representing a planned driving lane on which the vehicle 10 will travel, based on map information, the navigation route and surrounding environment information, and the current position of the vehicle 10, in the nearest driving section (e.g., 10 km) selected from the navigation route at a driving lane plan generation time set at a predetermined cycle. The driving lane planning device 14 generates a driving lane plan so that the vehicle 10 travels on a lane other than an overtaking lane, for example. The driving lane planning device 14 outputs the driving lane plan to the driving planning device 15 every time it generates a driving lane plan.
[0045] In addition, the driving lane planning device 14 determines whether or not a lane change is required in the nearest driving section selected from the navigation route based on the driving lane plan, map information, the navigation route, and the current position of the vehicle 10, and generates a lane change plan according to the determination result. Specifically, the driving lane planning device 14 determines whether or not a lane change is required to move to a lane leading to the destination position of the vehicle 10 based on the navigation route and the current position of the vehicle 10. It determines whether or not the vehicle 10 will enter another road at a junction from the driving road on which the vehicle 10 is currently traveling (merging), and whether or not the vehicle 10 will exit from the driving road to another road at a junction (branching). At merging and branching, the vehicle moves from a lane of the driving road to a lane of another road, so a lane change is performed. The driving lane planning device 14 may further use surrounding environment information or vehicle state information to determine whether or not a lane change is required. The surrounding environment information includes the positions and speeds of other vehicles traveling around the vehicle 10. The vehicle state information includes the current position, vehicle speed, acceleration, and traveling direction of the vehicle 10. When the driving lane planning device 14 generates a lane change plan, the driving lane planning device 14 outputs the driving lane plan to which the lane change plan has been added to the driving planning device 15.
[0046] The driving plan device 15 executes a driving plan process to generate a driving plan representing a planned driving trajectory of the vehicle 10 up to a predetermined time (for example, 5 seconds) ahead based on the driving lane plan, map information, the current position of the vehicle 10, surrounding environment information, and vehicle state information at a driving plan generation time set at a predetermined cycle. The driving plan is expressed as a set of a target position of the vehicle 10 and a target vehicle speed at the target position at each time from the current time to the predetermined time ahead. It is preferable that the cycle in which the driving plan is generated is shorter than the cycle in which the driving lane plan is generated. The driving plan device 15 generates a driving plan so that a gap of a predetermined distance or more can be maintained between the vehicle 10 and other vehicles. Even if the driving lane plan includes a lane change in which the vehicle 10 moves between lanes, the driving plan device 15 generates a driving plan so that the vehicle 10 is stopped when a gap of a predetermined distance or more cannot be secured between the vehicle 10 and other vehicles. The driving plan device 15 outputs the driving plan to the vehicle control device 16 every time the driving plan is generated.
[0047] The vehicle control device 16 controls each part of the vehicle 10 based on the current position, the vehicle speed, the yaw rate, and the driving plan generated by the driving plan device 15. For example, the vehicle control device 16 determines the steering angle, acceleration, and angular acceleration of the vehicle 10 according to the driving plan, the vehicle speed, and the yaw rate of the vehicle 10, and sets the steering amount, the accelerator opening, or the brake amount so as to obtain the steering angle, acceleration, and angular acceleration. The vehicle control device 16 then outputs a control signal corresponding to the set steering amount to an actuator (not shown) that controls the steered wheels of the vehicle 10 via the in-vehicle network 17. The vehicle control device 16 also determines the fuel injection amount according to the set accelerator opening, and outputs a control signal corresponding to the fuel injection amount to a drive device (not shown) such as an engine of the vehicle 10 via the in-vehicle network 17. Alternatively, the vehicle control device 16 outputs a control signal corresponding to the set brake amount to a brake (not shown) of the vehicle 10 via the in-vehicle network 17.
[0048] The vehicle control device 16 has an automatic control driving mode in which the automatic control system 1 drives the vehicle 10, and a manual control driving mode in which the driver drives the vehicle 10. When the automatic control driving mode is applied, the vehicle control device 16 can automatically control all of the vehicle 10's operations, including driving, braking, and steering. When a control change notification requesting a change from automatic control to manual control is approved by the driver, the vehicle control device 16 in the automatic control driving mode changes the driving of the vehicle 10 from the automatic control driving mode to the manual control driving mode. This allows the driver to operate the vehicle 10 by manual control using the steering wheel, accelerator pedal, brake pedal (not shown), etc., when the vehicle 10 cannot be driven safely under automatic control. In the manual control driving mode, at least one of the operations of driving, braking, and steering of the vehicle 10 is manually controlled. The vehicle control device 16 generates a control signal according to the amount of operation of the steering wheel, accelerator pedal, and brake pedal. It is also possible to change from automatic control to manual control according to the driver's request.
[0049] In FIG. 2, the map information storage device 11, the position estimation device 12, the object detection device 13, the driving lane planning device 14, the driving planning device 15, and the vehicle control device 16 are described as separate devices (e.g., Electronic Control Unit: ECU), but all or some of these devices may be configured as a single device.
[0050] Fig. 3 is an example of an operation flowchart relating to the position accuracy determination process of the position estimation device 12 of this embodiment. The position accuracy determination process of the position estimation device 12 will be described below with reference to Fig. 4. The position estimation device 12 executes the position accuracy determination process according to the operation flowchart shown in Fig. 4 every time a camera image is input.
[0051] First, the position estimation unit 230 estimates a first estimated position of the vehicle 10 at the time the current camera image is captured, based on a camera image showing road features on the road surface around the vehicle 10 at the time the current camera image is captured, and position information of the road features on the road surface (step S101). The position estimation unit 230 is an example of a first position estimation unit. For example, the position estimation unit 230 compares lane markings identified in the camera image with lane markings shown in map information input from the map information storage device 11, to determine a first estimated position and a first estimated azimuth angle of the vehicle 10 at the time the camera image is captured. The lane markings are an example of road features.
[0052] Next, the position estimation unit 230 estimates a second estimated position (position estimated by dead reckoning) and a second estimated azimuth of the vehicle 10 at the current camera image capture time based on the position of the moving object at the previous camera image capture time and the movement amount and azimuth angle change amount of the vehicle 10 from the previous camera image capture time to the current camera image capture time (step S102). The position estimation unit 230 is an example of a second position estimation unit. The position estimation unit 230 integrates the vehicle speed obtained from the vehicle speed information of the vehicle 10 to obtain the movement amount of the vehicle 10 between the previous and current camera image capture times. In addition, the position estimation unit 230 integrates the yaw rate obtained from the yaw rate information of the vehicle 10 to obtain the azimuth angle change amount of the vehicle 10 between the previous and current camera image capture times. The position estimation unit 230 obtains the second estimated position and the second estimated azimuth angle estimated by dead reckoning using the position and azimuth angle of the vehicle 10 at the previous camera image capture time and the movement amount and azimuth angle change amount.
[0053] Next, as shown in Fig. 4, the calculation unit 231 inputs the first estimated position and first estimated azimuth angle and the second estimated position and second estimated azimuth angle to a prediction filter to calculate the current position and current azimuth angle of the vehicle 10 at the current camera image capture time (step S103). Fig. 4 is a diagram for explaining the prediction filter. For example, a Kalman filter can be used as the prediction filter. Note that a filter other than the Kalman filter may also be used as the prediction filter.
[0054] Furthermore, the position estimation unit 230 may estimate the driving lane on the road on which the vehicle 10 is located, based on lane markings shown in the map information and the current position and current azimuth angle of the vehicle 10. Every time the position estimation unit 230 determines the current position, current azimuth angle, and driving lane of the vehicle 10 at the time an image is captured by the camera, the position estimation unit 230 outputs this information to the object detection device 13, the driving lane planning device 14, the driving planner 15, the vehicle control device 16, etc.
[0055] Next, the position estimation unit 230 estimates a third estimated position of the vehicle 10 at the current camera image capture time based on the position and azimuth of the vehicle 10 at the camera image capture time prior to the current camera image capture time, and the amount of movement and azimuth angle change of the vehicle 10 from the previous camera image capture time to the current camera image capture time (step S104). The previous camera image capture time may be used as the camera image capture time prior to the current camera image capture time. In this case, since the third estimated position is the same as the second estimated position, step S104 is omitted. Note that, for example, another time such as the camera image capture time before last may be used as the camera image capture time prior to the current camera image capture time.
[0056] Next, the determination unit 232 determines a first discrepancy between the first estimated position and the second estimated position of the vehicle 10 at the current camera image capture time (step S105). The first discrepancy represents the distance between the first estimated position and the second estimated position. The first discrepancy may be divided into a vertical discrepancy in a direction that coincides with the traveling direction of the vehicle 10 and a horizontal discrepancy in a horizontal direction perpendicular to the traveling direction of the vehicle 10. The first discrepancy may also be the distance between two positions on a map. The first discrepancy is an example of a second discrepancy in the claims.
[0057] 5 is a diagram illustrating an example of the first difference amount. At the current camera image capture time t2, the vehicle 10 has moved from the position at the previous camera image capture time t1 to the first estimated position P1. The determination unit 232 determines the lateral difference amount between the lateral position at the first estimated position P1 and the lateral position at the second estimated position P2 at the current camera image capture time t2 as the first difference amount D1. When the first difference amount is large, possible causes include an abnormality of the camera 2, a mismatch between the map information and the current topography, an abnormality of the vehicle speed sensor 6 and / or the yaw rate sensor 7, etc.
[0058] A first difference amount D1 between a first estimated position P1 of a vehicle 10 estimated based on an image representing road features and position information of the road features, and a second estimated position P2 of the vehicle 10 estimated by dead reckoning represents the relative validity of the second estimated position P2 with respect to the first estimated position P1.
[0059] Next, the determination unit 232 obtains a second difference between the third estimated position of the vehicle 10 at the current camera image capture time and the current position (step S106). The second difference represents the distance between the third estimated position and the current position. The second difference may be divided into a vertical difference in a direction that coincides with the traveling direction of the vehicle 10 and a horizontal difference in a direction perpendicular to the traveling direction of the vehicle 10. The first difference may be the distance between two positions on a map. If the second difference is large and the first difference is small, it may be due to the vehicle 10 skidding. The second difference is an example of the first difference in the claims.
[0060] 6 is a diagram illustrating an example of the second difference amount. At the current camera image capture time t2, the vehicle 10 moves from the position at the previous camera image capture time t3 to the third estimated position P3. The determination unit 232 determines the difference amount between the lateral position of the vehicle 10 at the current position P0 and the lateral position at the third estimated position P3 at the current camera image capture time t2 as the second difference amount D2. As in the example shown in FIG. 6, when the vehicle 10 is traveling on a curved road, it may skid depending on the condition of the road surface.
[0061] A second difference amount D2 between the third estimated position P3 of the vehicle 10 estimated by dead reckoning and the current position P0 of the vehicle 10 calculated using a predictive filter represents the validity of the current position P0 of the vehicle 10 relative to the third estimated position P3.
[0062] Next, the determination unit 232 determines the state of accuracy of the current position of the vehicle 10 based on the first difference amount and / or the second difference amount, and ends the series of processes (step S106). Details of the determination process by the determination unit 232 will be described next.
[0063] Fig. 7 is a diagram for explaining an example of the determination process. As shown in Fig. 7, the state of accuracy of the current position of the vehicle 10 is determined to be normal 1 (normal), normal 2 (hands off), poor condition 1 (hands on), or poor condition 2 (Transition Demand: TD).
[0064] When the state of accuracy of the current position of the vehicle 10 is determined to be normal 1 (normal), the driving of the vehicle 10 is automatically controlled safely based on the current position of the vehicle 10 estimated by the position estimation device 12.
[0065] When the state of accuracy of the current position of the vehicle 10 is determined to be normal 2 (hands off), the accuracy of the current position of the vehicle 10 is inferior to normal 1 (normal), but is within the allowable range of control of the automatic control system 1. Therefore, the driving of the vehicle 10 is automatically controlled safely based on the current position of the vehicle 10 estimated by the position estimation device 12.
[0066] When the state of accuracy of the current position of the vehicle 10 is determined to be poor condition 1 (hands on), the accuracy of the current position of the vehicle 10 may exceed the allowable range of control of the automatic control system 1. Therefore, when the determination unit 232 determines that the state of accuracy of the current position of the vehicle 10 is poor condition 1 (hands on), it notifies the driver of a request for involvement in driving the vehicle 10 via the UI 5. Specifically, the determination unit 232 notifies the driver of a gripping request for gripping the steering wheel. The automatic control system 1 automatically controls the driving of the vehicle 10 with the driver gripping the steering wheel. When the driver determines that driving the vehicle 10 under automatic control is not safe, he or she can operate the steering wheel.
[0067] When the state of accuracy of the current position of the vehicle 10 is determined to be poor condition 2 (TD), it is estimated that the accuracy of the current position of the vehicle 10 exceeds the allowable range of control of the automatic control system 1. When the determination unit 232 determines that the state of accuracy of the current position of the vehicle 10 is poor condition 2 (TD), it notifies the driver via the UI 5 of a request for further involvement in the driving of the vehicle 10. Specifically, the determination unit 232 notifies the driver via the UI 5 of a control change request requesting that the driving of the vehicle 10 be changed from automatic control to manual control.
[0068] 8 is an example of an operational flowchart relating to the determination process of the position estimation device 12 of this embodiment. For each current state of the accuracy of the current position of the vehicle 10, the determination process is executed according to the operational flowchart shown in FIG.
[0069] First, the determination process when the current state of the accuracy of the current position of the vehicle 10 is normal 1 will be described below.
[0070] First, the determination unit 232 determines whether the first difference amount satisfies a condition for worsening the state (step S201). The condition for worsening the state is a condition for determining whether the state of accuracy of the current position of the vehicle 10 is worse than the current state. As the condition for worsening the state, the ratio of the first difference amount exceeding the condition worsening threshold among a plurality of first difference amounts obtained between the current camera shooting time and the time a predetermined time (for example, 1 second) before is equal to or greater than a reference value. For example, the condition th1 for changing from normal 1 (normal) to normal 2 (hands off) can be set to 0.5 with the condition worsening threshold set to 0.1 m. Moreover, the condition th2 for changing from normal 1 (normal) to malfunction 1 (hands on) can be set to 0.6 with the condition worsening threshold set to 0.3 m. Moreover, the condition th3 for changing from normal 1 (normal) to malfunction 2 (TD) can be set to 0.8 with the condition worsening threshold set to 0.5 m.
[0071] In this specification, being determined to satisfy condition 1 means that a plurality of first difference amounts obtained between the current camera shooting time and a time a predetermined time (e.g., 1 second) earlier satisfy condition 1, but do not satisfy condition 2. In this specification, being determined to satisfy condition 2 means that a plurality of first difference amounts obtained between the current camera shooting time and a time a predetermined time (e.g., 1 second) earlier satisfy condition 2, but do not satisfy condition 3. This also applies to other determination processes.
[0072] If the first difference amount satisfies the condition deterioration condition (step S201-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the first difference amount satisfies the condition th1, the state of accuracy of the current position of the vehicle 10 is changed from Normal 1 (normal) to Normal 2 (hands off). If the first difference amount satisfies the condition th2, the state of accuracy of the current position of the vehicle 10 is changed from Normal 1 (normal) to Malfunction 1 (hands on). If the first difference amount satisfies the condition th3, the state of accuracy of the current position of the vehicle 10 is changed from Normal 1 (normal) to Malfunction 2 (TD).
[0073] On the other hand, if the first difference amount does not satisfy the condition deterioration condition (step S201-No), the determination unit 232 determines whether or not the second difference amount satisfies the condition deterioration condition (step S202). The condition deterioration condition may be that at least one of the second difference amounts among the multiple second difference amounts obtained between the current camera shooting time and the time a predetermined time (for example, 1 second) before is equal to or greater than the condition deterioration threshold. For example, the condition th1 for changing from normal 1 (normal) to normal 2 (hands off) may have a condition deterioration threshold of 0.2 m. The condition th2 for changing from normal 1 (normal) to malfunction 1 (hands on) may have a condition deterioration threshold of 0.4 m. The condition th3 for changing from normal 1 (normal) to malfunction 2 (TD) may have a condition deterioration threshold of 0.6 m. In addition, when the curvature judgment of the road on which the vehicle 10 travels is greater than the reference curvature, the condition deterioration threshold may be made larger than when the curvature is equal to or less than the reference curvature. This is because the amount of change in position is likely to be large when the road is curved. It should be noted that, for the second difference amount, it is not necessary to make a determination to change from Normal 1 (normal) to Normal 2 (hands off).
[0074] If the second difference amount satisfies the condition deterioration condition (step S202-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the second difference amount satisfies the condition th1, the state of accuracy of the current position of the vehicle 10 is changed from Normal 1 (normal) to Normal 2 (hands off). If the second difference amount satisfies the condition th2, the state of accuracy of the current position of the vehicle 10 is changed from Normal 1 (normal) to Malfunction 1 (hands on). If the second difference amount satisfies the condition th3, the state of accuracy of the current position of the vehicle 10 is changed from Normal 1 (normal) to Malfunction 2 (TD).
[0075] On the other hand, if the second difference amount does not satisfy the condition deterioration condition (step S202-No), the determination unit 232 determines that the state of accuracy of the current position of the vehicle 10 has not changed (step S205), and the series of processes ends. If the current state of the accuracy of the current position of the vehicle 10 is normal 2 (hands off), the processes of steps S203 and S204 are not performed.
[0076] Next, a determination process when the current state of the accuracy of the current position of the vehicle 10 is normal 2 (hands off) will be described below.
[0077] First, the determination unit 232 determines whether the first difference amount satisfies a condition for worsening of the condition (step S201). The condition for worsening of the condition may be that, among a plurality of first difference amounts obtained between the current camera shooting time and a time a predetermined time (for example, 1 second) before, the ratio of the first difference amount exceeding the condition worsening threshold is equal to or greater than a reference value. For example, the condition th2 for changing from normal 2 (hands off) to malfunction 1 (hands on) may be set to 0.3 m and the reference value to 0.6. The condition th3 for changing from normal 2 (hands off) to malfunction 2 (TD) may be set to 0.5 m and the reference value to 0.8.
[0078] If the first difference amount satisfies the condition deterioration condition (step S201-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the first difference amount satisfies the condition th2, the state of accuracy of the current position of the vehicle 10 is changed from normal 2 (hands off) to poor condition 1 (hands on). Also, if the first difference amount satisfies the condition th3, the state of accuracy of the current position of the vehicle 10 is changed from normal 2 (hands off) to poor condition 2 (TD).
[0079] On the other hand, if the first difference amount does not satisfy the condition deterioration condition (step S201-No), the determination unit 232 determines whether or not the second difference amount satisfies the condition deterioration condition (step S202). The condition deterioration condition may be that at least one of the second difference amounts among the multiple second difference amounts obtained between the current camera shooting time and the time a predetermined time (for example, 1 second) before is equal to or greater than the condition deterioration threshold. For example, the condition th2 for changing from normal 2 (hands off) to malfunction 1 (hands on) may have a condition deterioration threshold of 0.4 m. Also, the condition th3 for changing from normal 2 (hands off) to normal 2 (hands off) may have a condition deterioration threshold of 0.6 m. When the curvature judgment of the road on which the vehicle 10 travels is greater than the reference curvature, the condition deterioration threshold may be made larger than when the curvature is equal to or less than the reference curvature.
[0080] If the second difference amount satisfies the condition deterioration condition (step S202-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the second difference amount satisfies the condition th2, the state of accuracy of the current position of the vehicle 10 is changed from normal 2 (hands off) to poor condition 1 (hands on). Also, if the second difference amount satisfies the condition th3, the state of accuracy of the current position of the vehicle 10 is changed from normal 2 (hands off) to poor condition 2 (TD).
[0081] On the other hand, if the second difference amount does not satisfy the condition worsening condition (step S202-No), the determination unit 232 determines whether or not the first difference amount satisfies the condition improvement condition (step S203). The condition improvement condition is a condition for determining whether or not the accuracy of the current position of the vehicle 10 is better than the current state. As the condition improvement condition, the ratio of the first difference amounts that are equal to or less than the condition improvement threshold among the multiple first difference amounts obtained between the current camera shooting time and the time a predetermined time ago (for example, 1 second) is equal to or greater than a reference value. For example, the condition th4 for changing from Normal 2 (hands off) to Normal 1 (normal) can be set to 0.8 with the condition improvement threshold set to 0.1 m.
[0082] If the first difference amount satisfies the state improvement condition (step S203-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the first difference amount satisfies the condition th4, the state of accuracy of the current position of the vehicle 10 is changed from Normal 2 (hands off) to Normal 1 (normal).
[0083] On the other hand, if the first difference amount does not satisfy the condition improvement condition (step S203-No), the determination unit 232 determines whether or not the second difference amount satisfies the condition improvement condition (step S204). The condition improvement condition may be that at least one of the second difference amounts obtained between the current camera shooting time and the time a predetermined time (for example, 1 second) before is equal to or less than the condition improvement threshold. For example, the condition th4 for changing from Normal 2 (hands off) to Normal 1 (normal) may have a condition improvement threshold of 0.2 m.
[0084] If the second difference amount satisfies the state improvement condition (step S204-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the second difference amount satisfies the condition th4, the state of accuracy of the current position of the vehicle 10 is changed from Normal 2 (hands off) to Normal 1 (normal).
[0085] On the other hand, if the second difference amount does not satisfy the state improvement condition (step S203-No), the determination unit 232 determines that the state of accuracy of the current position of the vehicle 10 has not changed (step S205), and the series of processes ends.
[0086] Next, a determination process for a case where the current state of accuracy of the current position of the vehicle 10 is poor condition 1 (hands-on) will be described below.
[0087] First, the determination unit 232 determines whether the first difference amount satisfies a condition for a worsening state (step S201). The condition for a worsening state may be that, among a plurality of first difference amounts obtained between the current camera shooting time and a time a predetermined time (for example, 1 second) before, the rate at which the first difference amount exceeds the condition worsening threshold is equal to or greater than a reference value. For example, the condition th3 for changing from poor condition 1 (hands-on) to poor condition 2 (TD) may be set to a condition worsening threshold of 0.5 m and a reference value of 0.8.
[0088] If the first difference amount satisfies the condition deterioration condition (step S201-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the first difference amount satisfies the condition th3, the state of accuracy of the current position of the vehicle 10 is changed from poor condition 1 (hands-on) to poor condition 2 (TD).
[0089] On the other hand, if the first difference amount does not satisfy the condition deterioration condition (step S201-No), the judgment unit 232 judges whether or not the second difference amount satisfies the condition deterioration condition (step S202). The condition deterioration condition may be such that at least one of the second difference amounts among the multiple second difference amounts obtained between the current camera shooting time and the time a predetermined time (for example, 1 second) before is equal to or less than the condition deterioration threshold. For example, the condition th3 for changing from poor condition 1 (hands-on) to poor condition 2 (TD) may be set to a condition deterioration threshold of 0.6 m. When the curvature judgment of the road on which the vehicle 10 is traveling is greater than the reference curvature, the condition deterioration threshold may be set to be larger than when the curvature is equal to or less than the reference curvature.
[0090] If the second difference amount satisfies the condition deterioration condition (step S202-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the second difference amount satisfies the condition th3, the state of accuracy of the current position of the vehicle 10 is changed from poor condition 1 (hands-on) to poor condition 2 (TD).
[0091] On the other hand, if the second difference amount does not satisfy the condition deterioration condition (step S202-No), the determination unit 232 determines whether or not the first difference amount satisfies the condition improvement condition (step S203). The condition improvement condition may be that, among a plurality of first difference amounts obtained between the current camera shooting time and a time a predetermined time (for example, 1 second) before, the proportion of first difference amounts that are equal to or less than the condition improvement threshold is equal to or greater than a reference value. For example, the condition th5 for changing from poor condition 1 (hands on) to normal condition 2 (hands off) may be set to 0.3 m as the condition improvement threshold and 1.0 as the reference value.
[0092] If the first difference amount satisfies the state improvement condition (step S203-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the first difference amount satisfies the condition th5, the state of accuracy of the current position of the vehicle 10 is changed from poor 1 (hands on) to normal 2 (hands off).
[0093] On the other hand, if the first difference amount does not satisfy the condition improvement condition (step S203-No), the determination unit 232 determines whether or not the second difference amount satisfies the condition improvement condition (step S204). The condition improvement condition may be that at least one of the second difference amounts obtained between the current camera shooting time and the time a predetermined time (for example, 1 second) before is equal to or less than the condition improvement threshold. For example, the condition th5 for changing from Malfunction 1 (hands on) to Normal 2 (hands off) may have a condition improvement threshold of 0.4 m.
[0094] If the second difference amount satisfies the state improvement condition (step S204-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the second difference amount satisfies the condition th4, the state of accuracy of the current position of the vehicle 10 is changed from poor 1 (hands on) to normal 2 (hands off).
[0095] On the other hand, if the second difference amount does not satisfy the state improvement condition (step S203-No), the determination unit 232 determines that the state of accuracy of the current position of the vehicle 10 has not changed (step S205), and the series of processes ends.
[0096] Next, the determination process when the current state of the accuracy of the current position of the vehicle 10 is poor 2 (TD) will be described below. When the current state of the accuracy of the current position of the vehicle 10 is poor 2 (TD), the determination process is executed until the driver approves the control transition request.
[0097] First, the determination unit 232 determines whether the first difference amount satisfies a condition improvement condition (step S203). If the current state of the accuracy of the current position of the vehicle 10 is normal 2 (hands off), the processes of steps S201 and S202 are not performed. As a condition improvement condition, the ratio of the first difference amount that is equal to or less than the condition improvement threshold among the multiple first difference amounts obtained between the current camera shooting time and the time a predetermined time ago (for example, 1 second) is equal to or more than a reference value. For example, the condition th5 for changing from malfunction 2 (TD) to normal 2 (hands off) can be set to 1.0 with the condition improvement threshold being 0.3 m.
[0098] If the first difference amount satisfies the state improvement condition (step S203-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the first difference amount satisfies the condition th5, the state of accuracy of the current position of the vehicle 10 is changed from malfunction 2 (TD) to normal 2 (hands off).
[0099] On the other hand, if the first difference amount does not satisfy the condition improvement condition (step S203-No), the determination unit 232 determines whether or not the second difference amount satisfies the condition improvement condition (step S204). The condition improvement condition may be that at least one of the second difference amounts obtained between the current camera shooting time and the time a predetermined time (for example, 1 second) before is equal to or less than the condition improvement threshold. For example, the condition th5 for changing from malfunction 2 (TD) to normal 2 (hands off) may have a condition improvement threshold of 0.4 m.
[0100] If the second difference amount satisfies the state improvement condition (step S204-Yes), the determination unit 232 changes the state of accuracy of the current position of the vehicle 10 (step S206), and the series of processes ends. If the second difference amount satisfies the condition th4, the state of accuracy of the current position of the vehicle 10 is changed from malfunction 2 (TD) to normal 2 (hands off).
[0101] On the other hand, if the second difference amount does not satisfy the state improvement condition (step S203-No), the determination unit 232 determines that the state of accuracy of the current position of the vehicle 10 has not changed (step S205), and the series of processes ends.
[0102] In the above-described determination process, the determination 233 determines the state of accuracy of the current position of the vehicle 10 based on the first difference amount or the second difference amount. The determination 233 may determine the state of accuracy of the current position of the vehicle 10 based on the first difference amount and the second difference amount. In this case, the determination 233 determines that the state of accuracy of the current position has worsened if the first difference amount satisfies the state worsening condition (step S201-Yes) and the second difference amount satisfies the state worsening condition (step S202-Yes). Also, the determination 233 determines that the state of accuracy of the current position has improved if the first difference amount satisfies the state improvement condition (step S203-Yes) and the second difference amount satisfies the state improvement condition (step S204-Yes).
[0103] Next, the concept of determining the above-mentioned worsening condition and improving condition will be described below with reference to Figures 9 and 10. Figures 9 and 10 are diagrams for explaining the concept of determining the worsening condition and improving condition.
[0104] In the example shown in FIG. 9, the vehicle 900 indicates a first estimated position (estimated position based on road features) from time t1 to t4, the vehicle 901 indicates a second estimated position (estimated position based on dead reckoning) from time t1 to t4, and the vehicle 902 indicates a current position (estimated position based on a prediction filter) from time t1 to t4. Assume that a camera abnormality occurs at time t1, and the first estimated position indicated by the vehicle 900 moves lateral to the second estimated position indicated by the vehicle 901 by δ (1 m). This camera abnormality continues thereafter. The vehicles are assumed to be traveling at a constant speed, and the subsequent first estimated position, second estimated position, and current position are obtained by simulation. The current position indicated by the vehicle 902 approaches the first estimated position indicated by the vehicle 901 over time.
[0105] 10 shows the lateral position deviation of the current position of the vehicle 902 over time for vehicle speeds of 40 km / h, 80 km / h, and 136 km / h. Each position calculation is performed every 100 ms.
[0106] The current position of the vehicle 902 has moved to 90% of the deviation δ (1 m) due to the abnormality in the first estimated position of the vehicle 900 about 1 second later (21000 ms) after time t1 (20000 ms). The current position of the vehicle 902 has moved laterally about 0.1 m in 100 ms, about 0.3 m in 150 ms, and about 0.5 m in 300 ms. The deviation of the lateral position of the current position of the vehicle 902 was almost the same when the vehicle speed was 40 km / h, 80 km / h, and 136 km / h. It is assumed that the first difference amount and the second difference amount can be calculated about every 32 ms.
[0107] Regarding the condition deterioration condition for the first difference amount, based on the results shown in FIG. 10, it is considered that condition th1 is a condition deterioration threshold of 0.1 m and a reference value of 0.5, condition th2 is a condition deterioration threshold of 0.3 m and a reference value of 0.6, and condition th3 is a condition deterioration threshold of 0.5 m and a reference value of 0.8.
[0108] In addition, with regard to the condition for the second difference amount, based on the results shown in FIG. 10, it is possible that condition th1 has a condition deterioration threshold of 0.2 m, condition th2 has a condition deterioration threshold of 0.4 m, and condition th3 has a condition deterioration threshold of 0.6 m.
[0109] In addition, with regard to the condition improvement condition for the first difference amount, based on the results shown in Figure 10, it is considered that condition th4 is a condition improvement threshold of 0.1 m and a reference value of 0.8, and condition th5 is a condition improvement threshold of 0.3 m and a reference value of 1.0.
[0110] As for the condition improvement condition for the second difference amount, based on the result shown in FIG. 10, it is considered that the condition improvement threshold for th4 is set to 0.2 m, and the condition improvement threshold for th5 is set to 0.4 m.
[0111] According to the position accuracy determination device of the present embodiment described above, the state of accuracy of the estimated current position of the vehicle can be determined.
[0112] In the present disclosure, the position accuracy determination device, the computer program for determining position accuracy, and the position accuracy determination method of the above-mentioned embodiments can be modified as appropriate without departing from the spirit of the present disclosure. Furthermore, the technical scope of the present disclosure is not limited to those embodiments, but extends to the inventions described in the claims and their equivalents.
[0113] For example, in the above-described embodiment, the determination unit determined the state of accuracy of the vehicle's current position based on the first difference amount or the second difference amount, but the determination unit may also determine the state of accuracy of the vehicle's current position based on the second difference amount.
[0114] In the above-described embodiment, the first estimated position represents the estimated position of the vehicle at each camera shooting time. In this case, the estimated position based on the road feature cannot be obtained between the previous and current camera shooting times. Therefore, the vehicle position between the estimated position of the vehicle at the previous camera shooting time and the estimated position of the vehicle at the current camera shooting time may be obtained by dead reckoning starting from the estimated position of the vehicle at the previous camera shooting time, and may be set as the first estimated position.
[0115] Moreover, the above-described determination process is an example, and the determination conditions are not limited to those described above. [Explanation of symbols]
[0116] 1 Vehicle Control System 2 Camera 3 Positioning information receiver 4. Navigation devices 5 User Interface 5a Display device 6 Vehicle Speed Sensor 7 Yaw rate sensor 10 Vehicles 11 Map information storage device 12 Position estimation device 21 Communication Interface 22 Memory 23 Processors 230 Position estimation part 231 Calculation Section 232 Judgment section 13 Object detection device 14 Traffic lane planning device 15 Operation planning device 16 Vehicle control device 17 In-vehicle network
Claims
1. a first position estimation unit that estimates a first position of the moving object at a first time based on an image representing a road feature on a road surface around the moving object at the first time and position information of the road feature on the road surface; a second position estimation unit that estimates a second position of the moving object at the first time based on a position of the moving object at a second time prior to the first time and an amount of movement and an amount of change in azimuth angle of the moving object from the second time to the first time; a calculation unit that inputs the first position and the second position at the first time into a prediction filter to calculate a current position of the moving object at the first time; a determination unit that determines a state of accuracy of the current position of the moving object based on a first difference amount that represents a distance between the current position of the moving object at the first time, a position of the moving object at a time prior to the first time, and a position estimated based on an amount of movement and an amount of change in azimuth angle of the moving object from the previous time to the first time; having The position accuracy determination device is characterized in that the determination unit determines that the accuracy of the current position of the moving object has deteriorated if the percentage by which the multiple first difference amounts obtained between the first time and a time a predetermined time prior exceed a predetermined first threshold is equal to or greater than a first reference value, and determines that the accuracy of the current position of the moving object has not deteriorated if the percentage by which the first difference amounts exceed the first threshold is less than the first reference value.
2. the determination unit determines a second difference amount representing a distance between the first position and the second position of the moving object at the first time; The determination unit determines a state of accuracy of the current position of the moving object based on the first difference amount and the second difference amount; 2. The position accuracy determination device of claim 1, wherein the determination unit determines that the accuracy of the current position of the moving object has deteriorated if at least one of the multiple second difference amounts obtained between the first time and the time the specified time prior is equal to or greater than a specified second threshold, and determines that the accuracy of the current position of the moving object has not deteriorated if all of the second difference amounts are less than the second threshold.
3. The position accuracy determination device of claim 1 or 2, wherein the determination unit uses different criteria when determining that the accuracy of the current position of the moving object should be changed from a good state to a bad state and when determining that the accuracy of the current position of the moving object should be changed from a bad state to a good state.
4. The position accuracy determination device according to claim 2 , wherein the determination unit compares the second difference amount with a predetermined reference threshold value to determine a state of estimation accuracy of the position of the moving object.
5. A position accuracy determination device as described in any one of claims 1 to 4, wherein the determination unit notifies the driver via a notification unit of a request to participate in driving the moving object based on the state of the estimation accuracy of the position of the moving object.
6. 6. The position accuracy determination device according to claim 1, wherein the determination unit uses the second time as the previous time.
7. estimating a first position of the moving object at a first time based on an image representing a road feature on a road surface around the moving object at the first time and position information of the road feature on the road surface; estimating a second position of the moving object at the first time based on a position of the moving object at a second time prior to the first time and an amount of movement and an amount of change in azimuth angle of the moving object from the second time to the first time; inputting the first position and the second position at the first time into a prediction filter to calculate a current position of the moving object at the first time; determining a state of accuracy of the current position of the moving object based on a first difference amount representing a distance between the current position of the moving object at the first time, a position of the moving object at a time prior to the first time, and a position estimated based on an amount of movement and an amount of change in azimuth angle of the moving object from the previous time to the first time; and causing the processor to execute the When a rate at which the first difference amounts, among the multiple first difference amounts calculated between the first time and a time a predetermined time earlier, exceed a predetermined first threshold is equal to or greater than a reference value, it is determined that the state of accuracy of the current position of the moving object has deteriorated, and when a rate at which the first difference amounts exceed the first threshold is less than the reference value, it is determined that the state of accuracy of the current position of the moving object has not deteriorated. A computer program for determining positional accuracy.
8. estimating a first position of the moving object at a first time based on an image representing a road feature on a road surface around the moving object at the first time and position information of the road feature on the road surface; estimating a second position of the moving object at the first time based on a position of the moving object at a second time prior to the first time and an amount of movement and an amount of change in azimuth angle of the moving object from the second time to the first time; inputting the first position and the second position at the first time into a prediction filter to calculate a current position of the moving object at the first time; determining a state of accuracy of the current position of the moving object based on a first difference amount representing a distance between the current position of the moving object at the first time, a position of the moving object at a time prior to the first time, and a position estimated based on an amount of movement and an amount of change in azimuth angle of the moving object from the previous time to the first time; The position accuracy determination device executes the above. When a rate at which the first difference amounts, among the multiple first difference amounts calculated between the first time and a time a predetermined time earlier, exceed a predetermined first threshold is equal to or greater than a reference value, it is determined that the state of accuracy of the current position of the moving object has deteriorated, and when a rate at which the first difference amounts exceed the first threshold is less than the reference value, it is determined that the state of accuracy of the current position of the moving object has not deteriorated. A computer program for determining positional accuracy.
Citation Information
Patent Citations
Device, method and program for evaluating reliability
JP2011017989A
Vehicle controller and program
JP2016224802A
Travel controller for vehicles
JP2018173304A
Position estimation apparatus
JP2021017073A
