Trajectory information collection device, trajectory information collection method, and computer program product

By determining and generating trajectory information in the trajectory information collection device, combining camera and sensor detection, the problem of abnormal identification of vehicle driving trajectory is solved, and detailed information collection of abnormal trajectory is realized, and the control accuracy of the autonomous driving system is improved.

CN118942266APending Publication Date: 2024-11-12WOVEN BY TOYOTA INC
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410528133.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-05-09
Filing Date
2024-04-29
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The prior art is difficult to effectively distinguish and collect abnormal trajectory information in the vehicle's driving trajectory, especially when the trajectory caused by the influence of the surrounding conditions of the vehicle is out of the standard driving range.

Method used

A trajectory information collection device is provided, which determines whether the vehicle's driving trajectory is within a standard driving range through the determination unit. If it is present, the trajectory information is mainly trajectory coordinates. If it is separated, the trajectory information includes trajectory coordinates and driver's operation quantity information is generated. , and send it to the server through the communication processing unit. The device can also use a camera to detect lane division lines and sensors to detect peripheral vehicle positions, for setting a standard driving range and determining trajectory deviation.

Benefits of technology

It realizes information collection of abnormal trajectories, provides detailed data on vehicle driving trajectories, helps distinguish between normal and abnormal trajectories, and improves the control accuracy of the autonomous driving system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942266A_ABST
    Figure CN118942266A_ABST
Patent Text Reader

Abstract

The invention relates to a trajectory information collection device, a trajectory information collection method, and a computer program product. A trajectory information collection device is provided with: a determination unit (43) that determines whether or not a travel trajectory when a vehicle (2) travels in a prescribed section is included in a prescribed standard travel range; a trajectory information generation unit (44) that generates trajectory information by including the coordinates of the respective positions on the travel trajectory in the trajectory information when the travel trajectory is included in the standard travel range, and generates the trajectory information by including the coordinates of the respective positions on the travel trajectory in the trajectory information when the travel trajectory is out of the standard travel range; generating trajectory information by including, in the trajectory information, coordinates of each position on the travel trajectory and operation amount information indicating an operation amount of the vehicle (2) applied by a driver in a predetermined section; and a communication processing unit (45) that transmits the generated trajectory information to a server (4) via a communication device (23) mounted on the vehicle (2).
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a trajectory information collection device, a trajectory information collection method, and a computer program product for collecting trajectory information for collecting information indicating a trajectory along which a vehicle has traveled. Background Art

[0002] A technology has been proposed that generates data indicating the range in which a vehicle can travel in each road section as one of the information included in a high-precision map that is referenced by the vehicle's autonomous driving system to perform autonomous driving control of the vehicle (see Japanese Patent Application Laid-Open No. 2020-101745).

[0003] The map data generating device disclosed in Japanese Patent Application Laid-Open No. 2020-101745 performs statistical processing on the crossing driving trajectory data from the start section of the first lane to the end section of the second lane. Then, the map data generating device generates the drivable range data indicating the drivable range when the vehicle is actually driving using the automatic driving function and the driving assistance function, excluding the crossing driving trajectory data that deviates from the prescribed range.

[0004] The driving trajectory of a vehicle when it is actually driving is affected by the surrounding conditions of the vehicle. Therefore, depending on the situation, the driving trajectory of the vehicle may sometimes become an abnormal trajectory in which the vehicle deviates from the lane in which it is driving. It is ideal to distinguish such abnormal driving trajectories from normal driving trajectories and collect them. Summary of the invention

[0005] Therefore, an object of the present invention is to provide a track information collecting device capable of collecting information on a travel track of a vehicle that has an abnormal track.

[0006] According to one embodiment, a trajectory information collection device is provided. The trajectory information collection device comprises: a determination unit that determines whether a driving trajectory of a vehicle traveling in a prescribed interval is included in a prescribed standard driving range; a trajectory information generation unit that generates trajectory information by including coordinates of each position on the driving trajectory in the trajectory information when the driving trajectory is included in the standard driving range, and generates trajectory information by including coordinates of each position on the driving trajectory and operation amount information indicating an operation amount of the vehicle applied by a driver in the prescribed interval in the trajectory information when the driving trajectory deviates from the standard driving range; and a communication processing unit that sends the generated trajectory information to a server via a communication device mounted on the vehicle.

[0007] Preferably, the track information collection device further comprises a storage unit that stores information indicating a reference driving track in a specified interval. Furthermore, preferably, when the deviation between the driving track and the reference driving track at any position on the driving track is greater than a specified allowable distance corresponding to the standard driving range, the determination unit determines that the driving track is out of the standard driving range.

[0008] Alternatively, preferably, the trajectory information collection device further includes a detection unit that detects lane dividing lines that divide the lanes in which the vehicle travels in a predetermined section from an image obtained by a camera mounted on the vehicle. And preferably, the determination unit sets the standard driving range based on the detected lane dividing lines.

[0009] Alternatively, preferably, the trajectory information collection device further includes a vehicle detection unit, which detects other vehicles traveling around the vehicle when the vehicle is traveling in a specified interval from sensor signals indicating the conditions around the vehicle obtained by sensors mounted on the vehicle, and estimates the relative positional relationship of the detected other vehicles with respect to the vehicle. Furthermore, preferably, when the driving trajectory deviates from the standard driving range, the trajectory information generation unit includes relative positional information indicating the relative positional relationship of the detected other vehicles with respect to the vehicle at any position on the driving trajectory in the trajectory information.

[0010] According to another embodiment, a trajectory information collection method is provided. The trajectory information collection method includes: determining whether a driving trajectory of a vehicle when it travels in a specified interval is included in a specified standard driving range; if the driving trajectory is included in the standard driving range, generating trajectory information by including the coordinates of each position on the driving trajectory in the trajectory information; if the driving trajectory deviates from the standard driving range, generating trajectory information by including the coordinates of each position on the driving trajectory and operation amount information indicating the operation amount of the vehicle applied by the driver in the specified interval in the trajectory information; and sending the generated trajectory information to a server via a communication device mounted on the vehicle.

[0011] According to another embodiment, a computer program product for collecting trajectory information is provided. The computer program product for collecting trajectory information includes a command for causing a computer to perform the following processing: determining whether a driving trajectory of a vehicle when it travels in a prescribed interval is included in a prescribed standard driving range; if the driving trajectory is included in the standard driving range, generating trajectory information by including the coordinates of each position on the driving trajectory in the trajectory information; if the driving trajectory deviates from the standard driving range, generating trajectory information by including the coordinates of each position on the driving trajectory and operation amount information indicating the operation amount of the vehicle applied by the driver in the prescribed interval in the trajectory information; and sending the generated trajectory information to a server via a communication device mounted on the vehicle.

[0012] The trajectory information collection device of the present disclosure has an effect of being able to collect information on the travel trajectory of a vehicle that has an abnormal trajectory. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a schematic diagram of the structure of a trajectory information collection system equipped with a trajectory information collection device.

[0014] Figure 2 This is a schematic diagram of the vehicle.

[0015] Figure 3 The hardware structure diagram of a trajectory information collection device according to one embodiment.

[0016] Figure 4 It is a functional block diagram of a processor of a trajectory information collection device.

[0017] Figure 5A This is a diagram showing an example of the collected travel trajectories.

[0018] Figure 5B This is a diagram showing another example of the collected travel trajectories.

[0019] Figure 6 This is a flow chart of the trajectory information collection and processing operation. DETAILED DESCRIPTION

[0020] Hereinafter, a trajectory information collection device, a trajectory information collection method executed by the trajectory information collection device, and a computer program for trajectory information collection will be described with reference to the accompanying drawings. The trajectory information collection device is mounted on a vehicle, generates trajectory information representing the driving trajectory of the vehicle when the vehicle travels in a prescribed interval, and uploads the trajectory information to a server. In particular, the trajectory information collection device determines whether the driving trajectory of the vehicle when it travels in a prescribed interval is included in a prescribed standard driving range. Then, in the case where the driving trajectory is included in the standard driving range, the trajectory information collection device generates the trajectory information by including the coordinates of each position on the driving trajectory in the trajectory information. On the other hand, in the case where the driving trajectory deviates from the standard driving range, the trajectory information collection device generates the trajectory information by including the coordinates of each position on the driving trajectory and the operation amount information representing the operation amount of the vehicle applied by the driver in the prescribed interval in the trajectory information.

[0021] Figure 1 1 is a schematic diagram of a trajectory information collection system equipped with a trajectory information collection device. In this embodiment, the trajectory information collection system 1 has a trajectory information collection device 3 and a server 4 mounted on at least one vehicle 2. The trajectory information collection device 3 accesses a wireless base station 6 connected to a communication network 5 connected to the server 4 via a gateway (not shown), and is connected to the server 4 via the wireless base station 6 and the communication network 5. It should be noted that in Figure 1 In the figure, only one vehicle 2 is shown, but the trajectory information collection system 1 may include a plurality of vehicles 2 equipped with the trajectory information collection devices 3. Similarly, a plurality of wireless base stations 6 may be connected to the communication network 5.

[0022] The following describes the vehicle 2 and the trajectory information collection device 3. As described above, the trajectory information collection system 1 may include a plurality of vehicles 2 equipped with the trajectory information collection device 3, but with regard to the trajectory information collection process, each vehicle 2 and each trajectory information collection device 3 may have the same configuration and perform the same process. Therefore, the following describes one vehicle 2 and one trajectory information collection device 3.

[0023] Figure 2This is a schematic diagram of the structure of the vehicle 2. The vehicle 2 has a camera 21 for photographing the surroundings of the vehicle 2, a GPS (Global Positioning System) receiver 22, a wireless communication terminal 23, a vehicle control device (ECU: Electronic Control Unit) 24, and a trajectory information collection device 3. The camera 21, the GPS receiver 22, the wireless communication terminal 23, the ECU24, and the trajectory information collection device 3 are communicatively connected via a standard in-vehicle network such as a controller area network. In addition, the vehicle 2 may further have a distance measuring sensor (not shown) such as a LiDAR (Light Detection and Ranging) sensor for measuring the distance to objects around the vehicle 2.

[0024] The camera 21 is an example of a sensor for sensing the surrounding conditions of the vehicle 2, and has: a two-dimensional detector such as a CCD (Charge Coupled Device) or a C-MOS (Complementary Metal Oxide Semiconductor), which is composed of an array of photoelectric conversion elements that are sensitive to visible light; and an imaging optical system that images the image of the area to be photographed on the two-dimensional detector. In addition, the camera 21 is installed in the cabin of the vehicle 2, for example, in a manner facing the front of the vehicle 2. In addition, the camera 21 photographs the front area of ​​the vehicle 2 at a predetermined shooting cycle (for example, 1 / 30 second to 1 / 10 second) to generate an image of the front area. The image obtained by the camera 21 is an example of a sensor signal representing the surrounding conditions of the vehicle 2, and can be a color image or a grayscale image. It should be noted that a plurality of cameras 21 with different shooting directions or focal lengths can also be set in the vehicle 2.

[0025] Every time an image is generated, the camera 21 outputs the generated image together with the generation time to the trajectory information collecting device 3 via the in-vehicle network.

[0026] The GPS receiver 22 receives GPS signals from GPS satellites at predetermined intervals, and locates the position of the vehicle 2 based on the received GPS signals. In addition, the GPS receiver 22 outputs the positioning information indicating the positioning result of the vehicle 2 based on the GPS signals together with the generation time to the trajectory information collection device 3 via the in-vehicle network at predetermined intervals. It should be noted that the vehicle 2 may also have a receiver that complies with the satellite positioning system other than the GPS receiver 22. In this case, the receiver only needs to locate the position of the vehicle 2.

[0027] The wireless communication terminal 23 is an example of a communication device, and is a device that performs wireless communication processing that complies with a prescribed wireless communication standard, for example, by accessing the wireless base station 6, and connecting to the server 4 via the wireless base station 6 and the communication network 5. That is, a communication line is established between the wireless communication terminal 23 and the server 4 via the wireless base station 6 and the communication network 5. In addition, the wireless communication terminal 23 receives a downlink wireless signal containing information indicating a collection target area received from the server 4, and outputs the received information to the trajectory information collection device 3, wherein the collection target area includes a section that becomes a collection target of trajectory information. In addition, the wireless communication terminal 23 generates an uplink wireless signal containing the trajectory information received from the trajectory information collection device 3. In addition, the wireless communication terminal 23 sends the trajectory information to the server 4 by sending the uplink wireless signal to the wireless base station 6.

[0028] The ECU 24 controls each part of the vehicle 2 according to the operation performed by the driver. Moreover, the ECU 24 outputs the operation amount information indicating the operation amount of the vehicle 2 applied by the driver to the trajectory information collection device 3 at a predetermined period. The operation amount information includes at least one of the steering angle of the steering wheel, the accelerator opening, and the brake operation amount, and the time when the driver's operation amount represented by the operation amount information is detected.

[0029] Figure 3 2 is a hardware configuration diagram of the trajectory information collection device 3. The trajectory information collection device 3 generates trajectory information indicating the travel trajectory of the vehicle 2 when traveling in a predetermined section, and transmits the generated trajectory information to the server 4 via the wireless communication terminal 23. To this end, the trajectory information collection device 3 has a communication interface 31, a memory 32, and a processor 33.

[0030] The communication interface 31 is an example of an in-vehicle communication unit, and has an interface circuit for connecting the trajectory information collection device 3 to the in-vehicle network. That is, the communication interface 31 is connected to the camera 21, the GPS receiver 22, the wireless communication terminal 23, and the ECU 24 via the in-vehicle network. And, whenever an image is received from the camera 21, the communication interface 31 transmits the received image to the processor 33. In addition, whenever positioning information is received from the GPS receiver 22, the communication interface 31 transmits the received positioning information to the processor 33. Moreover, whenever information from the server 4 such as information indicating the collection object area is received from the wireless communication terminal 23, the communication interface 31 transmits the information to the processor 33. In addition, whenever operation amount information is received from the ECU 24, the communication interface 31 transmits the operation amount information to the processor 33. In addition, the communication interface 31 outputs the trajectory information received from the processor 33 to the wireless communication terminal 23 via the in-vehicle network.

[0031] The memory 32 is an example of a storage unit, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 32 may further include other storage devices such as a hard disk device. In addition, the memory 32 stores various data used in the processing associated with the trajectory information collection performed by the processor 33 of the trajectory information collection device 3. For example, the memory 32 stores the identification information of the vehicle 2, the focal length of the camera 21, the shooting direction, the setting position of the camera 21, and the various parameters of the classifier (classifier) ​​used to determine the detection object such as the lane dividing line and other vehicles from the image received from the camera 21. In addition, the memory 32 temporarily stores the image received from the camera 21, the positioning information received from the GPS receiver 22, the operation amount information received from the ECU 24, and their generation time. In addition, the memory 32 stores information representing the collection object area. It should be noted that the information representing the collection object area includes information representing the position and range of the specified interval (for example, the coordinates of each end point of the specified interval). In addition, the memory 32 can also store a high-precision map of the ground objects such as the lane dividing line used for the detection of the position of the vehicle 2. Furthermore, the memory 32 may store information indicating a reference driving trajectory and information indicating a standard driving range. In addition, the memory 32 may store a computer program or the like for realizing each process executed by the processor 33 .

[0032] The processor 33 has one or more CPUs (Central Processing Units) and their peripheral circuits. The processor 33 may further have other computing circuits such as a logic operation unit, a numerical operation unit, or a graphics processing unit. In addition, the processor 33 performs trajectory information collection processing while the vehicle 2 is traveling. In addition, whenever an image is received from the camera 21, the processor 33 saves the image together with the time it is generated in the memory 32. Moreover, whenever positioning information is received from the GPS receiver 22, the processor 33 saves the positioning information together with the time it is generated in the memory 32. In addition, whenever operation amount information is received from the ECU 24, the processor 33 saves the operation amount information together with the time it is generated in the memory 32.

[0033] Figure 4 3 is a functional block diagram of the processor 33 of the trajectory information collection device 3. The processor 33 includes a detection unit 41, a vehicle detection unit 42, a determination unit 43, a trajectory information generation unit 44, and a communication processing unit 45. These units of the processor 33 are, for example, functional modules implemented by a computer program running on the processor 33. Alternatively, these units of the processor 33 may also be dedicated operation circuits provided in the processor 33.

[0034] The processor 33 determines whether the vehicle 2 has entered a predetermined section. Then, when the vehicle 2 has entered a predetermined section, the trajectory information collection process is executed. The predetermined section may be set as a road section included in the collection target area. The predetermined section may be set as a section including a curve section, an intersection, a junction, or a branch point, for example. However, the predetermined section is not limited to these sections, and may be only a straight section.

[0035] The processor 33 determines whether the current position of the vehicle 2 indicated by the latest positioning information is included in the specified interval indicated by the information indicating the collection target area. Then, if the current position of the vehicle 2 is included in the range of the specified interval included in the information indicating the collection target area, the processor 33 determines that the vehicle 2 has entered the specified interval and performs the trajectory information collection process.

[0036] The detection unit 41 detects the lane dividing line that divides the lane in which the vehicle 2 travels in the specified section (hereinafter, sometimes referred to as the own lane). To this end, when the vehicle 2 has entered the specified section, the detection unit 41 detects the lane dividing line by inputting the latest image obtained by the camera 21 to the classifier that has been pre-learned in a manner to detect the lane dividing line at a specified period. In addition, the detection unit 41 sets the lane dividing line detected at the position closest to the vehicle 2 in the area corresponding to the left and right of the vehicle 2 on the image as the lane dividing line that divides the own lane.

[0037] Furthermore, the detection unit 41 may detect predetermined ground objects other than lane dividing lines from the image by inputting the image into the above-mentioned classifier. The detected predetermined ground objects are used to accurately detect the position of the vehicle 2. The predetermined ground objects include, for example, at least one of road markings other than lane dividing lines such as curbs, guardrails, road signs, and temporary stop lines.

[0038] The detection unit 41 may use a deep neural network (DNN: Deep Learning Neural Network) with a convolutional neural network (CNN: Convolutional Neural Network)-like architecture such as a single shot multibox detector or a fast R-CNN (Faster Region-Convolutional Neural Network) as a classifier. Alternatively, the detection unit 41 may use a DNN for semantic segmentation such as a fully convolutional network (Fully Convolutional Network) or U-Net as a classifier. Alternatively, the detection unit 41 may use a DNN with a self-attention network (SAN: self attention network)-like architecture such as a vision transformer as a classifier. Alternatively, the detection unit 41 may use a classifier based on other machine learning methods such as an adaptive boosting (AdaBoost) classifier as a classifier. Such a classifier detects ground objects such as lane dividing lines that are detection objects from an image, and uses many training images representing the ground objects to perform pre-learning according to a prescribed learning method such as an error back propagation method. Then, the classifier outputs information indicating an object region including the land feature to be detected in the input image and information indicating the type of the land feature shown in the object region.

[0039] The detection unit 41 notifies the determination unit 43 of the position of the detected planimetric feature on the image and the type of the planimetric feature.

[0040] The vehicle detection unit 42 detects other vehicles (hereinafter, sometimes referred to as surrounding vehicles for convenience of explanation) traveling around the vehicle 2. To this end, when the vehicle 2 has entered a predetermined section, the vehicle detection unit 42 detects surrounding vehicles by inputting the latest image obtained by the camera 21 into a classifier that has been pre-learned in a manner to detect surrounding vehicles at predetermined intervals.

[0041] As such a classifier, the vehicle detection unit 42 may use the same classifier as the classifier used by the detection unit 41 to detect lane dividing lines, etc. It should be noted that the classifier used by the detection unit 41 may be pre-learned in a manner that also detects surrounding vehicles. In this case, the detection unit 41 and the vehicle detection unit 42 are integrally configured.

[0042] In addition, when the vehicle 2 has a ranging sensor, the vehicle detection unit 42 may also detect surrounding vehicles by inputting a ranging signal obtained by the ranging sensor into a classifier. It should be noted that the ranging sensor is another example of a sensor that senses the surrounding conditions of the vehicle 2, and the ranging signal is another example of a sensor signal that indicates the surrounding conditions of the vehicle 2. In this case, the vehicle detection unit 42 may also use a classifier based on other machine learning methods such as a DNN or a support vector machine having a CNN-type or SAN-type architecture as a classifier.

[0043] When the surrounding vehicles are detected, the vehicle detection unit 42 obtains relative position information indicating the relative positional relationship between the vehicle 2 and the surrounding vehicles. In the present embodiment, the relative position information includes the distance between the vehicle 2 and the surrounding vehicles and the direction from the vehicle 2 to the surrounding vehicles. Here, it is assumed that the position of the lower end of the object area indicating the surrounding vehicles on the image indicates the direction to the position where the surrounding vehicles are in contact with the road surface observed from the camera 21. Therefore, the vehicle detection unit 42 can estimate the distance between the vehicle 2 and the surrounding vehicles based on the position of the lower end of the object area indicating the surrounding vehicles on the image, the shooting direction of the camera 21, the focal length, and the installation height. Moreover, the vehicle detection unit 42 sets the direction from the camera 21 corresponding to the center of gravity position of the object area indicating the surrounding vehicles on the image as the direction from the vehicle 2 to the surrounding vehicles. In addition, when the vehicle 2 is equipped with a distance measuring sensor, the vehicle detection unit 42 can also estimate the distance measured for the direction corresponding to the center of gravity position of the object area indicating the surrounding vehicles on the image, which is indicated by the distance measuring signal obtained by the distance measuring sensor when the image is generated, as the distance between the vehicle 2 and the surrounding vehicles. Alternatively, when a surrounding vehicle is detected based on the distance measurement signal, the vehicle detection unit 42 may estimate the distance measured for the direction indicating the surrounding vehicle indicated by the distance measurement signal as the distance between the vehicle 2 and the surrounding vehicle.

[0044] It should be noted that, when a plurality of surrounding vehicles are detected, the vehicle detection unit 42 may perform the above-mentioned processing for each surrounding vehicle and obtain the relative position information for each surrounding vehicle.

[0045] The vehicle detection unit 42 notifies the trajectory information generation unit 44 of the relative position information obtained for each surrounding vehicle.

[0046] The determination unit 43 determines whether the driving trajectory of the vehicle 2 when it has traveled in the prescribed section is included in the prescribed standard driving range. For this purpose, when the vehicle 2 has exited the prescribed section, the determination unit 43 determines the driving trajectory of the vehicle 2 during the period of traveling in the prescribed section. It should be noted that the determination unit 43 can determine whether the vehicle 2 has exited the prescribed section by comparing the position of the vehicle 2 represented by the latest positioning information with the prescribed section. In the following, the driving trajectory of the vehicle 2 in the prescribed section may be referred to as simply the driving trajectory.

[0047] The determination unit 43 obtains the odometer information of the vehicle 2 from the ECU 24, and obtains the movement amount and the displacement amount of the orientation of the vehicle 2 at each generation interval of each image. Then, the determination unit 43 estimates the position of the vehicle 2 when each image is generated according to the so-called Structure from Motion (SfM) method based on the ground objects detected from each image and the movement amount and the displacement amount of the orientation of the vehicle 2 at each generation interval of each image. Then, the determination unit 43 obtains the driving trajectory of the vehicle 2 by arranging the coordinates of the estimated position of the vehicle 2 when each image is generated in chronological order.

[0048] In addition, when the memory 32 stores a high-precision map, the determination unit 43 may also compare each image with the high-precision map based on the ground features detected from each image, thereby detecting the position of the vehicle 2 when each image was generated. In this case, the determination unit 43 assumes the position and orientation of the vehicle 2 and projects the ground features detected from the image onto the high-precision map, or projects the ground features around the vehicle 2 represented by the high-precision map onto the image. Then, the determination unit 43 detects the position and orientation of the vehicle 2 when the ground features detected from the image are most consistent with the ground features represented on the high-precision map as the actual position and orientation of the vehicle 2.

[0049] In this case, the determination unit 43 can determine the position of the projected feature on the high-precision map or image using the parameters of the camera 21 such as the assumed position and orientation of the vehicle 2, the focal length, the installation height, and the shooting direction. It should be noted that the position of the vehicle 2 represented by the latest positioning information or the position obtained by correcting the position and orientation of the vehicle 2 estimated at the time of the last detection of the position of the vehicle 2 using the odometer information is used as the initial value of the position and orientation of the vehicle 2. Then, the determination unit 43 calculates the degree of consistency between the feature detected from the image and the corresponding feature represented on the high-precision map (for example, the inverse of the sum of the squares of the distances between the corresponding features). The determination unit 43 repeatedly performs the above-mentioned processing while changing the assumed position and orientation of the vehicle 2. Then, the determination unit 43 detects the assumed position and orientation when the degree of consistency becomes the maximum as the actual position and orientation of the vehicle 2.

[0050] It should be noted that, if the accuracy of the position of the vehicle 2 indicated by the positioning information is sufficient, the determination unit 43 may also obtain the travel trajectory of the vehicle 2 by arranging the coordinates of the position of the vehicle 2 indicated by the positioning information in chronological order.

[0051] The determination unit 43 compares the obtained driving trajectory with the standard driving range. The standard driving range can be set to a range that the vehicle 2 is assumed to pass through if the vehicle 2 drives in a manner that does not violate road regulations and does not cause danger to the vehicle 2 itself and surrounding vehicles. For example, the standard driving range is set to be included between two lane dividing lines that divide the own lane. In addition, when the prescribed section is a section including an intersection, it is preferred that the standard driving range is set not to cross lanes before and after the intersection.

[0052] The determination unit 43 sets the standard driving range based on the two lane dividing lines that divide the own lane detected by the detection unit 41. In this case, the determination unit 43 obtains the positions of the lane dividing lines in the real space based on the parameters of the camera 21 such as the installation height, focal length, and shooting direction of the camera 21, and the position and orientation of the vehicle 2 when the image in which the lane dividing lines are detected is generated. It should be noted that the determination unit 43 performs the above-mentioned processing on each image generated while the vehicle 2 is traveling in a prescribed section, and connects the lane dividing lines detected from each image and projected into the real space, thereby obtaining the positions of the lane dividing lines in the real space throughout the entire prescribed section. Then, the determination unit 43 sets the standard driving range in such a manner that the position is included between the two lane dividing lines that divide the own lane and is a predetermined safety distance (for example, several tens of centimeters to two meters) inside the own lane than the lane dividing lines as the boundary of the standard driving range.

[0053] It should be noted that, when the memory 32 stores a high-precision map, the determination unit 43 may also use the lane dividing lines in the prescribed section indicated by the high-precision map instead of the lane dividing lines detected by the detection unit 41 to set the standard driving range. In this case, the determination unit 43 may set the lane including the position of the vehicle 2 when the vehicle 2 enters the prescribed section among the lanes in the prescribed section indicated by the high-precision map as the own lane.

[0054] The determination unit 43 determines whether the driving trajectory of the vehicle 2 is included in the standard driving range by comparing the set standard driving range with the driving trajectory of the vehicle 2. Then, if the driving trajectory is included in the standard driving range throughout the entire specified interval, the determination unit 43 determines that the driving trajectory is included in the standard driving range. On the other hand, if the driving trajectory deviates from the standard driving range at any position in the specified interval, the determination unit 43 determines that the driving trajectory deviates from the standard driving range.

[0055] In addition, the high-precision map may also include information indicating the reference driving trajectory of each lane in a specified section. Unless there are any special circumstances, the reference driving trajectory for each lane is a standard trajectory that a vehicle passes through when driving in the lane. For example, the reference driving trajectory is set to be a driving trajectory obtained by averaging multiple driving trajectories of vehicles that actually drove in the lane. Alternatively, the reference driving trajectory may also be set to pass through the center of the lane.

[0056] In this case, the standard driving range of each lane can be set as: a range centered on the reference driving trajectory of the lane and within the allowable distance specified from the reference driving trajectory. The allowable distance in each lane is set to a distance that is shorter than the width from the reference driving trajectory of the lane to the lane dividing line that divides the lane by a specified safety distance. Therefore, at each position on the driving trajectory, the determination unit 43 calculates the distance from the position to the reference driving trajectory as the deviation between the driving trajectory at that position and the reference driving trajectory. Then, if the deviation at any position on the driving trajectory is less than or equal to the allowable distance, the determination unit 43 determines that the driving trajectory is included in the standard driving range. On the other hand, if the deviation at any position on the driving trajectory is larger than the allowable distance, the determination unit 43 determines that the driving trajectory is out of the standard driving range.

[0057] The determination unit 43 notifies the trajectory information generation unit 44 of the coordinates of each position included in the driving trajectory of the vehicle 2 and the time when the vehicle 2 is located at each position (that is, the image generation time corresponding to the time when each position is detected or the generation time of the positioning information). In addition, the determination unit 43 notifies the trajectory information generation unit 44 of the determination result of whether the driving trajectory is included in the standard driving range.

[0058] The trajectory information generating unit 44 generates trajectory information indicating the driving trajectory of the vehicle 2 when it travels in the prescribed interval. In the present embodiment, when the driving trajectory is included in the standard driving range, the trajectory information generating unit 44 generates the trajectory information by including the coordinates of each position on the driving trajectory in the trajectory information. On the other hand, when the driving trajectory deviates from the standard driving range, the trajectory information generating unit 44 generates the trajectory information by including the operation amount information at each position on the driving trajectory together with the coordinates of each position in the trajectory information. In this case, the trajectory information generating unit 44 sets the operation amount information at the moment closest to the moment when the vehicle 2 exists at the position as the operation amount information at the position for each position on the driving trajectory. Thus, the main reason why the driving trajectory of the vehicle 2 becomes an abnormal trajectory such as deviating from the standard driving range can be determined. It should be noted that the trajectory information generating unit 44 can also include the operation amount information obtained from the time when the vehicle 2 enters the prescribed interval to the time when the vehicle 2 exits the prescribed interval in the trajectory information without associating it with each position on the driving trajectory.

[0059] Figure 5A and Figure 5B They are diagrams showing examples of the collected driving trajectories. Figure 5A In the example shown, the driving trajectory 501 is included in the standard driving range 510. Therefore, the coordinates of each position on the driving trajectory 501 are included in the trajectory information.

[0060] In contrast, Figure 5B In the example shown, the driving trajectory 502 has a portion outside the standard driving range 510. Therefore, the trajectory information includes not only the coordinates of each position on the driving trajectory 502 but also the operation amount information at each position.

[0061] Furthermore, when the driving track deviates from the standard driving range, the track information generating unit 44 may include at least one of a flag indicating that the driving track deviates from the standard driving range, information indicating the standard driving range, and coordinates of a position where the driving track deviates from the standard driving range in the track information.

[0062] In addition, the processor 33 may also receive information indicating the speed and acceleration / deceleration of the vehicle 2 from the ECU 24 during the period from when the vehicle 2 enters the prescribed interval to when the vehicle 2 exits the prescribed interval. Furthermore, when the driving trajectory deviates from the standard driving range, the trajectory information generating unit 44 may include at least one of the speed and acceleration / deceleration of the vehicle 2 during the period in the trajectory information. Thus, the behavior of the vehicle 2 when the driving trajectory of the vehicle 2 becomes an abnormal trajectory such as deviating from the standard driving range can be analyzed.

[0063] Furthermore, when the driving trajectory deviates from the standard driving range, the trajectory information generating unit 44 may include the relative position information between the surrounding vehicles and the vehicle 2 detected by the vehicle detecting unit 42 during the period when the vehicle 2 is traveling in the prescribed interval in the trajectory information. In this way, it is possible to determine whether the main reason why the driving trajectory of the vehicle 2 becomes an abnormal trajectory is due to the relative position relationship between the surrounding vehicles and the vehicle 2.

[0064] The trajectory information generating unit 44 transmits the generated trajectory information to the communication processing unit 45 .

[0065] When receiving the trajectory information, the communication processing unit 45 sends the trajectory information to the server 4 via the wireless communication terminal 23. It should be noted that the communication processing unit 45 can send the trajectory information immediately after the vehicle 2 exits the specified section, but is not limited to this timing, and can also send the trajectory information at other timings. For example, the communication processing unit 45 can also send the trajectory information at the timing when the ignition switch of the vehicle 2 is turned off.

[0066] Furthermore, the communication processing unit 45 may transmit a series of images generated while the vehicle 2 is traveling in a predetermined section or partial images respectively cut out from the series of images to the server 4 via the wireless communication terminal 23. Furthermore, the communication processing unit 45 may transmit data indicating predetermined ground features such as lane dividing lines respectively detected from a series of images generated while the vehicle 2 is traveling in a predetermined section to the server 4 via the wireless communication terminal 23.

[0067] Figure 6 2 is an operation flow chart of the trajectory information collection process. When the vehicle 2 has entered a predetermined section, the processor 33 executes the trajectory information collection process according to the following operation flow chart.

[0068] The detection unit 41 of the processor 33 detects a lane dividing line that divides the host lane (step S101 ). In addition, the vehicle detection unit 42 of the processor 33 detects surrounding vehicles (step S102 ).

[0069] The determination unit 43 of the processor 33 determines whether the vehicle 2 has exited the predetermined section (step S103 ). If the vehicle 2 has not exited the predetermined section (step S103 —No), the processor 33 repeatedly executes the processes after step S101 .

[0070] On the other hand, when the vehicle 2 has exited the specified interval (step S103-yes), the determination unit 43 determines the driving trajectory of the vehicle 2 during the period of driving in the specified interval (step S104). Moreover, the determination unit 43 sets the standard driving range based on the lane dividing line that divides the lane (step S105). It should be noted that when the determination unit 43 can use a high-precision map, the determination unit 43 can also set the standard driving range based on the high-precision map. Then, the determination unit 43 determines whether the driving trajectory of the vehicle 2 is included in the standard driving range (step S106).

[0071] When the driving trajectory of vehicle 2 is included in the standard driving range (step S106-yes), the trajectory information generating unit 44 of the processor 33 generates trajectory information by including the coordinates of each position on the driving trajectory in the trajectory information (step S107). On the other hand, when the driving trajectory of vehicle 2 deviates from the standard driving range (step S106-no), the trajectory information generating unit 44 generates trajectory information by including the operation amount information at each position on the driving trajectory together with the coordinates of each position in the trajectory information (step S108). It should be noted that in step S108, as described above, the trajectory information generating unit 44 may also include information representing the behavior of vehicle 2, such as the speed or acceleration / deceleration of vehicle 2, or the relative position information between vehicle 2 and surrounding vehicles in the trajectory information.

[0072] After step S107 or step S108, the communication processing unit 45 of the processor 33 transmits the trajectory information to the server 4 via the wireless communication terminal 23 (step S109). Then, the processor 33 ends the trajectory information collection process.

[0073] The server 4 generates or updates a high-precision map based on the trajectory information received from the trajectory information collection device 3 of each vehicle 2. For example, the processor of the server 4 averages the multiple driving trajectories included in the standard driving range for each lane in a specified interval, thereby obtaining a reference driving trajectory for the lane in the specified interval. Then, the processor of the server 4 includes information representing the reference driving trajectory obtained for each lane in the high-precision map. Moreover, the processor of the server 4 may also include information representing driving trajectories that have deviated from the standard driving range in the high-precision map for each lane in the specified interval. In addition, the processor of the server 4 may also parse the operation amount information included in the trajectory information for driving trajectories that have deviated from the standard driving range.

[0074] As described above, the trajectory information collection device determines whether the driving trajectory of the vehicle when it travels in a specified interval is included in the specified standard driving range. And, in the case where the driving trajectory is included in the standard driving range, the trajectory information collection device generates the trajectory information by including the coordinates of each position on the driving trajectory in the trajectory information. On the other hand, in the case where the driving trajectory deviates from the standard driving range, the trajectory information collection device generates the trajectory information by including not only the coordinates of each position on the driving trajectory in the trajectory information, but also the operation amount information indicating the operation amount of the vehicle applied by the driver in the trajectory information. Therefore, the trajectory information collection device can collect information related to the driving trajectory of the vehicle that has become an abnormal trajectory. Moreover, with respect to the normal driving trajectory included in the standard driving range, the trajectory information collection device does not include redundant information in the trajectory information, thereby suppressing the unnecessary increase in the amount of data sent to the server.

[0075] According to a modified example, in the trajectory information generating unit 44, even when the driving trajectory of the vehicle 2 deviates from the standard driving range, if the trajectory information does not include the relative position information between the vehicle 2 and the surrounding vehicles, the processing of the vehicle detection unit 42 can be omitted. In addition, if the standard driving range is set based on the high-precision map and the lane dividing line is not used for detecting the position of the vehicle 2, the processing of the detection unit 41 can also be omitted.

[0076] The computer program that enables a computer to implement the functions of each part of the processor of the trajectory information collection device based on each of the above-mentioned embodiments or variations can be provided in the form of a recording medium that can be read by a computer. It should be noted that the recording medium that can be read by a computer can be, for example, a magnetic recording medium, an optical recording medium, or a semiconductor memory.

[0077] As described above, those skilled in the art can make various changes in accordance with the implementation modes within the scope of the present invention.

Claims

1. A trajectory information collection device, comprising: A determination unit determines whether a driving trajectory of the vehicle when traveling in a predetermined section is included in a predetermined standard driving range; a trajectory information generating unit that generates the trajectory information by including the coordinates of each position on the driving trajectory in the trajectory information when the driving trajectory is included in the standard driving range, and generates the trajectory information by including the coordinates of each position on the driving trajectory and operation amount information indicating an operation amount of the vehicle applied by the driver of the vehicle in the prescribed section in the trajectory information when the driving trajectory deviates from the standard driving range; and The communication processing unit transmits the trajectory information to a server via a communication device mounted on the vehicle.

2. The trajectory information collection device according to claim 1, further comprising: a storage unit storing information indicating a reference driving trajectory in the predetermined section, When the amount of deviation between the driving trajectory and the reference driving trajectory at any position on the driving trajectory is larger than a predetermined allowable distance corresponding to the standard driving range, the determination unit determines that the driving trajectory deviates from the standard driving range.

3. The trajectory information collection device according to claim 1 further comprises: a detection unit that detects a lane dividing line that divides a lane in which the vehicle travels in the predetermined section from an image obtained by a camera mounted on the vehicle, The determination unit sets the standard driving range based on the lane dividing line.

4. The trajectory information collection device according to any one of claims 1 to 3, further comprising: a vehicle detection unit that detects other vehicles traveling around the vehicle while the vehicle is traveling in the predetermined section from a sensor signal indicating a condition around the vehicle obtained by a sensor mounted on the vehicle, and estimates a relative positional relationship of the detected other vehicles with respect to the vehicle, When the travel track deviates from the standard travel range, the track information generating unit includes relative position information indicating a relative positional relationship of the detected other vehicle with respect to the vehicle at an arbitrary position on the travel track in the track information.

5. A method for collecting trajectory information, include: Determining whether a driving trajectory of the vehicle when traveling in a specified interval is included in a specified standard driving range; generating the trajectory information by including coordinates of each position on the driving trajectory in the trajectory information when the driving trajectory is included in the standard driving range; generating the trajectory information by including coordinates of each position on the driving trajectory and operation amount information indicating an operation amount of the vehicle applied by the driver of the vehicle in the prescribed section in the trajectory information when the driving trajectory deviates from the standard driving range; as well as The trajectory information is transmitted to a server via a communication device mounted on the vehicle.

6. A computer program product for collecting trajectory information, configured to cause a computer to execute: Determining whether a driving trajectory of the vehicle when traveling in a specified interval is included in a specified standard driving range; generating the trajectory information by including coordinates of each position on the driving trajectory in the trajectory information when the driving trajectory is included in the standard driving range; generating the trajectory information by including coordinates of each position on the driving trajectory and operation amount information indicating an operation amount of the vehicle applied by the driver of the vehicle in the prescribed section in the trajectory information when the driving trajectory deviates from the standard driving range; as well as The trajectory information is transmitted to a server via a communication device mounted on the vehicle.