Azimuth angle acquisition device, azimuth angle acquisition system, and azimuth angle acquisition method
By combining the azimuth calculation method of the external and internal states, the problem of low azimuth accuracy of autonomous or remote control vehicles is solved, more accurate path driving is achieved, and control accuracy and reliability are improved.
Patent Information
- Application Number
- CN202410369193.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-05-22
- Filing Date
- 2024-03-28
- Publication Date
- 2024-11-22
AI Technical Summary
Existing autonomous or remotely controlled self-propelled vehicles have low accuracy when obtaining azimuth angle, resulting in the inability to accurately drive along a predetermined path.
Using an azimuth calculation method combining the external state and the internal boundary state, the vehicle's motion state is obtained through the external state detection unit and the internal boundary state detection unit, and the external azimuth angle and the internal boundary azimuth angle are calculated according to the vehicle state and the detection unit. Reliability adjustment prioritizes the vehicle's azimuth angle.
The accuracy of azimuth attraction of self-propelled vehicles is improved, ensuring that the vehicle can travel more accurately along the predetermined path, and enhancing the accuracy and reliability of autonomous or remote control.
Smart Images

Figure CN118991793A_ABST
Abstract
Description
[0001] Cross-reference to related applications
[0002] This application claims the benefit of priority based on Japanese Application No. 2023-083792, filed on May 22, 2023, which is incorporated herein by reference for all purposes. Technical Field
[0003] The present disclosure relates to techniques for obtaining the heading angle of a self-propelled vehicle. Background Art
[0004] A technology for driving a vehicle by autonomous control or remote control in a vehicle manufacturing system has been proposed.
[0005] Prior art literature
[0006] In a self-propelled vehicle that travels by autonomous control or remote control, the vehicle's travel control is performed using the vehicle's position coordinates and azimuth. However, there is a problem that the azimuth cannot be obtained with the desired acquisition accuracy. If the azimuth is obtained with low accuracy, the self-propelled vehicle cannot be driven along a desired path.
[0007] Therefore, it is required to improve the accuracy of obtaining the azimuth angle of the self-propelled vehicle. Summary of the invention
[0008] The present disclosure can be implemented as the following aspects.
[0009] A first aspect provides an azimuth acquisition device for a self-propelled vehicle. The azimuth acquisition device according to the first aspect comprises: an acquisition unit that acquires an external state and an internal state, wherein the external state is a motion state of the vehicle detected from the outside, and the internal state is a motion state of the vehicle detected from the inside; an azimuth calculation unit that calculates an external azimuth using the acquired external state, and calculates an internal azimuth using the acquired internal state; and an azimuth determination unit that determines a vehicle azimuth for self-propelled movement of the vehicle using the calculated external azimuth and internal azimuth.
[0010] According to the azimuth angle acquisition device of the first aspect, it is possible to improve the accuracy of acquisition of the azimuth angle of the self-propelled vehicle.
[0011] In the azimuth acquisition device of the first embodiment, the azimuth determination unit may be configured to determine the vehicle azimuth by changing the priority of the external azimuth and the internal azimuth according to the state of the vehicle and the state of the external state detection unit that detects the external state. In this case, the accuracy of obtaining the azimuth of the self-propelled vehicle can be further improved according to the state of the vehicle and the state of the external state detection unit.
[0012] In the azimuth acquisition device of the first embodiment, the azimuth determination unit may be configured to determine the vehicle azimuth by increasing the priority of the external azimuth when the vehicle is in a stopped state. In this case, the accuracy of obtaining the azimuth of the self-propelled vehicle can be further improved by using the external azimuth.
[0013] In the azimuth acquisition device of the first embodiment, the azimuth determination unit may be configured to determine the vehicle azimuth by increasing the priority of the inner boundary azimuth when the vehicle is in a turning state. In this case, the accuracy of obtaining the azimuth of the self-propelled vehicle can be further improved by using the inner boundary azimuth.
[0014] In the azimuth acquisition device of the first embodiment, the azimuth determination unit may be configured to use the external azimuth to correct the inner boundary azimuth when the vehicle is in a straight-moving state and the reliability of the external state detection unit is greater than a predetermined threshold value, and to increase the priority of the inner boundary azimuth to determine the vehicle azimuth when the reliability of the external state detection unit is less than the predetermined threshold value. In this case, the internal boundary azimuth is corrected using the external azimuth according to the reliability of the external state detection unit, thereby further improving the accuracy of obtaining the azimuth of the self-propelled vehicle.
[0015] In the azimuth acquisition device of the first embodiment, the external state detection unit may be a camera disposed outside the vehicle, and the azimuth calculation unit may calculate the external azimuth of the vehicle using an image captured by the camera. In this case, the external azimuth can be directly calculated using the image, thereby further improving the accuracy of obtaining the azimuth of the self-propelled vehicle.
[0016] In the azimuth acquisition device of the first embodiment, the inner boundary state detection unit may be a yaw rate sensor provided on the vehicle, and the azimuth calculation unit may calculate the inner boundary azimuth of the vehicle using the yaw rate obtained by the yaw rate sensor. In this case, the inner boundary azimuth can be calculated by directly detecting the behavior of the vehicle, so that the acquisition accuracy of the azimuth of the self-propelled vehicle can be further improved.
[0017] A second aspect provides an azimuth acquisition system for a self-propelled vehicle. The azimuth acquisition system of the second aspect comprises: an external state detection unit, which is arranged outside the vehicle to detect the motion state of the vehicle from the outside; an internal state detection unit, which is mounted on the vehicle to detect the motion state of the vehicle from the internal boundary; and an azimuth acquisition device, the azimuth acquisition device comprising: an azimuth calculation unit, which calculates an external azimuth using an external state, and calculates an internal azimuth using an internal state, the external state being the motion state of the vehicle detected by the external state detection unit, and the internal state being the motion state of the vehicle detected by the internal state detection unit; and an azimuth determination unit, which determines a vehicle azimuth for self-propelled movement of the vehicle using the calculated external azimuth and the internal azimuth.
[0018] According to the azimuth acquisition system of the second aspect, it is possible to improve the accuracy of acquiring the azimuth of the self-propelled vehicle. In addition, the azimuth acquisition system of the second aspect can be implemented in various aspects similarly to the azimuth acquisition device of the first aspect.
[0019] A third aspect provides a method for obtaining an azimuth angle of a self-propelled vehicle. The azimuth angle obtaining method of the third aspect includes the following steps: obtaining an external state and an internal state, wherein the external state is a motion state of the vehicle detected from the outside, and the internal state is a motion state of the vehicle detected from the inside; using the obtained external state to calculate an external azimuth angle; using the obtained internal state to calculate an internal azimuth angle; and using the calculated external azimuth angle and the internal azimuth angle to determine a vehicle azimuth angle for self-propelled movement of the vehicle.
[0020] According to the azimuth acquisition method of the third embodiment, the accuracy of the azimuth of the self-propelled vehicle can be improved. In addition, the azimuth acquisition method of the third embodiment can be implemented in various ways like the azimuth acquisition device of the first embodiment. In addition, the azimuth acquisition method of the third embodiment can also be implemented as an azimuth acquisition program or a computer-readable recording medium recording the program. In addition, the determination of the vehicle azimuth in the first to third embodiments can also be performed using AI, that is, a learning model. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 It is an explanatory diagram showing a schematic configuration of a vehicle heading angle acquisition system according to the first embodiment.
[0022] Figure 2 This is a block diagram showing an example of the internal structure of the vehicle heading angle acquisition device according to the first embodiment.
[0023] Figure 3 This is a block diagram showing an example of the internal structure of the vehicle according to the first embodiment.
[0024] Figure 4 This is a flowchart showing the flow of vehicle heading angle acquisition processing executed by the vehicle heading angle acquisition device according to the first embodiment.
[0025] Figure 5 It is an explanatory diagram showing an example of the traveling state of a vehicle.
[0026] Figure 6 It is an explanatory diagram showing the correspondence relationship between the vehicle heading angle and the movement vector.
[0027] Figure 7 This is a flowchart showing an example of a remote control process flow of a vehicle.
[0028] Figure 8 This is a flowchart showing an example of the autonomous control processing flow of the vehicle. DETAILED DESCRIPTION
[0029] Hereinafter, the azimuth angle acquisition device, azimuth angle acquisition system, and azimuth angle acquisition method of the self-propelled vehicle of the present disclosure will be described based on several embodiments.
[0030] First embodiment:
[0031] like Figure 1 As shown, the vehicle heading angle acquisition system 500 of the first embodiment includes a vehicle heading angle acquisition device 10, a self-propelled vehicle 30, an external state detection unit 21, and an internal state detection unit 31. The vehicle heading angle acquisition device 10 is a so-called server computer, and determines and acquires the vehicle heading angle that can be used as a parameter indicating the direction of the vehicle 30.
[0032] The vehicle heading angle acquisition device 10 is connected to an external state detection unit 21 for detecting the external state of the vehicle 30 by wire or wireless. The vehicle heading angle acquisition device 10 acquires the external state of the vehicle 30 via the external state detection unit 21. The external state of the vehicle is the movement state of the vehicle detected from the outside of the vehicle 30, that is, the outside of the vehicle. The movement state of the vehicle refers to, for example, the driving state of the vehicle such as the vehicle being stopped, running, accelerating, decelerating, going straight, and turning. The vehicle heading angle acquisition device 10 is connected by wire to an access point 22 for transmitting and receiving signals with the vehicle 30 via wireless communication W / C. Wireless communication is achieved, for example, by a wireless local area network (LAN) complying with the IEEE802.11 standard or by a wireless connection via Bluetooth.
[0033] In the present embodiment, the self-propelled vehicle 30 is a vehicle that can travel by autonomous control or remote control. The vehicle 30 is a vehicle having an internal combustion engine as a power source, a vehicle having a motor, or a hybrid vehicle having an internal combustion engine and a motor. The vehicle having a motor may have at least one of a secondary battery and a fuel cell as a power source. The vehicle 30 is provided with an inner boundary state detection unit 31 for detecting the inner boundary state of the vehicle 30. The vehicle azimuth acquisition device 10 acquires the inner boundary state detected by the inner boundary state detection unit 31 and transmitted by wireless communication via the access point 22. The inner boundary state of the vehicle is the inner boundary of the vehicle 30, that is, the movement state of the vehicle detected inside the vehicle. In the present embodiment, the vehicle may be a vehicle that travels by wheels or a vehicle that travels by tracks, such as a passenger car, a truck, a bus, a two-wheeled vehicle, a four-wheeled vehicle, a chariot, a construction vehicle, etc. In the present embodiment, the vehicle refers to an object that can move, and may also be referred to as a "mobile body", for example, it may also include an electric vertical take-off and landing machine (so-called flying car in the air). When using the term "mobile body", the expressions "vehicle" and "car" in this specification can be replaced by "mobile body", and the expression "travel" can be replaced by "move".
[0034] In this embodiment, the external state detection unit 21 is arranged in a plurality of locations on the path of the vehicle 30 (see Figure 5 ). The external state detection unit 21 is, for example, at least one of a camera and a distance measuring device. Generally, a camera is a photographing device having a photographing element such as a CCD or a photographing element array, and outputs the appearance information or shape information of the object as still image data or dynamic image data by receiving visible light. A laser radar as a distance measuring device generally emits an infrared laser, and receives the reflected light reflected by the object through a light receiving element, thereby measuring the distance to the object. The reflected light reflected by the object is detected as a detection point group corresponding to the object. The external state detection unit 21 outputs still image data or dynamic image data, or detection point group data as a parameter representing the external state. In the present embodiment, as described above, the external state detection unit 21 only needs to be able to detect information for determining the appearance of the vehicle 30 and output it as information representing the external state. As described later, the vehicle azimuth angle acquisition device 10 uses the information for determining the appearance detected by the external state detection unit 21 to determine the driving state of the vehicle 30. In addition, the determination of the driving state of the vehicle 30 performed by the vehicle azimuth angle acquisition device 10 can also be performed by the external state detection unit 21. In this case, the external state detection unit 21 transmits information indicating the determined driving state to the vehicle heading angle acquisition device 10. When a camera or a laser radar is used, the image data and the detection point group data may be fused by fusion processing and used.
[0035] In the present embodiment, the inner boundary state detection unit 31 is used to detect the azimuth angle of the vehicle 30 in the inner boundary of the vehicle. The inner boundary state detection unit 31 uses, for example, a yaw rate sensor. Hereinafter, the inner boundary state detection unit 31 is mainly described using a yaw rate sensor. The yaw rate sensor outputs the yaw rate as the angular velocity around the yaw axis of the vehicle when the vehicle turns, that is, a parameter indicating the inner boundary state. The inner boundary state detection unit 31 is mounted on the vehicle 30 and can directly detect the behavior of the vehicle 30. As long as it is a sensor that can at least detect the turning state, a gyro sensor or a multi-axis acceleration sensor can be used.
[0036] like Figure 2 As shown, the vehicle heading angle acquisition device 10 includes a central processing unit (CPU) 101, a memory 102 as a storage unit, an input / output interface 103 as an acquisition unit, and a clock generator (not shown). The CPU 101, the memory 102, the input / output interface 103, and the clock generator are connected via an internal bus 104 in a manner capable of bidirectional communication. The memory 102 includes a memory such as a ROM that stores a vehicle heading angle acquisition program Pr1 in a nonvolatile and read-only manner, and a memory such as a RAM that can be read and written by the CPU 101. The vehicle heading angle acquisition program Pr1 is executed by the CPU 101 to calculate the external heading angle using the acquired external state, calculate the internal heading angle using the acquired internal state, and determine the vehicle heading angle for the vehicle 30 to move itself using the external heading angle and the internal heading angle. The nonvolatile and readable and writable area of the memory 102 includes a reliability storage area 102a that stores the reliability of the external state detection unit 21. CPU101, i.e., the vehicle azimuth angle acquisition device 10, functions as an azimuth angle acquisition unit and an azimuth angle determination unit by expanding and executing the vehicle azimuth angle acquisition program Pr1 stored in the memory 102 in a readable and writable memory. In addition, CPU101 may be a single CPU, or may be a plurality of CPUs that execute various programs, or may be a multi-tasking type or a multi-threading type CPU that can execute a plurality of programs simultaneously. In addition, the vehicle azimuth angle acquisition device 10 can function as a remote control device that remotely controls the vehicle 30 by having a remote control program.
[0037] The camera 21 and the access point 22 as the external state detection unit are connected to the input / output interface 103 via signal lines. A shooting control signal instructing shooting processing for object detection is sent from the input / output interface 103 to the camera 21, and a shooting signal indicating a shot image as a detection result is sent from the camera 21 to the input / output interface 103. When the vehicle heading angle acquisition device 10 also functions as a remote control device, a driving control signal for driving the vehicle 30 by itself is sent from the input / output interface 103 to the access point 22. The driving control signal is, for example, a control signal sent to the driving control device 300 provided in the vehicle 30, and is a control signal for indicating a required accelerator opening or a required torque value, a required braking amount, and a required steering angle. The driving control device 300 controls each actuator according to the driving control signal, thereby realizing driving control including acceleration / deceleration and cruising in the vehicle 30, stopping control of the vehicle 30, and turning control including left and right turns. Vehicle information indicating the state of the vehicle is sent from the access point 22 to the input / output interface 103. The vehicle information includes, for example, driving information indicating the driving state detected in the vehicle 30, such as yaw rate, steering angle, speed, acceleration and deceleration, and information such as whether the wipers are working and whether the headlights are on. In addition, environmental information indicating environmental conditions outside the vehicle, such as weather, temperature, and brightness, may be input to the input / output interface 103. The environmental information may be obtained by various detection devices arranged on the path of the vehicle, or may be obtained through a network as information on an area including the path of the vehicle.
[0038] like Figure 3 As shown, the vehicle 30 includes a central processing unit (CPU) 301, a memory 302 as a storage unit, an input / output interface 303, and a driving control device 300 including a clock generator (not shown). The CPU 301, the memory 302, the input / output interface 303, and the clock generator are connected via an internal bus 304 in a manner capable of bidirectional communication. The memory 302 includes a non-volatile memory, such as a ROM, which stores a remote control corresponding program Pr2 in a read-only manner, and a memory, such as a RAM, which can be read and written by the CPU 301. The remote control corresponding program Pr2 controls the driving state of the vehicle 30 according to the driving control signal received from the remote control device.
[0039] The yaw rate sensor 31, the wireless transceiver 32, and the vehicle driving control actuator 33 are connected to the input / output interface 303 via signal lines, respectively. The yaw rate as a detection result is sent from the yaw rate sensor 31 to the input / output interface 303. The driving information and vehicle information including the yaw rate received from the yaw rate sensor 31 are sent from the input / output interface 303 to the wireless transceiver 32. The driving control signal is sent from the wireless transceiver 32 to the input / output interface 303. The driving control signal for indicating the required accelerator opening or the required torque value, the required braking amount, and the required steering angle is sent from the input / output interface 303 to the vehicle driving control actuator 33. The driving control device 300 includes a fuel injection device in the internal combustion engine corresponding to the required accelerator opening, a motor control device in the motor corresponding to the required torque value, a brake pad actuator in the braking device corresponding to the required braking amount, and a steering actuator for controlling the steering angle of the steering wheel in the steering device corresponding to the required steering angle. The brake actuator adjusts the amount of operation of the brake pad, i.e., the amount of braking / braking force, by controlling the hydraulic pressure through a motor. The steering actuator adjusts the steering angle of the steering wheel by controlling the pinion that engages with the rack connected to the steering wheel through a motor. In addition, the wireless transceiver 32 can also be a detachable type. The detachable wireless transceiver 32 only needs to have a structure that can send a driving control signal to the vehicle driving control actuator 33 via the input / output interface 303 of the vehicle 30 when installed in the external communication connection port of the vehicle 30. That is, when the wireless transceiver 32 is removed, the vehicle 30 is not remotely controlled and becomes a normal vehicle that is driven by a person or an unmanned person in the vehicle 30. Furthermore, instead of the memory 302, the wireless transceiver 32 may have a remote control corresponding program Pr2.
[0040] Reference Figure 4 and Figure 5 , a vehicle heading angle acquisition process performed by the vehicle heading angle acquisition device 10 of the present embodiment will be described. Figure 4 The processing routine shown is repeatedly executed at predetermined time intervals, for example, several milliseconds to several seconds. The CPU 101 executes the vehicle heading angle acquisition program Pr1 to acquire the vehicle heading angle as a heading angle calculation unit and a heading angle determination unit. Figure 5 It shows the positional relationship between the vehicle 30 and the external state detection unit 21 and shows, as the transition of the vehicle's running state, the transition of the vehicle 30 from a stationary state to a straight state Po1 including a start state, the vehicle 30 in a turning state Po2, and the vehicle 30 in a straight state Po3.
[0041] The CPU 101 obtains shooting information from the external state detection unit 21, i.e., the camera 21, via the input / output interface 103 (step S100). The shooting information obtained from the camera 21 is preferably a dynamic image consisting of a plurality of frame images captured at a frame rate in the range of 30fps to 60fps, for example. Alternatively, it may be a still image captured in units of 1s. In the case where the displacement of the vehicle 30, such as the moving speed or the turning speed, is low, it may also be a still image. The CPU 101 uses the shooting information to calculate the external azimuth and the reliability of the external state detection unit 21 (step S102). Specifically, the CPU 101 uses a plurality of frame images to calculate a motion vector associated with a predetermined feature point (focus point) of the vehicle 30, and calculates the azimuth represented by the calculated motion vector as the external azimuth. The predetermined feature of the vehicle 30 may be, for example, a plurality of feature point groups defining an area representing the vehicle 30 or a centroid point of an area extracted as an area representing the vehicle 30, or may be a portion of the vehicle 30 where the brightness value changes greatly, such as the edge of the rear side of the vehicle. The image processing technology for calculating / extracting the motion vector using a plurality of frame images is a known technology, and thus the description thereof is omitted. When calculating the external azimuth, the rectangular area representing the vehicle 30 may be extracted from each frame image by pattern matching, and the azimuth of the main direction, i.e., the long side direction of the extracted rectangular area, may be determined, and the determined main direction azimuth may be obtained as the external azimuth. In addition, when calculating the external azimuth, the position coordinates of the vehicle 30 may also be determined.
[0042] The reliability of the external state detection unit 21, that is, the external azimuth angle, can be calculated, for example, in the following manner.
[0043] ·For a part or all of the frame images obtained from the camera 21, a pattern matching process is performed using AI to score the similarity (matching degree) between the model of the vehicle 30 and the vehicle contained in the frame image. When the obtained similarity is high, the reliability is high, and when the obtained similarity is low, the reliability is low. The pattern matching process using AI is performed, for example, using a machine learning model that extracts vehicles from images through pattern matching with or without a teacher, or that performs learning through reinforcement learning. As a machine learning model, for example, a neural network or a support vector machine (SVM) can be used. Deep learning can also be used when learning the reinforcement learning model.
[0044] Image processing is performed on a part or all of the frame images obtained from the camera 21 to calculate image quality parameters such as brightness and clarity. For example, brightness can be calculated as an average pixel value obtained by finding a pixel value (brightness value) for each pixel forming the frame image and dividing it by the total number of pixels. When the brightness is high (bright), the reliability is high, and when the brightness is low (dark), the reliability is low. This is because when the brightness is high, the range of pixel values becomes wider, so the brightness difference in the outline representing the vehicle body becomes larger, and the vehicle body can be distinguished / extracted with high accuracy. In addition, clarity can be calculated, for example, as the ratio of high-frequency components in the spectrum distribution obtained by performing fast Fourier transform on the frame image. It can also be set that the reliability is high when the clarity is high, and the reliability is low when the clarity is low. This is because when the clarity is high, the outline representing the vehicle body in the frame image is clear, and the vehicle body can be distinguished / extracted with high accuracy. When the above image quality parameters are used, as the value indicating the reliability, a value obtained by normalizing the value of the image quality parameter with the range width that the image quality parameter can adopt can be used.
[0045] As the external environmental conditions of the vehicle 30, for example, time and weather can be used. The time can be used as an index of the brightness of the external environment. The reliability is set high for the time between morning and evening when sufficient brightness is expected, and low for other times. In addition to being used as an index indicating the brightness of the external environment, the weather obtained from the meteorological information can also be used as an index of the clarity of the frame image affected by yellow sand and fog. When yellow sand and fog are predicted based on the meteorological information, the reliability is set low.
[0046] As external environmental conditions of the vehicle 30, for example, Figure 5 As shown, the positional relationship between the external state detection unit 21 and the vehicle 30 can be used. When the vehicle 30 is close to the installation position of the external state detection unit 21, it is expected that the vehicle 30 is photographed at an appropriate field angle, and more pixels in the frame image represent the vehicle area, so the vehicle 30 can be represented at a higher resolution. The closer the vehicle 30 is to the installation position of the external state detection unit 21, the higher the reliability is set. The distance between the vehicle 30 and the external state detection unit 21 or the standardized distance is obtained as a value representing the reliability. As a result, the vehicle body can be discriminated / extracted from the frame image with high accuracy. The installation position of the external state detection unit 21 is known, and the position information of the vehicle 30 relative to the external state detection unit 21 is obtained as the distance of the vehicle 30 relative to the external state detection unit 21 measured using a laser radar or a radar. Alternatively, the position coordinates of the vehicle 30 located by a GNSS (Global Positioning System) provided on the vehicle 30 and the position coordinates of the external state detection unit 21 are used to obtain the positional relationship between the external state detection unit 21 and the vehicle 30.
[0047] The above various reliabilities may be used only one, or may be used in combination in any manner. When combined, the reliabilities in each manner may be simply added together, or may be added together using a predetermined weight / coefficient, or may be normalized by setting the maximum value to 1 and the minimum value to 0. In addition, the calculated reliability may be stored in the reliability storage area 102a in the memory 102 so that it can be repeatedly used for multiple vehicles 30.
[0048] CPU 101 obtains the yaw rate from yaw rate sensor 31 (step S104). CPU 101 uses the obtained yaw rate to calculate the inner bound azimuth (step S106). As is well known, the calculation of the azimuth of the vehicle using the yaw rate is performed by integrating the yaw rate obtained before this time. CPU 101 determines whether the vehicle 30 is in a stopped state (steps S108, Figure 5 Po1 in). Specifically, the vehicle speed included in the driving information sent and received from the vehicle 30 is used. When the CPU 101 determines that the vehicle 30 is in a stopped state, that is, when the vehicle speed is determined to be 0 km / h (step S108: yes), the priority / priority of the external azimuth angle is set higher, the vehicle azimuth angle of the vehicle 30 is calculated (step S110), and the present processing routine is terminated. The vehicle azimuth angle is an azimuth angle used for self-control of the vehicle 30, for example, it is calculated by weighted averaging in the manner of vehicle azimuth angle = (wi×inner boundary azimuth angle + wo×outer boundary azimuth angle) / 2. As a method of setting the priority of the external azimuth angle higher, in addition to the method of using only the external boundary azimuth angle (wi=0, Wo=1: total weight=1), it is also possible to set the weighting of the internal boundary azimuth angle to 0<wi<0.2, and set the weighting of the external boundary azimuth angle to wo=1-wi. Usually, the inner bearing angle is calculated by integral operation, so the previous value / initial value is required. On the other hand, for example, when the vehicle 30 stops after traveling straight, the last inner bearing angle obtained just before the vehicle 30 stops can be used.
[0049] When the CPU 101 determines that the vehicle 30 is not in a stopped state, that is, when the vehicle speed is determined to be ≠ 0 km / h (step S108: No), it determines whether the vehicle 30 is in a turning state (steps S112, Figure 5Po2 in). Whether the vehicle 30 is in a turning state is determined by, for example, using the steering angle included in the driving information sent and received from the vehicle 30. In the present embodiment, the operating angle of the steering wheel based on the steering wheel operation of the vehicle 30 is set as the steering angle, and the actual turning angle of the steering wheel is set as the steering angle. In the case where the vehicle 30 does not have a sensor for detecting the steering angle, the steering angle detected and sent in the vehicle 30 may also be used. When the acquired steering angle or steering angle is the determined steering angle or is greater than the determined steering angle within a predetermined time, the CPU 101 determines that the vehicle 30 is in a turning state. In order to exclude temporary steering operations not accompanied by turning, the predetermined time is, for example, 2 seconds to 5 seconds. In order to exclude steering angle adjustments for maintaining straight driving, the determined steering angle or the determined steering angle is, for example, 2 degrees to 5 degrees. In addition, whether the vehicle 30 is in a turning state can also be determined by using the output of the yaw rate sensor 31 to determine whether the rotational torque centered on the yaw axis of the vehicle 30 generates a predetermined determination value or more within a predetermined time.
[0050] When CPU101 determines whether the vehicle 30 is in a turning state (step S112: yes), it sets the priority of the inner boundary azimuth angle to be higher, calculates the vehicle azimuth angle of the vehicle 30 (step S114), and ends the processing routine. As a method of setting the priority of the inner boundary azimuth angle to be higher, in addition to using only the inner boundary azimuth angle (wi=1, Wo=0: total weight=1), it is also possible to set the weighting of the outer boundary azimuth angle to 0<wo<0.2, and set the weighting of the inner boundary azimuth angle to wi=1-wo. In the present embodiment, the moving vector is used in the calculation of the outer boundary azimuth angle. As Figure 6 As shown, the moving vector Oaz represents the movement of the characteristic point of the vehicle 30, and is a physical quantity different from the azimuth angle Iaz of the vehicle 30. In particular, when the vehicle 30 is in a turning state, the moving vector Oaz tends to deviate from the azimuth angle Iaz. In addition, generally speaking, the S / N ratio of the signal representing the moving vector Oaz is low. In order to improve the S / N ratio, a smoothing filter such as a low-pass filter is applied. In a turning state where the displacement of the azimuth angle is large, it is possible to more significantly deviate from the true value due to phase delay. On the other hand, the moving vector Oaz is useful as a parameter for estimating whether the vehicle 30 is in a straight state or a turning state. In addition, the calculated inner boundary azimuth angle has the characteristic of generating an integral error accompanied by the accumulation of sensor tolerance. Therefore, by considering the external azimuth angle, the vehicle azimuth angle with reduced integral error can be obtained. In addition, when the external azimuth angle of the vehicle 30 is determined by pattern matching processing for each frame image, the external azimuth angle becomes the same physical quantity as the inner boundary azimuth angle, so by considering the external azimuth angle, the vehicle azimuth angle with further improved accuracy can be obtained.
[0051] When the CPU 101 determines that the vehicle 30 is not in the turning state (step S112: No: Figure 5 Po1, Po3 in the figure), determine whether the reliability of the external azimuth is above a predetermined threshold (step S116). As described above, the reliability can take various forms of values. As a predetermined threshold, in the next step S118, a threshold of the external azimuth that can be determined to be suitable for the correction of the internal boundary azimuth is used. For example, regardless of the reliability of the form, a threshold that obtains a reliability of more than 70%, preferably more than 80%, and more preferably more than 90% can be used.
[0052] When the CPU 101 determines that the reliability of the external azimuth angle is above a predetermined threshold value (step S116: yes), the CPU 101 uses the external azimuth angle to correct the internal azimuth angle and calculate the vehicle azimuth angle (step S118), and ends the processing routine. That is, when the driving state of the vehicle 30 is in a straight-moving state where the external azimuth angle can represent the vehicle azimuth angle and the reliability of the external azimuth angle is above a predetermined threshold value, the internal azimuth angle is corrected. The correction of the internal azimuth angle using the external azimuth angle is performed at a timing when the distance between the vehicle 30 and the external state detection unit 21 is close, that is, at a timing when the external state detection unit 21 that detects the vehicle 30 is switched. This is because, at this timing, as described above, the reliability of the external azimuth angle is high. As examples of correction methods, there is a method of replacing the internal azimuth angle with the external azimuth angle at a single timing, and a method of gradually replacing the calculated value of the external azimuth angle by applying a moving average filter process to multiple samplings of the external azimuth angle, such as 10 times. In addition, by increasing the number of calculation values of the moving average filter, a smoother correction can be achieved, but an appropriate smooth correction can be achieved by sampling about 10 to 20 times. Furthermore, as a specific method of replacement, the inner boundary azimuth angle can also be replaced by a weighted average of the inner boundary azimuth angle and the outer boundary azimuth angle. As a weighted value, for example, a value obtained by subtracting a weighted value relative to the outer boundary azimuth angle from 70 to 100% relative to the outer boundary azimuth angle and 100% relative to the inner boundary azimuth angle can be used.
[0053] When the CPU 101 determines that the reliability of the external azimuth is not equal to or greater than the predetermined threshold value (step S116: No), the CPU 101 does not correct the internal azimuth using the external azimuth, but moves to step S114 and ends the processing routine. This is because, when the reliability of the external azimuth is low, the correction of the internal azimuth using the external azimuth may result in an erroneous correction of the internal azimuth.
[0054] According to the vehicle heading angle acquisition device 10 of the first embodiment described above, the outside heading angle is calculated using the outside state, which is the motion state of the vehicle 30 detected from the outside, and the inside heading angle is calculated using the inside state, which is the motion state of the vehicle 30 detected from the inside, and the vehicle heading angle for self-driving of the vehicle 30 is determined using the calculated outside heading angle and the inside heading angle. The accuracy of obtaining the heading angle of the self-propelled vehicle can be improved.
[0055] Usually, the azimuth angle obtained by performing image processing on the frame image, that is, the external azimuth angle, can be directly obtained as an absolute value. On the other hand, the S / N ratio of the signal representing the azimuth angle and the moving vector Oaz is low, and a smoothing process is performed by applying a low-pass filter or the like to the signal. Therefore, in a straight-ahead state in which the displacement of the azimuth angle of the vehicle 30 is small, the error associated with the phase delay accompanying the signal processing is small, and it can be used as the vehicle azimuth angle. On the other hand, in a turning state in which the displacement of the azimuth angle of the vehicle 30 is large, the error between the external azimuth angle and the vehicle azimuth angle at the current position of the vehicle 30 becomes large due to the phase delay, and the vehicle azimuth angle of the vehicle 30 cannot be represented with high accuracy. In addition, when the moving vector Oaz is used as the external azimuth angle, it is different from the vehicle azimuth angle as a physical quantity.
[0056] In contrast, the azimuth angle obtained by the yaw rate sensor 31 mounted on the vehicle 30, that is, the inner boundary azimuth angle, has a high S / N ratio. On the other hand, when the inner boundary state detection unit 31 such as the yaw rate sensor is used, the azimuth angle is calculated by accumulating the detection values, so the tolerance is also accumulated and deviates from the true value.
[0057] The vehicle heading angle acquisition device 10 of the first embodiment calculates the vehicle heading angle based on the characteristics of the external heading angle and the internal heading angle, so that the deviation from the true value can be reduced compared with the case where only the external heading angle and the internal heading angle are used, or only the combination of the external heading angle and the internal heading angle is used, and the vehicle heading angle can be acquired with a good S / N ratio. That is, when the vehicle 30 is in a stopped state, the priority of the external heading angle is higher than the priority of the internal heading angle to acquire the vehicle heading angle. When the vehicle 30 is in a turning state, or when the vehicle 30 is in a straight state and the reliability of the external heading angle is low, the priority of the internal heading angle is higher than the priority of the external heading angle to acquire the vehicle heading angle, and when the vehicle 30 is in a straight state and the reliability of the external heading angle is high, in order to correct the cumulative error of the internal heading angle, a correction using the external heading angle is performed. In addition, when the external heading angle and the internal heading angle are combined, AI, that is, a learning model, can also be used. By using the learning model and continuing the learning of the learning model, it is possible to achieve a more appropriate combination priority of the outside azimuth angle and the inside azimuth angle corresponding to each driving state of the vehicle.
[0058] According to the vehicle heading angle acquisition device 10 of the first embodiment, the vehicle heading angle can be acquired with high accuracy, so the position of the vehicle in the autonomous control of the vehicle 30 using the vehicle heading angle can be controlled with high accuracy. As a result, the accuracy of the stop position of the vehicle 30 at the final destination of the vehicle 30 can be improved.
[0059] The various advantages described above can also be obtained in the vehicle heading angle acquisition system 100 and the vehicle heading angle acquisition method of the present embodiment.
[0060] Other embodiments:
[0061] (1) The vehicle heading angle acquisition device 10 of the first embodiment changes the priority of the inner boundary heading angle and the outer boundary heading angle when calculating the vehicle heading angle according to the driving state of the vehicle. In contrast, the vehicle heading angle acquisition device 10 may also change the priority of the inner boundary heading angle and the outer boundary heading angle according to the state of the external state detection unit 21 disposed on the path Rt on which the vehicle 30 is traveling. For example, Figure 5 In the figure, the configuration density / configuration frequency of the external state detection unit 21 around the vehicle in the straight state Po3 is higher than that of the external state detection unit 21 around the vehicle in the straight state P0. In this case, since the external azimuth with high reliability can be used, the priority of the external azimuth can also be set higher than the priority of the internal azimuth. In particular, when the vehicle 30 is in the straight state, the movement vector Oaz and the azimuth of the vehicle can be treated as substantially the same physical quantity, and the reliability is high. By using the external azimuth as an absolute value, the vehicle azimuth with good accuracy can be obtained without using the internal azimuth.
[0062] (2) In the first embodiment, the vehicle heading angle acquisition device 10 is described as a server computer having a function of acquiring a vehicle heading angle. The server computer can also function as a remote control device for remotely controlling the vehicle 30 by having a remote control program for making the vehicle 30 autonomous. Figure 7To explain. In order to realize remote control, the server computer obtains the vehicle position information (step S1). Specifically, the server computer obtains the vehicle information indicating the driving state from the vehicle 30, calculates the inner boundary azimuth, obtains the external information from the external state detection unit 21, and calculates the external boundary azimuth. The server computer obtains the vehicle azimuth obtained using the position coordinates, the inner boundary azimuth and the external boundary azimuth as the vehicle position information. The position coordinates are obtained, for example, by detecting the shape of the vehicle 30 from the captured image, calculating the coordinates of the positioning points of the vehicle 30 in the coordinate system of the captured image, that is, the local coordinate system, and converting the calculated coordinates into coordinates in the global coordinate system. The shape of the vehicle 30 contained in the captured image can be detected, for example, by inputting the captured image into a detection model that makes use of artificial intelligence. The detection model is prepared, for example, inside or outside the system and pre-stored in the memory of the server computer. As a detection model, for example, a machine learning model that has been learned in a manner that realizes either semantic segmentation or instance segmentation can be cited. As the machine learning model, for example, a convolutional neural network (hereinafter referred to as CNN) learned by supervised learning using a learning data set can be used. The learning data set includes, for example, a plurality of training images including the vehicle 30 and a label indicating whether each region in the training image is a region representing the vehicle 30 or a region other than the vehicle 30. When learning the CNN, it is preferred to update the parameters of the CNN by back propagation (error back propagation method) to reduce the error between the output result of the detection model and the label. The server computer can obtain the direction of the vehicle 30 by, for example, inferring the direction of the moving vector of the vehicle 30 calculated based on the position change of the feature point of the vehicle 30 between the frames of the captured image using the optical flow method. The server computer determines the target position to which the vehicle 30 should travel (step S3). The target position is represented by, for example, the coordinates of X, Y, and Z in the global coordinate system. The path that the vehicle 30 should travel, i.e., the reference path, is pre-stored in the memory of the server computer. The path is represented by a node representing the departure point, a node representing the passing point, a node representing the destination, and a link connecting each node. The server computer uses the vehicle position information and the reference path to determine the target position that the vehicle 30 should go to next. The server computer determines the target position on the reference path before the current position of the vehicle 30. The server computer generates a driving control signal for controlling the vehicle 30 by using the vehicle position information and the vehicle information (step S4). The driving control signal includes, for example, the acceleration and the steering angle of the vehicle 30 as parameters. The server computer calculates the driving speed of the vehicle 30 based on the change in the position of the vehicle 30, and compares the calculated driving speed with the target speed. The server computer as a whole determines the acceleration in such a way that the vehicle 30 accelerates when the driving speed is lower than the target speed, and determines the acceleration in such a way that the vehicle 30 decelerates when the driving speed is higher than the target speed.In addition, when the vehicle 30 is on the reference path, the server computer determines the steering angle and acceleration so that the vehicle 30 does not deviate from the reference path, and when the vehicle 30 is not on the reference path, in other words, when the vehicle 30 deviates from the reference path, the server computer determines the steering angle and acceleration so that the vehicle 30 returns to the reference path. In other embodiments, the driving control signal may include the speed of the vehicle 30 as a parameter instead of the acceleration of the vehicle 30 or in addition thereto. The server computer sends the generated driving control signal to the vehicle 30 (step S4). The server computer repeatedly acquires the vehicle position information, determines the target position, generates the driving control signal, and sends the driving control signal in a predetermined cycle. The vehicle 30 receives the driving control signal (step S5), and adjusts the output of the driving source, adjusts the braking amount of the braking device to achieve acceleration, and adjusts the steering angle of the steering device to achieve self-driving of the vehicle 30 according to the driving control signal (step S6). The vehicle 30 repeatedly receives the driving control signal and controls actuators such as the driving source, the braking device, and the steering device of the vehicle 30 in a predetermined cycle. According to the system in this embodiment, the vehicle 30 can be driven by remote control, and the vehicle 30 can be moved without using a transporting device such as a crane or a conveyor. The capture of the vehicle 30 during remote control can be performed, for example, by capturing a predetermined endpoint in a frame image obtained by the external state detection unit 21 as a focus point. Therefore, the vehicle 30 is captured at a timing when the external azimuth and position coordinates of the vehicle 30 as a target are obtained by the vehicle azimuth acquisition device 10. That is, the acquisition of the vehicle azimuth in the first embodiment can be performed as a part of the processing routine for remote control of the vehicle 30. By using the vehicle azimuth acquired by the vehicle azimuth acquisition device 10 of the first embodiment, the accuracy of remote control of the vehicle 30 is improved. The accuracy of remote control includes the position offset relative to the path from the departure point to the target point and the offset relative to the arrival position at the target point.
[0063] (3) In the first embodiment, the control method of the self-propelled vehicle 30 using the vehicle azimuth angle obtained by the vehicle azimuth angle acquisition device 10 is not described. As a method of applying the vehicle azimuth angle acquisition device 10 of the first embodiment, there is a self-transportation method in which the vehicle 30 is transported by the vehicle 30 by itself without using a separate transport device in a factory that manufactures the vehicle 30, and a self-driving method based on unmanned driving in a site where the completed vehicle is placed. More specifically, in the factory, there are forms such as the movement of the vehicle 30 without the belt conveyor or the separate conveyor between each manufacturing process, the movement of the vehicle to the site after the vehicle is completed, and the movement of the vehicle between the site and the vehicle transport ship / train. In each of these movements, the vehicle 30 travels by self-control. By improving the accuracy of obtaining the vehicle azimuth angle when the vehicle 30 is self-propelled, the stopping position of the vehicle 30 at the final purpose can be achieved with the desired accuracy.
[0064] (4) In the first embodiment, the vehicle 30 only needs to have a structure that can be moved by remote control, for example, it can also be a platform having the structure described below. Specifically, in order to perform the three functions of "driving", "turning" and "stopping" by remote control, the vehicle 30 only needs to have a vehicle control device, a drive device, a steering device, a brake device and a wireless transceiver 32. That is, the vehicle 30 that can be moved by remote control may not be equipped with at least a part of the interior parts such as the driver's seat and the instrument panel, may not be equipped with at least a part of the exterior parts such as the bumper and the fender, and may not be equipped with a body shell. In this case, the remaining parts such as the body shell may be installed on the vehicle 30 before the vehicle 30 is shipped from the factory, or the remaining parts such as the body shell may be installed on the vehicle 30 after the vehicle 30 is shipped from the factory in a state where the remaining parts such as the body shell are not installed on the vehicle 30. In addition, for the form of the platform, the position determination of capturing a predetermined end point as a focus point can be performed in the same way as the vehicle 30.
[0065] (5) In the first embodiment, the vehicle heading angle acquisition device 10 that uses the external heading angle and the internal heading angle to determine the vehicle heading angle used in the self-driving of the vehicle 30 is implemented by the CPU 101 executing the vehicle heading angle acquisition program Pr1, but it can also be implemented in hardware by a pre-programmed integrated circuit or discrete circuit. That is, the control unit and the method thereof in each of the above-mentioned embodiments can also be implemented by a dedicated computer, which is provided by a processor and a memory that are programmed to execute one or more functions embodied by a computer program. Alternatively, the control unit and the method thereof described in the present disclosure can also be implemented by a dedicated computer provided by a processor composed of one or more dedicated hardware logic circuits. Alternatively, the control unit and the method thereof described in the present disclosure can also be implemented by one or more dedicated computers, which are composed of a combination of a processor and a memory that are programmed to execute one or more functions and a processor composed of one or more hardware logic circuits. In addition, the computer program can also be stored as an instruction executed by a computer in a non-transient tangible recording medium that can be read by a computer.
[0066] (6) The vehicle 30 in each of the above-mentioned embodiments is a vehicle that can be driven unmanned. "Unmanned driving" refers to driving that does not rely on the driving operation of the passengers. Driving operation refers to operations related to at least one of "driving", "turning" and "stopping" of the vehicle 30. Unmanned driving is achieved by automatic or manual remote control using a device located outside the vehicle 30, or autonomous control of the vehicle 30. In the vehicle 30 that is driven unmanned, there may also be passengers who do not perform driving operations. Passengers who do not perform driving operations include, for example, people who only sit in the seats of the vehicle 30, and people who perform operations different from driving operations such as assembly, inspection, and switch operations while riding in the vehicle 30. In addition, driving based on the driving operations of the passengers is sometimes referred to as "manned driving".
[0067] (7) The term "remote control" in this specification includes "full remote control" in which all actions of the vehicle 30 are completely determined outside the vehicle 30, and "partial remote control" in which part of the actions of the vehicle 30 are determined outside the vehicle 30. The term "autonomous control" in this specification includes "partial autonomous control" in which the vehicle 30 uses information received from a device outside the vehicle 30 to autonomously control its own actions. In other embodiments (2) and (3), the vehicle heading angle is obtained by the vehicle heading angle obtaining device 10 as a server computer, and the processing from obtaining the vehicle position information including the vehicle heading angle to generating the driving control signal is performed. In contrast, at least a part of the processing from obtaining the vehicle position information to generating the driving control signal may be performed by the vehicle 30. For example, the following methods (7a) and (7b) may also be used. In the following, the vehicle heading angle obtaining device 10 is described as a server.
[0068] (7a) The server may also obtain vehicle position information, determine the target position to which the vehicle 30 should go next, and generate a path from the current position of the vehicle 30 indicated by the obtained vehicle position information to the target position. The server may generate a path to the target position between the current position and the destination, or may generate a path to the destination. The server may send the generated route to the vehicle 30. The vehicle 30 may also generate a travel control signal in such a way that the vehicle 30 travels on the path received from the server, and use the generated travel control signal to control the actuator of the vehicle 30.
[0069] (7b) The server may also obtain the vehicle position information and send the obtained vehicle position information to the vehicle 30. Figure 8 As shown, the vehicle 30 can also obtain vehicle position information (step S801), determine the target position to which the vehicle 30 should go next (step S802), generate a path from the current position of the vehicle 30 represented by the received vehicle position information to the target position, generate a travel control signal in such a way that the vehicle 30 travels on the generated path (step S903), and use the generated travel control signal to control the actuator of the vehicle 30 (step S804).
[0070] (8) In each of the above embodiments, the vehicle 30 only needs to have a structure that can be moved by unmanned driving, for example, it can also be a platform having the structure described below. Specifically, in order to perform the three functions of "driving", "turning" and "stopping" by unmanned driving, the vehicle 30 at least has a control device that controls the driving of the vehicle 30 and an actuator that realizes the driving of the vehicle 30. In the case where the vehicle 30 obtains information from the outside for unmanned driving, the vehicle 30 can also have a communication device. That is, the vehicle 30 that can be moved by unmanned driving may not be equipped with at least a part of the interior parts such as the driver's seat and the instrument panel, may not be equipped with at least a part of the exterior parts such as the bumper and the fender, and may not be equipped with a body shell. In this case, the remaining parts such as the body shell may be installed on the vehicle 30 before the vehicle 30 is shipped from the factory, or the remaining parts such as the body shell may be installed on the vehicle 30 after the vehicle 30 is shipped from the factory in a state where the remaining parts such as the body shell are not installed on the vehicle 30. Each component can be installed from any direction such as the upper side, lower side, front side, rear side, right side or left side of the vehicle 30, and can be installed from the same direction or from different directions. In addition, the position of the platform can also be determined in the same way as the vehicle 30 in the first embodiment.
[0071] (9) The vehicle 100 may also be manufactured by combining a plurality of modules. A module refers to a unit composed of a plurality of components assembled according to the location and function of the vehicle 30. For example, the platform of the vehicle 30 may be manufactured by combining a front module constituting the front portion of the platform, a central module constituting the central portion of the platform, and a rear module constituting the rear portion of the platform. In addition, the number of modules constituting the platform is not limited to three, and may be two or less or four or more. In addition, in addition to or in lieu of the components constituting the platform, components constituting portions of the vehicle 30 that are different from the platform may also be modularized. In addition, the various modules may also include any exterior components such as a bumper or grille, and any interior components such as a seat or console. In addition, not limited to the vehicle 30, any type of mobile body may be manufactured by combining a plurality of modules. Such a module may be manufactured, for example, by joining a plurality of components by welding, fixings, etc., or by integrally molding at least a portion of the components constituting the module into one component by casting. The molding method of integrally molding a component, especially a relatively large component, is also called integrated die casting (ギガキャスト) or giant casting (メガキャスト). For example, the front module, the center module, and the rear module mentioned above can also be manufactured using gear casting.
[0072] (10) Transporting the vehicle 30 by driving the unmanned vehicle 30 is also referred to as "autonomous transport". In addition, a structure for realizing autonomous transport is also referred to as a "vehicle remote control autonomous driving transport system". In addition, a production method for producing the vehicle 100 by autonomous transport is also referred to as "autonomous production". In autonomous production, for example, in a factory that manufactures the vehicle 100, at least a part of the transport of the vehicle 100 is realized by autonomous transport.
[0073] The present disclosure has been described above based on the embodiments and variations, but the embodiments of the invention described above are for easy understanding of the present disclosure and do not limit the present disclosure. The present disclosure can be changed and improved without departing from its main purpose and claims, and its equivalents are included in the present disclosure. For example, the technical features in the embodiments and variations corresponding to the technical features in each method recorded in the content of the invention column can be appropriately replaced or combined in order to solve part or all of the above-mentioned problems, or in order to achieve part or all of the above-mentioned effects. In addition, if its technical features are not described as essential features in this specification, they can be appropriately deleted.
Claims
1. An azimuth acquisition device, which is an azimuth acquisition device for a self-propelled vehicle, comprising: an acquisition unit, which acquires an external state and an internal state, wherein the external state is a motion state of the vehicle detected from the external world, and the internal state is a motion state of the vehicle detected from the internal world; an azimuth angle calculation unit, which uses the acquired external state to calculate an external azimuth angle, and uses the acquired internal state to calculate an internal azimuth angle; and The azimuth angle determination unit determines a vehicle azimuth angle for self-driving of the vehicle using the calculated external azimuth angle and the internal azimuth angle.
2. The azimuth acquisition device according to claim 1, wherein: The azimuth angle determination unit is configured to determine the vehicle azimuth angle by changing the priority of the external azimuth angle and the internal azimuth angle according to the state of the vehicle and the state of an external state detection unit that detects the external state.
3. The azimuth acquisition device according to claim 2, wherein: The azimuth angle determination unit is configured to determine the vehicle azimuth angle by giving higher priority to the external azimuth angle when the vehicle is in a stopped state.
4. The azimuth acquisition device according to claim 2, wherein: The heading angle determination unit is configured to determine the vehicle heading angle by giving higher priority to the inner boundary heading angle when the vehicle is in a turning state.
5. The azimuth acquisition device according to claim 2, wherein: The azimuth angle determination unit is configured to use the external azimuth angle to correct the inner boundary azimuth angle when the vehicle's motion state is in a straight-ahead state and the reliability of the external state detection unit is above a predetermined threshold value, and to increase the priority of the inner boundary azimuth angle to determine the vehicle azimuth angle when the reliability of the external state detection unit is less than a predetermined threshold value.
6. The azimuth acquisition device according to claim 2, wherein: The external state detection unit is a photographing device disposed outside the vehicle. The azimuth angle calculation unit calculates an external azimuth angle of the vehicle using the image captured by the imaging device.
7. The azimuth acquisition device according to claim 2, wherein: The inner boundary state detection unit for detecting the inner boundary state is a yaw rate sensor provided in the vehicle. The azimuth angle calculation unit calculates an inner boundary azimuth angle of the vehicle using the yaw rate acquired by the yaw rate sensor.
8. An azimuth acquisition system, which is an azimuth acquisition system for a self-propelled vehicle, comprising: An external state detection unit is arranged outside the vehicle in order to detect the motion state of the vehicle from the outside; an inner boundary state detection unit mounted on the vehicle for detecting a motion state of the vehicle from an inner boundary; and Azimuth acquisition device, The azimuth angle obtaining device comprises: an azimuth angle calculation unit, which calculates an external azimuth angle using an external state, and calculates an internal azimuth angle using an internal state, wherein the external state is a motion state of the vehicle detected by the external state detection unit, and the internal state is a motion state of the vehicle detected by the internal state detection unit; and The azimuth angle determination unit determines a vehicle azimuth angle for self-driving of the vehicle using the calculated external azimuth angle and the internal azimuth angle.
9. A method for obtaining an azimuth angle of a self-propelled vehicle, comprising the following steps: Obtaining an external state and an internal state, wherein the external state is a motion state of the vehicle detected from the external world, and the internal state is a motion state of the vehicle detected from the internal world; Using the obtained external state to calculate the external azimuth, using the obtained internal state to calculate the internal azimuth; and The calculated exterior bearing angle and interior bearing angle are used to determine a vehicle bearing angle for self-driving of the vehicle.
Citation Information
Patent Citations
Aqueous suspension containing layered silicate
JP2023083792A
