Location estimation device and traffic control system

Abstract

To highly accurately estimate information relating to a present position and an attitude of an own vehicle for performing desired operation control of the vehicle even without loading a satellite positioning sensor on the vehicle.SOLUTION: A position estimation device comprises: an information reception unit for receiving first mobile information including at least a position, an angle and a speed of a mobile and environmental information including road information around the mobile; a recognition unit for creating integrated environmental information by integrating the first mobile information and the environmental information; and an information transmission unit for transmitting to the mobile the integrated environmental information including positional information of the mobile.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present application relates to a position estimation device and a traffic control system. [Background technology]

[0002] In recent years, there has been active development of autonomous driving technology for automobiles. For autonomous driving, and in any other case, for desired vehicle operation control, it is necessary to acquire information on the current position and attitude of the vehicle with high accuracy. A position estimation device is a device that estimates the current position and attitude of the vehicle.

[0003] One method for estimating the current position and attitude of a vehicle using a position estimation device is the satellite positioning method. This method estimates the position using a satellite positioning device installed on the vehicle. However, when using the satellite positioning method, it is necessary to correct sensor errors when the satellite positioning is unstable. For example, Patent Document 1 describes that when estimating a position, errors in the satellite positioning sensor are corrected by using not only the satellite positioning method but also other methods, such as a method for calculating the relative position between a feature and a vehicle and information such as road alignment data.

[0004] Furthermore, Patent Document 2 discloses a technology in which errors in the satellite positioning sensor of a vehicle are compensated for by other vehicles with small errors in the satellite positioning sensor.The technology describes that the relative position of the vehicle is relayed from other vehicles with small errors in the satellite positioning sensor through inter-vehicle communication, and the estimated position of the vehicle is identified and corrected in a relay format. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 7034379 [Patent Document 2] Japanese Patent Publication No. 2022-118535 Summary of the Invention [Problem to be solved by the invention]

[0006] Although satellite positioning sensors are expensive, in the technology disclosed in Patent Document 1, even if an expensive satellite positioning sensor is installed in a vehicle, it may be necessary to use it in combination with other methods. Also, even when estimating the vehicle's own position using dead reckoning, there is a limit to the estimation accuracy. Furthermore, in the technology disclosed in Patent Document 2, unless at least one of the other vehicles is equipped with an expensive satellite positioning sensor, it is not possible to accurately and stably estimate the vehicle's current position and attitude.

[0007] The present application discloses technology for solving the above-mentioned problems, and aims to provide a position estimation device and a traffic control system that can estimate with high accuracy information related to the current position and attitude of a vehicle in order to perform desired vehicle operation control, even if the vehicle is not equipped with a satellite positioning sensor. [Means for solving the problem]

[0008] The position estimation device disclosed in the present application comprises: receiving, from a plurality of environment information acquisition devices, first moving body information including at least the position, angle, and speed of the moving body and surrounding environment information including road information including at least white lines around the moving body; and receiving second moving body information including at least a target route, a target vehicle speed, a position, and an attitude from the moving body. information receiving unit, The received surrounding environment information is integrated to generate integrated environment information including the position information of the mobile object. and calculating the reliability of each of the environmental information acquisition devices that acquired the surrounding environmental information and the reliability of the second moving body information, comparing the calculated reliabilities, and selecting the integrated environmental information or the second moving body information from the environmental information acquisition device having the highest reliability. recognition part, an information recording unit that records the surrounding environment information including the first moving object information and the road information received by the information receiving unit and the integrated environment information created by the recognition unit; and The recognition unit The selected information is used as the location information. The information transmitting unit transmits information to the mobile unit. [Effects of the Invention]

[0009] According to the present application, even if the vehicle is not equipped with a satellite positioning sensor, it is possible to estimate with high accuracy information relating to the current position and attitude of the vehicle in order to perform desired vehicle operation control. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram showing a configuration of a traffic control system according to a first embodiment. [Figure 2] 1 is a functional block diagram of each component of a traffic control system according to a first embodiment. [Figure 3] 4 is a flowchart showing the operation of the position estimation device according to the first embodiment. [Figure 4] 1 is a hardware configuration diagram of a position estimation device according to a first embodiment. [Figure 5] FIG. 10 is a diagram showing the configuration of a traffic control system according to a second embodiment. [Figure 6] FIG. 10 is a functional block diagram showing each component of a traffic control system according to a second embodiment. [Figure 7] 10 is a flowchart showing the operation of the position estimation device according to the second embodiment. [Figure 8] 8A is an overhead view for explaining the calculation of reliability, and FIG. 8B is an example in which the vehicle is traveling along the lane, and FIG. 8B is an example in which the vehicle is facing diagonally relative to the lane. [Figure 9] 9A and 9B are diagrams for explaining calculation of reliability as seen from the environment recognition device, where FIG. 9A corresponds to FIG. 8A and FIG. 9B corresponds to FIG. 8B. [Figure 10] FIG. 10 is a diagram illustrating correction information corresponding to reliability. [Figure 11] FIG. 10 is a diagram illustrating correction information corresponding to reliability. [Figure 12] FIG. 10 is a functional block diagram showing each component of a traffic control system according to a third embodiment. [Figure 13] 10 is a flowchart showing the operation of the position estimation device according to the third embodiment. [Figure 14] FIG. 10 is a diagram for explaining a method for predicting a future position of a vehicle. [Figure 15] FIG. 10 is a diagram for explaining a method for predicting a future position of a vehicle. [Figure 16]FIG. 10 is a diagram for explaining a method for predicting a future position of a vehicle. [Figure 17] FIG. 10 is a diagram for explaining a method for predicting a future position of a vehicle. [Figure 18] FIG. 10 is a diagram showing the configuration of a traffic control system according to a fourth embodiment. [Figure 19] FIG. 10 is a functional block diagram showing each component of a traffic control system according to a fourth embodiment. [Figure 20] 10 is a flowchart showing the operation of the position estimation device according to the fourth embodiment. [Figure 21] 21A and 21B are diagrams for explaining a method for generating an instruction to change the detection range of an environment recognition device, in which FIG. 21A shows a state before adjustment and FIG. 21B shows a state after adjustment. [Figure 22] FIG. 10 is a functional block diagram showing each component of a traffic control system according to a fifth embodiment. [Figure 23] 11 is a flowchart showing the operation of the position estimation device according to the fifth embodiment. [Figure 24] 24A and 24B are diagrams for explaining a method for generating instructions for an operation to confirm reliability, in which FIG. 24A shows the state as viewed from the rear of the vehicle, FIG. 24B shows the state as viewed from the side of the vehicle, and FIG. 24C shows the state after the confirmation operation in FIG. 24A. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the position estimation device and traffic control system disclosed in the present application will be described with reference to the drawings. In the following embodiments, an automobile will be used as an example of a moving object to be controlled, to which the position estimation device and traffic control system are applied. In addition, the same reference numerals in each drawing indicate the same or corresponding parts. Therefore, detailed descriptions thereof may be omitted to avoid duplication.

[0012] Embodiment 1 The position estimation device and traffic control system according to the first embodiment will be described below with reference to the drawings. <Traffic control system configuration> FIG. 1 is a diagram showing the configuration of a traffic control system according to a first embodiment, and FIG. 2 is a functional block diagram of each component of the traffic control system. The traffic control system 1 includes a vehicle 3, which is an object to be controlled; an environment recognition device 4 installed on the side of the road along the route along which the vehicle 3 travels; and a position estimation device 2 that receives surrounding environment information X of the vehicle 3 from the environment recognition device 4, generates integrated environment information Za from the surrounding environment information X, and transmits the integrated environment information Za to the vehicle. Although FIG. 1 shows only one environment recognition device 4, there may be multiple environment recognition devices 4 as shown in FIG. 2. In addition, in FIG. 1, the area within the dotted dashed line indicates the detection range S of the environment recognition device 4, the solid lines above and below the vehicle 3 indicate lanes, and the open dashed lines indicate lane centerlines.

[0013] <Configuration of environment recognition device 4> The environment recognition device 4 includes an environment information acquisition unit 41 that serves as a sensor and includes at least one of a camera, a LiDAR (Light Detection And Ranging), a millimeter wave radar, and the like, and a communication unit 42 that serves as a communication device. The camera acquires information from the captured image that indicates the environment in which the vehicle 3 is located, such as information about the vehicle 3 and the lanes and obstacles around the vehicle 3. LiDAR detects the position of an object within its detection range by emitting a laser and detecting the time difference between the time it takes for the laser to reflect off the object and return. Millimeter-wave radar emits millimeter waves and detects the reflected waves to measure the relative distance and relative speed of objects within its detection range, and outputs the measurement results. A sonar sensor detects the position and distance of an object by emitting ultrasonic waves to the area around the vehicle and detecting the time difference between the time it takes for the waves to reflect off an object and return.

[0014] The environment recognition device 4 acquires information about the vehicle 3 and information about the shape, type, position, attitude, speed, and other objects within the detection range S of the sensor in real time, and transmits this information to the position estimation device 2 as surrounding environment information X. Note that in FIG. 2, the surrounding environment information acquired by each of the two environment recognition devices 4 is shown as surrounding environment information X1 and X2.

[0015] <Vehicle 3 Configuration> The vehicle 3, which is the object to be controlled, is a vehicle equipped with a vehicle driving system that includes an information receiving unit 31 that receives information transmitted from the position estimation device 2 and a control unit 32 that controls the driving of the vehicle 3. Furthermore, the vehicle 3 acquires its own position based on the integrated environmental information Za transmitted from the position estimation device 2, and performs desired operational control. Note that in the following explanation, detailed explanation of the processing inside the vehicle 3 will be omitted.

[0016] <Configuration of position estimation device 2> The position estimation device 2 collects, as information about the vehicles 3, controlled object information for each vehicle and information about the surrounding environment in which the vehicle operates. Here, the "controlled object information" includes at least the position, attitude (direction), and speed of each vehicle recognized by the environment recognition device 4, which are obtained from the surrounding environment information X. Furthermore, the "environment information" is road information including at least white lines, which are obtained from the surrounding environment information X, and includes center lines, road width, white lines, road curvature, etc.

[0017] As shown in FIG. 2, the position estimation device 2 includes an information receiving unit 21 that receives information sent from the environment recognition device 4, a recognition unit 22 that integrates the acquired surrounding environment information X using a known sensor fusion technique, an information transmitting unit 23 that transmits the integrated environment information including at least the position and attitude information of the destination vehicle 3 to the vehicle 3, and an information recording unit 24 that records at least the position and attitude information of the detected vehicle, each determination result, the reason for the determination, etc.

[0018] The information receiving unit 21 receives surrounding environment information X (respectively, X1, X2, ...) from one or more environment recognition devices 4. In the recognition unit 22, the received surrounding environment information X is integrated by the information integration unit 221 using a known technique. The integrated environment information is added with position information including at least the type, position, and angle of the vehicle. In other words, the integrated environment information includes the position information of the vehicle. This When there are multiple environment recognition devices 4 as described above, the surrounding environment information X is integrated by the recognition unit 22 of the position estimation device 2. The information transmission unit 23 transmits the integrated environment information Za integrated by the recognition unit 22 to the vehicle 3.

[0019] Based on the integrated environmental information Za transmitted from the position estimation device 2, the vehicle 3 acquires its own position and attitude, and the control unit 32 performs desired operational control.

[0020] <Operation of the position estimation device 2> Next, the operation of the position estimation device 2 will be described with reference to the flowchart of FIG. First, in step S101, the position estimation device 2 collects surrounding environment information X (surrounding information collection step). That is, the information receiving unit 21 of the position estimation device 2 receives the surrounding environment information X acquired by a sensor, which is the environment information acquisition unit 41 of the environment recognition device 4 installed on the roadside.

[0021] Next, in step S102, the information integration unit 221 integrates each piece of surrounding environment information X using a known technique (information integration step). This allows the object information from the multiple environment recognition devices 4 to be integrated to produce more accurate information.

[0022] Next, in step S103, the integrated surrounding environment information Za is transmitted to each vehicle 3. The position estimation device 2 repeatedly executes the flow shown in FIG. 3 at predetermined intervals (for example, every second).

[0023] In this way, the surrounding environment information X acquired by the environment recognition device 4 is integrated by the position estimation device 2 and received as information including the vehicle's position information, so that the vehicle 3 can acquire information regarding the current position and attitude of the vehicle with high accuracy in order to perform desired operation control, even if it is not equipped with a satellite positioning sensor. If the environment recognition device 4 is installed inside a tunnel, between buildings, or the like, the present embodiment can estimate the vehicle position that is difficult to obtain using a satellite positioning sensor.

[0024] <Hardware Configuration of Position Estimation Device 2> Next, a description will be given of the hardware configuration of the position estimation device 2. Fig. 4 is a diagram showing an example of a hardware configuration that realizes the position estimation device 2 according to the first embodiment. The position estimation device 2 includes a processor 201, a memory 202 as a main storage device, and an auxiliary storage device 203. The processor 201 is configured with, for example, a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array), etc.

[0025] The memory 202 is configured as a volatile storage device such as a random access memory, and the auxiliary storage device 203 is configured as a non-volatile storage device such as a flash memory or a hard disk. A predetermined program executed by the processor 201 is stored in the auxiliary storage device 203, and the processor 201 reads and executes this program as appropriate to perform various arithmetic processing. At this time, the predetermined program is temporarily saved from the auxiliary storage device 203 to the memory 202, and the processor 201 reads the program from the memory 202. Various arithmetic processing of the control system according to the first embodiment is realized by the processor 201 executing the predetermined program as described above. The results of the arithmetic processing by the processor 201 are temporarily stored in the memory 202 and then stored in the auxiliary storage device 203 according to the purpose of the executed arithmetic processing.

[0026] Furthermore, a transmitting device 204 and a receiving device 205 are provided as communication modules for communicating with the vehicle 3 and the environment recognition device 4 .

[0027] Similarly, the hardware configuration of the vehicle 3 and the environment recognition device 4 may each include a processor 201, a memory 202 as a main storage device, and an auxiliary storage device 203.

[0028] As described above, according to the first embodiment, the position estimation device includes an information receiving unit that receives, as surrounding environment information, controlled object information, which is moving body information including at least the position, angle, and speed of a vehicle that is a moving body, and environmental information, which includes road information around the vehicle, from a plurality of environment recognition devices installed on the roadside; neighborhood The system includes a recognition unit that integrates environmental information to create integrated environmental information, an information recording unit that records the controlled object information and environmental information received by the receiving unit and the integrated environmental information created by the recognition unit, and an information transmitting unit that transmits the integrated environmental information created by the recognition unit to a moving object as information including vehicle position information. This makes it possible to estimate the vehicle's position with high accuracy from the integrated environmental information, even if the vehicle itself does not have an expensive sensor such as a satellite positioning sensor.

[0029] In addition, since the traffic control system is equipped with a vehicle, an environment recognition device, and the above-mentioned position estimation device, the information obtained from the environment recognition device is integrated by the position estimation device and provided to the vehicle, allowing the vehicle to estimate its own position and angle (attitude) with high accuracy, thereby enabling stable driving.

[0030] Embodiment 2 The following describes a position estimation device and a traffic control system according to the second embodiment with reference to the drawings. Note that descriptions that overlap with those of the first embodiment will be omitted. <Traffic control system configuration> Fig. 5 is a diagram showing the configuration of a traffic control system according to embodiment 2, and Fig. 6 is a functional block diagram of each functional unit constituting the traffic control system. In Fig. 5, the traffic control system 1 includes a vehicle 3, an environment recognition device 4, and a position estimation device 2, similar to embodiment 1. The difference from embodiment 1 is that the position estimation device 2 receives controlled object information Y, which is vehicle information, from the vehicle 3, and generates integrated environment information Za that integrates surrounding environment information X, reliability information Zb of the surrounding environment information X and the controlled object information Y, and correction information Zc, and transmits these to the vehicle 3. The configuration of the environment recognition device 4 is the same as in embodiment 1.

[0031] <Vehicle 3 Configuration> The vehicle 3 includes an information receiving unit 31 that receives each piece of information transmitted from the position estimation device 2, a dead reckoning unit 34 that estimates the vehicle's current position from an arbitrary position, a vehicle driving system that is a control unit 32 that controls the driving of the vehicle 3, a self-information acquiring unit 33 that acquires its own vehicle information including at least a target route, a target vehicle speed, its own position, and its attitude, and an information transmitting unit 35 that transmits controlled object information Y that is its own vehicle information to the position estimation device 2. The vehicle 3 also appropriately corrects its own position based on the integrated environment information Za, reliability information Zb, and correction information Zc according to the reliability transmitted from the position estimation device 2, and performs the desired operational control; however, in the following explanation, a description of the internal processing of the vehicle 3 will be omitted.

[0032] <Configuration of position estimation device 2> The position estimation device 2 collects, as information about the vehicle 3, control object information for each vehicle and information about the surrounding environment in which the vehicle operates. Here, the "control object information" includes at least the target route, target vehicle speed, vehicle position, and attitude sent from the vehicle 3. Also, here, the "environment information" includes the position, attitude, and speed of each vehicle recognized by the environment recognition device 4 obtained from the surrounding environment information X, as in the first embodiment, as well as road information including at least white lines obtained from the surrounding environment information X. Information and This includes the center line, road width, white lines, and road curvature.

[0033] As shown in FIG. 6 , the position estimation device 2 includes an information receiving unit 21 that receives information sent from the environment recognition device 4 and the vehicle 3, a recognition unit 22 that integrates the acquired surrounding environment information X using a well-known sensor fusion technique, an information transmitting unit 23 that transmits the integrated environment information to the vehicle 3, and an information recording unit 24 that records at least the detected position and attitude information of the vehicle, each determination result, the reason for the determination, etc.

[0034] The information receiving unit 21 receives surrounding environment information X from one or more environment recognition devices 4 and control object information Y from one or more vehicles 3, which includes at least a target route, a target vehicle speed, a target vehicle speed, a vehicle's own position, and an attitude.

[0035] The recognition unit 22 integrates the received surrounding environment information X using known technology in the information integration unit 221. The integrated environment information includes at least vehicle type information, position, and angle information. In this way, when there are multiple environment recognition devices 4, the integration of the surrounding environment information X is performed by the recognition unit 22 of the position estimation device 2. Furthermore, the recognition unit 22 calculates the reliability indicating the accuracy and reliability of the information obtained from each sensor based on the surrounding environment information obtained from each sensor in the reliability calculation unit 222. The recognition unit 22 also calculates the reliability indicating the accuracy and reliability of the controlled object information Y, which is vehicle information obtained from the vehicle 3. The reliability comparison unit 223 compares the calculated reliability to determine which information is most reliable and selects the content of the correction information to be transmitted to the vehicle based on the result. The information transmission unit 23 transmits the integrated environment information Za integrated by the information integration unit 221, the reliability information Zb calculated by the reliability calculation unit 222, and the correction information Zc corresponding to this reliability to the vehicle 3.

[0036] Based on the integrated environmental information Za, reliability information Zb, and correction information Zc transmitted from the position estimation device 2, the vehicle 3 corrects its own position and attitude, and the control unit 32 performs desired operational control.

[0037] <Operation of the position estimation device 2> Next, the operation of the position estimation device 2 will be described with reference to the flowchart of Fig. 7. Note that the same operations as those in Fig. 3 of the first embodiment will be explained in a simplified manner. First, in step S201, the position estimation device 2 collects surrounding environment information X in the same manner as in step S101 of the first embodiment (surrounding information collection step).

[0038] Next, in step S202, vehicle information transmitted from the vehicle 3, which is control object information Y including at least the target route, target vehicle speed, target vehicle speed, host vehicle position, and attitude, is received (vehicle information collection step).

[0039] Next, in step S203, similarly to step S102 in the first embodiment, the information integration unit 221 integrates each piece of surrounding environment information X using a known technique (information integration step). This allows the object information from the multiple environment recognition devices 4 to be integrated to produce more accurate information.

[0040] Next, in step S204, the reliability of each environment recognition device 4 or each sensor, and the reliability of the control object information Y are calculated (reliability calculation step). The calculation of reliability will be described later. The environment recognition device 4 or the sensor equipped therein may also be referred to as an "environment information acquisition device."

[0041] Next, in step S205, the calculated reliability is compared to determine which environment recognition device 4 or sensor (environment information acquisition device), or control object information Y has the highest reliability, and the position estimation result with the highest reliability is selected as the information to be transmitted to the vehicle 3 (reliability comparison process).

[0042] Next, in step S206, it is determined whether or not correction information needs to be transmitted to the vehicle 3 (correction information creation determination step). Whether or not correction information needs to be transmitted is determined, for example, based on the result of the reliability comparison step. If the highest reliability value is smaller than a preset first reference value (No in step S206), it is determined that correction information should be created, and the process proceeds to step S207.

[0043] If the highest reliability value is smaller than a preset first reference value and it is determined in the correction information creation determination step that correction information Zc should be created, then in step S207, correction information Zc to be transmitted to vehicle 3 is created (correction information creation step). For example, the creation of correction information Zc may involve transmitting information about the area in which vehicle 3 is located. However, this is not limited to the above. Then, the process proceeds to step S208.

[0044] In step S206, if the highest reliability value is equal to or greater than a preset first reference value and it is determined in the correction information creation determination step that creation of correction information is not necessary (Yes in step S206), the process proceeds to step S208.

[0045] In step S208, each piece of information, that is, the integrated environmental information Za which is the integrated surrounding environment information, the most reliable position information, the reliability information Zb, and correction information Zc as required, is transmitted to each vehicle 3. The position estimation device 2 repeatedly executes the flow shown in FIG. 7 at predetermined intervals (for example, every second).

[0046] <Calculation method of reliability information Zb> Next, a reliability calculation method in the reliability calculation step of step S204 will be described using an example in which the sensor included in the environment recognition device 4 is a LiDAR. Note that in this application, reliability is a value indicating how close the information acquired by the sensor is to the true value, and high reliability means closeness to the true value. Fig. 8 is a bird's-eye view for explaining a reliability calculation method, with Fig. 8A showing an example in which vehicle 3 is traveling along a route along a lane, and Fig. 8B showing an example in which vehicle 3 is facing diagonally relative to the lane, with the two examples showing different postures (angles). Fig. 9 shows the state as seen from the environment recognition device 4, with Figs. 9A and 9B corresponding to Figs. 8A and 8B, respectively. For convenience, vehicle 3 as seen from the environment recognition device 4 is represented as a hexahedral perspective view.

[0047] 8A and 8B, the thick lines on the side of vehicle 3 indicate surface 3S recognized by the environment recognition device 4. As shown in FIGS. 8A and 9A, when vehicle 3 is traveling along a route, three surfaces can be recognized by environment recognition device 4. On the other hand, as shown in FIGS. 8B and 9B, when vehicle 3 is facing diagonally to the lane and is parallel to environment recognition device 4, i.e., perpendicular to the axis of the detection direction of the sensor of environment recognition device 4, only one surface can be recognized by environment recognition device 4.

[0048] 9A and 9B each show reflection points for each surface of the vehicle 3 detected by the environment recognition device 4, with the horizontal length of each surface indicated as Lsi and the vertical length as Lli. That is, in FIGS. 9A and 9B, reflection points on a surface consisting of horizontal Ls1 and vertical Ll1 are indicated by black circles ●, reflection points on a surface consisting of horizontal Ls2 and vertical Ll2 are indicated by white circles ○, and reflection points on a surface consisting of horizontal Ls3 and vertical Ll3 are indicated by squares □. Here, the number of reflection point groups for the vehicle 3 is Npi, i is the number of detected vehicle surfaces (maximum Nf), j is the type of evaluation method, and Wj is the weighting coefficient. In FIG. 9A, the number of reflection point groups Np1 is the total number of black circles ●, the number of reflection point groups Np2 is the total number of white circles ◯, and the number of reflection point groups Np3 is the total number of squares □. In FIG. 9B, the number of reflection point groups Np1 is the total number of black circles ●.

[0049] When the sensor is a LiDAR as in the second embodiment and the reliability of the vehicle's attitude (angle) is evaluated using the number of reflection point clouds of the LiDAR, the reliability Rij of the sensor alone (LiDAR) can be defined by the following equation (1).

number

[0050] As described above, the reliability evaluation is not limited to the example in which the number of reflection point clouds of the LiDAR is used based on the attitude (angle) of the vehicle 3, but the reliability for the attitude (angle) can also be evaluated by using the detection distance of the vehicle 3 in combination, or the reliability for the detection distance can be evaluated. Also, in the above example, the evaluation was centered on the side of the vehicle, but the front and rear sides may also be captured. The evaluation method is not limited to these.

[0051] Next, a method for calculating the reliability of the vehicle position information of the control object information Y, which is another reliability, will be described. The time calculated by the dead reckoning unit 34 of the vehicle 3 is denoted by t(s), the acceleration of the vehicle is denoted by αt, the gradient of the road on which the vehicle is traveling is denoted by St, and the weighting coefficient is denoted by Wk. When using a method for calculating the reliability of self-position estimation by dead reckoning in the control object information Y, the reliability Rij of a single sensor can be defined by the following equation (2).

number

[0052] Although two examples of reliability calculation methods have been given, the reliability evaluation method and calculation method are not limited to these.

[0053] The reliability described above is calculated and integrated by the reliability calculation unit 222 for each reliability evaluation method, or for each environment recognition device 4, or for each sensor, or for each piece of controlled object information Y. There are various integration methods, and one possible method is to take the average of the reliability of each individual sensor. If N is the number of sensors mounted on the environment recognition device, and Ri is the reliability for each reliability evaluation method or for each sensor, the integrated reliability Rall of the environment recognition device 4 or sensor can be found by the following formula (3):

number

[0054] Reliability of each integrated environmental recognition device or sensor Rail Alternatively, the reliability Rall of the control object information Y is compared, and the vehicle information output from the environment recognition device 4 or sensor with the highest reliability or the vehicle information of the control object information Y is output as the position information. At this time, if the value of the highest reliability is less than a preset first reference value, correction information is created with the granularity of information according to that reliability.

[0055] 8A and 9A, when the calculation time in the dead reckoning unit 34 is short, the reliability according to formula (2) is higher than the reliability according to formula (1), and is determined to be the most reliable of the other sensors. Therefore, in order to obtain high position estimation accuracy, it is useful to compare the reliability and select the highest reliability, and output the vehicle information or the vehicle information of the controlled object information Y output from the environment recognition device 4 or sensor with the highest reliability.

[0056] <How to create correction information Zc> Next, a method for creating correction information Zc when the value of the highest reliability is less than a preset first reference value will be described. FIG. 10 is a diagram illustrating a method for generating correction information corresponding to reliability. FIG. 10A in FIG. 10 illustrates a method for generating correction information related to the vehicle position to be transmitted to the vehicle 3 when the reliability is less than a first reference value. Based on the target route along which the vehicle 3 is traveling or the road information recognized by the environment recognition device 4, the center line of the lane is used as a dividing line. A region is divided into two areas, a1 and b1, a certain distance D1 (e.g., 12 m) from the position recognized by the environment recognition device 4 in the direction of vehicle travel. Here, by varying the set certain distance D1 depending on the reliability, the granularity of the correction information can be changed according to the reliability. Then, it is determined which of the areas a1 and b1 the vehicle is currently in based on the environment recognition device 4's current recognition, and the coordinates (a1_p, a1_q, a1_r, a1_s) of the four corners of the existing area a1 are generated as correction information.

[0057] FIG. 10B in FIG. 10 shows a method for creating correction information related to the vehicle position to be transmitted to the vehicle 3 when the reliability is less than the first reference value but higher than that in FIG. 10A. In this case, the area is divided into two areas a2 and b2 using the same method as in FIG. 10A described above. However, the fixed distance D2 in the direction of travel is shorter (e.g., 6 m) than the fixed distance D1 in FIG. 10A. Thereafter, it is determined in which of the areas a2 and b2 the vehicle exists based on its current recognition by the environment recognition device 4, and the coordinates (a2_p, a2_q, a2_r, a2_s) of the four corners of the existing area a2 are created as correction information.

[0058] FIG. 11 is a diagram for explaining a method for creating correction information corresponding to reliability, and shows an example in which the number of driving lanes is greater than that in FIG. 10. In FIG. 11, FIG. 11A shows a method for creating correction information regarding the vehicle position to be transmitted to the vehicle 3 when the reliability is less than the first reference value. Based on the target route along which the vehicle 3 will travel or the road information recognized by the environment recognition device 4, the center line of the lane is used as a demarcation point, and in terms of the vehicle traveling direction, a certain distance in the traveling direction from the position recognized by the environment recognition device 4 is used as a demarcation point. D3 The area secured for 100 m (for example, 12 m) is divided into two. The divisions are further subdivided into areas a3, b3, c3, and d3 according to the separated lanes. Here, by making the set fixed distance D3 variable depending on the reliability, the granularity of the correction information can be changed according to the reliability. After that, it is determined in which of areas a3, b3, c3, and d3 the object exists based on the current recognition by the environment recognition device 4, and the coordinates (b3_p, b3_q, b3_r, b3_s) of the four corners of area b3 that exists are created as correction information.

[0059] Figure 11 Medium Figure 11 B has a reliability below the first standard value, Figure 11 11B shows a method for creating correction information about the vehicle position to be transmitted to vehicle 3 when the reliability is higher than in case A. Similarly, in Fig. 11B, the coordinates (b4_p, b4_q, b4_r, b4_s) of the four corners of the area where vehicle 3 is located are created as correction information. Here, the fixed distance D4 is smaller than the fixed distance D3.

[0060] Although the coordinates indicating the area where the vehicle 3 is located, which is the position information of the vehicle 3, have been described as an example of the correction information, the correction information is not limited to this. The correction information includes at least the position information of the vehicle, and may also include the attitude of the vehicle, the speed of the vehicle, etc.

[0061] The correction information created as described above is information for a vehicle position estimation system such as the dead reckoning unit 34 installed in the vehicle 3, and by using this correction information, it is possible to suppress the accumulation of errors that occur due to long-term estimation in the dead reckoning unit 34.

[0062] As a method of calculating the fixed distance D in the traveling direction, for example, if the reliability is Rall and the coefficient is K, it can be obtained by the following equation (4). D = Rall × K (4) However, the calculation method is not limited to this.

[0063] As described above, according to the second embodiment, the same effects as those of the first embodiment can be achieved. That is, even if the vehicle itself does not have an expensive sensor such as a satellite positioning sensor, it is possible to estimate the vehicle position and angle with high accuracy based on the integrated environmental information transmitted from the position estimation device. Furthermore, the position estimation device of embodiment 2 further includes a reliability calculation unit that calculates the reliability of each environment recognition device or each sensor equipped therein, and the reliability of the controlled object information Y, and a reliability comparison unit that compares the calculated reliability.The reliability comparison unit selects the integrated environment information from the environment recognition device or sensor with the highest reliability, or the vehicle information of the controlled object information Y, and outputs it as the vehicle position information, thereby making it possible to estimate the position and angle with even higher accuracy.

[0064] Furthermore, if the highest reliability is smaller than a predetermined first reference value, correction information including at least the position information of the moving body is created with information granularity corresponding to the reliability and output together with the selected integrated environmental information, so that the vehicle can estimate or correct its own position and angle by referring to the correction information.

[0065] Embodiment 3 A position estimation device and a traffic control system according to the third embodiment will be described below with reference to the drawings. Explanations that overlap with those of the first and second embodiments will be omitted. In addition to the configuration of the second embodiment, the position estimation device according to the third embodiment has a function of predicting whether a vehicle will deviate from a target route based on at least two or more pieces of information provided by the vehicle: at least a target route, control object information including a target vehicle speed, map information, or vehicle travel route information (travel history) recorded in the position estimation device.

[0066] <Traffic control system configuration> 12 is a functional block diagram of each functional unit constituting the traffic control system according to embodiment 3. The configuration of the traffic control system according to embodiment 3 is the same as that of embodiment 2 shown in FIG. 5. The configuration of the environment recognition device 4 is the same as that of embodiments 1 and 2, and the configuration of the vehicle 3 is the same as that of embodiment 2.

[0067] <Configuration of position estimation device 2> 12, the position estimation device 2 includes an information receiving unit 21 that receives information sent from the environment recognition device 4 and the vehicle 3, a recognition unit 22 that integrates the acquired surrounding environment information X and controlled object information Y using a known sensor fusion technique, an information transmitting unit 23 that transmits each piece of information to the vehicle 3, and an information recording unit 24 that records detected vehicle position information, etc. The recognition unit 22 includes an information integration unit 221 that integrates the acquired surrounding environment information X and controlled object information Y, a reliability calculation unit 222 that calculates the reliability of each environment recognition device 4 or each sensor and the reliability of the controlled object information Y, a reliability comparison unit 223 that compares the calculated reliabilities and creates correction information according to the comparison results, and a vehicle position prediction unit 224.

[0068] The vehicle position prediction unit 224 predicts whether the vehicle 3 will deviate from the target route or the behavior of the vehicle 3 based on at least two or more pieces of information from the control object information Y provided by the vehicle 3, which includes at least the target route, target vehicle speed, vehicle position, and attitude, map information, or the vehicle's past driving trajectory information recorded in the information recording unit 24.

[0069] <Operation of the position estimation device 2> Next, the operation of the position estimation device 2 will be described with reference to the flowchart of Fig. 13. Note that the same operations as those in Fig. 3 of the first embodiment and Fig. 7 of the second embodiment will be explained in a simplified manner. First, in step S301, the position estimation device 2 collects surrounding environment information X in the same manner as in step S101 of the first embodiment (surrounding information collection step).

[0070] Next, in step S302, similar to step S202 in embodiment 2, vehicle information, which is control object information Y including at least the target route, target vehicle speed, target vehicle speed, vehicle position, and attitude, transmitted from vehicle 3 is received (vehicle information collection process).

[0071] Next, in step S303, similarly to step S102 in the first embodiment, the information integration unit 221 integrates each piece of surrounding environment information X using a known technique (information integration step). This allows the object information from the multiple environment recognition devices 4 to be integrated to produce more accurate information.

[0072] Next, in step S304, similarly to step S204 in the second embodiment, the reliability of each environment recognition device 4 or each sensor, and the reliability of the control object information Y are calculated (reliability calculation step). The calculation of the reliability is similar to that in the second embodiment.

[0073] Next, in step S305, similar to step S205 in embodiment 2, the calculated reliabilities are compared to determine which environment recognition device 4, sensor, or controlled object information Y has the highest reliability, and the location information with the highest reliability is selected as the information to be transmitted to vehicle 3 (reliability comparison process).

[0074] Next, in step S306, similar to step S206 in the second embodiment, it is determined whether or not correction information needs to be sent to the vehicle 3 (correction information creation determination step). Whether or not correction information needs to be sent is determined, for example, based on the results of the reliability comparison step. If the highest reliability value is smaller than a preset first reference value (No in step S306), it is determined that correction information should be created, and the process proceeds to step S307. Similar to step S207 in the second embodiment, in step S307, correction information Zc to be sent to the vehicle 3 is created (correction information creation step), and the process proceeds to step S310. The creation of correction information Zc is the same as in the second embodiment.

[0075] In step S306, if the highest reliability value is equal to or greater than a preset first reference value and it is determined in the correction information creation determination step that creation of correction information is not necessary (Yes in step S306), the process proceeds to step S308. In step S308, the vehicle position prediction unit 224 predicts whether the future position of the vehicle 3 will not match the target route and will deviate from the target route based on at least two or more pieces of information from the vehicle information (control object information Y) including the target route and target vehicle speed provided by the vehicle 3, the map information, or the driving trajectory information of the vehicle 3 up to the present recorded in the information recording unit 24 (vehicle position prediction process).

[0076] In step S308, if the future position of the vehicle 3 does not match the target route and is predicted to deviate from the target route (Yes in step S308), correction information Zc is created. (Step S309) Here, the correction information Zc may be created in the same manner as described in embodiment 2. Then, the process proceeds to step S310.

[0077] In step S308, if it is predicted that the future position of the vehicle 3 will match the target route and will not deviate from the target route (No in step S308), the process proceeds to step S310. In step S310, the information transmission unit 23 transmits each piece of information to the vehicle 3, including the correction information Zc generated when the future position of the vehicle 3 does not match the target route and is predicted to deviate from the target route.

[0078] The position estimation device 2 repeatedly executes the flow shown in FIG. 13 at predetermined intervals (for example, every second).

[0079] <Method for predicting the future position of vehicle 3> A method for predicting the future position of the vehicle 3 in the vehicle position predicting unit 224 will be described. FIG. 14 is a diagram for explaining a method for predicting the future position of vehicle 3. In FIG. 14, the attitude of vehicle 3 does not match the direction of target route R1, and if vehicle 3 continues traveling at this rate, it will deviate from target route R1. Therefore, it is predicted that vehicle 3 will deviate from target route R1 in the future. An example of the determination criterion is when the angle θ of vehicle 3 deviates from target route R1 by ±45 degrees or more. However, the determination method and criteria are not limited to this.

[0080] FIG. 15 is a diagram illustrating another method for predicting the future position of vehicle 3. FIG. 15 shows the relationship between vehicle 3 and driving history R2 recorded in the information recording unit 24 of the position estimation device 2. From the driving history recorded in the information recording unit 24, scenes that are close to the current target route of vehicle 3 are extracted for driving history R2. The vehicle position in that scene is compared with the current position of vehicle 3. If the position difference d is greater than a preset reference value, or if the vehicle angle θ is clearly different as in the example of FIG. 14, a future deviation is predicted. Examples of judgment criteria include when the angle θ of vehicle 3 deviates by ±45 degrees or more from driving history R2, or when vehicle 3 is one vehicle away from driving history R2.

[0081] 16 and 17 are diagrams for explaining yet another method for predicting the future position of vehicle 3. Another vehicle 3b is a vehicle different from the vehicle 3 that is the control target, and may or may not be the control target of the traffic control system according to the third embodiment. In Fig. 16, vehicle 3 is traveling in the center of the lane, so another vehicle 3b is also traveling in the center of the lane along traveling route R3. However, in Fig. 17, vehicle 3 is traveling in the center line of the lane, so another vehicle 3b is traveling on traveling route R4, which is to the left of the lane. Position estimation device 2 detects this situation, and if other vehicle 3b is not traveling in the center of the lane with no obstacles ahead, it predicts that vehicle 3 is traveling or may deviate from the target route.

[0082] In addition, the correction information Zc, which is created when the future position of vehicle 3 does not match the target route and it is predicted that the vehicle will deviate from the target route, preferably includes at least the vehicle's position information, and the vehicle's angle (attitude) and speed, which are used to determine whether the vehicle will deviate from the target route.

[0083] As described above, according to the third embodiment, the same effects as those of the first embodiment can be achieved. That is, even if the vehicle itself does not have an expensive sensor such as a satellite positioning sensor, it is possible to estimate the vehicle position and angle with high accuracy based on the integrated environmental information transmitted from the position estimation device. Furthermore, the position estimation device according to the third embodiment receives second control object information, which is second moving body information including at least a target route, a target vehicle speed, a position, and an attitude, from the moving body, and the recognition unit further includes a vehicle position prediction unit that predicts a future position of the moving body. When the reliability comparison unit determines that the highest reliability value is equal to or greater than a predetermined first reference value, the vehicle position prediction unit predicts whether the future position of the moving body will match the target route based on at least two of the second moving body information, the map information, and the driving route history recorded in the information recording unit. If a mismatch is predicted, the vehicle position prediction unit creates correction information including at least the position information and angle of the moving body and transmits it to the vehicle. This makes it possible to provide information for the vehicle to travel along the target route, enabling the vehicle to travel stably.

[0084] Embodiment 4 A location estimation device and a traffic control system according to embodiment 4 will be described below with reference to the drawings. Note that descriptions that overlap with embodiments 1 to 3 will be omitted.

[0085] <Traffic control system configuration> Fig. 18 is a diagram showing the configuration of a traffic control system according to the fourth embodiment, and Fig. 19 is a functional block diagram of each functional unit constituting the traffic control system. The configuration of the environment recognition device 4 is the same as that of the first to third embodiments, and the configuration of the vehicle 3 is the same as that of the second and third embodiments. In addition to the configuration of the second embodiment, the position estimation device 2 according to the fourth embodiment has a function of adjusting the detection range of each sensor of the environment recognition device 4 based on the reliability created by the position estimation device 2. Therefore, each sensor of the environment recognition device 4 receives detection range change information Zd from the position estimation device 2, and recognizes objects within the detection range corresponding to that information.

[0086] <Configuration of position estimation device 2> 19, the position estimation device 2 includes an information receiving unit 21 that receives information sent from the environment recognition device 4 and the vehicle 3, a recognition unit 22 that integrates the acquired surrounding environment information X and controlled object information Y using a publicly known sensor fusion technique, an information transmitting unit 23 that transmits each piece of information to the vehicle 3, and an information recording unit 24 that records detected vehicle position information, etc. The recognition unit 22 includes an information integrating unit 221 that integrates the acquired surrounding environment information X, a reliability calculating unit 222 that calculates the reliability of each environment recognition device 4 or each sensor and the reliability of the controlled object information Y, a reliability comparing unit 223 that compares the calculated reliabilities and creates correction information according to the comparison results, and a detection range change instruction creating unit 225.

[0087] The detection range change instruction creation unit 225 determines whether the detection range of each sensor is appropriate based on the reliability created by the reliability calculation unit 222 and the reliability comparison unit 223 and the comparison result, and generates an instruction to change the detection range of each sensor if it is determined that the detection range is inappropriate. For example, determining whether the detection range of a sensor is appropriate can be done by narrowing the sensor's detection range so that the vehicle can be clearly seen when the vehicle is located far away from the sensor and the detection resolution is lower than a preset resolution. However, the method is not limited to this.

[0088] <Operation of the position estimation device 2> Next, the operation of the position estimation device 2 will be described with reference to the flowchart of Fig. 20. Note that operations similar to those described in the first to third embodiments will be explained in a simplified manner. First, in step S401, the position estimation device 2 collects surrounding environment information X in the same manner as in step S101 of the first embodiment (surrounding information collection step).

[0089] Next, in step S402, similar to step S202 in embodiment 2, vehicle information, which is control object information Y including at least the target route, target vehicle speed, target vehicle speed, vehicle position, and attitude, transmitted from vehicle 3 is received (vehicle information collection process).

[0090] Next, in step S403, similarly to step S102 in the first embodiment, the information integration unit 221 integrates each piece of surrounding environment information X using a known technique (information integration step).

[0091] Next, in step S404, similarly to step S204 in the second embodiment, the reliability of each environment recognition device 4 or each sensor and the reliability of the control object information Y are calculated (reliability calculation step). The calculation of the reliability is similar to that in the second embodiment.

[0092] Next, in step S405, it is determined whether the highest reliability value among the calculated reliability values ​​is smaller than a preset second reference value (reliability confirmation step). If the reliability value is equal to or greater than the preset second reference value (No in step S405), the process proceeds to step S406. In step S406, correction information Zc to be transmitted to vehicle 3 is created (correction information creation step). The creation of correction information Zc is the same as in embodiment 2. Here, the second reference value is set to a value equal to or smaller than the first reference value described in embodiment 2.

[0093] In step S405, if it is determined that the highest reliability is smaller than the second reference value set in advance (Yes in step S405), the process proceeds to step S407. In step S407, the detection range change instruction creation unit 225 creates an instruction to change the detection range of the sensor corresponding to the reliability determined to be smaller than the second reference value (detection range change instruction creation step). The created instruction is transmitted to the environment recognition device 4 as detection range change information Zd.

[0094] The position estimation device 2 repeatedly executes the flow shown in FIG. 20 at predetermined intervals (for example, every second).

[0095] <Example of creating an instruction to change the detection range> Next, a method for generating an instruction to adjust the detection range of a sensor will be described. FIG. 21 is a diagram for explaining a method for generating an instruction to change the detection range of a sensor provided in the environment recognition device 4, with FIG. 21A showing the state before the change and FIG. 21B showing the state after the change. In FIG. 21A, the distance between the vehicle 3 and the environment recognition device 4 is far, and the vehicle 3 appears small to the environment recognition device 4. In this case, changing the detection range so as to enlarge the upper right corner of the screen in the figure allows the vehicle 3 to be perceived as larger, which can lead to improved reliability. FIG. 21B shows the state after the detection range has been changed. In this way, it can be seen that reliability is improved by generating an instruction to change the detection range and changing the detection range.

[0096] 21 shows an example in which the sensor is a camera and the detection range for acquiring images is changed, but this is not limiting. For example, if the sensor is a LiDAR, the direction or angle of laser irradiation can be changed, and if the sensor is a millimeter-wave radar, the direction or angle of radar irradiation can be changed to change the detection range, thereby improving reliability.

[0097] As described above, according to the fourth embodiment, the same effects as those of the first embodiment can be achieved. That is, even if the vehicle itself does not have an expensive sensor such as a satellite positioning sensor, it is possible to estimate the vehicle position and angle with high accuracy based on the integrated environmental information transmitted from the position estimation device. Furthermore, the position estimation device according to the fourth embodiment further includes a reliability calculation unit that calculates the reliability of each environment recognition device or each sensor equipped therein and the reliability of the controlled object information Y, a reliability comparison unit that compares the calculated reliability, and a detection range change instruction creation unit that creates an instruction to change the detection range of the environment recognition device or sensor. If the detection range change instruction creation unit determines that the calculated reliability is smaller than a second reference value, it creates an instruction to change the detection range of the associated environment recognition device or sensor. This makes it possible to optimize the detection range and improve reliability, thereby enabling highly accurate position estimation.

[0098] Furthermore, as a result of the improved reliability, if the recognition unit 22 of the position estimation device 2 is equipped with a vehicle position prediction unit 224 that predicts the future position of the vehicle 3, as shown in embodiment 3, the prediction accuracy of the vehicle's future position will also be further improved.

[0099] Embodiment 5 A location estimation device and a traffic control system according to embodiment 5 will be described below with reference to the drawings. Explanations that overlap with embodiments 1 to 3 will be omitted. In addition to the configuration of embodiment 3, the location estimation device according to embodiment 5 has a function of generating a reliability confirmation operation instruction to the vehicle when the reliability generated by the reliability comparison unit is low.

[0100] <Traffic control system configuration> 22 is a functional block diagram of each functional unit constituting the traffic control system according to embodiment 5. The configuration of the traffic control system according to embodiment 5 is the same as that of embodiment 2 shown in FIG. 5. The configuration of the environment recognition device 4 is the same as that of embodiments 1 to 3, and the configuration of the vehicle 3 is the same as that of embodiments 2 and 3.

[0101] <Configuration of position estimation device 2> 22 , the position estimation device 2 includes an information receiving unit 21 that receives information sent from the environment recognition device 4 and the vehicle 3, a recognition unit 22 that integrates the acquired surrounding environment information X and controlled object information Y using a publicly known sensor fusion technique, an information transmitting unit 23 that transmits each piece of information to the vehicle 3, and an information recording unit 24 that records detected vehicle position information, etc. The recognition unit 22 includes an information integration unit 221 that integrates the acquired surrounding environment information X and controlled object information Y, a reliability calculation unit 222 that calculates the reliability for each environment recognition device 4 or each sensor, a reliability comparison unit 223 that compares the calculated reliability and creates correction information according to the comparison result, as well as a confirmation operation instruction creation unit 226 and an operation confirmation unit 227.

[0102] Based on the reliability created by the reliability calculation unit 222 and the reliability comparison unit 223 and the comparison result, the confirmation operation instruction creation unit 226 selects an operation to be performed by the vehicle 3 to confirm the reliability of the sensor of the environment recognition device 4 if the highest reliability is smaller than a third reference value, and creates a confirmation operation instruction Ze. The operation confirmation unit 227 confirms whether the expected result is obtained by the vehicle executing the confirmation operation instruction Ze created by the confirmation operation instruction creation unit 226. The method of creating the confirmation operation instruction Ze and the method of confirming the operation will be described later. Here, the third reference value is 4 The value is set to be equal to or smaller than the second reference value described in .

[0103] <Operation of the position estimation device 2> Next, the operation of the position estimation device 2 will be described with reference to the flowchart of FIG. Operations similar to those in the first to third embodiments will be explained briefly. First, in step S501, the position estimation device 2 collects surrounding environment information X in the same manner as in step S101 of the first embodiment (surrounding information collection step).

[0104] Next, in step S502, similar to step S202 in embodiment 2, vehicle information, which is control object information Y including at least the target route, target vehicle speed, target vehicle speed, vehicle position, and attitude, transmitted from vehicle 3 is received (vehicle information collection process).

[0105] Next, in step S503, similarly to step S102 in the first embodiment, the information integration unit 221 integrates each piece of surrounding environment information X using a known technique (information integration step).

[0106] Next, in step S504, similarly to step S204 in the second embodiment, the reliability of each environment recognition device 4 or each sensor, and the reliability of the control object information Y are calculated (reliability calculation step). The calculation of the reliability is similar to that in the second embodiment.

[0107] Next, in step S505, it is determined whether the highest reliability among the calculated reliability is smaller than a preset third reference value (reliability confirmation step). If the reliability is equal to or greater than the preset third reference value (No in step S505), the process proceeds to step S506. In step S506, correction information Zc to be transmitted to vehicle 3 is created (correction information creation step). The creation of correction information Zc is the same as in embodiment 2.

[0108] In step S505, if it is determined that the highest reliability is smaller than the preset third reference value (Yes in step S505), the process proceeds to step S507. In step S507, it is confirmed whether a confirmation operation instruction Ze for confirming reliability has been created within several cycles (operation instruction confirmation step). If a confirmation operation instruction Ze has not been created within several cycles (No in step S507), S508The process proceeds to step 2, where a confirmation operation is determined based on the location of the vehicle and the vehicle state that can be detected by the environment recognition device 4, and instructions are created (operation instruction determination and instruction creation step).

[0109] In step S507, if an operation instruction to confirm reliability has already been created within several cycles (Yes in step S507), proceed to step S509, where it is determined whether the instructed operation was performed as expected, or whether it has been confirmed that the vehicle's performance of the instructed operation has made it possible to detect easily detectable ground landmarks that were in the vehicle's blind spot (instructed operation execution confirmation process).

[0110] In step S509, if it is not possible to confirm that the operation has been performed in accordance with the instruction (No in step S509), the process proceeds to step S511, where correction information corresponding to the reliability is created or corrected. In step S509, if it is confirmed that the operation has been performed according to the instruction (Yes in step S509), S510 The reliability is recalculated (reliability recalculation step). This reliability recalculation may be performed using the same method as used this time, or a different method. After the reliability is recalculated in step S510, the process proceeds to step S511, where correction information corresponding to the reliability is created or corrected.

[0111] The position estimation device 2 repeatedly executes the flow shown in FIG. 23 at predetermined intervals (for example, every second).

[0112] <How to create an action instruction to check reliability> Next, a method for generating an instruction for an operation to confirm reliability will be described. Fig. 24 is a diagram for explaining a method for generating an instruction for an operation to confirm reliability, where Fig. 24A is a diagram showing the state as seen from behind the vehicle, Fig. 24B is a diagram showing the state as seen from the side of the vehicle, and Fig. 24C is a diagram showing the state after the confirmation operation in Fig. 24A. In Fig. 24A, the rear of the vehicle can be seen from the environment recognition device 4. However, vehicle 3 is in the blind spot of the environment recognition device 4, and the white line on the road cannot be detected. In this case, an example of an operation to confirm reliability that can be instructed to vehicle 3 is to drive slowly while turning the steering wheel to the right.

[0113] 24B, the side of the vehicle 3 can be seen from the environment recognition device 4, but the vehicle 3 is in a blind spot and some of the lanes (center lines) on the road cannot be detected. In this case, an example of a reliability confirmation action to be instructed to the vehicle 3 is to turn the steering wheel to the left and drive slowly.

[0114] In comparison with FIG. 24A, FIG. 24C shows that the white lines on the road can be detected, and it can be confirmed that the action instruction to slow down while turning the steering wheel to the right was executed in the state of FIG. 24A. In this way, the checking operation may be, for example, moving the vehicle forward diagonally or moving the vehicle forward or backward on the spot, but is not limited to this. The reliability confirmation operation is an operation for improving reliability. Confirming whether the instructed operation has been performed leads to confirmation of whether the reliability has improved. However, whether the reliability has improved depends on the magnitude of the effect or whether there is a delay, so here it is referred to as confirming whether the instructed operation has been performed. Furthermore, being able to detect white lines or center lines on the road, as in the above example, improves reliability and clarifies fixed points for position estimation, thereby contributing to improving the accuracy of position estimation.

[0115] As described above, according to the fifth embodiment, the same effects as those of the first embodiment can be achieved. That is, even if the vehicle itself does not have an expensive sensor such as a satellite positioning sensor, it is possible to estimate the vehicle position and angle with high accuracy based on the integrated environmental information transmitted from the position estimation device. The position estimation device according to the fifth embodiment includes a reliability calculation unit that calculates the reliability of each environment recognition device or each sensor included therein, and a reliability calculation unit that calculates the reliability of each environment recognition device or each sensor included therein. Tashin a reliability comparison unit that compares the reliability of the mobile unit and the mobile unit; and a verification operation instruction generation unit that generates an instruction for the mobile unit to perform a verification operation. confirmation The device further includes an operation confirmation unit that confirms whether an operation according to the instruction created by the operation instruction creation unit has been performed. When the confirmation operation instruction creation unit determines that the highest reliability value among the calculated reliability values ​​is smaller than a third reference value, the confirmation operation instruction creation unit creates a confirmation operation instruction to increase the reliability, and the operation confirmation unit confirms that the operation according to the instruction created by the confirmation operation instruction creation unit has been performed, and the reliability calculation unit recalculates the reliability. This improves the reliability and enables highly accurate position estimation.

[0116] Furthermore, since the reliability is improved, if the recognition unit 22 of the position estimation device 2 is equipped with a vehicle position prediction unit 224 that predicts the future position of the vehicle 3, as shown in embodiment 3, the prediction accuracy of the vehicle's future position is also further improved.

[0117] <Other embodiments> (1) A traffic control system 1 according to the present disclosure includes a position estimation device 2 according to any one of the first to fifth embodiments described above, an environment recognition device 4 installed on the roadside along a route traveled by the vehicle 3 and transmitting surrounding environment information X of the vehicle 3 to the position estimation device 2, and the vehicle 3 to be controlled. Communication is established at least between the position estimation device 2 and the environment recognition device 4, and between the position estimation device 2 and the vehicle 3. The position estimation device 2 receives surrounding environment information X from the environment recognition device 4, the surrounding environment information X including at least the position, attitude (direction, angle), and speed of the vehicle within the detection range S of the environment recognition device 4, generates integrated environment information Za from the surrounding environment information X, and transmits the integrated environment information Za to the vehicle. Therefore, even if the vehicle 3 itself does not have a device for measuring its own position, the vehicle 3 can obtain a highly accurate estimated position. Using this self-position information and information about obstacles and other factors along the travel route included in the integrated environment information Za, the vehicle 3 generates control signals for the vehicle's speed, handling, and the like via a control unit 32, and controls the operation of actuators that drive the vehicle, such as the brakes and steering.

[0118] If the vehicle 3 is capable of autonomous driving equivalent to level 3 or 4 as defined by the Society of Automotive Engineers (SAE International), for example, the vehicle 3 will be able to achieve the desired autonomous driving based on the integrated environmental information Za including its own position obtained from the position estimation device 2.

[0119] (2) In the first to fifth embodiments, the vehicle 3 is not equipped with a device for measuring its own position. However, the vehicle 3 may be equipped with an advanced self-position measuring device. By reducing the error of the self-position measuring device based on the integrated environmental information Za including the self-position acquired from the position estimation device 2, the vehicle can be controlled stably.

[0120] (3) The hardware configuration for realizing the position estimation device 2 according to embodiment 1 is illustrated in FIG. 4, but the hardware configuration for realizing the position estimation device 2 according to embodiments 2 to 5 is also similar to that illustrated in FIG. 4.

[0121] (4) In the traffic control system 1, wide-area communication and short-range communication are used as communication means. Wide-area communication is based on a predetermined wide-area wireless communication standard, such as LTE (Long Term Evolution), 4G, or 5G (5th Generation; fifth generation mobile communication system). Short-range communication is based on, for example, DSRC (Dedicated Short Range Communications), and although not described in the above embodiment, it can be used for communication with other vehicles (vehicle-to-vehicle communication) to obtain information about other vehicles around the vehicle. A certain communication speed is guaranteed for these communications. Communication between the environment recognition device 4 and the position estimation device uses, for example, LTE or 5G. Within the vehicle 3, they are connected using, for example, a Control Area Network (CAN: registered trademark) or the like.

[0122] (5) Although the mobile object to be controlled is an automobile, the application is not limited to automobiles, but can be applied to various other mobile objects. The traffic control system can be used as a system to control the behavior of mobile objects such as mobile robots that inspect the interior of buildings, line inspection robots, and personal mobility vehicles. When the mobile object is other than an automobile, environment recognition device The information to be acquired may be information from an obstacle information detection unit installed within a building, a line, or within the range in which the personal mobility moves.

[0123] Although the present application describes various exemplary embodiments and examples, the various features, aspects, and functions described in one or more embodiments are not limited to application to a particular embodiment, but may be applied to the embodiments alone or in various combinations. Therefore, countless variations not illustrated are conceivable within the scope of the technology disclosed in the present specification, including, for example, cases where at least one component is modified, added, or omitted, and cases where at least one component is extracted and combined with components of another embodiment.

[0124] Various aspects of the present disclosure are summarized below as appendices.

[0125] (Appendix 1) First moving object information including at least the position, angle, and speed of the moving object, and road information including at least white lines around the moving object and Contains Surrounding environment information an information receiving unit that receives information from a plurality of environmental information acquisition devices; The received neighborhood a recognition unit that integrates environmental information to create integrated environmental information including location information of the mobile object; The first moving body information and the road information received by the information receiving unit the surrounding area including an information recording unit that records environmental information and the integrated environmental information created by the recognition unit; and A position estimation device including an information transmission unit that transmits the integrated environmental information created by the recognition unit to the mobile body. (Appendix 2) The information receiving unit receiving second moving body information including at least a target route, a target vehicle speed, a position, and an attitude from the moving body; The recognition unit The aforementioned neighborhood a reliability calculation unit that calculates the reliability of each of the environmental information acquisition devices that has acquired the environmental information and the reliability of the second moving object information; and a reliability comparison unit that compares the calculated reliability; Equipped with picture, the reliability comparison unit selects the integrated environmental information or the second moving object information from the environmental information acquisition device having the highest reliability; 2. The position estimation device according to claim 1, wherein the information transmission unit transmits the information selected by the reliability comparison unit to the mobile object as the position information. (Appendix 3) The reliability comparison unit of the recognition unit A position estimation device as described in Appendix 2, which, when the highest reliability is smaller than a predetermined first reference value, creates correction information including at least the position information of the moving body and outputs it together with the integrated environmental information from the environmental information acquisition device having the selected highest reliability or the second moving body information. (Appendix 4) The recognition unit a vehicle position prediction unit that predicts a future position of the moving object; In the reliability comparison unit, when the highest reliability is equal to or greater than a first reference value set in advance, The position estimation device described in Appendix 3, wherein the vehicle position prediction unit predicts whether the future position of the moving body will match the target route based on any of the second moving body information, map information, and driving route history recorded in the information recording unit, and if it predicts that the future position of the moving body will not match the target route, creates correction information including at least the position information and angle of the moving body. (Appendix 5) The recognition unit The aforementioned neighborhood The information acquisition device further includes a reliability calculation unit that calculates the reliability of each of the environmental information acquisition devices that has acquired environmental information and the reliability of second moving object information, a reliability comparison unit that compares the calculated reliability, and a detection range change instruction creation unit that creates an instruction to change the detection range of the environmental information acquisition device, the reliability comparison unit compares whether the highest reliability among the calculated reliability is smaller than a second reference value; A position estimation device described in any one of appendix 1 to 4, wherein the detection range change instruction creation unit creates an instruction to change the detection range of the environmental information acquisition device when it is determined that the reliability is smaller than a second reference value. (Appendix 6) The recognition unit The aforementioned neighborhoodThe system further includes a reliability calculation unit that calculates the reliability of each of the environmental information acquisition devices that has acquired environmental information and the reliability of second moving body information, a reliability comparison unit that compares the calculated reliability, a confirmation operation instruction creation unit that creates an instruction for the moving body to perform a confirmation operation, and an operation confirmation unit that confirms whether the operation according to the instruction created by the confirmation operation instruction creation unit has been performed, the reliability comparison unit compares whether the highest reliability among the calculated reliability is smaller than a third reference value; the verification operation instruction creation unit creates a verification operation instruction to increase the reliability when it is determined that the reliability is smaller than a third reference value; The operation confirmation unit confirms that the operation according to the instruction created by the confirmation operation instruction creation unit has been performed, and 5. The position estimation device according to claim 1, wherein the reliability calculation unit recalculates the reliability. (Appendix 7) A traffic control system comprising: a position estimation device according to any one of Supplementary Note 1 to 6; a plurality of the environmental information acquisition devices; and the mobile body, wherein communication is performed between the position estimation device and the plurality of environmental information acquisition devices and between the position estimation device and the mobile body, The moving body is A traffic control system that acquires its own position based on the position information received from the position estimation device, and travels based on the integrated environmental information and its own position. [Explanation of symbols]

[0126] 1: traffic control system, 2: position estimation device, 21: information receiving unit, 22: recognition unit, 221: information integration unit, 222: reliability calculation unit, 223: reliability comparison unit, 224: vehicle position prediction unit, 225: detection range change instruction creation unit, 226: confirmation operation instruction creation unit, 227: operation confirmation unit, 23: information transmission unit, 24: information recording unit, 3: vehicle, 3b: other vehicle, 31: information receiving unit, 32: control unit, 33: self information acquisition unit, 34: dead reckoning unit, 35: information transmission unit, 4: environment recognition device, 41: environment information acquisition unit, 42: communication unit, 201: processor, 202: memory, 203: auxiliary storage device, 204: transmission device, 205: reception device, S: detection range, X: surrounding environment information, Y: Control object information, Za: Integrated environment information, Zb: Reliability information, Zc: Correction information, Zd: Detection range change information, Ze: Confirmation operation instruction.

Claims

1. an information receiving unit that receives, from a plurality of environment information acquisition devices, first moving body information including at least the position, angle, and speed of the moving body and surrounding environment information including road information including at least white lines around the moving body, and receives, from the moving body, second moving body information including at least a target route, a target vehicle speed, a position, and an attitude; a recognition unit that integrates the received surrounding environment information to create integrated environmental information including location information of the mobile body, calculates the reliability of each of the environmental information acquisition devices that acquired the surrounding environment information and the reliability of second mobile body information, compares the calculated reliabilities, and selects the integrated environmental information or the second mobile body information from the environmental information acquisition device having the highest reliability; an information recording unit that records the surrounding environment information including the first moving object information and the road information received by the information receiving unit and the integrated environment information created by the recognition unit; and a position estimation device including an information transmission unit that transmits the information selected by the recognition unit to the mobile body as the position information;

2. The recognition unit 2. The position estimation device of claim 1, wherein, when the highest reliability is smaller than a predetermined first reference value, correction information including at least the position information of the moving body is created and output together with the integrated environmental information or the second moving body information from the selected environmental information acquisition device having the highest reliability.

3. The recognition unit When the highest reliability is equal to or greater than a first reference value set in advance, 3. The position estimation device according to claim 2, wherein the device predicts whether the future position of the moving body will match the target route based on any of the second moving body information, map information, and driving route history recorded in the information recording unit, and if it predicts that the future position of the moving body will not match the target route, it creates correction information including at least the position information and angle of the moving body.

4. The recognition unit comparing whether the highest reliability among the calculated reliability is smaller than a second reference value; The position estimation device according to claim 1 , further comprising: a command to change the detection range of the environmental information acquisition device when it is determined that the highest reliability is smaller than the second reference value.

5. The recognition unit comparing whether the highest reliability among the calculated reliability is smaller than a third reference value; if it is determined that the highest reliability is smaller than the third reference value, creating a confirmation operation instruction to increase the reliability; Confirm that the operation according to the created confirmation operation instructions has been carried out, The location estimation device of claim 1 , further comprising: a step of recalculating the reliability.

6. 6. A traffic control system comprising: a position estimation device according to claim 1; a plurality of the environmental information acquisition devices; and the mobile body; wherein communication is performed between the position estimation device and the plurality of environmental information acquisition devices and between the position estimation device and the mobile body, The moving body is A traffic control system that acquires its own position based on the position information received from the position estimation device, and travels based on the integrated environmental information and its own position.

Images