Information processing device, information processing program, and information processing method

Abstract

This system allows for accurate prediction of the vehicle's condition at a predetermined time interval, based on the timestamp indicated by a sensor that measures the vehicle's status. [Solution] The information processing device (2) includes an acquisition unit (231) that acquires a status value indicating the state of a target vehicle (V1) along with a timestamp indicating the time when the state was measured; a prediction unit (232) that, upon receiving a status value, inputs the status value of the target vehicle to a prediction model (222) that calculates a predicted status value indicating the state after a predetermined time has elapsed from the time indicated by the timestamp corresponding to the status value, and obtains a predicted status value of the target vehicle calculated by the prediction model; and an output unit (21) that outputs information based on the predicted status value of the target vehicle. The prediction unit uses a model that takes into account errors related to the time interval of measurement by the sensor as the prediction model.

Description

[Technical Field]

[0001] This disclosure relates to an information processing device, an information processing program, and an information processing method. [Background technology]

[0002] Patent Document 1 describes a server comprising: an information receiving unit that receives location information and speed information of the first vehicle, information of detection results of unresponsive objects located on the road that do not respond to the second communication from the first vehicle, and information of measurement results of the location and speed of unresponsive objects from a first vehicle having a function to perform a first communication with a vehicle and a function to perform a second communication between the vehicle and a moving object; a vehicle information storage unit that stores the location information and speed information of the first vehicle, the information of detection results of unresponsive objects, and the information of measurement results of the location and speed of unresponsive objects received from the first vehicle; and an information processing unit that determines whether the unresponsive object is a vehicle or not based on the information of detection results of unresponsive objects, and if it is determined that the unresponsive object is a vehicle, stores the information of measurement results of the location and speed of the unresponsive object in the vehicle information storage unit as location information and speed information of a vehicle that does not support communication. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-160281 [Overview of the project] [Problems that the invention aims to solve]

[0004] There is variability in the time required (communication delay) for sensors to transmit measurement results to servers. Therefore, it is common practice for sensors to timestamp the measurement results, and for servers to make predictions based on the time indicated by the timestamp. However, with conventional technology, even using timestamps, it has been difficult to accurately predict the state at the same time the sensor actually measures. [Means for solving the problem]

[0005] The inventors of this disclosure focused on the uncertainty of timestamps, such as the resolution of the timestamps and the synchronization accuracy between the sensor and the server, as the reason why there are limitations to improving prediction accuracy even when using timestamps. The inventors then conceived the technical idea of ​​incorporating the uncertainty of timestamps into the process noise matrix, which led to this disclosure.

[0006] To solve the above problems, an information processing device according to one aspect of the present disclosure includes: an acquisition unit that acquires a status value indicating the state of a target vehicle along with a timestamp indicating the time when the state was measured; a prediction unit that, upon receiving a status value, inputs the status value of the target vehicle to a prediction model that calculates a predicted status value indicating the state after a predetermined time has elapsed from the time indicated by the timestamp corresponding to the status value, and obtains a predicted status value of the target vehicle calculated by the prediction model; and an output unit that outputs information based on the predicted status value of the target vehicle, wherein the prediction unit uses a model that takes into account errors related to the time interval of measurement by the sensor as the prediction model.

[0007] Furthermore, information processing programs in other aspects of this disclosure cause a computer to perform an acquisition process that acquires a status value indicating the state of a target vehicle along with a timestamp indicating the time when the state was measured; a prediction process that, when a status value is input, inputs the status value of the target vehicle into a prediction model that calculates a predicted status value indicating the state after a predetermined time has elapsed from the time indicated by the timestamp corresponding to the status value, and obtains the predicted status value of the target vehicle calculated by the prediction model; and an output process that outputs information based on the predicted status value of the target vehicle, wherein the prediction process uses a model that takes into account errors related to the time interval of measurement by the sensor as the prediction model.

[0008] Furthermore, an information processing method relating to another aspect of the present disclosure includes an acquisition step in which a computer acquires a status value indicating the state of a target vehicle, along with a timestamp indicating the time when the state was measured; a prediction step in which the computer inputs the status value of the target vehicle into a prediction model that calculates a predicted status value indicating the state after a predetermined time has elapsed from the time indicated by the timestamp corresponding to the status value, and obtains a predicted status value of the target vehicle calculated by the prediction model; and an output step in which the computer outputs information based on the predicted status value of the target vehicle, wherein in the prediction step, the computer uses a model that takes into account errors related to the time interval of measurement by the sensor as the prediction model. [Brief explanation of the drawing]

[0009] [Figure 1] This is a schematic diagram showing an example of the schematic configuration of an information provision system according to one embodiment of the present disclosure. [Figure 2] This is a schematic diagram showing another example of the system's general configuration. [Figure 3] An example of the functional configuration of the system is shown in block number. [Figure 4] This flowchart shows an example of the flow of an information provision method according to another embodiment of the present disclosure. [Modes for carrying out the invention]

[0010] <Information Provision System 100> The following describes in detail an information provision system 100 according to one embodiment of this disclosure.

[0011] [Configuration of Information Provision System 100] The information provision system 100 is a system for providing information about a target vehicle traveling on road R to other vehicles traveling on the same road R. As shown in Figure 1, the information provision system 100 comprises a sensor 1 and an information processing device 2. The information provision system 100 according to this embodiment further comprises a calculation device 3. The other vehicles are so-called connected cars configured to communicate with the information processing device 2. The target vehicle may be a connected car, or it may be a so-called unconnected car that does not have the function to communicate with the information processing device 2. The information provision system 100 may also have multiple sensors 1. Furthermore, the information processing device 2 may be located outside the vehicle or inside the vehicle.

[0012] [Sensor 1] The sensor 1 according to this embodiment is located outside the target vehicle V1. The sensor 1 according to this embodiment is located near the road R on which the target vehicle V1 travels. The vicinity of the road R includes, for example, the side of the road R, above the road R, and buildings, fences, etc. facing the road. The sensor 1 may also be installed as an on-board sensor on another vehicle V2 traveling on the road R on which the target vehicle V1 travels, as shown in Figure 2. Alternatively, the sensor 1 may be installed inside the target vehicle V1. The sensor 1 repeatedly detects the state of the target vehicle V1. The sensor 1 according to this embodiment is a LiDAR (Light Detection And Ranging) that detects the distance from the sensor 1 to the target vehicle V1. That is, the sensor 1 according to this embodiment detects the distance from the sensor 1 to the target vehicle V1. The sensor 1 may also be a camera, radar, etc. that photographs the target vehicle V1. If the information provision system 100 is equipped with multiple sensors 1, each sensor 1 may detect the state of the target vehicle V1, or some may detect the state of vehicles other than the target vehicle V1. In this embodiment, when the sensor 1 detects the state (distance) of the target vehicle V1, it transmits the detection result to the calculation device 3.

[0013] [Calculation device 3] The calculation device 3 includes a calculation unit 31. Based on the detection result of the sensor 1, the calculation unit 31 calculates a state value indicating the state of the target vehicle. The state value is a numerical value indicating the state of the target vehicle V1. As described above, the sensor 1 detects the distance from the sensor 1 to the target vehicle V1. Therefore, the calculation unit 31 according to this embodiment calculates at least one of the position, azimuth angle, speed, and vehicle length of the target vehicle V1 as the state value based on the distance. The calculation device 3 repeatedly calculates the state value. When the calculation device 3 calculates the state value, it transmits the state value to the information processing device 2. Note that the calculation unit 31 may be provided in the sensor 1 or in the information processing device 2. In this case, the information providing system 100 may not include the calculation device 3.

[0014] 〔Information processing device 2〕 As shown in FIG. 3, the information processing device 2 includes a communication unit 21, a storage unit 22, and an arithmetic unit 23.

[0015] 〔Communication unit 21〕 The communication unit 21 communicates with the calculation device 3. The communication unit 21 according to this embodiment also communicates with a vehicle having a communication function. The communication unit 21 according to this embodiment is composed of a communication module. Note that the communication unit 21 may be configured to communicate with the sensor 1.

[0016] 〔Storage unit 22〕 The storage unit 22 stores an information processing program 221. The information processing program 221 is a program that causes a computer to function as the information processing device 2. The storage unit 22 according to this embodiment stores a prediction model 222. Details of the prediction model 222 will be described later. Also, the storage unit 22 can store various calculation results (such as predicted state values) of the arithmetic unit 23. The storage unit 22 according to this embodiment is composed of a semiconductor memory, a hard disk drive, etc. Note that the storage unit 22 may be physically separated for each content to be stored (information processing program 221, prediction model 222, calculation result). <​​​​The arithmetic unit 23 includes an acquisition unit 231 and a prediction unit 232. The arithmetic unit according to this embodiment further includes a generation unit 233, a determination unit 235, a correction unit 236, and an output processing unit 237. The arithmetic unit 23 according to this embodiment is constituted by a processor (the information processing apparatus 2 is constituted by a computer). Therefore, the functions of each control block 231 to 237 are realized by the arithmetic unit 23 executing acquisition processing, prediction processing, generation processing, determination processing, and output processing in accordance with the information processing program 221 stored in the storage unit 22.

[0018] (Acquisition Unit 231) The acquisition unit 231 executes acquisition processing. In the acquisition processing, the acquisition unit 231 acquires, from the sensor 1, a state value indicating the state of the target vehicle together with a time stamp indicating the time when the state was measured. The acquisition unit 231 according to this embodiment acquires the state value received by the communication unit 21 from the calculation device 3 each time the calculation device 3 transmits the state value. When a plurality of received state values are accumulated in the queue, the acquisition unit 231 acquires them in order from the state value with the oldest time indicated by the time stamp. Further, the acquisition unit 231 according to this embodiment acquires a second state value from an in-vehicle sensor provided in a vehicle traveling on the road R on which the target vehicle V1 travels each time the in-vehicle sensor transmits the second state value. When a plurality of received second state values are accumulated in the queue, the acquisition unit 231 acquires them in order from the second state value with the oldest time indicated by the time stamp. The second state value is a numerical value indicating the state of the target vehicle V1. The vehicle in which the in-vehicle sensor is provided may be the target vehicle V1 or another vehicle V2. The second state value acquired by the acquisition unit 231 according to this embodiment includes the position (coordinates) of another vehicle V2.

[0019] (Prediction Unit 232) The prediction unit 232 executes prediction processing. In the prediction processing, the prediction unit 232 inputs the state value of the target vehicle V1 to the prediction model 222 to obtain the predicted state value of the target vehicle V1 calculated by the prediction model 222. The prediction unit 232 obtains the predicted state value each time the acquisition unit 231 acquires the state value.

[0020] The prediction model 222 is designed to calculate a predicted state value that indicates the state after a predetermined time (time step) has elapsed from the time indicated by the timestamp corresponding to the given state value, once a state value has been input. The predetermined time can be, for example, the elapsed time from the measurement of the state corresponding to the given state value to the measurement of the state corresponding to the next state value. In this way, by having the prediction model 222 calculate a predicted state value that indicates the state after a predetermined time has elapsed from the measurement time, rather than from the acquisition time, the effect of delay between the measurement time and the acquisition time can be eliminated from the prediction. As a result, the generation unit 233, which will be described later, will be able to reproduce a digital twin with higher accuracy.

[0021] Specifically, the prediction model 222 is a model that takes into account errors related to the time interval of measurements by the sensor. In this embodiment, the prediction model 222 is a model that takes into account errors based on the time resolution of the sensor or time synchronization errors as errors related to the time interval. Specifically, as shown in Figure 4, the prediction model 222 in this embodiment has a state equation that describes the state of the target vehicle V1 and includes a term for a process noise matrix (Q') that defines the amount of process noise.

[0022] The process noise matrix (Q') can be obtained as follows. First, for the state vector x, we set the vector x', which is coupled with the time step Δt, as shown in equation (1) below.

number

number

number

number

number

[0023] The prediction model 222 includes a noise component (σ) representing the error in the process noise matrix. Δt 2 This noise component includes the variance (σ) of the time step (Δt=(t2+δt2)-(t1+δt1):δt1,δt2 are random variables). Δt 2 Specifically, the noise component (variance) according to the embodiment is expressed by the following equation (6). However, it is assumed that δt1 and δt2 each follow different independent probability distributions.

number

[0024] The variance is the error δ related to the time interval of measurement by sensor 1. ti The contents of (i=1,2), that is, different values ​​are defined depending on which sensor 1 the information processing device 2 is communicating with. For example, the timestamp resolution (r t If the value of ) is relatively low and this is causing errors, the variance is determined based on the timestamp resolution of sensor 1. Specifically, Var(δt) in equation (6) above i ) can be expressed as shown in equation (7) below.

number

[0025] On the one hand, when the synchronization accuracy between the sensor 1 and the information processing device 2 is low (for example, there is a deviation between the timer of the sensor 1 and the timer of the information processing device 2, etc.) and an error occurs due to this, the dispersion is defined based on the standard deviation (σ t ) of the time synchronization with the sensor. Specifically, Var(δt i ) in the above formula (6) is expressed as the following formula (8).

Equation

[0026] Note that Var(δt i ) in the above formula (6) may be the sum, maximum value, or weighted average of the value on the right side of formula (7) and the value on the right side of formula (8). Also, the prediction model 222 may be configured to output, as a predicted state value, a numerical value indicating the state after a predetermined time has elapsed since the acquisition of the state value by the acquisition unit 231 described later. Further, the prediction model 222 may be stored in another storage device (not shown) different from the information processing device 2.

[0027] As described above, the acquisition unit ings the second state value. Therefore, the prediction unit 232 according to the present embodiment inputs the state value and the second state value associated with the state value into the prediction model 222 to obtain the predicted state value of the target vehicle V1 calculated by the prediction model 222. Note that the prediction unit 232 may be configured to input only the second state value into the prediction model 222 to obtain the predicted state value calculated by the prediction model 222.

[0028] When the acquisition unit 231 acquires a status value, the prediction unit 232 inputs the status value from the previous cycle (most recent) among the status values ​​held by the information processing device 2 up to that point into the prediction model 222 configured as described above, and obtains a predicted status value at the time the status value was acquired. When attempting to reproduce multiple target vehicles V1, or target vehicle V1 and other vehicles V2, in a single digital twin, the prediction unit 232 inputs the status values ​​(second status values) acquired from each vehicle V1 and V2 into the prediction model to obtain predicted status values ​​for each vehicle V1 and V2. In this case, the time of the corrected predicted status value is generally different for each vehicle. Therefore, in order to reproduce multiple target vehicles V1, or target vehicle V1 and other vehicles V2, in a single digital twin, it is necessary to synchronize the time of the predicted status value of each vehicle with the time of the digital twin. Accordingly, in such cases, the prediction model 222 according to this embodiment sets a predetermined time to the elapsed time from each time indicated by the status value of each vehicle to the time of the digital twin.

[0029] (Judgment Department 235) Each time the acquisition unit 231 acquires a status value, the determination unit 235 determines whether there is a correspondence between the newly acquired status value and the latest predicted status value calculated by the prediction model 222. The determination of whether there is a correspondence includes at least one of the following: whether the ID of the status value is the same as the ID of the predicted status value, and whether the distance (Euclidean distance, Mahalanobis distance, etc.) between the position of the target vehicle V1 indicated by the status value and the position of the target vehicle V1 indicated by the predicted status value is less than a threshold. If the determination unit 235 determines that there is a correspondence between the status value and the predicted status value, it then associates the new status value with the latest predicted status value. As described above, the acquisition unit 231 further acquires a second status value. Therefore, in this embodiment, each time the acquisition unit 231 acquires a second status value, the determination unit 235 also determines whether there is a correspondence between the newly acquired second status value and the latest predicted status value. Then, if the determination unit 235 determines that there is a correspondence between the second state value and the predicted state value, it also associates the new second state value with the latest predicted state value. On the other hand, if the determination unit 235 determines that there is no correspondence between the state value (second state value) and the predicted state value, it determines that the vehicle that transmitted the newly acquired state value is a new vehicle that was not previously targeted.

[0030] (Correction section 236) The correction unit 236 corrects the predicted state value associated with the state value based on the state value so that it approaches (matches) the state value. At the same time, the correction unit 236 also corrects the timestamp of the predicted state value so that it approaches (matches) the timestamp of the state value. In this embodiment, the correction unit 236 performs the correction using a Kalman filter. The correction unit 236 may be configured to adjust the degree of correction taking into account the reliability of the state value. The reliability can be set based on the characteristics of the sensor 1. Furthermore, the correction of the predicted state value may be performed by a device other than the information processing device 2. In this case, the calculation unit 23 does not need to include the correction unit 236.

[0031] (Generation unit 233) The generation unit 233 executes a generation process. In the generation process, the generation unit 233 generates a digital twin in a virtual space that reproduces the target vehicle V1 and its surrounding environment after a predetermined time has elapsed since the measurement of the state corresponding to the state value, based on the predicted state value. The generation unit 233 generates a digital twin each time the prediction model 222 generates a predicted state value. In this embodiment, the generation unit 233 generates a digital twin based on the predicted state value generated by the prediction model 222 and corrected by the correction unit 236. Note that the generation of the digital twin may be performed by a device other than the information processing device 2. In this case, the calculation unit 23 does not need to include the generation unit 233.

[0032] (Output processing unit 237) The output processing unit 237 performs output processing. In output processing, the output processing unit 237 according to this embodiment controls the communication unit 21. As a result, the communication unit 21 transmits (outputs) information based on the predicted state value of the target vehicle V1 to at least another vehicle V2. In other words, the communication unit 21 according to this embodiment also functions as an output unit. The information based on the predicted state value includes the digital twin generated by the generation unit 233. The output processing unit 237 may also be configured to transmit the information based on the predicted state value to something other than the other vehicle V2 (the target vehicle V1, a remote monitoring device, etc.). Furthermore, if the information processing device 2 is installed inside the vehicle, the output processing unit 237 may also be configured to supply the information based on the predicted state value to the vehicle's display unit, etc. In this case, the terminals, etc., connected to the vehicle in the information processing device become the output unit.

[0033] [Effects of the Information Processing Device 2 (Information Provisioning System 100)] The information processing device 2 (information providing system 100) described above uses a prediction unit 232 that takes into account errors related to the time interval of measurement by sensor 1 as the prediction model 222. As a result, the predicted state value absorbs the error that occurred between the timestamp and the actual measurement time. Therefore, according to the information processing device 2 (information providing system 100), the state after a predetermined time can be accurately predicted from the time indicated by the timestamp attached by sensor 1 that measures the state of the target vehicle V1. Note that the problem of errors occurring between the timestamp and the actual measurement time is particularly likely to occur when there are multiple sensors 1. Therefore, the information processing device 2 (information providing system 100) is even more effective when there are multiple sensors 1. Furthermore, according to the information processing device 2 (information providing system 100), more accurate prediction is possible, especially when the error in the timestamp is large compared to the driving speed of the target vehicle V1.

[0034] By using this disclosure, safer autonomous driving technologies (autonomous vehicles, control devices, remote monitoring devices, etc.) can be realized. Therefore, by using this disclosure, it is possible to contribute to achieving Sustainable Development Goals (SDGs) such as Goal 9 "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation" and Goal 11 "Make cities and human settlements inclusive, safe, resilient and sustainable."

[0035] <Information Processing Method S100> Next, an information processing method S100 according to another embodiment of the present disclosure will be described in detail.

[0036] [Flow of Information Processing Method S100] As shown in Figure 4, the information processing method S100 includes an acquisition step S1, a prediction step S2, and an output step S3. The information processing method S100 according to this embodiment further includes a generation step S4, a first decision step S6, a correction step S7, and a second decision step S8.

[0037] [Acquisition Step S1] In the initial acquisition step S1, the computer acquires a status value indicating the state of the target vehicle, along with a timestamp indicating the time when the state was measured. In the acquisition step S1 according to this embodiment, the computer further acquires a second status value from an on-board sensor installed on a vehicle traveling on the road R on which the target vehicle V1 is traveling. The computer that acquires the status value may be the information processing device 2 described above, or it may be another device.

[0038] [Prediction Step S2] After acquiring the status value, the process moves to prediction step S2. In prediction step S2, the computer inputs the status value of the target vehicle V1 into the prediction model 222 and obtains the predicted status value of the target vehicle V1 calculated by the prediction model 222. In prediction step S2, the computer uses a model as the prediction model 222 that takes into account errors related to the time interval of measurements by the sensor. As described above, in acquisition step S1, a second status value is acquired. Therefore, in prediction step S2 according to this embodiment, the computer inputs the status value and the second status value associated with the status value into the prediction model 222 and obtains the predicted status value of the target vehicle V1 calculated by the prediction model 222. The computer that obtains the predicted status value may be the information processing device 2 or another device.

[0039] [First decision step S6] After acquiring the status value, the process moves to the first decision step S6. In the first decision step S6, each time the computer acquires a status value in the acquisition step S1, it determines whether there is a correspondence between the newly acquired status value and the latest predicted status value calculated by the prediction model 222. If it determines that there is a correspondence between the status value and the predicted status value (step S6: YES), the computer performs the association between the new status value and the latest predicted status value. As described above, in the acquisition step S1, the computer acquires a second status value. Therefore, each time the second status value is acquired in the acquisition step S1, in the first decision step S6 according to this embodiment, the computer also determines whether there is a correspondence between the newly acquired second status value and the latest predicted status value. If it determines that there is a correspondence between the second status value and the predicted status value, the computer also performs the association between the new second status value and the latest predicted status value. The computer performing the association may be the information processing device 2 or another device.

[0040] On the other hand, if in the first judgment step S6 it is determined that there is no correspondence between the newly acquired status value and the latest predicted status value (the newly acquired status value could not be associated with the latest predicted status value) (step S6: NO), the computer determines that the vehicle that transmitted the newly acquired status value is a new vehicle that had not been targeted before. In this case, the computer starts the information processing method (steps S1 to S8) for the target vehicle V1 for the new vehicle. After determining in the first judgment step S6 that there is no correspondence between the status value and the predicted status value, it may further determine whether the determination that there is no correspondence has been repeated a predetermined number of times. If it is determined that the determination that there is no correspondence has been repeated a predetermined number of times, the computer may determine that the vehicle that transmitted the newly acquired status value is a new vehicle that had not been targeted before.

[0041] [Correction step S7] After associating the state value with the predicted state value, the process moves to correction step S7. In correction step S7, the computer corrects the predicted state value associated with the state value based on the state value so that it approaches (matches) the state value. At the same time, in correction step S7, the timestamp of the predicted state value is also corrected so that it approaches (matches) the timestamp of the state value. The computer that corrects the predicted state value may be the information processing device 2 described above, or it may be another device.

[0042] [Generation Step S4] After obtaining the predicted state values, the process moves to generation step S4. In generation step S4, the computer generates a digital twin in virtual space that reproduces the target vehicle V1 and its surrounding environment after a predetermined time has elapsed since the measurement of the state corresponding to the state value, based on the predicted state values. In generation step S4, a digital twin is generated each time the prediction model 222 generates predicted state values. In generation step S4 according to this embodiment, the digital twin is generated based on the predicted state values ​​generated by the prediction model 222 and corrected in correction step S7. The computer that generates the digital twin may be the information processing device 2 or another device.

[0043] [Output step S3] After obtaining the predicted state value, the process moves to output step S3. In output step S3, the computer outputs information based on the predicted state value of the target vehicle V1. In output step S3 according to this embodiment, the computer transmits information based on the predicted state value of the target vehicle V1 (digital twin, information indicating that collision avoidance action will be taken, etc.) to at least another vehicle V2. The computer that outputs the information based on the predicted state value may be the information processing device 2 described above, or it may be another device. In addition, in output step S3, the information based on the predicted state value may be output to something other than the other vehicle V2 (target vehicle V1, remote monitoring device, etc.).

[0044] [Second decision step S8] After outputting information based on the predicted state values, the process moves to the second decision step S8. In the second decision step S8, the computer determines whether it is necessary to continue generating the predicted state values ​​for the target vehicle V1. If it determines that it is not necessary to continue (step S8: NO), the information processing method S100 ends. On the other hand, if it determines that it is necessary to continue (step S8: YES), the process returns to step S1. The computer that determines whether to continue or not may be the information processing device 2 or another device.

[0045] [Effects and Effects of Information Processing Method S100] According to the information processing method S100 described above, similar to the information processing device 2 (information provision system 100), it is possible to accurately predict the state of the target vehicle V1 after a predetermined time from the time indicated by the time stamp attached by the sensor 1 that measures the state of the target vehicle V1.

[0046] <Variation> This disclosure is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of this disclosure.

[0047] For example, the predicted state value generated by the prediction unit 232 may include acceleration. In that case, the calculation unit 23 may include another determination unit that performs a determination process if there is another vehicle V2 traveling in the same direction as the target vehicle V1 in front of the target vehicle V1. In the determination process, the other determination unit determines, based on the acceleration (predicted state value), whether or not there is a possibility that the target vehicle V1 will rear-end the other vehicle V2. If the other determination unit determines that there is a possibility that the target vehicle V1 will rear-end the other vehicle V2, the output unit may output information indicating that it will take action to avoid the collision.

[0048] Furthermore, the above-mentioned information processing program may be recorded on one or more computer-readable recording media, rather than on a temporary basis. Each unit may or may not have such recording media. In the latter case, the information processing program may be supplied to each unit via any wired or wireless transmission medium.

[0049] Furthermore, some or all of the functions of each control block 231 to 237 provided by the above-mentioned arithmetic unit can also be realized by logic circuits. For example, an integrated circuit in which logic circuits functioning as each control block 231 to 235 are formed is also included in the scope of this disclosure. In addition, it is also possible to realize the functions of each part by, for example, a quantum computer.

[0050] <Summary> The information processing device according to Embodiment 1 of the present disclosure includes: an acquisition unit that acquires a status value indicating the state of a target vehicle along with a timestamp indicating the time when the state was measured; a prediction unit that, upon receiving a status value, inputs the status value of the target vehicle into a prediction model that calculates a predicted status value indicating the state after a predetermined time has elapsed from the time indicated by the timestamp corresponding to the status value, and obtains a predicted status value of the target vehicle calculated by the prediction model; and an output unit that outputs information based on the predicted status value of the target vehicle, wherein the prediction unit uses a model that takes into account errors related to the time interval of measurement by the sensor as the prediction model.

[0051] The information processing device according to Embodiment 2 of the present disclosure may be configured such that, in Embodiment 1 above, the prediction unit has a state equation that describes the state of the target vehicle, and includes a term for a process noise matrix that defines the amount of process noise, and the components of the process noise matrix include a noise component that represents the error.

[0052] The information processing device according to aspect 3 of this disclosure may be configured such that, in aspect 2 above, the noise component is the dispersion over a predetermined time and is defined based on the timestamp resolution of the sensor.

[0053] The information processing device according to aspect 4 of this disclosure may be configured such that, in aspect 2 above, the noise component is the variance over a predetermined time and is defined based on the standard deviation of time synchronization with the sensor.

[0054] The information processing device according to aspect 5 of the present disclosure may be configured such that, in any of aspects 1 to 4 described above, the acquisition unit acquires a second state value indicating the state of the target vehicle from an on-board sensor provided on a vehicle traveling on a road on which the target vehicle is traveling, and the prediction unit inputs the state value and the second state value to the prediction model to obtain a predicted state value of the target vehicle calculated by the prediction model.

[0055] The information processing program according to aspect 6 of this disclosure is configured to cause a computer to perform an acquisition process that acquires a status value indicating the state of a target vehicle along with a timestamp indicating the time when the state was measured; a prediction process that, when a status value is input, inputs the status value of the target vehicle into a prediction model that calculates a predicted status value indicating the state after a predetermined time has elapsed from the time indicated by the timestamp corresponding to the status value, and obtains a predicted status value of the target vehicle calculated by the prediction model; and an output process that outputs information based on the predicted status value of the target vehicle, wherein in the prediction process, a model that takes into account errors related to the time interval of measurement by the sensor is used as the prediction model.

[0056] An information processing method according to aspect 7 of the present disclosure includes: an acquisition step in which a computer acquires a status value indicating the state of a target vehicle, along with a timestamp indicating the time when the state was measured; a prediction step in which the computer inputs the status value of the target vehicle into a prediction model that calculates a predicted status value indicating the state after a predetermined time has elapsed from the time indicated by the timestamp corresponding to the status value, and obtains a predicted status value of the target vehicle calculated by the prediction model; and an output step in which the computer outputs information based on the predicted status value of the target vehicle, wherein in the prediction step, the computer uses a model that takes into account errors related to the time interval of measurement by the sensor as the prediction model. [Explanation of Symbols]

[0057] 100 Information Provision System 1 sensor 2. Information Processing Device 21. Communication section (output section) 22 Memory section 221 Information Processing Programs 222 Predictive Models 23 Arithmetic section 231 Acquisition Department 232 Prediction Section 233 Generation part 235 Judgment Department 236 Correction section 237 Output Processing Unit 3. Calculation device 31 Calculation Section S100 Information Processing Method S1 Acquisition Steps S2 Prediction Step S3 Output Step S4 Generation Step S6 First Decision Step S7 Correction Step S8 Second Decision Step V1 Applicable Vehicles V2 Other vehicles

Claims

1. An acquisition unit that acquires a status value indicating the status of the target vehicle, along with a timestamp indicating the time when the status was measured, When a status value is input, the prediction unit inputs the status value of the target vehicle to a prediction model that calculates a predicted status value indicating the state after a predetermined time has elapsed from the time indicated by the timestamp corresponding to the status value, and obtains the predicted status value of the target vehicle calculated by the prediction model. An output unit that outputs information based on the predicted status values ​​of the target vehicle, Equipped with, The prediction unit uses a model that takes into account errors related to the time interval of measurements by the sensor as the prediction model. Information processing device.

2. The prediction unit uses the following prediction model: A state equation describing the state of the subject vehicle, the state equation having a term for a process noise matrix that defines the amount of process noise, The components of the process noise matrix include a noise component representing the error, Using a model, The information processing apparatus according to claim 1.

3. The aforementioned noise component is The distribution over the predetermined time is as follows: The timestamp resolution of the aforementioned sensor is defined as follows: The information processing apparatus according to claim 2.

4. The aforementioned noise component is The distribution over the predetermined time is as follows: This is defined based on the standard deviation of time synchronization with the aforementioned sensor. The information processing apparatus according to claim 2.

5. The acquisition unit acquires a second status value indicating the status of the target vehicle from an on-board sensor installed on a vehicle traveling on the road on which the target vehicle is traveling. The prediction unit inputs the state value and the second state value into the prediction model to obtain the predicted state value of the target vehicle calculated by the prediction model. The information processing apparatus according to claim 1.

6. On the computer, An acquisition process that obtains a status value indicating the state of the target vehicle, along with a timestamp indicating the time when that state was measured, When a status value is input, a prediction process is performed to input the status value of the target vehicle into a prediction model that calculates a predicted status value indicating the state after a predetermined time has elapsed from the time indicated by the timestamp corresponding to the status value, and to obtain the predicted status value of the target vehicle calculated by the prediction model. Output processing that outputs information based on the predicted status values ​​of the aforementioned target vehicle, Make it run, In the prediction process, the prediction model used is one that takes into account errors related to the time interval of measurements by the sensor. Information processing program.

7. The computer acquires a status value indicating the state of the target vehicle, along with a timestamp indicating the time when that state was measured. A prediction step in which a computer inputs a status value, inputs the status value of the target vehicle into a prediction model that calculates a predicted status value indicating the state after a predetermined time has elapsed from the time indicated by the timestamp corresponding to the status value, and obtains the predicted status value of the target vehicle calculated by the prediction model. The computer outputs information based on the predicted state values ​​of the target vehicle in an output step, Includes, In the prediction step, the computer uses a model as the prediction model that takes into account errors related to the time interval of measurements by the sensor. Information processing methods.

Images