Information processing device

Abstract

To provide an information processing device which performs optimal vehicle deceleration control according to surrounding conditions.SOLUTION: An information processing device 100 that generates information about driving of a vehicle comprises a control unit 110 that executes periodic estimation of factors that cause a first vehicle 200 to stop on the basis of information collected from a second vehicle preceding the first vehicle, determination regarding whether or not the first vehicle 200 needs to stop and determination of the stop position, and generation of a driving plan including a deceleration pattern for stopping the first vehicle 200 at the stop position when it is determined that the first vehicle 200 needs to stop at the stop position, and the control unit 110 sets an estimation period to be shorter when the confidence level of the estimation is lower.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to driving assistance for vehicles.

Background Art

[0002] Numerous technologies related to driving assistance for vehicles are known. In this regard, for example, Patent Document 1 discloses a driving assistance device that determines whether a dangerous driving state exists when entering an intersection based on the distance to the intersection, the speed of the vehicle, and signal information, and when it is determined that the vehicle is in a dangerous driving state and should be stopped, identifies the time period for performing regenerative braking driving or coasting driving.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] With the development of machine learning, it is considered that the utilization of driving assistance technologies based on the analysis of data collected from vehicles will increase even more in the future.

[0005] An object of the present disclosure is to perform optimal deceleration control of a vehicle according to the surrounding situation.

Means for Solving the Problems

[0006] One aspect of an embodiment of the present disclosure is An information processing device for generating information related to the operation of a vehicle, comprising a control unit that periodically estimates the factors causing the first vehicle to stop based on information collected from a second vehicle preceding the first vehicle, determines whether the first vehicle needs to stop and where it will stop based on the results of the estimation, and, if it is determined that the first vehicle needs to stop at the stopping position, generates an operation plan including a deceleration pattern for the first vehicle to stop at the stopping position, wherein the control unit sets the estimation period to be shorter when the confidence level of the estimation is lower.

[0007] Other embodiments include a method performed by the above-mentioned device, a program for causing a computer to perform the method, or a computer-readable storage medium that non-temporarily stores the program. [Effects of the Invention]

[0008] According to this disclosure, optimal deceleration control of the vehicle can be performed in accordance with the surrounding conditions. [Brief explanation of the drawing]

[0009] [Figure 1] A conceptual diagram of the processes performed by an information processing device. [Figure 2] A diagram illustrating the components of a system including an information processing device according to an embodiment. [Figure 3] A flowchart of the estimation process executed by the control unit of the information processing device according to the embodiment. [Figure 4] A flowchart of the process for stopping the first vehicle, which is executed by the control unit 110 of the information processing device 100 according to the embodiment. [Figure 5] A flowchart of the process for updating a master pattern based on confidence level, which is performed by the control unit 110 of the information processing device 100 according to the embodiment. [Modes for carrying out the invention]

[0010] To achieve fuel-efficient driving, driver assistance systems are known that help the vehicle decelerate in accordance with the conditions of the intersection ahead.

[0011] For example, consider a scenario where information about traffic signals is received from beacons installed at intersections, and vehicle deceleration control is performed accordingly. For instance, if a stop is expected, such as when the traffic light ahead is red, acceleration can be cut off in advance, increasing coasting and improving fuel efficiency and electric energy consumption. However, in this case, in areas where beacons are not installed, it is not possible to receive information necessary for deceleration control, such as information regarding traffic signals, and therefore vehicle deceleration control cannot be performed. To achieve fuel-efficient driving, it is desirable to be able to control vehicle deceleration without being restricted by location, even outside of specific locations such as intersections.

[0012] For this reason, systems have been devised that predict the surrounding situation and determine whether or not to stop based on information received from other vehicles, rather than beacons installed at intersections, etc. For example, if there are many vehicles stopped at the intersection ahead, it can be predicted that a stop due to a red light will occur.

[0013] However, this approach has the drawback of lower prediction accuracy compared to using beacons. To improve prediction accuracy, it would be necessary to communicate with more vehicles and more frequently, but this would lead to another problem: increased communication costs. This disclosure solves this problem by adaptively estimating the factors causing vehicle stopping in response to prediction uncertainty.

[0014] An information processing device according to one aspect of the present disclosure is an information processing device for generating information relating to the operation of a vehicle, and includes a control unit that periodically estimates the factors causing the first vehicle to stop based on information collected from a second vehicle preceding a first vehicle, determines whether the first vehicle needs to stop and where it will stop based on the results of the estimation, and, if it is determined that the first vehicle needs to stop at the stopping position, generates a driving plan including a deceleration pattern for the first vehicle to stop at the stopping position, wherein the control unit sets the estimation period to be shorter when the confidence level of the estimation is lower.

[0015] The first vehicle is the vehicle for which the information processing device provides driving assistance or control. The information processing device estimates the factors that cause the first vehicle to stop and, based on the estimation results, generates a driving plan that includes the optimal deceleration pattern for the first vehicle. By applying such a driving plan to the first vehicle, unnecessary acceleration can be eliminated or deceleration can be initiated at the appropriate timing.

[0016] The second vehicle is a vehicle that travels ahead of the first vehicle. The second vehicle has communication capabilities and can transmit information regarding its own driving status to an information processing device.

[0017] The control unit periodically estimates the factors that would cause the first vehicle to stop, based on information collected from the second vehicle that precedes the first vehicle. Based on the estimation results, it determines whether the first vehicle needs to stop and where it should stop. If it is determined that the first vehicle needs to stop at the stopping position, it generates a driving plan that includes a deceleration pattern for the first vehicle to stop at the stopping position.

[0018] The factors for the first vehicle to stop are, for example, a red traffic light or traffic congestion. The stop position is, for example, a stop line at an intersection, the end of a vehicle queue stopped at a red traffic light, or the end of a vehicle queue stopped due to traffic congestion. The stop position may be a relative position based on the first vehicle, or may be an absolute position represented by latitude and longitude information. The deceleration pattern is, for example, a representation of the relationship between the speed of the first vehicle and the elapsed time (or travel distance). The deceleration pattern may be composed of a plurality of periods such as a period of deceleration and a period of coasting.

[0019] Furthermore, when the confidence level in estimating the factor for the vehicle to stop is lower, the control unit sets a shorter estimation period. As a result, the estimation of the stop factor can be performed based on newer information, and the estimation accuracy can be improved. With such a configuration, in an apparatus for estimating the stop factor based on information collected from the second vehicle, it is possible to reduce the costs associated with communication and processing.

[0020] In addition, the information processing device may store a master pattern, which is an ideal deceleration pattern to the stop position, in association with the geographical position of the stop position. Then, the control unit may generate a driving plan using the master pattern corresponding to the geographical position of the determined stop position.

[0021] Thereby, for example, the information processing device can generate a driving plan using a deceleration pattern according to the characteristics of the location. Therefore, the information processing device can generate a driving plan for appropriate deceleration control of the vehicle according to the location where the first vehicle travels.

[0022] In addition, the control unit may update the master pattern corresponding to the stop position based on the actual deceleration data representing the actual deceleration state of the first vehicle during the target period of the generated driving plan and the confidence level in the estimation during the target period of the driving plan.

[0023] The control unit may update the master pattern using actual deceleration data. In this case, the control unit may adjust the weights of the actual deceleration data according to the confidence level of the estimation. Furthermore, when updating the master pattern, the control unit may reduce the weight of the actual deceleration data as the confidence level of the estimation decreases.

[0024] This allows the information processing device to adjust the magnitude of the influence of actual deceleration data on the generation of the driving plan, depending on the confidence level of the estimation. Therefore, the information processing device can generate a driving plan for vehicle deceleration control that is more in line with reality.

[0025] If the speed of the first vehicle indicated by the deceleration pattern included in the generated driving plan deviates from the actual speed of the first vehicle by a predetermined value or more, the control unit may set the estimation period to be shorter than when the speed of the first vehicle indicated by the deceleration pattern does not deviate from the actual speed of the first vehicle by a predetermined value or more.

[0026] If the driving pattern anticipated in the driving plan differs from the actual driving pattern, it is possible that there is an error in the estimation of the stopping factors. In such cases, the estimation period may be set to a shorter duration, similar to when the confidence level of the estimation is low. This allows the information processing device to generate a more realistic driving plan for vehicle deceleration control.

[0027] The following describes specific embodiments of this disclosure with reference to the drawings. Unless otherwise specified, the hardware configurations, module configurations, functional configurations, etc., described in each embodiment are not intended to limit the technical scope of the disclosure to those configurations alone.

[0028] (First embodiment) An overview of the processing performed by the information processing device according to this embodiment will be explained with reference to Figure 1. Figure 1 is a conceptual diagram of the processing performed by the information processing device 100. In this embodiment, the information processing device 100 communicates with the first vehicle 200 and generates a driving plan for deceleration control of the first vehicle 200. In addition, in order to generate the driving plan, the information processing device 100 also communicates with the second vehicle 300, which is a vehicle that is traveling ahead of the first vehicle 200, and collects information regarding the driving status of the second vehicle 300 (hereinafter referred to as driving data).

[0029] The following is an overview of the processing performed by the information processing device 100. First, the information processing device 100 estimates the cause of the first vehicle 200 stopping. In this embodiment, the cause of the first vehicle 200 stopping is a traffic signal (specifically, a red light). The information processing device 100 periodically communicates with the second vehicle 300 (there may be multiple vehicles) that is traveling ahead of the first vehicle 200 and acquires driving data from the second vehicle 300. Then, based on the driving data acquired from the second vehicle 300, the information processing device 100 estimates the state of the traffic signal 400 (the color of the illuminated lights, etc.) (corresponding to (1) signal estimation in Figure 1).

[0030] For example, the information processing device 100 may estimate the time when the traffic light 400 turned green based on the time when the second vehicle 300, which had been stopped, started moving. Alternatively, if some of the second vehicles 300 passing through the intersection stopped at the intersection, the information processing device 100 may estimate the time when the traffic light 400 turned red based on the time when those vehicles stopped. If there are multiple second vehicles 300, the time when the lights of the traffic signal 400 changed may be estimated based on the time when each vehicle started moving and stopped.

[0031] Based on the estimation of the traffic light 400 described above, the information processing device 100 can estimate the cycle of the traffic light 400's lights, etc. For example, the information processing device 100 may perform a process to estimate the cycle of the traffic light 400's lights up to 30 minutes ahead, at 5-minute intervals, based on information regarding the driving status of the second vehicle 300 over the past 30 minutes. Thus, the information processing device 100 may repeatedly perform the process of estimating the cause of stopping the first vehicle 200 at a predetermined interval.

[0032] Next, the information processing device 100 determines whether the first vehicle 200 needs to stop and the stopping position of the first vehicle 200 (corresponding to (2) Stop determination in Figure 1). In other words, the information processing device 100 determines whether the first vehicle 200 needs to stop based on the estimated light cycle of the traffic signal 400. If the information processing device 100 determines that the first vehicle 200 needs to stop, the information processing device 100 determines the position where the first vehicle 200 should stop.

[0033] Then, if the information processing device 100 determines that the first vehicle 200 needs to stop, it generates a driving plan. The driving plan includes a deceleration pattern to stop the first vehicle 200 at the stopping position. The deceleration pattern may be generated by referring to a table that indicates whether deceleration is possible, which is determined according to the distance to the stopping position and the current speed.

[0034] The information processing device 100 transmits the generated driving plan to the first vehicle 200, and the first vehicle 200 controls deceleration or provides driving assistance to the driver based on the driving plan. The information processing device 100 also updates the driving plan at regular intervals.

[0035] As mentioned above, the driving plan is generated based on the estimated state (light cycle) of signal 400. However, depending on when the estimation is performed, the correct estimation result may not be obtained. It may not always be possible to obtain the correct result. For example, even if you determine whether vehicle 1 200 needs to stop at the current time based on a signal cycle estimated from data acquired 30 minutes prior, you may not get the correct result.

[0036] Therefore, in the phase of generating the operation plan, the information processing device 100 changes the estimation period according to the confidence level of the signal estimation. Specifically, the lower the confidence level of the signal estimation, the shorter the estimation period is. Shortening the estimation period may mean temporarily shortening a predetermined period, or it may mean immediately re-executing the estimation without waiting for the next period to arrive.

[0037] This configuration allows for the estimation of stopping factors based on more up-to-date information, increasing the likelihood of generating a more appropriate operating plan.

[0038] Next, we will describe in detail each element that makes up the system. Figure 2 is a diagram illustrating the components of a system including the information processing device 100 according to the embodiment.

[0039] The information processing device 100 according to this embodiment includes a control unit 110, a storage unit 120, and a communication unit 130. The information processing device 100 communicates wirelessly with the first vehicle 200 and the second vehicle 300 to acquire information regarding the driving status of the vehicles. The information processing device 100 also generates a driving plan and transmits the driving plan to the first vehicle 200.

[0040] The control unit 110 is implemented using a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) and memory. The control unit 110 includes, as functional modules, a stop factor estimation unit 111, a stop determination unit 112, an operation plan generation unit 113, and a deviation determination unit 114. These functional modules may be implemented by executing a program using the control unit 110.

[0041] The stopping factor estimation unit 111 periodically estimates the factors (stopping factors) that cause the first vehicle 200 to stop, based on information collected from the second vehicle 300. The factors that cause the first vehicle 200 to stop include, for example, a traffic light (red light) or traffic congestion. The stopping factor estimation unit 111 estimates the circumstances (hereinafter also referred to as surrounding circumstances) related to the factors that cause the first vehicle 200 to stop, such as the cycle of the traffic light (red light) and the section where traffic congestion occurs.

[0042] For example, the stopping factor estimation unit 111 may predict the lighting cycle of the traffic light 400 based on information (driving data) about the vehicle's driving state obtained from the second vehicle 300. Based on this prediction, it may then estimate the time when the red light of the traffic light 400 will illuminate. Alternatively, the stopping factor estimation unit 111 may obtain information about the section where congestion occurs and the position where the second vehicle 300 began to decelerate, and predict the position at the end of the congestion.

[0043] The stop determination unit 112 determines, based on the surrounding conditions estimated by the stop factor estimation unit 111, whether the first vehicle 200 needs to stop and the position where the first vehicle 200 should stop.

[0044] For example, the stop determination unit 112 may determine whether the red light of the traffic light 400 is lit when the first vehicle 200 enters the vicinity of the intersection where the traffic light 400 is located, based on the time when the red light is estimated by the stop factor estimation unit 111. If the stop determination unit 112 determines that the red light of the traffic light 400 is lit when the first vehicle 200 enters the vicinity of the intersection, the stop determination unit 112 determines that the first vehicle 200 needs to stop at the intersection. If a determination is made, the position where the first vehicle 200 should stop is also determined. The position where the first vehicle 200 should stop may be, for example, a relative position from the point where the first vehicle 200 is traveling, or an absolute position represented by latitude and longitude information, etc.

[0045] The driving plan generation unit 113 generates a driving plan that includes a deceleration pattern for the first vehicle 200 to stop at the stopping position. The deceleration pattern may be generated by referring to a table that indicates whether the accelerator can be released or the brakes applied, which is discretized at equal intervals according to the distance to the stopping position and the current driving speed. This table may be generated, for example, based on actual deceleration data that represents the actual deceleration state of the first vehicle 200 in the past.

[0046] The operation plan generation unit 113 periodically generates an operation plan based on data provided by the stop factor estimation unit 111 and the stop determination unit 112. This period is a preset value (for example, 5 minutes), but can be dynamically changed by the operation plan generation unit 113, as described below.

[0047] In this embodiment, the operation plan generation process performed by the operation plan generation unit 113 is executed independently of the stop factor estimation process performed by the stop factor estimation unit 111. However, the operation plan generation unit 113 can change the cycle of the stop factor estimation process performed by the stop factor estimation unit 111 as needed. For example, if the confidence level of the estimation of the factors causing the first vehicle 200 to stop, which was used to generate the driving plan, is lower, the driving plan generation unit 113 instructs the stopping factor estimation unit 111 to perform estimation processing at a shorter interval. Furthermore, the driving plan can be regenerated using the estimation results obtained in this way.

[0048] The generated driving plan, including the deceleration pattern, is transmitted to the vehicle control system of the first vehicle 200, and the first vehicle 200 performs control of its own vehicle (e.g., accelerator off control, brake application control to start deceleration, etc.) according to the deceleration pattern. Here, an example is given in which the first vehicle 200 autonomously controls its speed, but the driving plan may also be used to assist the driver's driving operations. For example, the deceleration plan may be displayed on an in-vehicle terminal.

[0049] The deviation determination unit 114 determines whether the speed of the first vehicle 200 indicated by the deceleration pattern included in the driving plan generated by the driving plan generation unit 113 and the speed of the first vehicle 200 indicated by the actual deceleration data of the first vehicle 200 deviate by a predetermined value or more. In other words, the deviation determination unit 114 determines whether the first vehicle 200 is running according to the generated driving plan.

[0050] If the speed of the first vehicle 200 indicated by the deceleration pattern deviates from the actual speed of the first vehicle 200 by a predetermined value or more, it means that the driver of the first vehicle 200 has intervened in the vehicle control, or that the first vehicle 200 has not decelerated according to the deceleration pattern. In this case, it is presumed that the result of estimating the stopping factors is incorrect. Therefore, in such cases, the driving plan generation unit 113 sets a shorter estimation period for the stopping factor estimation unit 111 in order to improve the accuracy of the estimation.

[0051] The memory unit 120 is a main memory device such as RAM or ROM, an EPROM, a hard disk drive, and an auxiliary memory device such as removable media. The auxiliary memory device stores the operating system (OS), various programs, various tables, etc., and by executing the programs stored therein, each function that matches the predetermined purpose of each part of the control unit 110 can be realized. However, some or all of the functions may be realized by hardware circuits such as ASICs or FPGAs.

[0052] The storage unit 120 stores data used or generated in the processing performed by the control unit 110. The storage unit 120 may also store data necessary for generating the driving plan, such as map data acquired from an external device.

[0053] The communication unit 130 is composed of a communication circuit that performs wireless communication. The communication unit 130 may be, for example, a communication circuit that performs wireless communication using 4G (4th Generation), or a communication circuit that performs wireless communication using 5G (5th Generation). Alternatively, the communication unit 130 may be a communication circuit that performs wireless communication using LTE (Long Term Evolution), or LPWA (Low Power Wide Area). The communication circuit may perform communication using Area (Wi-Fi). Alternatively, the communication unit 130 may be a communication circuit that performs wireless communication using Wi-Fi (registered trademark).

[0054] Next, we will describe devices other than the information processing device 100. The first vehicle 200 is typically a passenger car. The first vehicle 200 may also be a bus or a truck, etc. The first vehicle 200 communicates wirelessly with the information processing device 100. The first vehicle 200 comprises a control unit 210, a storage unit 220, a communication unit 230, and a drive unit 240.

[0055] The control unit 210 transmits information regarding the vehicle's driving status to the information processing device 100 via the communication unit 230. The control unit 210 also receives a driving plan from the information processing device 100 via the communication unit 230. Based on the driving plan, the control unit 210 controls the operation of the first vehicle 200 or assists the driver's operation via the drive unit 240.

[0056] The control unit 210 is implemented using a processor such as a CPU or GPU and memory. The functions of the control unit 210 may also be implemented by executing a program using the control unit 210.

[0057] The memory unit 220 is a main memory device such as RAM or ROM, an EPROM, a hard disk drive, and an auxiliary memory device such as removable media. The auxiliary memory device stores the operating system (OS), various programs, various tables, etc., and by executing the programs stored therein, each function of the control unit 110 that matches the predetermined purpose can be realized. However, some or all of the functions may be realized by hardware circuits such as ASICs or FPGAs.

[0058] The storage unit 220 stores data used or generated in the processing performed by the control unit 210. The storage unit 220 may also store data necessary for controlling the operation of the first vehicle 200 or assisting the driver, such as map data acquired from an external device.

[0059] The communication unit 230 is composed of a communication circuit that performs wireless communication. The communication unit 230 may be, for example, a communication circuit that performs wireless communication using 4G, or a communication circuit that performs wireless communication using 5G. Alternatively, the communication unit 230 may be a communication circuit that performs wireless communication using LTE, or a communication circuit that performs communication using LPWA. Furthermore, the communication unit 230 may be a communication circuit that performs wireless communication using Wi-Fi (registered trademark).

[0060] The drive unit 240 is a means for moving the first vehicle 200. The drive unit 240 may consist of, for example, a motor and inverter for driving the wheels, brakes, and a steering mechanism. The drive unit 240 may be powered by electricity supplied from a battery.

[0061] The second vehicle 300 is typically a passenger car. The first vehicle 200 may be a bus, truck, or the like. The first vehicle 200 communicates wirelessly with the information processing device 100.

[0062] The second vehicle 300 comprises a control unit 310, a storage unit 320, a communication unit 330, and a drive unit 340. Each component of the second vehicle 300 is the same as that of the first vehicle 200.

[0063] Next, we will explain the specific details of the processing performed by the information processing device 100. Figure 3 is a flowchart of the estimation process (process for estimating the surrounding conditions) executed by the control unit 110 of the information processing device 100 according to this embodiment. The illustrated process is executed repeatedly at a predetermined cycle.

[0064] In step S10, the stopping factor estimation unit 111 acquires driving data from the second vehicle 300 that is traveling ahead of the first vehicle 200. The stopping factor estimation unit 111 may acquire driving data from multiple second vehicles 300. The stopping factor estimation unit 111 acquires driving data from the second vehicle 300 and stores it in the storage unit 120.

[0065] Next, in step S11, the stopping factor estimation unit 111 estimates the surrounding conditions of the first vehicle 200 using the acquired driving data of the second vehicle 300. The surrounding conditions of the first vehicle 200 refer to the conditions related to the factors that cause the first vehicle 200 to stop, and may include the color of the lights on the traffic light 400 at the intersection located in front of the first vehicle 200, or the cycle of the lights. The cycle of the lights may include the period (in seconds) during which each of the multiple lights is lit, or the time when the lights change. For example, the stopping factor estimation unit 111 estimates the time when the lights of the traffic light 400 at the intersection turn red, and the time when they turn green. Alternatively, the stopping factor estimation unit 111 may predict the position of the end of the traffic jam located in front of the first vehicle 200 as part of the surrounding conditions of the first vehicle 200.

[0066] After step S11, the stopping factor estimation unit 111 performs the process of step S10 again. In this way, the stopping factor estimation unit 111 periodically collects driving data from the second vehicle 300 and estimates the surrounding conditions of the first vehicle 200. The period of this process may be predetermined, such as every 5 minutes. Alternatively, the period may be changed by an external trigger. For example, if the stopping factor estimation unit 111 is performing periodic estimations at predetermined intervals such as every 5 minutes and receives instructions from the driving plan generation unit 113, the stopping factor estimation unit 111 may immediately start the next estimation process without waiting the 5-minute interval.

[0067] Furthermore, the stopping factor estimation unit 111 calculates the confidence level of the estimation when performing the estimation process in step S11. The stopping factor estimation unit 111 may also calculate the uncertainty of the estimation by a weighted sum of the confidence level output by the estimation algorithm, the confidence level calculated according to the predictable factors, and the confidence level of the unpredictable factors.

[0068] Here, the confidence level output by the estimation algorithm is a value that indicates the discrepancy between the estimation model and the actual data, such as the squared error in the estimation model. Furthermore, the confidence level calculated according to predictable factors is, for example, when the stopping factor estimation unit 111 estimates the signal light cycle, the confidence level is calculated from predictable factors such as the time-changing signal light cycle, the type of traffic light 400 (e.g., push-button or sensor-activated), or the low traffic volume on the road being estimated. Also, when the stopping factor estimation unit 111 estimates the signal light cycle, the confidence level for unpredictable factors is calculated from unpredictable factors such as the behavior of surrounding vehicles (e.g., lane changes or on-street parking) or sudden events (e.g., accidents, breakdowns, or pedestrians suddenly appearing).

[0069] Alternatively, when the stopping factor estimation unit 111 estimates whether or not there is congestion, the confidence level calculated according to the predictable factors is determined by selecting the lane in which the vehicle collecting information is traveling from among multiple lanes. These factors include the inability to identify the cause, the low number of vehicles on the road, or the difference between the current time and the predicted time. Furthermore, when the stopping factor estimation unit 111 estimates whether or not there is congestion, the confidence level for unpredictable factors is calculated from unpredictable factors such as the behavior of surrounding vehicles, such as stopping due to traffic lights or parking on the road, or sudden events such as accidents, breakdowns, or pedestrians suddenly appearing.

[0070] The level of confidence may change depending on the freshness of the information used for estimation. For example, the older the information used for estimation (e.g., driving data collected from the second vehicle 300), the lower the level of confidence may be. The confidence level, along with the estimation result, is provided to the stop determination unit 112 and the operation plan generation unit 113.

[0071] Figure 4 is a flowchart of the process performed by the control unit 110 of the information processing device 100 according to the embodiment to stop the first vehicle 200.

[0072] The information processing device 100 stores a master deceleration pattern in the storage unit 120 in advance, associating it with the geographical location of the stopping position. In other words, the information processing device 100 stores a typical deceleration pattern corresponding to the stopping position as a master pattern in the storage unit 120. Here, the geographical location refers to an absolute position expressed using latitude and longitude information, etc. The typical deceleration pattern corresponding to the stopping position may be generated taking into account road characteristics such as the road gradient of the stopping position. Although the master pattern is stored in association with the stopping position here, the master pattern may be common regardless of the geographical location.

[0073] In step S20, the stop determination unit 112 determines whether or not the first vehicle 200 is moving. In this step, if the stop determination unit 112 determines that the first vehicle 200 is moving, it is considered a positive determination. If the determination in step S20 is positive, the process proceeds to step S21. If the determination in step S20 is negative, the process proceeds to step S20. In other words, step S20 is repeated.

[0074] Next, in step S21, the stop determination unit 112 estimates whether the first vehicle 200 needs to stop and where it should stop. Specifically, the stop determination unit 112 determines whether the red light of the traffic signal 400 is illuminated at the intersection that the first vehicle 200 will enter next, at the time the first vehicle 200 enters the intersection. In other words, the stop determination unit 112 determines whether the first vehicle 200 needs to stop at the intersection. At the same time, the stop determination unit 112 determines the stopping position where the first vehicle 200 should stop.

[0075] Next, in step S22, the driving plan generation unit 113 generates a driving plan for the first vehicle 200. The driving plan includes the current speed of the first vehicle 200 and a deceleration pattern based on the distance to the stopping position. The deceleration pattern includes the time (distance) of the deceleration section to the stopping position and the time (distance) of the coasting section, etc.

[0076] In this embodiment, a typical deceleration pattern for the first vehicle 200 is stored in the memory unit 120, and the driving plan generation unit 113 retrieves the stored deceleration pattern and uses it to control the vehicle. This pre-stored deceleration pattern is called a master pattern. A master pattern is stored for each target stopping position (for example, each intersection).

[0077] In step S22, the driving plan generation unit 113 generates a driving plan using a master pattern corresponding to the geographical location of the stopping position. The driving plan generation unit 113 reflects the actual speed of the first vehicle 200 in the master pattern corresponding to the geographical location of the stopping position, and drives You may generate a plan.

[0078] If a master pattern corresponding to the target stopping position is not recorded in the storage unit 120, the reference master pattern may be corrected based on information such as the road characteristics of the target stopping position, and the deceleration pattern obtained through this correction may be used. Here, road characteristics refer to road gradient, etc.

[0079] Next, in step S23, the control unit 210 of the first vehicle 200 controls the drive unit 240 of the first vehicle 200. This initiates control of the movement of the first vehicle 200 or driver assistance. The control unit 210 of the first vehicle 200 may decelerate the first vehicle 200 according to a deceleration pattern included in the driving plan. Alternatively, the control unit 210 of the first vehicle 200 may assist the driver operating the first vehicle 200 so that it can decelerate according to a deceleration pattern included in the driving plan.

[0080] Next, in step S24, the operation plan generation unit 113 determines whether the confidence level of the estimation performed in step S11 is greater than a predetermined threshold. If the operation plan generation unit 113 determines that the confidence level of the estimation is greater than the predetermined threshold, this step is a positive determination, and the process proceeds to step S25.

[0081] If the confidence level of the estimation is less than a predetermined threshold, this step is judged as negative, and the process proceeds to step S26.

[0082] If the process transitions to step S26, the operation plan generation unit 113 temporarily changes the cycle of the estimation process performed by the stop factor estimation unit 111, as explained with reference to Figure 3. For example, the operation plan generation unit 113 may interrupt the batch processing of estimations, which are performed at intervals such as 5 minutes, and have the stop factor estimation unit 111 perform the estimation of the surrounding conditions again using the data newly acquired up to that point. This makes it possible to temporarily shorten the cycle of the estimation process.

[0083] In the above example, the stop factor estimation unit 111 was immediately instructed to perform the estimation process again, but this is not the only possible configuration. For example, the operation plan generation unit 113 may instruct the stop factor estimation unit 111 to temporarily shorten the estimation period depending on the confidence level of the estimation. For example, the higher the confidence level, the longer the estimation period may be set, and the lower the confidence level, the shorter the estimation period may be set. The estimation frequency may be defined by a function proportional to the confidence level, or the like.

[0084] Furthermore, if the stop factor estimation unit 111 performs a new estimation as a result of executing step S26, the operation plan generation unit 113 may regenerate the operation plan using the results of the newly performed estimation.

[0085] Thus, in this embodiment, if the confidence level is lower than the threshold, the driving plan generation unit 113 temporarily shortens the cycle of the surrounding conditions estimation process performed by the stopping factor estimation unit 111. Since this estimation is performed using data newly acquired since the previous estimation was performed, the confidence level of the estimation can be improved. This is because the more recently collected driving data from the second vehicle 300 is used, the more accurate the determination of the stopping position and the estimation of the time to reach the stopping position become.

[0086] If a positive determination is made in step S24 and the process proceeds to step S25, the deviation determination unit 114 determines whether the speed indicated by the deceleration pattern included in the driving plan and the speed indicated by the actual deceleration data deviate by a predetermined value or more. If the deviation determination unit 114 determines that the speed indicated by the deceleration pattern included in the driving plan and the speed indicated by the actual deceleration data deviate by a predetermined value or more, this step results in a positive determination.

[0087] If the result in step S25 is positive, the process proceeds to step S27. If the result in step S25 is negative, the process proceeds to step S26.

[0088] When the process transitions from step S25 to step S26, the operation plan generation unit 113 temporarily changes the estimation period as described above. For example, the operation plan generation unit 113 sets the estimation period to be shorter than when the speed indicated by the deceleration pattern included in the operation plan and the speed indicated by the actual deceleration data do not deviate by more than a predetermined value. The operation plan generation unit 113 may also instruct the stop factor estimation unit 111 to immediately start the next estimation process.

[0089] If the process proceeds to step S27, the control unit 210 of the first vehicle 200 determines whether the first vehicle 200 has stopped. If the control unit 210 determines that the first vehicle 200 has stopped, this step results in an affirmative determination.

[0090] If the result in step S27 is positive, the process proceeds to step S28.

[0091] If the result in step S27 is negative, the process proceeds to step S23.

[0092] If the process proceeds to step S28, the driving plan generation unit 113 updates the master pattern corresponding to the geographical location of the stopping position based on the data representing the change in vehicle speed (actual deceleration data) obtained during the period leading up to the stop.

[0093] The master pattern may be updated, for example, by learning the optimal value of the deceleration pattern included in the driving plan based on actual deceleration data obtained while driving from 300m before traffic light 400 to the stopping point, or from 20 seconds before stopping until stopping. Alternatively, the driving plan generation unit 113 may learn the optimal value of the deceleration pattern included in the driving plan based on actual deceleration data obtained while driving to the predicted end of the congestion point 300m, or from 20 seconds before stopping until stopping. This makes it possible to obtain an optimal deceleration pattern according to road characteristics such as gradient.

[0094] The driving plan generation unit 113 may select a suitable learning method from among several learning methods depending on the confidence level of the estimation used to generate the driving plan generated in step S22. Specifically, if the confidence level of the estimation used for the driving plan is high, online learning may be performed. If the confidence level of the estimation used for the driving plan is low, batch processing may be performed during learning, and after learning with actual deceleration data using the results of the low-confidence estimation, retraining may be performed with actual deceleration data using the results of the high-confidence estimation.

[0095] Furthermore, the driving plan generation unit 113 may switch the learning method depending on the amount of data available. For example, if there is a large amount of data available, only actual deceleration data with a high degree of confidence in the estimation may be used for learning, and if there is a small amount of data available, multiple learning methods, including the learning method described above, may be combined to perform learning and use as much data as possible.

[0096] Furthermore, if the confidence level of the estimation used during the period in which actual deceleration data was acquired is low, the operation plan generation unit 113 may expand the types of data used to generate the operation plan. Specifically, in this case, in addition to the current estimation result, past estimation results such as the most recent estimation result and estimation results for the same day of the week and time period in the past may also be used to perform the estimation and improve the confidence level of the estimation.

[0097] Next, we will explain the details of the process for updating the master pattern based on confidence level. As mentioned earlier, the master pattern is updated with actual deceleration data.

[0098] On the other hand, if the confidence level when estimating the stopping factors is low, there is a possibility that the necessity of stopping and the estimated stopping position are incorrect, and therefore it may not be appropriate to update the master pattern using actual deceleration data.

[0099] Therefore, the information processing device 100 may update the master pattern after weighting the actual deceleration data according to the confidence level of the estimation. Figure 5 is a flowchart of the process of updating the master pattern based on the confidence level, which is performed by the control unit 110 of the information processing device 100 according to the embodiment. The process described in Figure 5 is a detailed explanation of the process performed in step S28 of Figure 4.

[0100] First, in step S31, the driving plan generation unit 113 determines the weights of the actual deceleration data for the corresponding period used for learning the master pattern, based on the confidence level of the estimation used during the period in which the actual deceleration data was acquired. For example, the driving plan generation unit 113 may reduce the weights of the actual deceleration data for the corresponding period used for learning the master pattern if the confidence level of the estimation used during the period in which the actual deceleration data was acquired is low.

[0101] Next, in step S32, the operation plan generation unit 113 updates the master pattern of the deceleration pattern using the weights of the actual deceleration data determined in step S20.

[0102] Returning to Figure 4, we continue the explanation. If the process proceeds to step S29, the control unit 210 of the first vehicle 200 determines whether the first vehicle 200 has finished traveling. If the control unit 210 determines that the first vehicle 200 has finished traveling, this step results in an affirmative determination.

[0103] If the result in step S29 is positive, the process ends. If the result in step S29 is negative, the process proceeds to step S21.

[0104] As described above, the information processing device 100 collects information from a vehicle traveling ahead of the vehicle to be controlled and periodically estimates the stopping factors and stopping position of the vehicle to be controlled. The information processing device 100 then generates a driving plan that includes a deceleration pattern that allows the vehicle to be controlled to stop by the stopping position. Furthermore, if the confidence level in estimating the stopping factors is lower than a predetermined value, the information processing device 100 sets the estimation period for the stopping factors and the generation period for the driving plan to be shorter than the default values. This enables the information processing device 100 to appropriately decelerate the vehicle to be controlled.

[0105] (modified version) The embodiments described above are merely examples, and this disclosure may be modified as appropriate without departing from its essence.

[0106] For example, the processes and means described in this disclosure can be freely combined and implemented, as long as no technical inconsistencies arise.

[0107] Furthermore, a process described as being performed by a single device may be divided and executed by multiple devices. Conversely, a process described as being performed by different devices may be executed by a single device. In a computer system, the hardware configuration (server configuration) by which each function is implemented can be flexibly changed.

[0108] This disclosure provides a computer program that implements the functions described in the above embodiments to a computer, and one or more processors in the computer read the program. This can also be achieved by execution. Such computer programs may be provided to a computer by a non-temporary computer-readable storage medium that can be connected to the computer's system bus, or by being provided to a computer via a network. Non-temporary computer-readable storage mediums include, for example, any type of disk such as magnetic disks (floppy disks, hard disk drives (HDDs), etc.), optical disks (CD-ROMs, DVDs, Blu-ray discs, etc.), read-only memory (ROM), random access memory (RAM), EPROM, EEPROM, magnetic cards, flash memory, optical cards, and any type of medium suitable for storing electronic instructions. [Explanation of Symbols]

[0109] 100... Information Processing Device 110, 210, 310... Control Unit 111... Stopping Factor Estimation Unit 112...Stop judgment section 113...Driving plan generation unit 114...Discrepancy Determination Unit 120, 220, 320...Storage section 130, 230, 330... Communications Department 200...First vehicle 240, 340... Drive unit

Claims

1. An information processing device that generates information related to the operation of a vehicle, Based on information collected from a second vehicle preceding the first vehicle, the factors causing the first vehicle to stop are periodically estimated. Based on the results of the estimation, the necessity of stopping the first vehicle and the stopping position are determined. If it is determined that the first vehicle needs to stop at the aforementioned stopping position, a driving plan is generated that includes a deceleration pattern for the first vehicle to stop at the aforementioned stopping position. A control unit that performs the following: The system has a storage unit that stores a master pattern, which is an ideal deceleration pattern up to the aforementioned stopping position, in association with the geographical location of the stopping position. The control unit sets the estimation period to a shorter duration when the confidence level of the estimation is lower. Using the master pattern corresponding to the geographical location of the determined stopping position, the operation plan is generated. Based on the actual deceleration data representing the actual deceleration state of the first vehicle during the period covered by the generated driving plan, and the confidence level of the estimation during the period covered by the driving plan, the master pattern corresponding to the stopping position is updated. Information processing device.

2. The control unit, in updating the master pattern, reduces the weight of the actual deceleration data as the confidence level of the estimation decreases. The information processing apparatus according to claim 1.

3. If the speed of the first vehicle indicated by the deceleration pattern included in the generated driving plan differs from the actual speed of the first vehicle by a predetermined value or more, the control unit sets the estimation period to be shorter than when the speed of the first vehicle indicated by the deceleration pattern differs from the actual speed of the first vehicle by a predetermined value or more. The information processing apparatus according to claim 1.

Images