System, device, method, and program

Abstract

Provided are a system, a device, a method, and a program with which it is possible to ensure the safety of a plurality of vehicles. The system is configured to control a plurality of vehicles. The system comprises a calculation unit and an output unit. On the basis of an objective function representing the performance of the system according to safety conditions regarding the safety of a plurality of vehicles including a delay time in the system, the calculation unit calculates an optimal value of parameters included in the safety conditions. The output unit outputs the parameters that were calculated by the calculation unit.

Description

System, device, method and program

[0001] The present disclosure relates to a system, an apparatus, a method, and a program.

[0002] Technologies for autonomous driving of vehicles and remote control of vehicles are being developed. As a related technology, for example, Patent Literature 1 describes suppressing delays in data communication among multiple vehicles traveling in a convoy.

[0003] International Publication No. 2021 / 229780

[0004] For example, when multiple vehicles travel in a convoy, they are required to travel safely while maintaining a certain distance between the vehicles. However, in Patent Document 1, safety when multiple vehicles travel in a convoy is not taken into consideration, and therefore, for example, it may not be possible to maintain a certain distance between the vehicles and ensure the safety of the multiple vehicles.

[0005] In view of the above problems, one of the objects of the present disclosure is to provide a system, an apparatus, a method, and a program that can ensure the safety of multiple vehicles.

[0006] A system according to one aspect of the present disclosure is a system for controlling multiple vehicles, and includes a calculation unit that calculates optimal values ​​of parameters included in safety conditions based on an objective function that represents the performance of the system in accordance with safety conditions related to the safety of the multiple vehicles, including delay times in the system, and an output unit that outputs the calculated results.

[0007] An apparatus according to one aspect of the present disclosure is an apparatus in a system for controlling multiple vehicles, and includes a calculation unit that calculates optimal values ​​of parameters included in safety conditions based on an objective function that represents the performance of the system in accordance with safety conditions related to the safety of the multiple vehicles, including delay times in the system, and an output unit that outputs the calculated parameters.

[0008] A method according to one aspect of the present disclosure is a method executed by a system for controlling multiple vehicles, which calculates optimal values ​​of parameters included in safety conditions based on an objective function that represents the performance of the system in response to safety conditions related to the safety of the multiple vehicles, including delay times in the system, and outputs the calculated results.

[0009] A program according to one aspect of the present disclosure is a program for causing a computer to execute processing of a system for controlling multiple vehicles, the processing calculating optimal values ​​of parameters included in safety conditions based on an objective function representing the performance of the system according to safety conditions related to the safety of multiple vehicles, including delay times in the system, and outputting the calculated results.

[0010] According to the present disclosure, the safety of multiple vehicles can be ensured.

[0011] FIG. 1 is a block diagram illustrating an example configuration of a system according to some embodiments. FIG. 2 is a block diagram illustrating an example configuration of an apparatus according to some embodiments. FIG. 3 is a flowchart illustrating an example method according to some embodiments. FIG. 4 is a block diagram illustrating an example configuration of a communication system according to some embodiments. FIG. 5 is a block diagram illustrating an example configuration of a control device according to some embodiments. FIG. 6 is a flowchart illustrating an example operation of the control device according to some embodiments. FIG. 7 is a diagram illustrating a method for solving a nonlinear programming problem under inequality constraints according to some embodiments. FIG. 8 is a diagram for explaining safety conditions according to some embodiments. FIG. 9 is a block diagram illustrating an example configuration of a communication system according to some embodiments. FIG. 10 is a block diagram illustrating an example configuration of a control device according to some embodiments. FIG. 11 is a flowchart illustrating an example operation of the control device according to some embodiments. FIG. 12 is a block diagram illustrating an example configuration of computer hardware according to some embodiments.

[0012] Hereinafter, embodiments will be described with reference to the drawings. In the drawings, the same elements are denoted by the same reference numerals, and redundant description will be omitted as necessary.

[0013] (Embodiment 1) First, embodiment 1 will be described. In this embodiment, an outline of several embodiments will be described.

[0014] 1 illustrates an example configuration of a system 10 according to some embodiments. The system 10 is a system for controlling a plurality of vehicles. For example, the system 10 is a system for remotely controlling a plurality of vehicles that are traveling in a convoy via a network.

[0015] 1 , the system 10 includes a calculation unit 11 and an output unit 12. The calculation unit 11 calculates optimal values ​​of parameters included in the safety conditions based on an objective function that represents the performance of the system 10 according to safety conditions related to the safety of multiple vehicles, including delay times in the system 10.

[0016] For example, the safety conditions may be conditions for multiple vehicles to travel in a convoy safely. For example, the safety conditions may include the distance between vehicles based on the vehicle speed, vehicle acceleration, vehicle braking acceleration, and user response time. In this case, the response time may include a delay time of the system 10. The delay time may include a processing delay in the multiple vehicles, a processing delay in a server controlling the multiple vehicles, and a communication delay between the multiple vehicles and the server. The delay time may include a video encoding processing time, a video decoding processing time, a communication cycle, or a control cycle. The communication cycle is one cycle of time from transmitting communication data to receiving a response to the communication data. The control cycle is one cycle of time from transmitting a control command to receiving a response to the control command.

[0017] For example, the calculation unit 11 may search for optimal values ​​of parameters by solving a nonlinear programming problem that maximizes an objective function that represents performance. The performance represented by the objective function may be the vehicle speed, the time it takes for a predetermined number of vehicles to travel a predetermined distance, or the number of vehicles passing a predetermined point per unit time. The calculated parameter may be service quality information that indicates the quality of the service provided by the system 10. The service quality information may be called an SLA (Service Level Agreement). For example, the parameter may be the vehicle speed, the distance between vehicles, a delay time, etc.

[0018] The output unit 12 outputs the parameters calculated by the calculation unit 11. For example, the output unit 12 may set the calculated vehicle speeds, the distances between the vehicles, etc. to a plurality of vehicles or a server that controls a plurality of vehicles. The output unit 12 may set the calculated delay time, etc. to a base station or a relay device in the network.

[0019] The system 10 may be configured by one device or by multiple devices. Fig. 2 shows an example configuration of a device 20 according to some embodiments. In the example of Fig. 2, the device 20 includes the calculation unit 11 and the output unit 12 shown in Fig. 1. For example, some or all of the calculation unit 11 and the output unit 12 may be arranged in a control device that controls multiple vehicles. The calculation unit 11 and the output unit 12 may also be distributed across multiple devices.

[0020] 3 illustrates an example method according to some embodiments, which may be performed, for example, by the system 10 of FIG. 1 or the device 20 of FIG.

[0021] 3 , the calculation unit 11 calculates optimal values ​​of parameters included in the safety conditions based on an objective function that represents the performance of the system 10 according to the safety conditions of a plurality of vehicles, including delay times in the system 10 (S11). For example, the calculation unit 11 may search for optimal values ​​of the parameters by solving a nonlinear programming problem that maximizes the objective function that represents the performance.

[0022] Next, the output unit 12 outputs the calculated parameters (S12). For example, the output unit 12 may set the calculated parameters to a plurality of vehicles or a server that controls a plurality of vehicles.

[0023] As described above, in this embodiment, when controlling a plurality of vehicles traveling in a convoy, etc., optimal values ​​of parameters included in the safety conditions are calculated based on an objective function that represents the performance of the plurality of vehicles according to the safety conditions. Furthermore, the system delay time is set as the safety conditions of the plurality of vehicles. For example, the optimal values ​​of the parameters are searched for by solving a nonlinear programming problem that maximizes the objective function. This makes it possible to obtain optimal values ​​of parameters that satisfy the safety conditions including the system delay time, thereby ensuring the safety of the plurality of vehicles.

[0024] In the following embodiment, a specific example of the first embodiment will be described.

[0025] (Second Embodiment) Next, a second embodiment will be described. In this embodiment, as an example of calculating an SLA, which is a parameter of an objective function, an example of calculating an SLA for achieving target quality of a service provided via a network, not limited to vehicle control, will be described. For example, the target quality is the user's Quality of Experience (QoE) in an end-to-end (E2E) environment.

[0026] 4 shows an example configuration of a communication system 1 according to some embodiments. For example, the communication system 1 is a system that transmits application data and provides application services. For example, the application services include automated driving and remote driving of vehicles, remote control of forklifts, heavy machinery, and robots, video distribution, and audio distribution. In remote control, camera images are sent from a terminal such as a vehicle or robot to a server, and control commands are sent from the server to the terminal. In video distribution, content such as video is requested from the terminal, and the video is sent from the server to the terminal.

[0027] In the example of FIG. 4 , the communication system 1 includes a control device 100 , a terminal 200 , a base station 300 , a core network 400 , and an application server 500 .

[0028] The terminal 200 and the base station 300 can communicate with each other wirelessly. The base station 300 and the application server 500 can communicate with each other via a core network 400. The control device 100 can communicate with the terminal 200, the base station 300, the core network 400, and the application server 500 via any network or transmission path.

[0029] The terminal 200 is a wireless terminal that wirelessly communicates with the base station 300. The terminal 200 may be a wireless terminal of 4G, local 5G / 5G, LTE (Long Term Evolution), wireless LAN, or the like. The terminal 200 may be a mobile phone, a smartphone, a tablet terminal, an IoT (Internet of Things) terminal, or the like. The terminal 200 may be an automated guided vehicle (AGV), an autonomous mobile robot (AMR), an autonomous robot, a drone, a self-driving car, a forklift, heavy machinery, or the like that implements terminal functions. The terminal 200 may be, for example, a mobile terminal or a terminal with a fixed location. For example, in the case of autonomous driving of a vehicle or remote control of a robot, the terminal 200 transmits camera images of the surrounding area to the application server 500 via the base station 300 and also receives control commands from the application server 500 via the base station 300. In the case of video distribution or audio distribution, the terminal 200 receives video and audio from the application server 500 via the base station 300. For example, when transmitting video, the terminal 200 transmits the video at a video quality such as a set bit rate or frame rate.

[0030] The base station 300 is a base station device that performs wireless communication with the terminal 200. The base station 300 may be a local 5G base station, a 5G next generation Node B (gNB), an LTE eNB (evolved Node B), a wireless LAN access point, or the like. The base station 300 transfers data such as video, audio, and control commands between the terminal 200 and the core network 400. For example, the base station 300 constructs a slice for each application and performs QoS control of the wireless section based on the communication quality such as throughput and delay set in each slice.

[0031] The core network 400 is a backbone network above the base station 300. The core network 400 may be a 5th Generation Core network (5GC) or an Evolved Packet Core (EPC). For example, the core network 400 is connected to an upstream device such as an application server 500 via an upstream data network such as the Internet. The core network 400 transfers data such as video, audio, and control commands between the base station 300 and the application server 500. For example, the core network 400 is composed of multiple functions. In the case of 5GC, the core network 400 includes a User Plane Function (UPF) that performs transfer processing of user data. For example, the UPF constructs a slice for each application and performs QoS control in the wired section based on the communication quality such as throughput and delay set in each slice.

[0032] The application server 500 is a server that provides application services to the terminal 200. The application server 500 may be one or more physical servers, or may be a cloud server built on a cloud or other virtualized server. The application server 500 is not limited to a cloud, and may be a Mobile Edge Computing (MEC) server located on the base station 300 side. For example, in the case of autonomous driving of a vehicle or remote control of a robot, the application server 500 receives camera images of the surroundings of the terminal 200 from the terminal 200 via the core network 400, and transmits control commands corresponding to the received images to the terminal 200 via the core network 400. In the case of video distribution or audio distribution, the application server 500 transmits video and audio to the terminal 200 via the base station 300. For example, when transmitting video, the application server 500 transmits the video at a video quality, such as a set bit rate or frame rate.

[0033] The control device 100 is a control device that controls each device and network of the communication system 1. The control device 100 may be one or more physical servers, or may be a cloud server or other virtualized server built on a cloud. It is not limited to a cloud, and may also be an MEC server. The control device 100 may be an orchestrator that controls the base station 300 and the core network 400, or may be included in the application server 500. The control device 100 calculates SLAs such as video quality and communication quality that achieve a target QoE, and sets the calculated SLAs in each device and network.

[0034] Fig. 5 shows an example configuration of a control device 100 according to some embodiments. In the example of Fig. 5, the control device 100 includes an optimum value calculation unit 110 and a setting unit 120. Note that the configuration of Fig. 5 is just an example, and other configurations may be used as long as they are capable of executing the operation examples according to some embodiments.

[0035] The optimal value calculation unit 110 calculates the optimal value of the SLA required to achieve the target QoE. In this embodiment, the QoE optimization problem for calculating the SLA from the target QoE is formulated as a nonlinear programming problem. A function that is versatile for various QoE models is used as the objective function of the nonlinear programming problem. The optimal value calculation unit 110 calculates the optimal value of the SLA by solving the nonlinear programming problem using the objective function.

[0036] The optimum value calculation unit 110 includes a QoE model 111 that calculates the QoE in accordance with the SLA. The QoE model 111 is a QoE calculation unit that calculates the QoE. The QoE model 111 is a model that calculates the QoE corresponding to an application.

[0037] For example, the QoE model 111 may be a ToD MOS model that calculates the QoE in communication between a vehicle and a remote driver (tele-operated driving communication). The ToD MOS model is, for example, a model defined in ITU-T Technical Report GSTR-5GQoE (Quality of experience (QoE) requirements for real-time multimedia services over 5G networks). The ToD MOS model outputs a Mean Opinion Score (MOS) when video quality and communication quality are input. The MOS is a five-level evaluation value of QoE. The video quality includes a bit rate, a frame rate, a refresh interval, etc. The communication quality includes a throughput, a delay (RTT; Round Trip Time), and the number of burst losses. For example, the ToD MOS model may output an integrated QoE that integrates a video QoE calculated based on video quality and a communication QoE calculated based on communication quality.

[0038] Furthermore, the QoE model 111 may be a Web QoE model, a video QoE model, an audio QoE model, or the like. For example, the Web QoE model calculates the Web QoE in Web distribution based on Web quality such as session time. For example, the Web QoE model is a model defined in ITU-T G. 1030 (Estimating end-to-end performance in IP networks for data applications). The video QoE model calculates the video QoE in video distribution (movie distribution) based on video quality such as bit rate and frame rate. The video QoE model may be a model included in the ToD MOS model. The audio QoE model calculates the audio QoE in audio distribution based on audio quality such as bit rate. For example, the audio QoE model is a model defined in ITU-T P. 1201 (Parametric non-intrusive assessment of audiovisual media streaming quality).

[0039] The setting unit 120 sets the calculated SLA in each device and network. For example, the setting unit 120 may set video quality such as a bit rate and a frame rate in the terminal 200 and the application server 500, or may set communication quality such as a throughput and a delay in the base station 300 and the core network 400. The setting unit 120 may set the communication quality of each slice.

[0040] 6 shows an example of the operation of the control device 100 according to some embodiments. In the example of FIG. 6, the control device 100 calculates an SLA that achieves a target QoE (S101). The optimal value calculation unit 110 defines an objective function f(x) for calculating the SLA from the target QoE as follows:

[0041] In formula (1), x (x1, x2, ...) is an input parameter, and an SLA is input. The input parameter x may be one SLA or may include multiple SLAs. For example, in the case of video quality, it may be a bit rate, a frame rate, etc., and in the case of communication quality, it may be throughput, delay, etc. QoE(x) is a parametric QoE model 111, and calculates QoE (MOS) according to the input parameter x. As described above, the QoE model 111 may be any of a ToD MOS model, a Web QoE model, video QoE, audio QoE, etc. targetQoE is a target QoE (MOS). a １ , a ２ , . . . are parameters that determine the range (constraint) of each input parameter x.

[0042] The optimal value calculation unit 110 solves the objective function f(x) of equation (1) as a nonlinear programming problem under inequality constraints. The optimal value calculation unit 110 calculates an SLA that achieves the target QoE by finding input parameters x that minimize the objective function f(x) under the constraint conditions. A method for solving nonlinear programming problems under inequality constraints will be described later.

[0043] Next, the control device 100 sets the calculated SLA to each device and network (S102). For example, when the setting unit 120 calculates video quality such as bit rate and frame rate, the setting unit 120 sets the calculated video quality to the terminal 200 and the application server 500. Furthermore, when the setting unit 120 calculates communication quality such as throughput and delay, the setting unit 120 sets the calculated communication quality to the base station 300 and the core network 400.

[0044] 7 illustrates a method for solving a nonlinear programming problem under inequality constraints according to some embodiments. The optimal value calculation unit 110 searches for an input parameter x that minimizes the objective function, i.e., an SLA, using the augmented Lagrange multiplier method. The augmented Lagrange multiplier method is an example of a method for solving a nonlinear programming problem under inequality constraints.

[0045] 7, the optimum value calculation unit 110 solves an unconstrained nonlinear programming problem that minimizes an extended Lagrange function (S210). The extended Lagrange function is expressed by the following equation. In equation (2), λ is a Lagrange multiplier and σ is a constant. ２ｉ－１ ≦x ｉ ≦a ２ｉ ) is g ２ｉ－１ (x) = -x ｉ +a ２ｉ－１ , g ２ｉ (x) = x ｉ -a ２ｉ where i (=1, 2, . . . ) is the number of the constraint.

[0046] The gradient of the extended Lagrange function is given by the following equation:

[0047] In S210, the optimum value calculation unit 110 calculates the Lagrange multiplier λ ｉ is fixed, and the input parameter x that minimizes the extended Lagrange function is calculated (S211 to S213). That is, the calculation of the input parameter x that minimizes the extended Lagrange function is treated as an unconstrained nonlinear programming problem and solved by sequential search. The equation for updating the input parameter x by sequential search is as follows: In equation (4), d(x （ｋ） ) is the search direction, α （ｋ） is the step size, and k is the number of steps.

[0048] From equation (4), in order to perform a sequential search, the search direction d(x （ｋ） ) and step size α （ｋ） Therefore, the optimum value calculation unit 110 first determines the step width by the backtracking method (S211). The optimum value calculation unit 110 determines the step width α （ｋ） Determine. In equation (5), c1 is a constant and k is the number of steps. The optimum value calculation unit 110 determines the maximum value of α that satisfies equation (5) as the step size.

[0049] Next, the optimum value calculation unit 110 determines the search direction by the quasi-Newton method (S212). In the quasi-Newton method, the optimum value calculation unit 110 determines the search direction d(x （ｋ） ) to update. In equation (6), k is the number of steps, and B （ｋ） is a positive definite symmetric matrix.

[0050] Next, the optimum value calculation unit 110 updates the input parameter x using the determined step size and search direction (S213). The optimum value calculation unit 110 updates the input parameter x using the step size and search direction according to the above formula (4), and repeats S211 to S213 until the input parameter x converges.

[0051] Following S210, the optimum value calculation unit 110 updates the Lagrange multiplier (S220). After repeating S211 to S213, when the input parameter x converges, the optimum value calculation unit 110 updates the Lagrange multiplier λ using the converged input parameter x according to the following equation:

[0052] The optimal value calculation unit 110 updates the Lagrange multiplier λ using equation (7) so that the extended Lagrange function satisfies the Karush-Kuhn-Tucker (KKT) condition, and repeats steps S210 to S220 until the Lagrange multiplier λ converges. The input parameter x when the Lagrange multiplier λ converges becomes a solution to the nonlinear programming problem under the inequality constraint. The optimal value calculation unit 110 outputs the obtained input parameter x as an SLA that achieves the target QoE.

[0053] As described above, in this embodiment, it is possible to calculate an SLA that achieves a target QoE. Generally, an SLA is set for a system based on system test results and past experience, making it difficult to identify and set an optimal SLA. In this embodiment, the QoE optimization problem is formulated and solved as a nonlinear programming problem, making it possible to automatically calculate and set an optimal SLA value from the target QoE. By applying various QoE models to the QoE model used to calculate the optimal value, it is possible to calculate an SLA required depending on the application.

[0054] Furthermore, in a system that integrates multiple applications such as video and communication, such as in an autonomous driving vehicle or remote control robot, adjusting parameters to achieve the QoE of each application may not ultimately achieve the target QoE for the entire system. For example, by calculating an SLA to satisfy the QoE of multiple applications integrated together, such as the QoE of video and communication, the performance target for the entire system can be achieved.

[0055] Third Embodiment Next, a third embodiment will be described. In this embodiment, an example of calculating an optimal value of an SLA in a system that controls a plurality of vehicles will be described.

[0056] As described in the second embodiment, a mathematical model such as a QoE model is required to find the optimal value of the SLA. For example, by using the above-mentioned ToD MOS model (ITU-T GSTR-5GQoE), it is possible to calculate the QoE from the video quality and communication quality and calculate the optimal value of the SLA. However, the ToD MOS model can handle remote monitoring and remote control of a single vehicle, but cannot handle remote monitoring and remote control of multiple vehicles. Therefore, a model that can handle the control of multiple vehicles is required.

[0057] For example, when multiple vehicles travel in a convoy, they need to be controlled to travel safely. IEEE P. 2846 (IEEE Standard for Assumptions in Safety-Related Models for Automated Driving Systems) defines Responsibility Sensitive Safety (RSS), which is a safety condition for multiple vehicles traveling in a convoy. Specifically, in RSS, as shown in Figure 8, the rear vehicle speed is defined as v ｒ , the front vehicle speed is v ｆ Let the distance between the cars be d. ｍｉｎ The safety condition is that the above condition is met. The safety condition for RSS is expressed as follows: In equation (8), ρ is the user response time, a ｍａｘis the maximum front vehicle acceleration, b ｍａｘ is the front vehicle emergency braking acceleration, b ｍｉｎ is the rear vehicle comfortable braking acceleration.

[0058] Meeting the RSS ensures safety in platooning. However, the RSS does not take into account processing delays such as video and communication in a system that remotely controls multiple vehicles. Therefore, even if the RSS is applied to a model used to calculate the SLA, it is not possible to calculate the optimal SLA. Therefore, in this embodiment, the optimal SLA can be calculated by using safety conditions that take into account processing delays such as video and communication.

[0059] Fig. 9 shows an example of the configuration of a communication system 1 according to some embodiments. In the example of Fig. 9, the communication system 1 includes a plurality of vehicles 201 as terminals and a remote control server 501 as an application server. The rest is the same as Fig. 4.

[0060] The plurality of vehicles 201 are mobile terminals having the same functions as the terminals in embodiment 2. As in embodiment 2, the vehicles 201 may be self-driving cars, AGVs, AMRs, autonomous robots, drones, forklifts, heavy machinery, etc. For example, the vehicles 201 travel in a convoy at a fixed inter-vehicle distance under control of the remote control server 501.

[0061] The remote control server 501 has the same functions as the application server of the second embodiment, and is a server that remotely controls the vehicles 201. For example, the remote control server 501 controls the multiple vehicles 201 to travel in a convoy with a fixed inter-vehicle distance.

[0062] The control device 100 calculates an optimal SLA that satisfies the safety conditions for platooning, and sets the calculated SLA in the vehicles 201 and the remote control server 501. The SLA is a parameter related to the service quality of platooning, and may be the speed or inter-vehicle distance of the vehicles 201. The control device 100 and the remote control server 501 may be a single device.

[0063] Fig. 10 shows an example of the configuration of a control device 100 according to some embodiments. In the example of Fig. 10, the control device 100 includes an optimum value calculation unit 110 and a setting unit 120, similar to Fig. 5 .

[0064] 10 , the optimal value calculation unit 110 calculates an SLA that maximizes the performance index. In this embodiment, the QoE optimization problem shown in the second embodiment is modified to an optimization problem that maximizes the performance index based on the safety condition. The optimal value calculation unit 110 calculates the optimal value of the SLA by solving the nonlinear programming problem using the modified objective function in the same way as in the second embodiment.

[0065] The optimum value calculation unit 110 includes a performance index model 112 that calculates a performance index in accordance with the SLA. The performance index model 112 is a performance index calculation unit that calculates a performance index. The performance index model 112 calculates a performance index based on safety conditions in accordance with input parameters (SLA). The performance index model 112 is a model that includes RSS defined in IEEE P. 2846. In this embodiment, to take processing delays into consideration, communication and video processing delays are set as the response time in RSS.

[0066] The performance index model 112 may be any model including the RSS, and the input parameters (SLA) and the output performance index are not limited. The input parameters are any parameters that can be used to calculate a performance index based on the RSS. For example, the input parameters are parameters included in the above equation (8) that calculates the RSS. The input parameters may be vehicle speed or inter-vehicle distance, or may be communication delay or video processing delay.

[0067] The performance index is an arbitrary index that indicates the performance of the system that performs platooning, and is an index based on RSS. For example, the performance index is ｆ and v ｒ In this case, the performance index model 112 uses the vehicle distance as an input parameter based on the RSS equation (8), fixes the other parameters, and calculates the vehicle speed v ｆ and v ｒ You may ask for:

[0068] Alternatively, the performance index may be the time it takes for N vehicles to travel X [m]. In this case, the performance index model 112 calculates the vehicle speed v based on the RSS formula (8) with the inter-vehicle distance as the input parameter and the other parameters fixed. ｆ and v ｒ and calculate the calculated vehicle speed v ｆ and v ｒ The time required for N vehicles to travel X [m] may be calculated from the above.

[0069] The performance index may also be the number of vehicles passing a certain point per unit time. In this case, the performance index model 112 calculates the vehicle speed v based on the RSS formula (8) with the inter-vehicle distance as the input parameter and the other parameters fixed. ｆ and v ｒ and calculate the calculated vehicle speed v ｆ and v ｒ The number of vehicles passing a certain point per unit time may be calculated from

[0070] The setting unit 120 sets the calculated SLA in each device and network. For example, the setting unit 120 may set the vehicle speed and the inter-vehicle distance in the vehicle 201, may set the communication delay in the base station 300 or the core network 400, or may set the video processing delay in the vehicle 201 or the remote control server 501.

[0071] 11 shows an example of the operation of the control device 100 according to some embodiments. In the example of FIG. 11, the control device 100 sets a safety condition (S111). The optimum value calculation unit 110 sets a processing delay in the response time ρ of the safety condition used in the objective function. The processing delay can be expressed by a linear combination as shown in the following equation.

[0072] In equation (9), Delay ｉis the delay time of each process (system). For example, a delay related to communication is a communication delay, a video delay related to video is an encoding delay, a decoding delay, etc., and a control delay related to control is a communication cycle, a control cycle, etc. For example, if the base station 300 or the core network 400 measures a communication delay, the communication delay measured from the base station 300 or the core network 400 may be acquired. If the vehicle 201 or the remote control server 501 measures a video delay or a control delay, the video delay or the control delay measured from the vehicle 201 or the remote control server 501 may be acquired. The optimal value calculation unit 110 acquires the communication delay, the video delay, and the control delay from each device or network, and sums up each delay to determine the response time of the safety condition.

[0073] Next, the control device 100 calculates an SLA that maximizes the performance index (S112). The optimum value calculation unit 110 defines an objective function f(x) for calculating the performance index from the SLA as follows:

[0074] In equation (10), x (x1, x2, ...) are input parameters. The input parameter x is an SLA, and may be a vehicle speed or an inter-vehicle distance, or may be a communication delay or a video processing delay. The RSS condition is the safety condition in equation (8) above. The performance (x) is the performance index model 112, and calculates a performance index based on the safety condition according to the input parameters. As described above, the performance index model 112 calculates, for example, a vehicle speed v ｆ and v ｒ Alternatively, it may be the time it takes for N vehicles to travel X [m], or the number of vehicles passing a certain point per unit time.

[0075] The optimal value calculation unit 110 solves the objective function f(x) of equation (10) as a nonlinear programming problem under inequality constraints. The optimal value calculation unit 110 calculates an SLA that maximizes the performance index by determining the input parameters x that maximize the objective function f(x) under the constraint conditions. The method for solving the nonlinear programming problem under inequality constraints is the same as in the second embodiment. That is, as shown in FIG. 7 , the input parameters x that maximize the objective function, i.e., the SLA, are searched for using the extended Lagrange multiplier method.

[0076] Next, the control device 100 sets the calculated SLA in each device and network (S113). For example, when the setting unit 120 calculates the vehicle speed and the inter-vehicle distance, the setting unit 120 may set the calculated vehicle speed and inter-vehicle distance in the vehicle 201. Furthermore, when the setting unit 120 calculates the communication delay and the video processing delay, the setting unit 120 may set the communication delay in the base station 300 and the core network 400, and set the video processing delay in the vehicle 201 and the remote control server 501.

[0077] Next, a specific example of determining an SLA from a performance index will be described.

[0078] <Specific Example 1> In specific example 1, a safe travel method (speed and inter-vehicle distance) is searched for within a delay range that can be controlled by a certain platform (video or communication). The optimal value calculation unit 110 sets the end-to-end delay to the RSS response time ρ. For example, ρ = observed RTT + fixed video processing delay. The optimal value calculation unit 110 solves the optimization problem from the above objective function with input parameters x = {vehicle speed, inter-vehicle distance}. In this case, the performance index model 112 of the objective function may be a model that calculates the time it takes for N vehicles to travel X [m] based on the vehicle speed and inter-vehicle distance, or it may be the number of vehicles passing a certain point per unit time. The setting unit 120 notifies the vehicle 201 of the obtained values ​​{vehicle speed, inter-vehicle distance} as a travel control target. The vehicle 201 performs platooning or autonomous driving at the notified vehicle speed and inter-vehicle distance.

[0079] In the second specific example, an allowable delay is searched for when a travel pattern is determined. The optimum value calculation unit 110 sets the end-to-end delay as the RSS response time ρ=x1+x2, and calculates the vehicle speed v according to the RSS formula. ｒ ,v ｆ and the distance between vehicles d ｍｉｎ A fixed value is assigned to each of the following. The optimal value calculation unit 110 solves the optimization problem from the above objective function with input parameters x = {x1 = communication delay, x2 = video processing delay}. In this case, the performance index model 112 of the objective function may be a model that calculates the time it takes for N vehicles to travel X [m] based on the vehicle speed and inter-vehicle distance, or may be the number of vehicles passing a certain point per unit time. The setting unit 120 switches between edge and cloud processing using the obtained values ​​{communication delay, video processing delay} as the communication control target. Processing at the edge is characterized by small communication delay and large video processing delay, while processing in the cloud is characterized by large communication delay and small video processing delay. Therefore, when the communication delay is small and the video processing delay is large, the control processing by the remote control server 501 may be performed at the edge, and when the communication delay is large and the video processing delay is small, the control processing by the remote control server 501 may be performed in the cloud.

[0080] As described above, in this embodiment, when controlling the traveling of multiple vehicles, such as platooning, an optimal value for the SLA of an end-to-end system is calculated. By setting the system processing delay as the response time of the RSS (safety condition) of IEEE P. 2846 and calculating the SLA, the traveling of multiple vehicles can be appropriately controlled taking the system processing delay into account.

[0081] The present disclosure is not limited to the above-described embodiment, and can be modified as appropriate within the scope of the present disclosure.

[0082] Each component in the above-described embodiments may be configured by hardware or software, or both, and may be configured by a single piece of hardware or software, or may be configured by multiple pieces of hardware or software. The functions (processing) of the control device and the like may be realized by a computer 30 having a processor 31 such as a CPU (Central Processing Unit) and a memory 32 serving as a storage device, as shown in FIG. 12. For example, a program for performing the method in the embodiment may be stored in the memory 32, and each function may be realized by the processor 31 executing the program stored in the memory 32.

[0083] The above-mentioned program includes a set of instructions (or software code) that, when loaded into a computer, causes the computer to perform one or more functions described in the embodiments. The program may be stored in a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0084] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0085] Each drawing is merely an example for describing one or more embodiments. Each drawing may not relate to only one particular embodiment, but may also relate to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0086] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes.

[0087] (Supplementary Note 1) A system for controlling multiple vehicles, comprising: a calculation unit that calculates optimal values ​​of parameters included in safety conditions based on an objective function that represents the performance of the system in response to safety conditions related to the safety of the multiple vehicles, the safety conditions including a delay time in the system; and an output unit that outputs the calculated parameters. (Supplementary Note 2) The system described in Supplementary Note 1, wherein the safety conditions include a speed of the vehicle, an acceleration of the vehicle, a braking acceleration of the vehicle, and a distance between the vehicles based on a user's response time, and the response time includes the delay time. (Supplementary Note 3) The system described in Supplementary Note 1, wherein the delay time includes a processing delay in the multiple vehicles, a processing delay in a server that controls the multiple vehicles, and a communication delay between the multiple vehicles and the server. (Supplementary Note 4) The system described in Supplementary Note 3, wherein the delay time includes a video encoding processing time, a video decoding processing time, a communication cycle, or a control cycle. (Supplementary Note 5) The system described in Supplementary Note 2, wherein the parameters include the speed of the vehicle, the distance between the vehicles, or the delay time. (Supplementary Note 6) The system according to Supplementary Note 1, wherein the performance includes a speed of the vehicles, a time required for a predetermined number of the vehicles to travel a predetermined distance, or the number of the vehicles passing a predetermined point per unit time. (Supplementary Note 7) The system according to Supplementary Note 1, wherein the calculation unit searches for an optimal value of the parameter by solving a nonlinear programming problem that maximizes the objective function. (Supplementary Note 8) The system according to any one of Supplements 1 to 7, wherein the output unit sets the calculated parameter for the plurality of vehicles or a server that controls the plurality of vehicles. (Supplementary Note 9) A device in a system for controlling a plurality of vehicles, comprising: a calculation unit that calculates an optimal value of a parameter included in a safety condition based on an objective function that represents performance of the system in accordance with a safety condition related to the safety of the plurality of vehicles including a delay time in the system; and an output unit that outputs the calculated parameter.(Supplementary Note 10) A method executed by a system for controlling multiple vehicles, the method comprising: calculating optimal values ​​of parameters included in safety conditions based on an objective function that represents the performance of the system in accordance with safety conditions related to the safety of the multiple vehicles, including delay times in the system; and outputting the calculated parameters. (Supplementary Note 11) A program for causing a computer to execute processing of a system for controlling multiple vehicles, the processing comprising: calculating optimal values ​​of parameters included in the safety conditions based on an objective function that represents the performance of the system in accordance with safety conditions related to the safety of the multiple vehicles, including delay times in the system; and outputting the calculated parameters.

[0088] Some or all of the elements (e.g., configurations and functions) described in Supplementary Notes 2 to 8 that are dependent on Supplementary Note 1 (system) may also be dependent on Supplementary Note 9 (device), Supplementary Note 10 (method), and Supplementary Note 11 (program) in the same dependency relationship as Supplementary Note 2 to Supplementary Note 8. Some or all of the elements described in any Supplementary Note may be applied to various hardware, software, recording means for recording software, systems, and methods.

[0089] This application claims priority based on Japanese Patent Application No. 2024-092745, filed on June 7, 2024, the disclosure of which is incorporated herein in its entirety by reference.

[0090] REFERENCE SIGNS LIST 1 Communication system 10 System 11 Calculation unit 12 Output unit 20 Device 30 Computer 31 Processor 32 Memory 100 Control device 110 Optimum value calculation unit 111 QoE model 112 Performance index model 120 Setting unit 200 Terminal 201 Vehicle 300 Base station 400 Core network 500 Application server 501 Remote control server

Claims

1. A system for controlling multiple vehicles, comprising: a calculation unit that calculates optimal values ​​of parameters included in safety conditions related to the safety of multiple vehicles, based on an objective function that represents the performance of the system in accordance with the safety conditions, including delay times in the system; and an output unit that outputs the calculated parameters.

2. The system of claim 1, wherein the safety conditions include a speed of the vehicle, an acceleration of the vehicle, a braking acceleration of the vehicle, and a distance between the vehicles based on a user's response time, the response time including the delay time.

3. The system according to claim 1, wherein the delay time includes a processing delay in the plurality of vehicles, a processing delay in a server that controls the plurality of vehicles, and a communication delay between the plurality of vehicles and the server.

4. The system according to claim 3, wherein the delay time includes a video encoding process time, a video decoding process time, a communication cycle, or a control cycle.

5. The system of claim 2, wherein the parameters include the speed of the vehicles, the distance between the vehicles, or the delay time.

6. The system of claim 1, wherein the performance includes the speed of the vehicle, the time it takes for a predetermined number of the vehicles to travel a predetermined distance, or the number of the vehicles passing a predetermined point per unit time.

7. The system according to claim 1, wherein the calculation unit searches for optimal values ​​of the parameters by solving a nonlinear programming problem that maximizes the objective function.

8. The system according to any one of claims 1 to 7, wherein the output unit sets the calculated parameters in the plurality of vehicles or in a server that controls the plurality of vehicles.

9. A device in a system for controlling multiple vehicles, comprising: a calculation unit that calculates optimal values ​​of parameters included in safety conditions related to the safety of multiple vehicles, based on an objective function that represents the performance of the system in accordance with the safety conditions including delay times in the system; and an output unit that outputs the calculated parameters.

10. A method executed by a system for controlling multiple vehicles, the method comprising: calculating optimal values ​​of parameters included in safety conditions related to the safety of multiple vehicles, based on an objective function that represents the performance of the system in accordance with the safety conditions, including delay times in the system; and outputting the calculated parameters.

11. A program for causing a computer to execute processing for a system for controlling multiple vehicles, the processing comprising: calculating optimal values ​​of parameters included in safety conditions related to the safety of multiple vehicles, based on an objective function that represents the performance of the system in accordance with the safety conditions, including delay times in the system; and outputting the calculated parameters.

Images