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

Abstract

This information processing device is provided with a prediction calculation unit for calculating a predicted value of wireless quality in a control target, a risk determination unit for calculating a risk value corresponding to the predicted value, and a control method determination unit for calculating, by using the risk value, a cost of each of the control method options and selecting a control method for the control target by comparing the costs among the control method options.

Description

Information Processing Apparatus, Communication System, Information Processing Method, and Program

[0001] The present invention relates to a technique for performing control based on prediction of radio quality.

[0002] In order to operate autonomous driving or robot remote operation, stable communication using radio is required. For stable use of radio communication, there is a method of predicting radio quality (which may also be called radio communication quality) and performing control based on the predicted value. To apply the radio quality prediction result to terminal control, the mainstream method is to simply set a threshold and perform control when the value falls below it.

[0003] As a conventional technique related to prediction of radio quality, for example, there are the techniques disclosed in Non-Patent Documents 1 and 2. In these conventional techniques, a machine learning model (e.g., neural network) learned using performance data measured in advance is used to predict the radio quality at the location of the position information or the future position from the position information and environmental information, and it is used for control. However, simply adding control on the terminal side when a certain threshold is set and the value falls below it may result in unnecessary costs for the operation purpose of the terminal. For example, for the operation purpose of "the robot arriving at the delivery point quickly", as a result of performing route change control so that stable communication can be obtained by only judging the threshold, stable communication may be obtained, but the arrival may be significantly delayed.

[0004] Kenichi Kawamura, et al,. "Predictive QoS of wireless communication for autonomous driving vehicles by fine tuning" PIRMC2023, Toronto, ON, Canada, pp. 1-6, Sep 2023. Naoki Shibuya, et al. "A study on a method for judging the risk of radio quality deterioration using multiple predictions". General Conference 2023, May 2023.

[0005] The present invention has been made in view of the above points, and aims to realize control that takes into account the cost relative to the operational purpose in a technology that performs control based on predicted values ​​of wireless quality in a controlled object.

[0006] According to the disclosed technology, an information processing device is provided, comprising: a prediction calculation unit that calculates a predicted value of wireless quality in a controlled object; a risk determination unit that calculates a risk value corresponding to the predicted value; and a control method determination unit that calculates the cost for each control method option using the risk value and selects a control method for the controlled object by comparing the costs among the control method options.

[0007] According to the disclosed technology, in a technology that performs control based on predicted values ​​of wireless quality in the controlled object, it is possible to achieve control that takes into account the cost relative to the operating purpose.

[0008] This is a diagram illustrating the problem. This is a diagram illustrating an example of the configuration of a communication system in an embodiment of the present invention. This is a flowchart illustrating the operation of the communication system. This is a diagram illustrating a specific example of risk value calculation and cost calculation. This is a diagram illustrating a detailed example of the communication system configuration. This is a diagram illustrating an example of the hardware configuration of the device.

[0009] Hereinafter, embodiments of the present invention (this embodiment) will be described with reference to the drawings. The embodiments described below are merely examples, and the embodiments to which the present invention is applied are not limited to the embodiments described below.

[0010] The following will first describe the conventional technology and its problems in more detail, and then describe the technology according to this embodiment.

[0011] (Conventional Technology and its Challenges) Figure 1 shows an example of a system configuration in conventional technology. In the system shown in Figure 1, terminal 1, autonomous vehicle 2, and wireless quality prediction server 3 are shown. Measurement data (actual data) is transmitted from multiple terminals 1 to the wireless quality prediction server 3.

[0012] The wireless quality prediction server 3 trains a neural network model using actual data from numerous terminals 1. Using the trained model, the wireless quality prediction server 3 predicts, for example, the wireless quality of the autonomous vehicle 2 at a location several seconds in the future. Furthermore, the wireless quality prediction server 3 compares the prediction result with a threshold and takes action on the autonomous vehicle 2 if the prediction result falls below the threshold.

[0013] As described above, conventional technology uses machine learning with neural networks based on previously measured historical data to predict future wireless quality based on current location and environmental information, and then uses a threshold to control the system based on the prediction results. However, simply setting a certain threshold and applying control on the terminal side when the prediction result falls below the threshold may result in unnecessary costs for the purpose of the terminal's operation.

[0014] In other words, in conventional technology, a server or similar device collects pre-training data (past performance), performs training using that data, uses the trained model to predict wireless quality, and then performs terminal-side control such as route selection based on the obtained predicted values. However, conventional technology cannot flexibly determine whether to prioritize stable communication or the time / means to achieve the objective of the terminal operation (e.g., a robot reaching the delivery point quickly).

[0015] (Description of the technology relating to the embodiment) The technology for solving the above problems will be described below. In the technology relating to this embodiment, the configuration and operation of the terminal 100 that performs wireless communication and the server 200 that predicts wireless quality will be described. The terminal 100 may be a smartphone or other device held by a person, a vehicle such as an autonomous vehicle (or a terminal installed in a vehicle), or any other device. The terminal 100 is an example of a controlled object.

[0016] Furthermore, the configurations of the terminal 100 and server 200 shown below basically only represent the configuration according to this embodiment, and general functions such as wireless communication functions and data communication functions are not illustrated.

[0017] <Overall System Configuration> Figure 2 shows an example of the configuration of the communication system in this embodiment. As shown in Figure 2, this communication system has a terminal 100 and a server 200. Communication is possible between the terminal 100 and the server 200 via a network including a wireless section. Note that both the server 200 and the terminal 100 may be called information processing devices. Also, "terminal 100 and server 200", terminal 100, and server 200 may each be called a communication system.

[0018] <Configuration and Operation of Terminal 100> As shown in Figure 2, terminal 100 has a control unit 110. Terminal 100 also includes general functions for wireless communication.

[0019] The control unit 110 controls the terminal 100 according to the control method determined by the control method determination unit 230 in the server 200. In other words, the control unit 110 receives a control instruction from the control method determination unit 230 and controls the terminal 100 according to the control instruction. Examples of control include changing the travel route, changing the travel speed, selecting a network from multiple carriers, and controlling the video rate.

[0020] <Configuration and Operation of Server 200> As shown in Figure 2, Server 200 has a prediction calculation unit 210, a risk determination unit 220, and a control method determination unit 230. The operation of each unit is as follows.

[0021] The prediction calculation unit 210 has a pre-trained model (e.g., a machine learning model such as a neural network) necessary for calculating a future predicted value of wireless quality. In other words, the model has been pre-trained. The prediction calculation unit 230 can use this model to calculate, for example, the future wireless quality (predicted value) at a specified location.

[0022] In addition to predictions using machine learning models, the prediction calculation unit 230 can also perform estimations (predictions) using prior radio wave propagation simulations or estimations (predictions) using estimation formulas based on measured values.

[0023] The risk determination unit 220 receives predicted values ​​from the prediction calculation unit 210 and calculates a risk corresponding to those predicted values. That is, the risk determination unit 220 calculates a risk value corresponding to, for example, the degree of deterioration of communication quality based on the predicted values ​​output from the prediction calculation unit 210.

[0024] The method used by the risk determination unit 220 to calculate risk is not limited to a specific method. For example, the risk determination unit 220 compares a predicted value of wireless quality with a predetermined threshold, and determines the risk to be 0 if the predicted value is greater than or equal to the threshold, and determines the risk to be 1 if the predicted value is less than the threshold. In other words, it performs a binary determination.

[0025] Furthermore, the risk determination unit 220 may calculate the risk according to the degree of deterioration in wireless quality. Details of this will be described later.

[0026] The control method determination unit 230 adds the risk value from the risk determination unit 220 to the cost of each control method option, compares the costs among the control method options, and selects the control method with the lowest cost. In other words, the control method determination unit 230 calculates the cost for each control method option according to the risk value and selects the control method with the lowest cost.

[0027] The control method determination unit 230 instructs the control unit 110 of the terminal 100 of the selection result. Specific examples of the processing will be described later. In the specific examples described later, the cost used is a cost (evaluation value) based on mileage and quality (deterioration risk).

[0028] Furthermore, in this embodiment, the functional divisions between the terminal 100 and the server 200 are as shown in Figure 2, but the functional divisions are not limited to those shown in Figure 2. For example, one, two, or all of the prediction calculation unit 210, risk determination unit 220, and control method determination unit 230 may be provided in the terminal 100.

[0029] <Processing Flow> The processing flow of the communication system in this embodiment will be described with reference to Figure 3.

[0030] In S101, the prediction calculation unit 210 notifies the risk determination unit 220 of the predicted value. In S102, the risk determination unit 220 calculates a risk value corresponding to the predicted value and notifies the control method determination unit 230 of the calculated risk value.

[0031] In S103, the control method determination unit 230 converts the risk value received from the risk determination unit 220 into a cost. That is, it calculates the cost for each control method option by adding the risk value to the cost for each option. The control method determination unit 230 compares the costs among the control method options. Examples of control methods include changing the travel route, changing the travel speed, selecting a network from multiple carriers, and controlling the video rate.

[0032] The control method determination unit 230 determines that the additional control will result in lower costs than not performing the additional control, and proceeds to S105 (Yes in S104); otherwise, it proceeds to S106.

[0033] In S105, the control method determination unit 230 instructs the control unit 110 of the terminal 100 to perform additional control. The control unit 110 of the terminal 100 executes the additional control. In S106, the additional control is not actually performed.

[0034] (Example) Referring to Figures 4 and 5, a more specific example of calculating risk values ​​and costs will be described as an example.

[0035] In this embodiment, the control method options for terminal 100 (autonomous vehicle, etc.) are "not changing the driving route" and "changing the driving route." Here, the driving route when the driving route is not changed is referred to as driving route A, and the changed driving route when the driving route is changed is referred to as driving route B.

[0036] In this embodiment, the prediction calculation unit 210 calculates (predicts) the received power at each point in the terminal 100 along the travel route, from beginning to end (or between predetermined points). In this embodiment, RSSI is used as the received power.

[0037] Figures 4 and 5 show the relationship between RSSI and total distance traveled, respectively. The total distance traveled at a plotted RSSI point represents the distance traveled within that RSSI area. In this embodiment, a risk value of 1 is added for every 1 dB decrease from -75 dBm, and Figures 4 and 5 show the plotted points for the risk values, respectively.

[0038] Figure 4 shows the relationship between RSSI and total distance traveled on route A (when the route was not changed), and Figure 5 shows the relationship between RSSI and total distance traveled on route B (when the route was changed).

[0039] In this embodiment, the risk determination unit 220 basically calculates the risk value for the trip as "risk value × distance traveled in the relevant RSSI area". For example, if terminal 100 travels 5m through an area with a risk of -78dBm (risk: 4), the risk value for that trip will be "risk value 4 × 5m = +20".

[0040] As shown in Figure 4, in travel route A (when the travel route was not changed), the vehicle travels a long distance in an area where the RSSI is -75 dB or less.

[0041] In contrast, as shown in Figure 5, in the case of travel route B (when the travel route is changed), the travel distance in the area below -75 dBm is 0 m, so the overall risk value for travel route B is calculated as 0.

[0042] The control method determination unit 230 calculates the total cost for each of the following routes: Route A (when the route is not changed) and Route B (when the route is changed), using the formula: "Distance traveled × α + Risk value × β = Total cost". α and β are weights and can be set arbitrarily. Note that the above cost calculation formula is just one example, and other cost calculation formulas may be used.

[0043] In this embodiment, α = 1 and β = 1. At this time, the control method determination unit 230 calculates the total cost for travel route A (when the travel route is not changed) as "total cost = travel distance 70m × 1 + risk value 32 × 1 = 102".

[0044] Further, assume that the control method determination unit 230 calculates the total cost as "total cost = travel distance 100 m × 1 + risk value 0 × 1 = 100" for the travel route B (when the travel route is changed).

[0045] In the above case, since the cost is lower when the travel route is changed, the control method determination unit 230 determines to perform control to change the travel route. In the above example, received power is used as the predicted value used to calculate the risk value, but other radio qualities (e.g., throughput, interference, etc.) than received power may be used as the predicted value.

[0046] As described above, by converting the radio quality into a risk value and calculating the cost considering the travel distance and the risk, control considering the cost (evaluation value) becomes possible.

[0047] (Example of the detailed configuration of the system) FIG. 6 shows an example of the detailed configuration of the communication system in the present embodiment. As shown in FIG. 6, the terminal 100 (e.g., a robot, an autonomous vehicle, etc.) has a control unit 110 and a position information acquisition unit 120. The server 200 has a prediction calculation unit 210, a risk determination unit 220, a control method determination unit 230, a route selection unit 240, a position information collection unit 250, and a route information DB 260.

[0048] The control unit 110, the prediction calculation unit 210, the risk determination unit 220, and the control method determination unit 230 each have the functions already described.

[0049] In the examples so far, it has been assumed that the position information acquisition unit 120 is included in the control unit 110. The position information acquisition unit 120 acquires the position information of the terminal 100 and transmits the position information to the server 200.

[0050] In the examples so far, it has been assumed that the route selection unit 240, the position information collection unit 250, and the route information DB 260 are included in, for example, the control method determination unit 230.

[0051] The location information collection unit 250 collects location information from the terminal 100. The route information DB 260 stores route information. The route selection unit 240 selects a route that the terminal 100 can take based on the location information of the terminal 100 (e.g., current location and destination) and the route information, and passes the selected route information to the control method determination unit 230. The selected route information includes, for example, the distance traveled by the selectable route from the current location to the destination (e.g., in meters), and the location coordinate information of the route.

[0052] The selected route information is also passed to the prediction value calculation unit 210. The prediction value calculation unit 210 calculates a predicted value of wireless quality for each route (i.e., for each control method option). The risk determination unit 220 calculates a risk value for each route. The control method determination unit 230 calculates the cost for each route and sends a control instruction to the control unit 110 to select the route with the minimum cost.

[0053] (Example Hardware Configuration) Any of the devices described in this embodiment (terminals, servers, information processing devices, or communication systems, etc.) can be realized, for example, by having a computer run a program. This computer may be a physical computer or a virtual machine on the cloud.

[0054] In other words, the device can be realized by using hardware resources such as the CPU and memory built into a computer to execute a program corresponding to the processing performed by the device. The program can be recorded on a computer-readable recording medium (such as portable memory), saved, and distributed. It can also be provided via a network, such as the Internet or email.

[0055] Figure 7 shows an example of the hardware configuration of the computer described above. The computer in Figure 7 has a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, etc., all of which are interconnected by bus B. The computer may also be equipped with a GPU.

[0056] The program that enables processing on the computer is provided on a recording medium 1001, such as a CD-ROM or memory card. When the recording medium 1001 containing the program is set in the drive device 1000, the program is installed from the recording medium 1001 to the auxiliary storage device 1002 via the drive device 1000. However, the program does not necessarily have to be installed from the recording medium 1001; it may also be downloaded from another computer via a network. The auxiliary storage device 1002 stores the installed program as well as necessary files and data.

[0057] The memory device 1003 reads and stores a program from the auxiliary storage device 1002 when a program startup command is received. The CPU 1004 implements the functions related to the memory device 1003 according to the program stored in the memory device 1003. The interface device 1005 is used as an interface for connecting to a network, etc. The display device 1006 displays a GUI (Graphical User Interface) etc., based on a program. The input device 1007 consists of a keyboard and mouse, buttons, or a touch panel, etc., and is used to input various operation commands. The output device 1008 outputs the calculation results.

[0058] (Effects of the Embodiment) As described above, the technology described in this embodiment makes it possible to control the system while considering the cost (evaluation value) relative to the operational objective, without simply setting a threshold value for the predicted value and determining the control policy.

[0059] The following additional information is disclosed regarding the embodiments described above.

[0060] <Notes> (Note 1) An information processing device comprising: a prediction calculation unit that calculates a predicted value of wireless quality in a controlled object; a risk determination unit that calculates a risk value corresponding to the predicted value; and a control method determination unit that calculates the cost for each control method option using the risk value and selects a control method for the controlled object by comparing the costs among the control method options. (Note 2) The information processing device according to Note 1, wherein the risk determination unit calculates the risk value according to the degree of deterioration of the wireless quality. (Note 3) The information processing device according to Note 1, wherein the controlled object is a moving object, and the control method determination unit calculates the cost for each selectable travel route based on the risk value and the travel distance of the controlled object. (Note 4) The information processing device according to Note 1, wherein the control method determination unit selects the control method with the smallest cost from among a plurality of control method options and notifies the controlled object of the said control method. (Appendix 5) A communication system comprising: a prediction calculation unit that calculates a predicted value of wireless quality in a controlled object; a risk determination unit that calculates a risk value corresponding to the predicted value; a control method determination unit that calculates the cost for each control method option using the risk value and selects a control method for the controlled object by comparing the costs among the control method options; and a control unit that controls the controlled object using the control method selected by the control method determination unit. (Appendix 6) An information processing method executed by an information processing device, comprising: a prediction calculation step of calculating a predicted value of wireless quality in a controlled object; a risk determination step of calculating a risk value corresponding to the predicted value; and a control method determination step of calculating the cost for each control method option using the risk value and selecting a control method for the controlled object by comparing the costs among the control method options. (Appendix 7) A non-temporary storage medium storing a program for causing a computer to function as an information processing device described in any one of Appendix 1 to 4.

[0061] Although this embodiment has been described above, the present invention is not limited to this specific embodiment, and various modifications and changes are possible within the scope of the gist of the invention as described in the claims.

[0062] 100 Terminal 110 Control Unit 120 Location Information Acquisition Unit 200 Server 210 Prediction Calculation Unit 220 Risk Determination Unit 230 Control Method Determination Unit 240 Route Selection Unit 250 Location Information Collection Unit 260 Route Information DB 1000 Drive Device 1001 Recording Medium 1002 Auxiliary Storage Device 1003 Memory Device 1004 CPU 1005 Interface Device 1006 Display Device 1007 Input Device 1008 Output Device

Claims

1. An information processing device comprising: a prediction calculation unit that calculates a predicted value of wireless quality in a controlled object; a risk determination unit that calculates a risk value corresponding to the predicted value; and a control method determination unit that calculates the cost for each control method option using the risk value and selects a control method for the controlled object by comparing the costs among the control method options.

2. The information processing apparatus according to claim 1, wherein the risk determination unit calculates the risk value according to the degree of deterioration of the wireless quality.

3. The information processing apparatus according to claim 1, wherein the controlled object is a moving object, and the control method determination unit calculates the cost for each of the selectable travel routes based on the risk value and the travel distance of the controlled object.

4. The information processing apparatus according to claim 1, wherein the control method determination unit selects the control method that minimizes the cost from among a plurality of control method options and notifies the control target of the said control method.

5. A communication system comprising: a prediction calculation unit that calculates a predicted value of wireless quality in a controlled object; a risk determination unit that calculates a risk value corresponding to the predicted value; a control method determination unit that calculates the cost for each control method option using the risk value and selects a control method for the controlled object by comparing the costs among the control method options; and a control unit that controls the controlled object using the control method selected by the control method determination unit.

6. An information processing method executed by an information processing device, comprising: a prediction calculation step of calculating a predicted value of wireless quality in a controlled object; a risk determination step of calculating a risk value corresponding to the predicted value; and a control method determination step of calculating the cost for each control method option using the risk value and selecting a control method for the controlled object by comparing the costs among the control method options.

7. A program for causing a computer to function as an information processing device according to any one of claims 1 to 4.

Images