WO2023047492A1 - 制御装置、制御システム、制御方法、及びプログラム - Google Patents
制御装置、制御システム、制御方法、及びプログラム Download PDFInfo
- Publication number
- WO2023047492A1 WO2023047492A1 PCT/JP2021/034835 JP2021034835W WO2023047492A1 WO 2023047492 A1 WO2023047492 A1 WO 2023047492A1 JP 2021034835 W JP2021034835 W JP 2021034835W WO 2023047492 A1 WO2023047492 A1 WO 2023047492A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- mobile device
- sensor
- control
- data acquisition
- speed
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 12
- 238000004458 analytical method Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 25
- 230000001133 acceleration Effects 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 12
- 230000000087 stabilizing effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 description 16
- 238000013468 resource allocation Methods 0.000 description 15
- 238000005516 engineering process Methods 0.000 description 10
- 230000008859 change Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/40—Transportation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/30—Control
Definitions
- the present invention relates to technology for controlling mobile devices.
- Non-Patent Document 1 discloses automatic control by computational resources on the mobile device side as automatic control by video analysis in an autonomous vehicle. With this technology, image analysis is performed with a fixed quality (full HD/30 FPS) and automatic control is performed. will continue.
- Non-Patent Document 2 discloses automatic control by network cooperation (edge/cloud cooperation). In this technique, control is performed by changing the video bit rate at a fixed FPS (10 or 30 FPS). However, the functionality may not be maintained because the detection accuracy of object detection and the like is lowered.
- edge In the conventional technology for automatic control of mobile devices, computational resources are mainly deployed on the mobile device side. In the future, by performing high-load processing such as data analysis on the edge/cloud side (hereafter referred to as edge), it is believed that cost will be reduced by reducing computational resources on the mobile device side while maintaining functionality.
- the present invention has been made in view of the above points, and provides a technique for efficiently utilizing computational resources and accommodating more sensors for the same computational resources in automatic control of mobile devices. intended to
- a control system comprising a mobile device and a mobile device controller that controls the mobile device by analyzing data periodically acquired by a sensor of the mobile device
- data in the sensor is A control device for controlling an acquisition cycle, obtaining means for obtaining the speed of the moving device; a determining means for determining a data acquisition cycle to be set for the sensor based on the speed and a maximum data acquisition cycle of the sensor so as to satisfy an allowable idle running distance in the mobile device. be done.
- BRIEF DESCRIPTION OF THE DRAWINGS It is a figure for demonstrating the outline
- BRIEF DESCRIPTION OF THE DRAWINGS It is a figure for demonstrating the outline
- 4 is a flowchart for explaining an operation example; It is a figure which shows the example of vehicle-mounted camera information.
- FIG. 4 is a diagram showing an example of application information; It is a figure which shows the speed of each time. It is a figure which shows FPS of each time. It is a figure which shows the example of vehicle-mounted camera information. It is a figure which shows the speed and acceleration of each time. It is a figure which shows FPS of each time. It is a figure which shows the hardware configuration example
- a local-side control unit or an edge-side control unit (generically referred to as a control unit; the control unit may be called a control circuit), which will be described later, controls moving device information such as speed and acceleration of the moving device and running In accordance with environmental information such as location, the content of data sent from sensors such as in-vehicle cameras is changed.
- the sensor is a camera
- FPS frame rate
- computational resources capable of accommodating four 30FPS cameras computational resources capable of 120FPS processing
- By controlling the FPS according to the speed of the mobile device for example, 15 FPS can be achieved per camera. This allows eight cameras to be accommodated with the same computational resources.
- FIGS. 1 and 2 there is a mobile device controller on the edge side, and the mobile device controller receives video from the mobile device and performs video analysis.
- Fig. 1 shows an example in which the frame rate is not controlled according to the speed of the mobile device.
- Each mobile device (car) captures and outputs 30 FPS video with a camera.
- the capacity of the mobile device controller on the edge side is 60 FSP for two cameras, only two of the three mobile devices shown in the figure can be accommodated.
- This embodiment prevents excessive allocation of computational resources ignoring changes in mobile devices and environments, and improves computational resource utilization efficiency in the entire system including mobile devices and edges. Furthermore, by combining techniques for preventing arithmetic processing fluctuations and communication processing fluctuations, it is possible to improve the stability of the entire system.
- FIG. 3 shows the basic configuration and variables used in calculations in this embodiment.
- a mobile device 200 (automobile) exists on the local side, and a mobile device control apparatus 100 exists on the edge side.
- the mobile device 200 and the mobile device controller 100 can communicate via a network.
- the video quality is changed in consideration of the control cycle, mobile device speed, and mobile device acceleration, which are mobile device information. Furthermore, it is possible to achieve a state without fluctuations in calculation processing and communication processing by calculation resource allocation and TSN (Time Sensitive Network control).
- computational resource allocation itself is an existing technology.
- -cpu-resource/ can be used.
- TSN control itself is an existing technology (IEEE 802.1 (https://1.ieee802.org/tsn/)).
- computational resource allocation and TSN control are exclusive (independent), either computational resource allocation or TSN control may be implemented, or both may be implemented in combination. Also, neither calculation resource allocation nor TSN control may be performed.
- FIG. 4 is a diagram for explaining t TAT .
- t TAT is the time from a video frame to the timing of control on the mobile device by analysis based on that video frame. In other words, t TAT is the time from detection of an object not shown in the previous video frame to feedback to device control in the mobile device.
- 1/fps in FIG. 4 is the time between frames.
- t_delay is a one-way delay and is guaranteed a fixed time by TSN control.
- 1/(hz p max ) is the time it takes to analyze the video.
- hz m is the time it takes to control on the mobile device.
- the idling distance is, for example, the time from when a person appears in a video frame to when the video analysis is performed and the braking operation of the car is started.
- the allowable free running distance is calculated as a value obtained by subtracting the free running distance based on the maximum video FPS from the free running distance based on the set video FPS.
- the following formula (5) is obtained from the formula (4).
- the frame rate (fps) corresponding to v can be calculated by giving dt and fps max in advance.
- the settable minimum FPS is used, and the calculation result is rounded up to the nearest decimal point (because FPS is an integer value).
- the velocity obtained from the mobile device in real time may be used as v, or the legal velocity based on the position of the mobile device may be used.
- FIG. 5 shows a configuration example of a control system according to this embodiment. As shown in FIG. 5, there are a mobile device controller 100 provided on the edge side and a mobile device 200 on the local side.
- the mobile device control device 100 includes an edge-side control unit 110, a TSN control unit 120, a computational resource allocation unit 130, and an application 140 such as video analysis.
- the edge-side control unit 110 may be called a control device.
- a device including the edge-side controller 110 may be called a control device.
- the edge-side control unit 110 executes control according to this proposal.
- the TSN control 120 together with the TSN control unit 220 of the mobile device 200, performs TSN control so that the delay time between the mobile device controller 100 and the mobile device 200 is fixed.
- the computational resource allocation unit 130 executes computational resource allocation control for the application 140 so that the analysis speed (analysis time) is constant.
- the application 140 is, for example, an application that includes functions such as analyzing video and instructing the mobile device 200 to stop if it is judged to be dangerous.
- the mobile device 200 includes a local controller 210, a TSN controller 220, a sensor 230 such as a camera, and a device 240.
- the local-side control unit 210 may also be called a control device.
- a device including the local controller 210 may be called a controller.
- the local-side control unit 210 executes control according to this proposal.
- the TSN control 220 performs TSN control together with the TSN control section 120 on the edge side so that the delay time becomes a fixed time.
- Device 240 is the body of a mobile device (eg, an automobile) and includes a speedometer, accelerometer, and the like.
- the sensor 230 is a device that periodically acquires sensor data.
- a map information DB 300 may be provided, and an operation of acquiring map information from the map information DB 300 may be performed.
- the local-side control unit 210 (or the edge-side control unit 110) includes acquisition means for acquiring the velocity of the mobile device, determining means for determining the data acquisition period to be set for the sensor based on the maximum data acquisition period of the sensor. Both the acquiring means and the determining means may be replaced with "circuits". Also, “to satisfy the allowable free running distance” means that, for example, compared to the case of performing analysis at the maximum data acquisition cycle, when analyzing at the data acquisition cycle set for the sensor, extra The idling distance may be set to a maximum value equal to or less than a predetermined allowable value.
- the local-side control unit 210 acquires sensor information such as in-vehicle camera information from the sensor 230 .
- the vehicle-mounted camera information is, for example, maximum FPS, settable FPS, and the like. In addition, it is good also as acquiring map information from map information DB300 here.
- the edge-side control unit 110 acquires application information from the application 140 .
- the application information is, for example, analysis frequency (eg, time required for analysis per video frame).
- sensor information and application information are shared between the edge devices through communication between the edge-side control unit 110 and the local-side control unit 210 . That is, the information acquired by the edge-side control unit 110 is transmitted to the local-side control unit 210 , and the information acquired by the local-side control unit 210 is transmitted to the edge-side control unit 110 .
- the computational resource allocation unit 130 allocates computational resources to the application 140 in S105. Also, the TSN control unit 120 and the TSN control unit 220 execute TSN control.
- calculation resource allocation and TSN control may be executed.
- these are not implemented. Note that the case where the stability improvement is not performed may be, for example, the case where the delay or analysis time is stable (close to a fixed value) without the stability improvement being performed.
- the local-side control unit 210 acquires mobile device information from the device 240 .
- the mobile device information is, for example, velocity, acceleration, control period, and the like. It should be noted that although the subsequent processing is assumed to be performed by the local-side control unit 210 here, this is an example. By transmitting the mobile device information to the edge side, the edge side control section 110 may execute the subsequent processing.
- an allowable free running distance corresponding to the aforementioned dt is obtained.
- an allowable idling distance that occurs when the data acquisition cycle is reduced is set in advance in a storage device such as a memory, Get the allowable free running distance.
- the allowable idling distance may include the control cycle of the device.
- the local control unit 210 calculates the data acquisition period.
- the FPS corresponding to the data acquisition period is calculated by calculating the above-described formula (5).
- the local-side control unit 210 compares the acquisition cycle calculated in S108 with the currently set acquisition cycle, and changes the acquisition cycle if they are different. However, if an on-vehicle camera is assumed as the sensor, it can only be changed in units of FPS. Therefore, in S109, based on the settable cycle (FPS), it is determined whether or not the acquisition cycle calculated in S108 can be changed. If possible, proceed to S110. Otherwise, return to S106.
- FPS settable cycle
- the local control unit 210 sets the acquisition cycle calculated at S108 for the sensor 230. While the vehicle continues to run (No in S111), the processes of S106 to S111 are repeated, and when the vehicle finishes running, the process ends.
- Examples 1 to 3 will be described below as more specific examples of control.
- Examples 1 to 3 are examples in which the sensor is an in-vehicle camera and the application is a video analysis application.
- the functional unit names shown in FIG. 5 and the step numbers shown in FIG. 6 are used as appropriate.
- Example 1 First, Example 1 will be described. In the first embodiment, FPS control using environment information and device speed (statutory speed) will be described. Example 1 is an example when the control frequency is low. No processing is performed to improve stability.
- the local-side control unit 210 acquires vehicle-mounted camera information from the sensor 230 (vehicle-mounted camera), and the edge-side control unit 110 acquires application information from the application 140 (video analysis application). Further, here, the local side control unit 210 (or the edge side control unit 110) also acquires map information.
- FIG. 7 shows an example of in-vehicle camera information
- FIG. 8 shows an example of application information.
- the local controller 210 acquires mobile device information from the device 240 .
- the allowable free running distance is up to 1.0 [m] compared to the case of controlling with the maximum FPS of the camera.
- the FPS can be lowered as long as the difference in the distance generated until the camera image is analyzed at the edge or the like and fed back to the mobile device is within 1.0 [m].
- Example 2 Next, Example 2 will be described.
- a second embodiment describes FPS control using real-time device speed. Here, processing for improving stability is executed.
- Example 2 is an example with high control frequency.
- the local-side control unit 210 acquires vehicle-mounted camera information from the sensor 230 (vehicle-mounted camera), and the edge-side control unit 110 acquires application information from the application 140 (video analysis application).
- edge-side control unit 110 Through communication between the edge-side control unit 110 and the local-side control unit 210, sensor information and application information are shared between edge devices.
- the vehicle-mounted camera information and the application information are the same as in the first embodiment, as shown in FIGS. 7 and 8.
- FIG. 7 The vehicle-mounted camera information and the application information are the same as in the first embodiment, as shown in FIGS. 7 and 8.
- analysis processing and fixing of NW delay are performed by calculation resource allocation control and TSN control. Specifically, it is as follows.
- the calculation resource allocation unit 130 performs calculation resource allocation processing.
- computational resources such as CPU and memory are exclusively allocated, and the processing time required for applications such as video analysis to detect dangerous substances in video and feed back the detection results to the device is required for automatic control of the device. can be contained within the operating cycle (eg, every 100 [ms], etc.).
- this function By combining this function, there is no need to consider fluctuations in processing time, so more camera images can be processed. Note that, in the case of the first embodiment, in which this function is not combined, it may be necessary to process the camera video in a state in which the computational resources have sufficient margins in consideration of fluctuations in the processing time.
- the TSN control unit 120 and the TSN control unit 220 control a mechanism for guaranteeing fluctuations in data transfer time such as TSN.
- TSN data transfer time
- the TSN control unit 120 and the TSN control unit 220 control a mechanism for guaranteeing fluctuations in data transfer time such as TSN.
- the local controller 210 acquires the velocity of the mobile device 200 at the same frequency as the control period, for example.
- FIG. 9 shows velocities acquired by repeatedly executing a loop from mobile device information acquisition to determination of travel end (S106 to S111).
- the allowable idling distance is set to 1.0 [m] as in the first embodiment.
- the local-side control unit 210 calculates the FPS using Equation (5) in each loop and determines whether to change the FPS.
- Fig. 10 shows the FPS calculated by Equation (5) and the FPS set in the camera for the speed at each time.
- a change of FPS to 15 is made.
- the value of FPS according to equation (5) does not change, so the FPS is not changed.
- Example 3 Next, Example 3 will be described.
- a third embodiment describes FPS control using real-time device velocity and acceleration. No processing for improving stability is executed here.
- the third embodiment is an example in which control frequency is high and camera setting requires time.
- the local-side control unit 210 acquires vehicle-mounted camera information from the sensor 230 (vehicle-mounted camera), and the edge-side control unit 110 acquires application information from the application 140 (video analysis application).
- FIG. 11 shows vehicle-mounted camera information in the third embodiment.
- the application information is the same as in Example 1, as shown in FIG.
- the local-side control unit 210 acquires the velocity and acceleration of the mobile device 200 at, for example, the same frequency as the control period (1 [Hz], 1 [s] interval in the third embodiment).
- FIG. 12 shows the velocity and acceleration acquired by repeatedly executing the loop (S106 to S111) from acquisition of mobile device information to determination of end of travel.
- the allowable idling distance is set to 1.0 [m] as in the first embodiment.
- the local-side control unit 210 calculates the FPS using the following equation (5′) using the acceleration a and the time t [s] required for setting the FPS in addition to the velocity, and calculates the FPS determine changes.
- FIG. 13 shows the FPS calculated by Equation (5′) and the FPS set in the camera for the velocity and acceleration at each time.
- a change of FPS to 15 is made.
- the value of FPS according to equation (5') does not change, so the FPS is not changed.
- the negative acceleration increases and the FPS value according to formula (5') changes, so the FPS is changed to 10.
- deceleration changes the value of FPS according to equation (5') to change the FPS. If it takes a long time to set the FPS of the camera, the future speed may be predicted and the FPS may be set in advance.
- All of the mobile device controller 100, the edge controller 110, the local controller 210, and the "local controller 210+TSN controller 220" described in the present embodiment can be realized by causing a computer to execute a program.
- This computer may be a physical computer or a virtual machine on the cloud.
- the device can be realized by executing a program corresponding to the processing performed by the device using hardware resources such as a CPU and memory built into the computer.
- the above program can be recorded in a computer-readable recording medium (portable memory, etc.), saved, or distributed. It is also possible to provide the above program through a network such as the Internet or e-mail.
- FIG. 14 is a diagram showing a hardware configuration example of the computer.
- the computer of FIG. 14 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., which are interconnected by a bus BS.
- a program that implements the processing in the computer is provided by a recording medium 1001 such as a CD-ROM or memory card, for example.
- a recording medium 1001 such as a CD-ROM or memory card
- the program is installed from the recording medium 1001 to the auxiliary storage device 1002 via the drive device 1000 .
- the program does not necessarily need to be installed from the recording medium 1001, and may be downloaded from another computer via the network.
- the auxiliary storage device 1002 stores installed programs, as well as necessary files and data.
- the memory device 1003 reads and stores the program from the auxiliary storage device 1002 when a program activation instruction is received.
- the CPU 1004 implements functions related to the device according to programs stored in the memory device 1003 .
- the interface device 1005 is used as an interface for connecting to a network, various measuring devices, exercise intervention devices, and the like.
- a display device 1006 displays a GUI (Graphical User Interface) or the like by a program.
- An input device 1007 is composed of a keyboard, a mouse, buttons, a touch panel, or the like, and is used to input various operational instructions.
- the output device 1008 outputs the calculation result.
- the technology according to the present embodiment makes it possible to efficiently utilize computational resources and accommodate more sensors for the same computational resources in automatic control of mobile devices.
- control device In a control system comprising a mobile device and a mobile device controller for controlling the mobile device by analyzing data periodically acquired by a sensor of the mobile device, the controller for controlling the data acquisition cycle of the sensor and obtaining means for obtaining the speed of the moving device;
- a control device comprising: determining means for determining a data acquisition period to be set for the sensor based on the speed and a maximum data acquisition period of the sensor so as to satisfy an allowable idling distance in the mobile device.
- the acquisition means acquires a legal speed based on map information as the speed, or acquires the speed from the mobile device.
- the allowable idling distance is an allowable idling distance that occurs extra when analysis is performed at the data acquisition cycle set for the sensor compared to when analysis is performed at the maximum data acquisition cycle. 3.
- the determination means determines the data acquisition period to be set to the sensor by further using the acceleration of the mobile device and the time taken to set the data acquisition period to the sensor. 1.
- a control system comprising a mobile device and a mobile device controller for controlling the mobile device by analyzing data periodically acquired by a sensor of the mobile device, obtaining means for obtaining the speed of the moving device;
- a control system comprising: determining means for determining a data acquisition period to be set for the sensor based on the speed and a maximum data acquisition period of the sensor so as to satisfy an allowable idle running distance in the mobile device.
- network control means for stabilizing communication between the mobile device and the mobile device controller; computational resource control means for stabilizing analysis processing in the mobile device controller; or the network control means and the computation 6.
- a control system comprising a mobile device and a mobile device controller for controlling the mobile device by analyzing data periodically acquired by a sensor of the mobile device, the controller for controlling the data acquisition cycle of the sensor
- a control method executed by an obtaining step of obtaining the speed of the moving device;
- a control method comprising: determining a data acquisition period to be set for the sensor based on the speed and a maximum data acquisition period of the sensor so as to satisfy an allowable idle running distance in the mobile device.
- a program for causing a computer to function as the control device according to any one of claims 1 to 4.
Landscapes
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Operations Research (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
前記移動デバイスの速度を取得する取得手段と、
前記移動デバイスにおいて許容可能な空走距離を満たすように、前記速度と、前記センサの最大データ取得周期に基づいて、前記センサに設定するデータ取得周期を決定する決定手段と
を備える制御装置が提供される。
まず、図1、図2を参照して、本実施の形態の概要を説明する。本実施の形態では、移動デバイスとして自動車を想定し、移動デバイスから得られたセンサデータ等に基づき、移動デバイスの自動制御を行う。
次に、本実施の形態において使用するモデル及び計算式の例について説明する。図3に、本実施の形態における基本構成、及び計算で使用する変数等を示す。
移動デバイス速度:v[m/s]
移動デバイス加速度:a[m/s2]
移動デバイスにおける設定映像FPS:fps
移動デバイスにおける最大映像FPS:fpsmax
移動デバイスと移動デバイス制御装置間の片道遅延:tdelay[ms]
移動デバイス制御装置における解析頻度:hzp max=fpsmax
図4は、tTATを説明するための図である。tTATは、ある映像フレームから、その映像フレームに基づく解析による移動デバイスでの制御のタイミングまでの時間である。言い換えると、tTATは、移動デバイスにおいて、直前の映像フレームには映っていない物体を検知してから、デバイス制御までフィードバックされるまでの時間である。
図5に、本実施の形態における制御システムの構成例を示す。図5に示すように、エッジ側に備えられた移動デバイス制御装置100、及び、ローカル側の移動デバイス200が存在する。
次に、図5に示した構成を備えるシステムの動作例を、図6を参照して説明する。S101において、ローカル側制御部210は、センサ230から車載カメラ情報等のセンサ情報を取得する。車載カメラ情報は、例えば、最大FPS、設定可能なFPS等である。なお、ここで、地図情報DB300から地図情報を取得することとしてもよい。
まず、実施例1について説明する。実施例1では、環境情報とデバイス速度(法定速度)を使ったFPS制御について説明する。実施例1は、制御頻度が低い場合の例である。また、安定性向上のための処理は行わない。
ローカル側制御部210は、センサ230(車載カメラ)から車載カメラ情報を取得し、エッジ側制御部110が、アプリケーション140(映像解析アプリケーション)からアプリケーション情報を取得する。また、ここでは、ローカル側制御部210(又はエッジ側制御部110)は、地図情報も取得する。
S106において、ローカル側制御部210は、デバイス240から移動デバイス情報を取得する。
ローカル側制御部210は、式(5)に、dt=1.0[m]、v=16.7[m/s]、(=60[km/h])、fpsmax=30を代入してFPSを計算する。
図7に示すとおり、移動デバイス200のカメラに設定可能なFPSは15[FPS]であるため(10[FPS]とするとdt=1.0[m]を満たせない)、カメラの設定FPSを30から15に設定する。なお、ここでは、最初のFPSを30としている。FPSを15に設定したことで、最大FPSである30[FPS]で映像解析するより、少ない計算リソースで解析可能である。
その後、移動デバイス200が走行する場所の法定速度が60[km/h]から30[km/h]に変化したとする。
図7より、設定可能なFPSは10[FPS]であるため(5[FPS]とするとdt=1.0[m]を満たせない)、カメラの設定FPSを15から10に変更する。これにより、15[FPS]で映像解析するより、更に少ない計算リソースで解析可能である。
次に、実施例2を説明する。実施例2では、リアルタイムのデバイス速度を使ったFPS制御について説明する。ここでは、安定性向上のための処理を実行する。また、実施例2は、制御頻度が高い例である。
ローカル側制御部210は、センサ230(車載カメラ)から車載カメラ情報を取得し、エッジ側制御部110が、アプリケーション140(映像解析アプリケーション)からアプリケーション情報を取得する。
実施例2では、計算リソース割当制御及びTSN制御により解析処理及びNW遅延の固定化を行う。具体的には下記のとおりである。
ローカル側制御部210は、例えば、制御周期と同じ頻度で移動デバイス200の速度を取得する。移動デバイス情報取得から走行終了の判断のループ(S106~S111)が繰り返し実行されることにより取得された速度を図9に示す。許容可能な空走距離は、実施例1と同じく1.0[m]とする。
次に、実施例3について説明する。実施例3では、リアルタイムのデバイス速度と加速度を使ったFPS制御について説明する。ここでは、安定性向上のための処理を実行しない。実施例3は、制御頻度が高く、カメラの設定に時間が必要な例である。
ローカル側制御部210は、センサ230(車載カメラ)から車載カメラ情報を取得し、エッジ側制御部110が、アプリケーション140(映像解析アプリケーション)からアプリケーション情報を取得する。
ローカル側制御部210は、例えば、制御周期と同じ頻度(実施例3では、1[Hz]、1[s]間隔)で移動デバイス200の速度及び加速度を取得する。移動デバイス情報取得から走行終了の判断のループ(S106~S111)が繰り返し実行されることにより取得された速度及び加速度を図12に示す。許容可能な空走距離は、実施例1と同じく1.0[m]とする。
図13に、各時間の速度及び加速度に対して式(5´)により計算したFPS及びカメラに設定するFPSを示す。図13に示す例において、時間11ではFPSの15への変更を行う。時間13で減速するが、式(5´)によるFPSの値は変化しないためFPSの変更は行わない。
本実施の形態で説明した移動デバイス制御装置100、エッジ側制御部110、ローカル側制御部210、「ローカル側制御部210+TSN制御部220」はいずれも(これらを総称して「装置」と呼ぶ)、例えば、コンピュータにプログラムを実行させることにより実現できる。このコンピュータは、物理的なコンピュータであってもよいし、クラウド上の仮想マシンであってもよい。
本実施の形態に係る技術により、移動デバイスの自動制御において、計算リソースを効率的に利用して、同じ計算リソースに対してより多くのセンサを収容することが可能となる。
本明細書には、少なくとも下記各項の制御装置、制御システム、制御方法、及びプログラムが開示されている。
(第1項)
移動デバイスと、前記移動デバイスのセンサにより周期的に取得されるデータを解析することにより前記移動デバイスを制御する移動デバイス制御装置とを備える制御システムにおいて、前記センサにおけるデータ取得周期を制御する制御装置であって、
前記移動デバイスの速度を取得する取得手段と、
前記移動デバイスにおいて許容可能な空走距離を満たすように、前記速度と、前記センサの最大データ取得周期に基づいて、前記センサに設定するデータ取得周期を決定する決定手段と
を備える制御装置。
(第2項)
前記取得手段は、前記速度として地図情報に基づく法定速度を取得する、又は、前記移動デバイスから前記速度を取得する
第1項に記載の制御装置。
(第3項)
前記許容可能な空走距離は、前記最大データ取得周期で解析を行う場合と比較して、前記センサに設定するデータ取得周期で解析を行う場合に余計に発生する許容可能な空走距離である
第1項又は第2項に記載の制御装置。
(第4項)
前記決定手段は、前記移動デバイスの加速度、及び、データ取得周期の前記センサへの設定にかかる時間を更に用いて前記センサに設定するデータ取得周期を決定する
第1項ないし第3項のうちいずれか1項に記載の制御装置。
(第5項)
移動デバイスと、前記移動デバイスのセンサにより周期的に取得されるデータを解析することにより前記移動デバイスを制御する移動デバイス制御装置とを備える制御システムであって、
前記移動デバイスの速度を取得する取得手段と、
前記移動デバイスにおいて許容可能な空走距離を満たすように、前記速度と、前記センサの最大データ取得周期に基づいて、前記センサに設定するデータ取得周期を決定する決定手段と
を備える制御システム。
(第6項)
前記移動デバイスと前記移動デバイス制御装置との間の通信を安定化させるネットワーク制御手段、又は、前記移動デバイス制御装置における解析処理を安定化させる計算リソース制御手段、又は、前記ネットワーク制御手段と前記計算リソース制御手段の両方
を備える第5項に記載の制御システム。
(第7項)
移動デバイスと、前記移動デバイスのセンサにより周期的に取得されるデータを解析することにより前記移動デバイスを制御する移動デバイス制御装置とを備える制御システムにおいて、前記センサにおけるデータ取得周期を制御する制御装置が実行する制御方法であって、
前記移動デバイスの速度を取得する取得ステップと、
前記移動デバイスにおいて許容可能な空走距離を満たすように、前記速度と、前記センサの最大データ取得周期に基づいて、前記センサに設定するデータ取得周期を決定する決定ステップと
を備える制御方法。
(第8項)
コンピュータを、請求項1ないし4のうちいずれか1項における制御装置として機能させるためのプログラム。
110 エッジ側制御部
120 TSN制御部
130 計算リソース割当部
140 アプリケーション
200 移動デバイス
210 ローカル側制御部
220 TSN制御部
230 センサ
240 デバイス
300 地図情報DB
1000 ドライブ装置
1001 記録媒体
1002 補助記憶装置
1003 メモリ装置
1004 CPU
1005 インタフェース装置
1006 表示装置
1007 入力装置
1008 出力装置
Claims (8)
- 移動デバイスと、前記移動デバイスのセンサにより周期的に取得されるデータを解析することにより前記移動デバイスを制御する移動デバイス制御装置とを備える制御システムにおいて、前記センサにおけるデータ取得周期を制御する制御装置であって、
前記移動デバイスの速度を取得する取得手段と、
前記移動デバイスにおいて許容可能な空走距離を満たすように、前記速度と、前記センサの最大データ取得周期に基づいて、前記センサに設定するデータ取得周期を決定する決定手段と
を備える制御装置。 - 前記取得手段は、前記速度として地図情報に基づく法定速度を取得する、又は、前記移動デバイスから前記速度を取得する
請求項1に記載の制御装置。 - 前記許容可能な空走距離は、前記最大データ取得周期で解析を行う場合と比較して、前記センサに設定するデータ取得周期で解析を行う場合に余計に発生する許容可能な空走距離である
請求項1又は2に記載の制御装置。 - 前記決定手段は、前記移動デバイスの加速度、及び、データ取得周期の前記センサへの設定にかかる時間を更に用いて前記センサに設定するデータ取得周期を決定する
請求項1ないし3のうちいずれか1項に記載の制御装置。 - 移動デバイスと、前記移動デバイスのセンサにより周期的に取得されるデータを解析することにより前記移動デバイスを制御する移動デバイス制御装置とを備える制御システムであって、
前記移動デバイスの速度を取得する取得手段と、
前記移動デバイスにおいて許容可能な空走距離を満たすように、前記速度と、前記センサの最大データ取得周期に基づいて、前記センサに設定するデータ取得周期を決定する決定手段と
を備える制御システム。 - 前記移動デバイスと前記移動デバイス制御装置との間の通信を安定化させるネットワーク制御手段、又は、前記移動デバイス制御装置における解析処理を安定化させる計算リソース制御手段、又は、前記ネットワーク制御手段と前記計算リソース制御手段の両方
を備える請求項5に記載の制御システム。 - 移動デバイスと、前記移動デバイスのセンサにより周期的に取得されるデータを解析することにより前記移動デバイスを制御する移動デバイス制御装置とを備える制御システムにおいて、前記センサにおけるデータ取得周期を制御する制御装置が実行する制御方法であって、
前記移動デバイスの速度を取得する取得ステップと、
前記移動デバイスにおいて許容可能な空走距離を満たすように、前記速度と、前記センサの最大データ取得周期に基づいて、前記センサに設定するデータ取得周期を決定する決定ステップと
を備える制御方法。 - コンピュータを、請求項1ないし4のうちいずれか1項における制御装置として機能させるためのプログラム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/034835 WO2023047492A1 (ja) | 2021-09-22 | 2021-09-22 | 制御装置、制御システム、制御方法、及びプログラム |
JP2023549222A JPWO2023047492A1 (ja) | 2021-09-22 | 2021-09-22 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2021/034835 WO2023047492A1 (ja) | 2021-09-22 | 2021-09-22 | 制御装置、制御システム、制御方法、及びプログラム |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023047492A1 true WO2023047492A1 (ja) | 2023-03-30 |
Family
ID=85720243
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/034835 WO2023047492A1 (ja) | 2021-09-22 | 2021-09-22 | 制御装置、制御システム、制御方法、及びプログラム |
Country Status (2)
Country | Link |
---|---|
JP (1) | JPWO2023047492A1 (ja) |
WO (1) | WO2023047492A1 (ja) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1096638A (ja) * | 1996-09-24 | 1998-04-14 | Mazda Motor Corp | ナビゲーション装置 |
JP2008245268A (ja) * | 2007-02-26 | 2008-10-09 | Toyota Motor Corp | 車両通信装置及び車両通信方法 |
JP2017060114A (ja) * | 2015-09-18 | 2017-03-23 | 日本電信電話株式会社 | 画像取得システム及び画像取得方法 |
JP2020042643A (ja) * | 2018-09-12 | 2020-03-19 | アイシン精機株式会社 | 車両制御装置 |
JP2021018563A (ja) * | 2019-07-19 | 2021-02-15 | 株式会社デンソー | 自動運転運行計画装置、自動運転運行計画方法、及び自動運転運行計画プログラム |
WO2021199345A1 (ja) * | 2020-03-31 | 2021-10-07 | 日本電気株式会社 | 車両管制システム、装置、方法、及びコンピュータ可読媒体 |
-
2021
- 2021-09-22 JP JP2023549222A patent/JPWO2023047492A1/ja active Pending
- 2021-09-22 WO PCT/JP2021/034835 patent/WO2023047492A1/ja active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1096638A (ja) * | 1996-09-24 | 1998-04-14 | Mazda Motor Corp | ナビゲーション装置 |
JP2008245268A (ja) * | 2007-02-26 | 2008-10-09 | Toyota Motor Corp | 車両通信装置及び車両通信方法 |
JP2017060114A (ja) * | 2015-09-18 | 2017-03-23 | 日本電信電話株式会社 | 画像取得システム及び画像取得方法 |
JP2020042643A (ja) * | 2018-09-12 | 2020-03-19 | アイシン精機株式会社 | 車両制御装置 |
JP2021018563A (ja) * | 2019-07-19 | 2021-02-15 | 株式会社デンソー | 自動運転運行計画装置、自動運転運行計画方法、及び自動運転運行計画プログラム |
WO2021199345A1 (ja) * | 2020-03-31 | 2021-10-07 | 日本電気株式会社 | 車両管制システム、装置、方法、及びコンピュータ可読媒体 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2023047492A1 (ja) | 2023-03-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11124190B2 (en) | Vehicle-following speed control method, apparatus, system, computer device, and storage medium | |
US10766489B2 (en) | Model predictive adaptive cruise control for reducing rear-end collision risk with follower vehicles | |
CN109213143B (zh) | 操作自动驾驶车辆的使用事件循环的集中调度系统 | |
CN109131340B (zh) | 基于驾驶员行为的主动车辆性能调整 | |
US10747228B2 (en) | Centralized scheduling system for operating autonomous driving vehicles | |
CN105564431B (zh) | 控制混合动力车的滑行运行的方法及执行该方法的装置 | |
KR101500164B1 (ko) | 과속단속구간에서의 속도 제어 장치 및 그 방법 | |
US10635108B2 (en) | Centralized scheduling system using global store for operating autonomous driving vehicles | |
JP2017136922A (ja) | 車両制御装置、車載機器制御装置、地図情報生成装置、車両制御方法及び車載機器制御方法 | |
EP3751453A1 (en) | Detecting adversarial samples by a vision based perception system | |
CN109466554A (zh) | 自适应巡航加塞预防控制方法、系统、装置和存储介质 | |
CN111703418B (zh) | 一种基于车车通信的多车分布式协同避撞方法及装置 | |
KR20200060592A (ko) | 차량의 변속 제어 장치 및 방법 | |
CN115503632A (zh) | 无人驾驶矿用车辆制动距离获取方法、装置、电子设备及存储介质 | |
JP7172625B2 (ja) | 情報処理装置 | |
CN111739342A (zh) | 用于避让侧前方车辆的方法、装置、介质以及车辆 | |
WO2023047492A1 (ja) | 制御装置、制御システム、制御方法、及びプログラム | |
CN108860167A (zh) | 基于区块链的自动驾驶控制方法及装置 | |
WO2021210312A1 (ja) | 制御装置、制御方法、及びプログラム | |
CN115203078A (zh) | 基于soa架构的车辆数据采集系统、方法、设备及介质 | |
CN112528793A (zh) | 一种车辆的障碍物检测框抖动消除方法及装置 | |
CN113879301B (zh) | 一种车辆控制方法、装置、设备及存储介质 | |
CN114291113B (zh) | 风险阈值确定方法、装置、设备以及存储介质 | |
CN109144070A (zh) | 移动设备辅助自动驾驶方法、汽车和存储介质 | |
CN115112124A (zh) | 运动状态确定方法、装置、电子设备和可读存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21958369 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023549222 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18692030 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 21958369 Country of ref document: EP Kind code of ref document: A1 |