Information processing device, mobile object, control system, information processing method, and program
Through the information acquisition and control prediction unit of the information processing device, the control for the sensing device is predicted and executed, and the accuracy reduction caused by interference factors in the position estimation of the moving object is solved, and the effect of obtaining suitable images without delay is achieved .
Patent Information
- Application Number
- CN201880078729.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2017-12-12
- Filing Date
- 2018-11-06
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2038-11-06
AI Technical Summary
When estimating the position of a moving object itself, landmarks may be lost or misidentified due to disturbing factors in the surrounding environment, resulting in a decrease in estimation accuracy.
An information processing device is designed, including an information acquisition unit and a control prediction unit. By acquiring the position and posture information of the moving object and map information, the control for the sensing device is predicted and performed to mitigate the influence of interference factors and ensure the image capture. accuracy.
By predicting and adjusting the control for the sensing device, images suitable for the state of the moving object can be obtained without delay, reducing the influence of interference factors and improving estimation accuracy.
Smart Images

Figure CN111448529B_ABST
Abstract
Description
Technical Field
[0001] The present technology relates to an information processing device, a mobile object, a control system, an information processing method and a program, and in particular to an information processing device, a mobile object, a system, an information processing method and a program that are optimal for obtaining an appropriate image when estimating the mobile object's own position. Background Art
[0002] In the past, a method for estimating the self-position of a moving object that acts autonomously has been proposed, the method comprising, for example, extracting a plurality of feature points (also called landmarks) from an image of the surroundings of the moving object captured by a camera; and estimating the three-dimensional positions of the plurality of feature points (for example, refer to Patent Document 1).
[0003] Citation List
[0004] Patent Literature
[0005] Patent Document 1: Japanese Patent Application Laid-Open No. 2005-315746 Summary of the invention
[0006] Technical issues
[0007] When using images to estimate the own position, due to various interference factors present in the surrounding environment, the sight of landmarks may be lost or landmarks may be misidentified, which may lead to a decrease in the accuracy of estimating the own position.
[0008] In view of the above circumstances, an object of the present technology is to provide an information processing device, a mobile object, a control system, an information processing method, and a program that make it possible to mitigate the influence of a disturbance factor.
[0009] Solution to the problem
[0010] In order to achieve the above-mentioned object, an information processing device according to the present technology includes an information acquisition unit and a control prediction unit.
[0011] The information acquisition unit acquires information about the position and posture of the first moving object including the sensing device.
[0012] The control prediction unit predicts control performed on the sensing device based on information on the position and posture acquired by the information acquisition unit and the map information.
[0013] According to this configuration, based on the information about the position and posture of the first mobile object at time T and the map information, the control performed for the sensing device at T+N (i.e., N seconds after time T) and suitable for the mobile object is predicted. Since the control for the sensing device is performed in the mobile object at T+N based on the information about the control prediction, the control can be performed without time lag.
[0014] The sensing device may include an image capture device. The information processing apparatus may further include a unit for predicting the position and posture of a mobile object, the unit predicting the position and posture of a first mobile object based on information about the position and posture, the information about the position and posture being acquired by the information acquisition unit; and a unit for predicting the position of an interference factor, the unit predicting the position of the interference factor in an image captured by the image capture device based on map information and a result of the prediction performed by the unit for predicting the position and posture of the mobile object. The control prediction unit may predict the control to be performed on the image capture device based on the result of the prediction performed by the unit for predicting the position of the interference factor.
[0015] According to this configuration, based on the information about the position and posture of the first moving object at time T and the map information, the position of the interference factor in the image to be captured by the image capture device is predicted at T+N (i.e., N seconds after time T). Then, control to be performed on the image capture device is predicted based on the prediction result of the position of the interference factor, so that an image in which the influence due to the interference factor is mitigated is obtained.
[0016] In the first moving object, control conditions for the image capture device to capture an image of the moving object at T+N are set based on information about the control prediction, and this enables an image suitable for the state of the moving object at T+N to be obtained without time lag at T+N and in which the influence caused by interference factors is mitigated.
[0017] The control prediction unit may predict exposure control performed for the image capturing device.
[0018] The control prediction unit may predict the photometric area control performed for the image capturing device.
[0019] The sensing device may include an image capture device. The first mobile object may include a self-position estimation system, which estimates the position and posture of the first mobile object using feature points extracted from image information from the image capture device. The information processing device may also include a unit for predicting the position and posture of the mobile object, which predicts the position and posture of the first mobile object based on information about the position and posture, the information about the position and posture being acquired by the information acquisition unit; and a unit for predicting the position of an interference factor, which predicts the position of the interference factor in the image captured by the image capture device based on map information and a result of the prediction performed by the unit for predicting the position and posture of the mobile object. The control prediction unit may predict the control to be performed on the self-position estimation system based on the result of the prediction performed by the unit for predicting the position of the interference factor.
[0020] According to this configuration, based on the information about the position and posture of the first mobile object at time T and the map information, the position of the interference factor in the image to be captured by the image capture device is predicted at T+N (i.e., N seconds after time T). Then, the control performed for the own position estimation system is predicted based on the prediction result of the position of the interference factor so that the influence caused by the interference factor is mitigated.
[0021] In the first mobile object, control performed for the own position estimation system at T+N is set based on information about control prediction. This makes it possible to perform processing for estimating the own position and posture at T+N using, for example, information about an image that is suitable for the state of the mobile object at T+N and in which the influence due to interference factors is mitigated. This allows estimation accuracy to be improved.
[0022] The control prediction unit may predict a region where extraction of feature points in the image is not performed in the own position estimation system based on a result of prediction performed by the unit for predicting the position of the disturbance factor.
[0023] The sensing device may include an image capture device and a mobile object state detection sensor that detects the state of a first mobile object. The first mobile object may include a self-position estimation system that estimates the position and posture of the first mobile object using at least one of image information and mobile object state information from the mobile object state detection sensor. The control prediction unit may predict how to weight the image information and mobile object state information, respectively, based on the result of the prediction performed by the unit for predicting the position of the interference factor, and the image information and mobile object state information are used when estimating the position and posture of the first mobile object in the self-position estimation system.
[0024] The sensing device may include a plurality of image capture devices. The control prediction unit may predict how to weight individual image information from the plurality of image capture devices based on the result of the prediction performed by the unit for predicting the position of the interference factor, and the individual image information is used when estimating the position and posture of the first mobile object in the self-position estimation system.
[0025] The control prediction unit may predict the control to be performed on the image capturing device based on a result of the prediction performed by the unit for predicting the position of the interference factor.
[0026] The interference factor may be the sun, and the unit for predicting the position of the interference factor may predict the position of the sun in the image captured by the image capture device based on map information, a result of prediction performed by the unit for predicting the position and posture of a moving object, and sun position information.
[0027] The interference factor may be a tunnel, and the unit for predicting the position of the interference factor may predict the position of the tunnel in the image captured by the image capturing device based on the map information and the result of the prediction performed by the unit for predicting the position and posture of the mobile object.
[0028] The interference factor may be a shadow of a structure, and the unit for predicting the position of the interference factor may predict the position of the shadow caused by the structure in the image captured by the image capture device based on map information, a result of a prediction performed by the unit for predicting the position and posture of a moving object, and sun position information.
[0029] The information acquisition unit may acquire information about the position and posture of a second mobile object that includes a sensing device and is different from the first mobile object. The control prediction unit may set a prediction of control performed on the sensing device of the first mobile object as a prediction of control performed on the sensing device of the second mobile object, the prediction of control performed on the sensing device of the first mobile object being performed by the control prediction unit based on information about the position and posture of the first mobile object and map information, the information about the position and posture of the first mobile object being acquired by the information acquisition unit.
[0030] In order to achieve the above-mentioned object, a mobile object according to the present technology includes a sensing device and an acquisition unit.
[0031] The acquisition unit acquires information on the own position and posture of the moving object.
[0032] The sensing device is controlled according to control prediction information about a prediction of control to be performed on the sensing device, the control to be performed on the sensing device being predicted based on information about its own position and posture and map information, the information about its own position and posture being acquired by an acquisition unit.
[0033] In order to achieve the above-mentioned object, a control system according to the present technology includes a mobile object, an information acquisition unit, a control prediction unit, and a control unit.
[0034] The mobile object includes a sensing device.
[0035] The information acquisition unit acquires information on the position and posture of the moving object.
[0036] The control prediction unit predicts control performed on the sensing device based on information on the position and posture acquired by the information acquisition unit and the map information.
[0037] The control unit performs control for the sensing device based on control prediction information regarding control prediction performed by the control prediction unit.
[0038] To achieve the above-mentioned purpose, an information processing method according to the present technology includes acquiring information about the position and posture of a mobile object including a sensing device; and predicting control performed on the sensing device based on the information about the position and posture and map information.
[0039] In order to achieve the above-mentioned purpose, a program according to the present technology causes an information processing device to perform processing, wherein the processing includes acquiring information about the position and posture of a mobile object including a sensing device; and predicting control performed on the sensing device based on the information about the position and posture and map information.
[0040] Advantageous Effects of the Invention
[0041] As described above, according to the present technology, it is possible to provide an information processing device, a mobile object, a system, an information processing method, and a program that make it possible to mitigate the influence of a disturbance factor.
[0042] Note that the effects described here are not necessarily restrictive, and any effects described in the present disclosure may be provided. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 A sensing device control system according to a first embodiment of the present technology is schematically illustrated.
[0044] Figure 2 is a block diagram of an example of a schematic functional configuration of a vehicle control system in a sensing device control system.
[0045] Figure 3 is a block diagram of an example of a schematic functional configuration of a self-position estimation unit in the self-position estimation system.
[0046] Figure 4 is a block diagram of an example of a schematic functional configuration of a camera included in a vehicle.
[0047] Figure 5 is a block diagram of an example of a schematic functional configuration of a server device in a sensing device control system.
[0048] Figure 6 is a flowchart describing a process of generating a control signal in an image processing apparatus.
[0049] Figure 7 It is a block diagram of a functional configuration of a server apparatus in a sensing device control system according to a second embodiment of the present technology.
[0050] Figure 8 is a flowchart describing a process of generating a control signal in the image processing apparatus according to the second embodiment.
[0051] Fig. 9 It is a block diagram of the functional configuration of an image processing apparatus in a sensing device control system according to a third embodiment of the present technology.
[0052] Fig.10 is a flowchart describing a process of generating a control signal in the image processing apparatus according to the third embodiment. DETAILED DESCRIPTION
[0053] Embodiments for carrying out the present technology will now be described below.
[0054] According to the present technology, based on information about the mobile object's own position and posture at time T and map information, the position of the mobile object at T+N (N>0) (i.e., N seconds after time T) is predicted, and the control performed on the sensing device included in the mobile object at T+N is predicted.
[0055] In the first to third embodiments described below, description is made taking a vehicle such as an automobile as an example of a first moving object and taking a camera (image capturing device) and a vehicle state detection sensor as examples of sensing devices.
[0056] Note that here, a car is used as a moving object for description, but it is not limited thereto. Examples of moving objects include bicycles, motorcycles, unmanned aerial vehicles (UAVs) such as drones, and various robots.
[0057] The vehicle includes a camera, a vehicle state detection sensor, and an own position estimation system, which is used to assist the vehicle in autonomous driving.
[0058] In the first and third embodiments described below, the position of the vehicle at T+N (ie, N seconds after time T) is predicted based on information about the vehicle's own position and posture at time T and map information.
[0059] Next, based on the information on the prediction of the position of the moving object, the map information, and the information on the date and time / weather, the position of the disturbing factor in the captured image is predicted to be at T+N.
[0060] Next, the control performed on the camera and the control performed on the self-position estimation system are predicted based on the prediction result of the position of the interference factor. In the first embodiment, the sun is described as an example of the interference factor, and in the third embodiment, the shadow of a structure such as a building is described as an example of the interference factor.
[0061] In addition, in the second embodiment, based on the information on the own position of the moving object at time T and the map information, the position and posture of the vehicle at T+N (ie, N seconds after time T) are predicted.
[0062] Next, based on the information on the prediction of the position of the moving object and the map information, the position of the tunnel as a disturbance factor in the image captured is predicted to be predicted at T+N.
[0063] Next, control to be performed for the camera and control to be performed for the own position estimation system are predicted based on the prediction result of the position of the disturbance factor.
[0064] Various embodiments are described in detail below.
[0065] <First Embodiment>
[0066] [Example of configuration of control system]
[0067] Figure 1 1 is a block diagram of an example of a schematic functional configuration of a control system 1 for a sensing device to which the present technology is applied. Here, only the main configuration is described, and the following will be used later. Figure 2 and Figure 2 The following figures describe the detailed configuration.
[0068] The control system 1 includes a vehicle control system 100 installed in a vehicle 10 as a mobile object and a server device 500 serving as an information processing device. The vehicle control system 100 and the server device 500 can communicate with each other, for example, through a wireless communication network.
[0069] Note that, in the present embodiment, an example is described in which the server device 500 serving as the information processing device is provided outside the vehicle 10 , but the server device 500 may be installed in the vehicle 10 .
[0070] The vehicle control system 100 includes a self-position estimation system 200 and a data acquisition unit 102 .
[0071] The data acquisition unit 102 includes a camera 300 serving as a sensing device and a vehicle state detection sensor 400. The camera 300 is used to capture an image of the exterior of the vehicle 10, and a plurality of cameras 300 are installed in the vehicle 10.
[0072] In the own position estimation system 200, the own position and posture of the vehicle 10 required to perform autonomous driving are estimated. In the own position estimation system 200, the own position and posture of the vehicle 10 are estimated using information from a sensing device such as image information about an image captured by the camera 300 and vehicle state detection information from the vehicle state detection sensor 400.
[0073] In the own position estimation system 200 , when estimating the own position and posture of the vehicle 10 based on the image information from the camera 300 , the position is estimated based on the result of tracking feature points (landmarks) in the image.
[0074] The server device 500 includes an information acquisition unit 502 , a unit 503 for predicting the position and posture of the vehicle at T+N, a unit 504 for predicting the position of an interference factor in an image, and a control prediction unit 505 .
[0075] In the data acquisition unit 102 of the vehicle 10 , information about the vehicle 10 at time T is acquired using the camera 300 and the vehicle state detection sensor 400 . The information about the vehicle 10 at time T is transmitted to the server device 500 .
[0076] The information acquisition unit 502 of the server device 500 acquires information on the vehicle 10 at time T transmitted from the vehicle control system 100 .
[0077] Based on the information about the vehicle 10 at time T acquired by the information acquisition unit 502, the unit 503 for predicting the position and posture of the vehicle at T+N (which is a unit for predicting the own position and posture of a moving object) predicts the own position and posture of the vehicle 10 at T+N (i.e., N seconds after time T).
[0078] In this embodiment, the unit 504 for predicting the position of the interference factor in the image predicts the position of the sun as the interference factor in the image.
[0079] The unit 504 for predicting the position of an interference factor (sun) in an image (hereinafter referred to as the unit for predicting the position of the sun in an image) predicts the position of the sun in an image captured at T+N based on information about the predicted own position and posture of the vehicle 10 at T+N, map information, and information about the date and time / weather.
[0080] The control prediction unit 505 predicts control to be performed for the camera 300 at T+N and control to be performed for the own position estimation system 200 at T+N based on the prediction result of the position of the sun in the image captured at T+N. Information on the control prediction is transmitted to the vehicle 10. In the vehicle 10, control for the camera 300 and control for the own position estimation system 200 are performed at T+N based on the information on the control prediction.
[0081] Examples of control performed on the camera 300 include exposure control and photometry area control.
[0082] Examples of control performed for the own position estimation system 200 include control performed for a sensing device when estimating the own position and posture of the vehicle 10 .
[0083] Specifically, the control prediction unit 505 predicts how the image information from the camera 300 and the detection information from the vehicle state detection sensor 400 are respectively weighted in the own position estimation system 200 for estimating the position and posture of the vehicle.
[0084] In addition, when estimating the own position and posture in the own position estimation system 200 based on image information about the image captured by the camera 300, the control prediction unit 505 predicts how to set the occlusion area, which is a feature point extraction area that is not used for feature point extraction performed to estimate the own position and posture.
[0085] Furthermore, when estimating the own position in the own position estimation system 200 based on image information about images captured by the camera 300, the control prediction unit 505 predicts how to weight the respective image information from the plurality of cameras 300 to be used in estimating the own position and posture.
[0086] As described above, the operation of the sensing device regarding the vehicle 10 is controlled based on the control prediction information sent from the server device 500, and the control prediction information is information about the prediction of the control performed on the sensing device (such as the camera 300 and the vehicle state detection sensor 400 installed in the vehicle 10).
[0087] This allows for a highly robust control system that mitigates the effects of disturbing factors, ie the sun.
[0088] Each structural element is described in detail below.
[0089] [Example of Configuration of Vehicle Control System]
[0090] Figure 2 is a block diagram of an example of a schematic functional configuration of a vehicle control system 100 which is an example of a mobile object control system to which the present technology is applied.
[0091] Note that when the vehicle provided with the vehicle control system 100 is to be distinguished from other vehicles, the vehicle provided with the vehicle control system 100 will be referred to as the host vehicle or the host vehicle hereinafter.
[0092] The vehicle control system 100 includes an input unit 101, a data acquisition unit 102, a communication unit 103, an on-board equipment 104, an output control unit 105, an output unit 106, a powertrain control unit 107, a powertrain system 108, a body-related control unit 109, a body-related system 110, a storage unit 111, and an automatic driving control unit 112. The input unit 101, the data acquisition unit 102, the communication unit 103, the output control unit 105, the powertrain control unit 107, the body-related control unit 109, the storage unit 111, and the automatic driving control unit 112 are connected to each other through a communication network 121. For example, the communication network 121 includes a bus or an on-board communication network that conforms to any standard, such as a controller area network (CAN), a local interconnect network (LIN), a local area network (LAN), or FlexRay (registered trademark). Note that the various structural elements of the vehicle control system 100 can be directly connected to each other without using the communication network 121.
[0093] Note that when the various structural elements of the vehicle control system 100 communicate with each other through the communication network 121, the description of the communication network 121 will be omitted below. For example, when the input unit 101 and the automatic driving control unit 112 communicate with each other through the communication network 121, it will be simply said that the input unit 101 and the automatic driving control unit 112 communicate with each other.
[0094] The input unit 101 includes a device used by the on-board personnel to input various data, instructions, etc. For example, the input unit 101 includes an operating device such as a touch panel, a button, a microphone, a switch, or a joystick; an operating device that can perform input by a method other than manual operation (such as voice or gesture); and the like. Alternatively, for example, the input unit 101 may be an externally connected device such as a remote control device using infrared or another radio wave, or a mobile device or wearable device compatible with the operation of the vehicle control system 100. The input unit 101 generates an input signal based on the data, instructions, etc. input by the on-board personnel, and supplies the generated input signal to each structural element of the vehicle control system 100.
[0095] The data acquisition unit 102 includes various sensors and the like for acquiring data used for processing performed by the vehicle control system 100 , and supplies the acquired data to the various structural elements of the vehicle control system 100 .
[0096] For example, the data acquisition unit 102 includes various sensors for detecting the state of the vehicle, etc. Specifically, for example, the data acquisition unit 102 includes a gyro sensor; an acceleration sensor; an inertial measurement unit (IMU); and sensors for detecting the amount of operation of the accelerator pedal, the amount of operation of the brake pedal, the steering angle of the steering wheel, the number of revolutions of the engine, the number of revolutions of the motor, the speed of wheel rotation, etc.
[0097] In addition, for example, the data acquisition unit 102 includes various sensors for detecting information about the outside of the vehicle. Specifically, for example, the data acquisition unit 102 includes image capture devices such as a time-of-flight (ToF) camera, a stereo camera, a monocular camera, an infrared camera, and other cameras. In addition, for example, the data acquisition unit 102 includes an environmental sensor for detecting weather, meteorological phenomena, etc., and a surrounding information detection sensor for detecting objects around the vehicle. For example, the environmental sensor includes a raindrop sensor, a fog sensor, a sunshine sensor, a snow sensor, etc. The surrounding information detection sensor includes an ultrasonic sensor, a radar, a LiDAR (light detection and ranging, laser imaging detection and ranging) sensor, a sonar, etc.
[0098] Furthermore, for example, the data acquisition unit 102 includes various sensors for detecting the current position of the vehicle. Specifically, for example, the data acquisition unit 102 includes a global navigation satellite system (GNSS) receiver, etc. The GNSS receiver receives GNSS signals from GNSS satellites.
[0099] In addition, for example, the data acquisition unit 102 includes various sensors for detecting information about the interior of the vehicle. Specifically, for example, the data acquisition unit 102 includes an image capture device that captures an image of the driver, a biometric sensor that detects biometric information of the driver, a microphone that collects sounds inside the vehicle, etc. For example, the biometric sensor is provided on a seat surface, a steering wheel, etc., and detects biometric information of a person sitting on the seat or a driver holding the steering wheel.
[0100] The communication unit 103 communicates with the vehicle-mounted equipment 104 and various vehicle external equipment, servers, base stations, etc., transmits data supplied by various structural elements of the vehicle control system 100, and supplies received data to various structural elements of the vehicle control system 100. It is noted that there is no particular limitation on the communication protocol supported by the communication unit 103. The communication unit 103 may also support multiple types of communication protocols.
[0101] For example, the communication unit 103 wirelessly communicates with the in-vehicle equipment 104 using wireless LAN, Bluetooth (registered trademark), near field communication (NFC), wireless USB (WUSB), etc. In addition, for example, the communication unit 103 communicates with the in-vehicle equipment 104 through a connection terminal (not shown) (and a cable if necessary) by an electric wire using a universal serial bus (USB), a high-definition multimedia interface (HDMI) (registered trademark), a mobile high-definition link (MHL), etc.
[0102] In addition, for example, the communication unit 103 communicates with equipment (e.g., an application server or a control server) located in an external network (e.g., the Internet, a cloud network, or an operator-specific network) through a base station or an access point. In addition, for example, the communication unit 103 communicates with a terminal (e.g., a terminal of a pedestrian or a store, or a machine type communication (MTC) terminal) located near the vehicle using a peer-to-peer (P2P) technology. Moreover, for example, the communication unit 103 performs V2X communication, such as vehicle-to-vehicle communication, vehicle-to-infrastructure communication, vehicle-to-home communication between the vehicle and a home, and vehicle-to-pedestrian communication. In addition, for example, the communication unit 103 includes a beacon receiver that receives radio waves or electromagnetic waves transmitted from, for example, a radio station installed on a road, and obtains information about, for example, the current position, traffic congestion, traffic control, or necessary time.
[0103] Examples of the in-vehicle equipment 104 include mobile equipment or wearable equipment of persons on board the vehicle, information equipment brought into or attached to the vehicle, and a navigation device that searches for a route to any destination.
[0104] The output control unit 105 controls the output of various information to the occupants of the vehicle or to the outside of the vehicle. For example, the output control unit 105 generates an output signal including at least one of visual information (such as image data) or audio information (such as sound data), supplies the output signal to the output unit 106, and thereby controls the output of the visual information and the audio information from the output unit 106. Specifically, for example, the output control unit 105 combines the data of the images captured by the different image capture devices of the data acquisition unit 102, generates a bird's-eye view image, a panoramic image, etc., and supplies the output signal including the generated image to the output unit 106. In addition, for example, the output control unit 105 generates sound data including, for example, a warning buzzer or a warning message that warns of collision, contact, or entering a dangerous area, and supplies the output signal including the generated sound data to the output unit 106.
[0105] The output unit 106 includes a device capable of outputting visual information or audio information to a person on board the vehicle or outside the vehicle. For example, the output unit 106 includes a display device, an instrument panel, an audio speaker, headphones, a wearable device (such as a glasses-type display for wearing on a person on board), a projector, a lamp, etc. Instead of a device including a conventional display, the display device included in the output unit 106 may be a device that displays visual information in the driver's field of view, such as a head-up display, a transparent display, or a device including an augmented reality (AR) display function.
[0106] The powertrain control unit 107 generates various control signals and supplies them to the powertrain 108, thereby controlling the powertrain 108. In addition, the powertrain control unit 107 supplies control signals to structural elements other than the powertrain 108 as necessary to, for example, notify them of the state of controlling the powertrain 108.
[0107] The powertrain 108 includes various devices related to the power transmission of the vehicle. For example, the powertrain 108 includes a driving force generating device (such as an internal combustion engine and a driving motor) for generating driving force, a driving force transmitting mechanism for transmitting driving force to wheels, a steering mechanism for adjusting a steering angle, a braking device for generating braking force, an anti-lock braking system (ABS), an electronic stability control (ESC) system, an electric power steering device, etc.
[0108] The vehicle body-related control unit 109 generates various control signals, supplies them to the vehicle body-related system 110, and thereby controls the vehicle body-related system 110. In addition, the vehicle body-related control unit 109 supplies control signals to structural elements other than the vehicle body-related system 110 as necessary to, for example, notify them of the state of controlling the vehicle body-related system 110.
[0109] The vehicle body related system 110 includes various vehicle body related devices provided to the vehicle body. For example, the vehicle body related system 110 includes a keyless entry system, a smart key system, a power window device, a power seat, a steering wheel, an air conditioner, various lights (such as headlights, taillights, brake lights, direction indicators, and fog lights), and the like.
[0110] For example, the storage unit 111 includes a read-only memory (ROM), a random access memory (RAM), a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device, an optical storage device, a magneto-optical storage device, etc. The storage unit 111 stores therein various programs, data, etc. used by various structural elements of the vehicle control system 100. For example, the storage unit 111 stores therein map data such as a three-dimensional high-accuracy map, a global map, and a local map. The high-accuracy map is a dynamic map, etc. The accuracy of the global map is lower than that of the high-accuracy map, but it covers a wider area than the high-accuracy map. The local map includes information about the surroundings of the vehicle.
[0111] The automatic driving control unit 112 performs control related to automatic driving, such as autonomous driving or driving assistance. Specifically, for example, the automatic driving control unit 112 performs cooperative control aimed at realizing the functions of an advanced driver assistance system (ADAS), including collision avoidance or shock absorption for the vehicle, driving behind a leading vehicle based on the distance between vehicles, driving while maintaining the vehicle speed, collision warning of the vehicle, warning of lane departure of the vehicle, etc. In addition, for example, the automatic driving control unit 112 performs cooperative control aimed at realizing, for example, automatic driving (autonomous driving without the need for driver operation). The automatic driving control unit 112 includes a detection unit 131, a self-position estimation unit 132, a state analysis unit 133, a planning unit 134, and a mobile control unit 135.
[0112] The detection unit 131 detects various information required for controlling the automatic driving. The detection unit 131 includes a vehicle exterior information detection unit 141, a vehicle interior information detection unit 142, and a vehicle state detection unit 143.
[0113] The vehicle external information detection unit 141 performs processing for detecting information about the outside of the vehicle based on data or signals from each structural element of the vehicle control system 100. For example, the vehicle external information detection unit 141 performs processing for detecting, identifying and tracking objects around the vehicle and processing for detecting the distance of the object. Examples of detection target objects include vehicles, people, obstacles, structures, roads, traffic lights, traffic signs and road signs. In addition, for example, the vehicle external information detection unit 141 performs processing for detecting the environment around the vehicle. Examples of the detection target surrounding environment include weather, temperature, humidity, brightness and road conditions. The vehicle external information detection unit 141 supplies data indicating the result of the detection processing to, for example, the own position estimation unit 132, the map analysis unit 151 of the state analysis unit 133, the traffic rule recognition unit 152 and the state recognition unit 153, and the emergency avoidance unit 171 of the mobile control unit 135.
[0114] The vehicle interior information detection unit 142 performs processing for detecting information about the interior of the vehicle based on data or signals from each structural element of the vehicle control system 100. For example, the vehicle interior information detection unit 142 performs processing for authenticating and identifying the driver, processing for detecting the driver's state, processing for detecting the person on board, and processing for detecting the interior environment of the vehicle. Examples of the driver's detection target state include physical condition, degree of arousal, degree of concentration, degree of fatigue, and direction of sight. Examples of detection target interior vehicle environments include temperature, humidity, brightness, and odor. The vehicle interior information detection unit 142 supplies data indicating the result of the detection processing to, for example, the state recognition unit 153 of the state analysis unit 133 and the emergency avoidance unit 171 of the mobile control unit 135.
[0115] The vehicle state detection unit 143 performs processing for detecting the state of the host vehicle based on data or signals from each structural element of the vehicle control system 100. Examples of the detection target state of the host vehicle include speed, acceleration, steering angle, presence or absence of abnormality and its details, driving operation state, position and inclination of the electric seat, state of the door lock, and state of other vehicle-mounted equipment. The vehicle state detection unit 143 supplies data indicating the result of the detection processing to, for example, the state recognition unit 153 of the state analysis unit 133 and the emergency avoidance unit 171 of the mobile control unit 135.
[0116] The own position estimation unit 132 performs processing for estimating the position, posture, etc. of the own vehicle based on data or signals from various structural elements of the vehicle control system 100 (such as the vehicle external information detection unit 141, and the state recognition unit 153 of the state analysis unit 133). In addition, the own position estimation unit 132 generates a local map (hereinafter referred to as the own position estimation map) for estimating the own position as needed. For example, the own position estimation map is a high-accuracy map using a technology such as simultaneous localization and mapping (SLAM). The own position estimation unit 132 supplies data indicating the result of the estimation processing to, for example, the map analysis unit 151 of the state analysis unit 133, the traffic rule recognition unit 152, and the state recognition unit 153. In addition, the own position estimator 132 stores the own position estimation map in the storage unit 111.
[0117] The state analysis unit 133 performs a process of analyzing the state of the vehicle and its surroundings. The state analysis unit 133 includes a map analysis unit 151 , a traffic regulation recognition unit 152 , a state recognition unit 153 , and a state prediction unit 154 .
[0118] The map analysis unit 151 performs processing of analyzing various maps stored in the storage unit 111, and constructs a map including information required for the automatic driving process, using data or signals from various structural elements of the vehicle control system 100, such as the own position estimation unit 132 and the vehicle external information detection unit 141, as necessary. The map analysis unit 151 supplies the constructed map to, for example, the traffic rule recognition unit 152, the state recognition unit 153, and the state prediction unit 154, as well as the route planning unit 161, the behavior planning unit 162, and the movement planning unit 163 of the planning unit 134.
[0119] The traffic rule recognition unit 152 performs processing for recognizing traffic rules around the host vehicle based on data or signals from the various structural elements of the vehicle control system 100, such as the own position estimation unit 132, the vehicle external information detection unit 141, and the map analysis unit 151. The recognition processing makes it possible to recognize the position and state of traffic lights around the host vehicle, the details of traffic control performed around the host vehicle, and the drivable lanes. The traffic rule recognition unit 152 supplies data indicating the result of the recognition processing to, for example, the state prediction unit 154.
[0120] The state recognition unit 153 performs processing for recognizing the state related to the vehicle based on data or signals from various structural elements of the vehicle control system 100 (such as the own position estimation unit 132, the vehicle external information detection unit 141, the vehicle internal information detection unit 142, the vehicle state detection unit 143, and the map analysis unit 151). For example, the state recognition unit 153 performs processing for recognizing the state of the vehicle, the state of the surroundings of the vehicle, the state of the driver of the vehicle, etc. In addition, when necessary, the state recognition unit 153 generates a local map (hereinafter referred to as a state recognition map) for recognizing the state of the surroundings of the vehicle. The state recognition map is, for example, an occupancy grid map.
[0121] Examples of the recognition target state of the vehicle include the position, posture, and movement (such as speed, acceleration, and direction of movement) of the vehicle, as well as the presence or absence of abnormalities and their details. Examples of the recognition target state around the vehicle include the type and position of stationary objects around the vehicle; the type, position, and movement (such as speed, acceleration, and direction of movement) of moving objects around the vehicle; the structure of the road around the vehicle and the condition of the road surface; and the weather, temperature, humidity, and brightness around the vehicle. Examples of the recognition target state of the driver include physical condition, degree of arousal, degree of concentration, degree of fatigue, line of sight movement, and driving operation.
[0122] The state recognition unit 153 supplies data indicating the result of the recognition processing (including the state recognition map as necessary) to, for example, the own position estimation unit 132 and the state prediction unit 154. In addition, the state recognition section 153 stores the state recognition map in the storage unit 111.
[0123] The state prediction unit 154 performs processing for predicting a state related to the own vehicle based on data or signals from various structural elements of the vehicle control system 100, such as the map analysis unit 151, the traffic rule recognition unit 152, and the state recognition unit 153. For example, the state prediction unit 154 performs processing for predicting the state of the own vehicle, the state around the own vehicle, the state of the driver, and the like.
[0124] Examples of predicted target states of the vehicle include the behavior of the vehicle, the occurrence of abnormalities in the vehicle, and the drivable distance of the vehicle. Examples of predicted target states around the vehicle include the behavior of moving objects, changes in the state of traffic lights, and changes in the environment around the vehicle (such as weather). Examples of predicted target states of the driver include the driver's behavior and physical condition.
[0125] The state prediction unit 154 supplies data indicating the result of the prediction processing together with the data from the traffic regulation recognition unit 152 and the state recognition unit 153 to, for example, the route planning unit 161 , the behavior planning unit 162 , and the movement planning unit 163 of the planning unit 134 .
[0126] The route planning unit 161 plans a route to a destination based on data or signals from various structural elements of the vehicle control system 100, such as the map analysis unit 151 and the state prediction unit 154. For example, the route planning unit 161 sets a route from a current position to a specified destination based on a global map. In addition, for example, the route planning unit 161 appropriately changes the route based on the state of, for example, traffic congestion, accidents, traffic control, and construction, and the physical condition of the driver. The route planning unit 161 supplies data indicating the planned route to, for example, the behavior planning unit 162.
[0127] Based on data or signals from various structural elements of the vehicle control system 100 (such as the map analysis unit 151 and the state prediction unit 154), the behavior planning unit 162 plans the behavior of the host vehicle so as to safely travel on the route planned by the route planning unit 161 within the time planned by the route planning unit 161. For example, the behavior planning unit 162 makes plans about, for example, starting to move, stopping, driving directions (such as forward movement, backward movement, left turn, right turn, and direction change), driving lanes, driving speeds, and passing. The behavior planning unit 162 supplies data indicating the planned behavior of the host vehicle to, for example, the movement planning unit 163.
[0128] Based on data or signals from various structural elements of the vehicle control system 100 (such as the map analysis unit 151 and the state prediction unit 154), the movement planning unit 163 plans the movement of the host vehicle so as to realize the behavior planned by the behavior planning unit 162. For example, the movement planning unit 163 makes plans regarding, for example, acceleration, deceleration, and a driving route. The movement planning unit 163 supplies data indicating the planned movement of the host vehicle to, for example, the acceleration / deceleration control unit 172 and the direction control unit 173 of the movement control unit 135.
[0129] The movement control unit 135 controls the movement of the vehicle. The movement control unit 135 includes an emergency avoidance unit 171 , an acceleration / deceleration control unit 172 , and a direction control unit 173 .
[0130] Based on the results of the detection performed by the vehicle external information detection unit 141, the vehicle internal information detection unit 142, and the vehicle state detection unit 143, the emergency avoidance unit 171 performs processing for detecting emergency events (such as collision, contact, entry into a dangerous area, an unusual situation of the driver, and anomalies in the vehicle). When the emergency avoidance unit 171 detects the occurrence of an emergency, the emergency avoidance unit 171 plans the movement of the vehicle, such as sudden stops or quick turns, to avoid the emergency. The emergency avoidance unit 171 supplies data indicating the planned movement of the vehicle to, for example, the acceleration / deceleration control unit 172 and the direction control unit 173.
[0131] The acceleration / deceleration control unit 172 controls acceleration / deceleration to realize the movement of the host vehicle planned by the movement planning unit 163 or the emergency avoidance unit 171. For example, the acceleration / deceleration control unit 172 calculates a control target value of a driving force generating device or a braking device in order to realize a planned acceleration, a planned deceleration, or a planned sudden stop, and supplies a control instruction indicating the calculated control target value to the powertrain control unit 107.
[0132] The direction control unit 173 controls the direction to realize the movement of the host vehicle planned by the movement planning unit 163 or the emergency avoidance unit 171. For example, the direction control unit 173 calculates the control target value of the steering mechanism in order to realize the travel route planned by the movement planning unit 163 or the quick turn planned by the emergency avoidance unit 171, and supplies a control instruction indicating the calculated control target value to the powertrain control unit 107.
[0133] [Example of Configuration of Self-Position Estimation System]
[0134] Figure 31 is a block diagram of an example of the configuration of the own position estimation system 200 to which the present technology has been applied. The own position estimation system 200 mainly relates to the processing performed by the own position estimation unit 132, the vehicle external information detection unit 141, and the state recognition unit 153 in the vehicle control system 100, and the processing of generating a map for performing the processing of estimating the own position.
[0135] The own position estimation system 200 is a system that estimates the own position and posture of the vehicle 10 .
[0136] The own position estimation system 200 includes a control unit 201 , an image acquisition unit 202 , a vehicle state information acquisition unit 203 , a feature point extraction unit 204 , a feature point tracking unit 205 , a map generation unit 206 , an estimation unit 207 , and a map information storage unit 208 .
[0137] In the own position estimation system 200, the own position (of the vehicle 10) required for the control processing performed by the vehicle control system 100 is estimated. In the own position estimation system 200, image information about the image captured by the camera 300, vehicle state information from the vehicle state detection sensor 400, and the like are used to estimate the position of the vehicle 10.
[0138] Based on the control prediction information from the server device 500 , the control unit 201 outputs weight assignment information regarding weight assignment at the time of estimation to the estimation unit 207 , which weight assignment information indicates how the image information and the vehicle state detection information are respectively weighted for estimating the own position and posture of the vehicle 10 .
[0139] In addition, based on the control prediction information, the control unit 201 controls how to weight the respective image information acquired from the plurality of cameras 300 for estimating the own position and posture of the vehicle 10. The control unit 201 outputs weight assignment information on weight assignment to each camera to the image acquisition unit 202.
[0140] Furthermore, based on the control prediction information, the control unit 201 performs control for masking of feature extraction areas not used for feature point extraction performed for estimating the own position and posture of the vehicle 10. The control unit 201 outputs information on masking of feature point extraction areas to the feature point extraction unit 204.
[0141] The image acquisition unit 202 acquires images captured by the camera 300 installed in the vehicle 10 and used as a sensing device in time sequence. In the present embodiment, a plurality of cameras 300 are installed, and this makes it possible to acquire a distance image obtained due to parallax. Note that a single camera may be installed to acquire a distance image from a plurality of frames of images captured in time sequence. The camera is included in the above-mentioned data acquisition unit 102.
[0142] The image acquisition unit 202 outputs the time-sequential images as the selected images to the feature point extraction unit 204 together with the weight assignment information on the assignment of weights to each camera from the control unit 201 .
[0143] The weight assignment to the camera 300 includes, for example, selecting a camera 300 not used in estimating the own position and orientation from among the plurality of cameras 300. In this case, the weight assigned to the image information about the image captured by the unused camera 300 is zero.
[0144] The vehicle state information acquisition unit 203 acquires the results of vehicle state detection performed by the vehicle state detection sensor 400 installed in the vehicle 10 in time series.
[0145] Examples of the vehicle state detection sensor 400 include a GNSS for detecting the current position of the vehicle 10, and sensors for detecting the state of the vehicle 10, such as a gyro sensor; an acceleration sensor; an inertial measurement unit (IMU); and sensors for detecting the operation amount of an accelerator pedal, the operation amount of a brake pedal, the steering angle of a steering wheel, the number of revolutions of an engine, the number of revolutions of a motor, the speed of wheel rotation, etc.
[0146] Based on the information on masking of the feature point extraction area from the control unit 201 , the feature point extraction unit 204 masks the feature point extraction area in the time-sequential image input by the image acquisition unit 202 as necessary.
[0147] For example, the area where the sun is located in the image is a masked area obtained by masking the feature point extraction area, and feature points located in this area are not extracted.
[0148] The feature point extraction unit 204 extracts feature points of the stationary object from an area outside a masked area obtained by masking the feature point extraction area in the image, and outputs the extracted feature points to the feature point tracking unit 205 .
[0149] Specifically, the feature point extraction unit 204 extracts stationary objects (landmarks) from the time-sequential images that are successively input, and extracts feature points of the extracted stationary objects.
[0150] The feature point tracking unit 205 tracks the feature points extracted by the feature point extraction unit 204 in the sequentially input time-sequential images, and supplies information on the tracking to the map generation unit 206 .
[0151] The map generation unit 206 generates map information which is suitable for estimation of the own position and includes three-dimensional coordinates (three-dimensional points) of stationary objects (feature points) in the world coordinate system of the object.
[0152] The map generation unit 206 updates the initial map at preset intervals. In other words, the map generation unit 206 initializes the map information of the object (the coordinates of the object in the world coordinate system) stored in the map information storage unit 208 at preset intervals to update the map information.
[0153] Based on the weight assignment information about the estimated assigned weights output by the control unit 201, the estimation unit 207 assigns weights to the map information generated by the map generation unit 206 and the vehicle state detection information output by the vehicle state information acquisition unit 203, and uses this information to estimate the vehicle 10's own position and posture.
[0154] Based on the coordinates of the object in the world coordinate system (the three-dimensional coordinates of the feature point), the estimation unit 207 estimates a transformation matrix representing the transformation from the world coordinate system to the camera coordinate system representing the camera-based coordinate system, and estimates a rotation angle representing the position and posture of the vehicle 10 relative to the stationary object (feature point) based on the transformation matrix.
[0155] For example, when the weight assignment information indicates that the weight assigned to image information is 100 and the weight assigned to vehicle state detection information is 0, the estimation unit 207 estimates the own position and posture of the vehicle 10 based only on the map information generated by the map generation unit 206 based on the image information.
[0156] On the other hand, when the weight assignment information indicates that the weight assigned to the image information is 0 and the weight assigned to the vehicle state detection information is 100, the estimation unit 207 estimates the own position and posture of the vehicle 10 based only on the vehicle state detection information.
[0157] For example, when it is difficult to use the camera 300 to obtain an image suitable for estimating the own position and posture due to sunlight (because the sun is reflected in the image), the own position and posture of the vehicle 10 are estimated using the vehicle state detection information and the image information in a state where the vehicle state detection information has a greater weight than the image information.
[0158] The map information storage unit 208 stores therein map information including coordinates of objects in the world coordinate system.
[0159] [Example of camera configuration]
[0160] Figure 4 ] is a block unit of a configuration example of the camera 300 serving as an image capturing device.
[0161] The camera 300 is an image sensor that captures an image around the vehicle 10 at a designated frame rate, and detects image information about the image around the vehicle 10 .
[0162] For example, two front cameras and two rear cameras are installed in the vehicle 10, the two front cameras capture images of the field of view in front of the vehicle 10 and are respectively arranged on the left and right sides of the front part of the vehicle body, and the two rear cameras capture images of the field of view behind the vehicle 10 and are respectively arranged on the left and right sides of the rear part of the vehicle body.
[0163] For example, an RGB camera including an image sensor such as CCD or CMOS is used as the camera 300. The camera 300 is not limited thereto, and, for example, an image sensor that detects infrared light or polarized light may be appropriately used. The use of infrared light or polarized light makes it possible to generate image information about an image in which, for example, the image does not appear to change greatly even if the weather changes.
[0164] In the camera 300 according to the present embodiment, image information is generated by performing, for example, exposure control and photometry area control based on control prediction information from the server device 500 .
[0165] The camera 300 includes a camera control unit 301, a lens unit driving circuit 302, a lens unit 303, a mechanical shutter (hereinafter referred to as the mechanical shutter, and the same applies to this figure) driving circuit 304, a mechanical shutter 305, an image sensor driving circuit 306, an image sensor 307, an automatic gain control (AGC) circuit 308, a signal processing unit 309 and a metering unit 310.
[0166] The camera control unit 301 includes an exposure control unit 3011 and a photometry area control unit 3012 .
[0167] The exposure control unit 3011 generates a control signal for controlling exposure based on the control prediction information supplied from the server device 500 and the result of light metering performed by the light metering unit 310 .
[0168] Based on the control prediction information supplied by the server device 500, the exposure control unit 3011 generates a control signal that controls the lens position and the stop of the lens unit 303 through the lens unit drive circuit 302, controls the drive of the mechanical shutter 305 through the mechanical shutter drive circuit 304, controls the electrical operation of the image sensor 307 through the image sensor drive circuit 306, and controls the operation timing of the AGC circuit 308. Thus, the exposure is controlled.
[0169] Based on the control prediction information supplied from the server device 500 , the photometry area control unit 3012 supplies a control signal defining the photometry area to the photometry unit 310 .
[0170] For example, the metering area control unit 3012 generates a control signal defining an area for the metering unit 310 based on control prediction information indicating that areas in the image that have been predicted by the server device 500 as where the sun will be reflected will not be set as metering targets (regarding the shielding processing of the metering area) while other areas will be set as metering targets.
[0171] The lens unit driving circuit 302 includes a motor and the like, and adjusts the focal position and the aperture by moving the lens position of the lens unit 303 based on a control signal supplied from the camera control unit 301 .
[0172] The mechanical shutter drive circuit 304 controls the shutter speed and shutter timing of the mechanical shutter 305 based on a control signal supplied from the camera control unit 301 .
[0173] The mechanical shutter 305 is arranged on the entire surface of the image sensor 307 , and is opened or closed according to control performed by the mechanical shutter driving circuit 304 , so that light passing through the lens unit 303 is transmitted through the mechanical shutter 305 or is blocked by the mechanical shutter 305 .
[0174] Note that an example using a mechanical shutter is described in the present embodiment, but an electronic shutter may be used.
[0175] The image sensor driving circuit 306 generates a signal for driving the image sensor 307 based on, for example, a timing signal supplied from the camera control unit 301 , and adjusts, for example, the timing of capturing an image.
[0176] The image sensor 307 includes a solid-state imaging element such as a complementary metal oxide semiconductor (CMOS) image sensor or a charge coupled device (CCD) image sensor.
[0177] The image sensor 307 receives light entering through the lens unit 303 from the subject to photoelectrically convert the received light, and outputs an analog image signal to the AGC circuit 308 and the light metering unit 310 depending on the amount of the received light.
[0178] The AGC circuit 308 adjusts the gain of the image signal based on the control signal from the exposure control unit 3011 , and outputs the image signal whose gain has been adjusted to the signal processing unit 309 .
[0179] The signal processing unit 309 performs analog / digital (A / D) conversion on the analog image signal from the AGC circuit 308. In addition, the signal processing unit 309 applies denoising processing and the like to the image data represented by the digital signal obtained by the A / D conversion, and outputs the image data (image information) obtained as a result of applying the denoising processing and the like to the image acquisition unit 202 of the self-position estimation system 200.
[0180] The photometry unit 310 performs photometry based on the image signal from the image sensor 307. When performing photometry, the photometry unit 310 performs photometry on a defined photometry area based on a control signal supplied from the camera control unit 301. The photometry unit 310 outputs the result of photometry to the camera control unit 301.
[0181] [Example of Configuration of Server Device]
[0182] Figure 5 is a block diagram of a configuration example of the server device 500 .
[0183] like Figure 5 As shown in , the server device 500 includes a communication unit 501, an information acquisition unit 502, a unit 503 for predicting the position and posture of the vehicle at T+N, a unit 504 for predicting the position of an interference factor (sun) in the image, and a control prediction unit 505.
[0184] The communication unit 501 communicates with equipment (eg, an application server or a control server) located in the vehicle 10 or an external network (eg, the Internet, a cloud network, or an operator-specific network) through a base station or an access point.
[0185] The communication unit 501 receives various information from the vehicle 10 and outputs the received information to the information acquisition unit 502. The communication unit 501 transmits the control prediction information received from the control prediction unit 505 to the vehicle 10.
[0186] The information acquisition unit 502 acquires parameter information about parameters of the camera 300 , information about the position and posture of the vehicle 10 at time T, and vehicle state information of the vehicle 10 at time T from the vehicle 10 through the communication unit 501 .
[0187] Parameter information about the parameters of the camera 300 is output to a unit 504 for predicting the position of the sun in the image.
[0188] Information on the position and posture of the vehicle 10 at time T and vehicle state information of the vehicle 10 at time T are output to a unit 503 for predicting the position and posture of the vehicle at time T+N.
[0189] The information about the position of the vehicle 10 is, for example, information of a GNSS signal detected by the data acquisition unit 102 .
[0190] Vehicle status information includes information detected by a gyro sensor, an acceleration sensor, and an inertial measurement unit (IMU); and information such as the operation amount of an accelerator pedal, the operation amount of a brake pedal, the steering angle of a steering wheel, the number of engine revolutions, the number of motor revolutions, or the speed at which wheels rotate.
[0191] The parameters of the camera 300 include internal parameters and external parameters.
[0192] The internal parameters of the camera 300 are information specific to the camera that is determined regardless of the vehicle state, such as the focal length of the camera lens, the distortion characteristics of the lens, and the error of the installation position of the lens.
[0193] The external parameters of the camera 300 are information about the position and orientation of each camera 300 installed with the own position and posture of the vehicle 10 as the center of the vehicle 10, that is, information about the position and posture of the camera 300 using the center of the vehicle 10 as a reference.
[0194] The unit 503 for predicting the position and posture of the vehicle at T+N predicts the position and posture of the vehicle 10 at T+N based on the information about the position and posture of the vehicle 10 at time T output from the information acquisition unit 502 and the vehicle state information of the vehicle 10 at time T. The unit 503 for predicting the position and posture of the vehicle at T+N outputs the prediction result to the unit 504 for predicting the position of the sun in the image.
[0195] The unit 504 for predicting the position of the sun in the image predicts the position of the sun in the image to be captured by the camera 300 at T+N based on parameter information of the camera 300, information about the position and posture of the vehicle at T+N, information 506 about the date and time / weather, and map information 507.
[0196] Specifically, first, using date and time information, information about the predicted position and posture of the vehicle 10 at T+N, and map information 507, the unit 504 for predicting the position of the sun in the image calculates the altitude (elevation angle) and azimuth angle of the sun in the position where the vehicle 10 is predicted to be at T+N.
[0197] Next, the unit 504 for predicting the position of the sun in the image determines whether the sun will appear at the position where the vehicle 10 is predicted to exist at T+N based on weather information about the weather.
[0198] For example, when the unit 504 for predicting the position of the sun in the image determines that the sun will appear in clear weather based on weather information, the unit 504 for predicting the position of the sun in the image predicts the position of the sun in the image to be captured by the camera 300 at T+N based on information about the altitude and azimuth of the sun at T+N, information about the position and posture of the vehicle 10, and parameter information of the camera 300.
[0199] On the other hand, when the unit 504 for predicting the position of the sun in the image has determined based on weather information that the sun will not appear in rainy weather, the unit 504 for predicting the position of the sun in the image predicts that the sun will not be reflected in the image captured by the camera 300 at T+N.
[0200] Here, for example, the information 506 on date and time / weather may be acquired by the server device 500 communicating with an application server existing in an external network.
[0201] The map information 507 is stored in advance in the server device 500 and is updated at preset intervals when necessary.
[0202] The result of the prediction performed by the unit 504 for predicting the position of the sun in the image on the position of the sun in the image is output to the control prediction unit 505 .
[0203] Based on the input result of the prediction performed on the position of the sun in the image, the control prediction unit 505 predicts the control performed on the sensing device. Control prediction information on the control predicted by the control prediction unit 505 is transmitted to the vehicle 10 through the communication unit 501.
[0204] The control performed for the sensing device includes the control performed for the camera 300 and the control performed for the sensing device in the own position estimation system 200 .
[0205] The control performed for the camera 300 includes exposure control and photometry area control.
[0206] First, exposure control as control performed on the camera 300 is described.
[0207] In general, in the camera 300, an image sensor included in the camera 300 receives light from a subject, and an image signal depending on the amount of light received is supplied to a photometric unit. In the photometric unit, photometry is performed based on the image signal, and an appropriate exposure value is calculated based on a brightness value obtained as a photometric value. Exposure control is performed based on the calculated exposure value.
[0208] When exposure control is performed based on the exposure value calculated at time T, an image captured under the appropriate exposure condition at time T is obtained at T+M (M>0), that is, after M minutes have passed since time T. In other words, it is impossible to obtain a perfect image for time T under the appropriate exposure condition at time T, and thus a time lag occurs.
[0209] On the other hand, in the camera 300 of the vehicle 10, the exposure condition for the camera 300 to perform image capturing at T+N can be set in advance based on the control prediction information about the exposure control performed at T+N for the camera 300 predicted by the server device 500. This makes it possible to perform image capturing at T+N without a time lag under an appropriate exposure condition for the state at T+N.
[0210] Examples of exposure control include controls such as adjustment of shutter speed and adjustment of gain of image signals. For example, when the sun is reflected in an image, the control prediction unit 505 predicts exposure controls such as increasing shutter speed and reducing gain because the sun makes the image too clear.
[0211] Information on the control prediction is transmitted to the vehicle 10, and exposure control is performed for the camera 300 based on the transmitted information. This is the exposure condition when image capturing is performed at T+N.
[0212] Here, when an image is used in the self-position estimation system 200 to estimate the self-position and posture, the line of sight of the feature points in the image may be lost or the feature points in the image may be incorrectly identified due to the sun being reflected in the image when extracting the feature points, and this will result in a decrease in the accuracy of estimating the self-position and posture.
[0213] On the other hand, in the present embodiment, the reflection of the sun in the image at T+N is predicted in advance to predict exposure control so that an appropriate image can be obtained. The image to be captured can be captured at T+N under the exposure condition based on the information about the prediction.
[0214] This enables the vehicle 10 to obtain an image captured with sufficient exposure and suitable for the state at T + N. Therefore, when estimating the own position and posture using the image, an image captured under appropriate exposure conditions and in which the line of sight of the feature point is less likely to be lost can be used, and this improves the accuracy of estimating the own position and posture.
[0215] Next, photometry area control as control performed on the camera 300 is described.
[0216] For example, when the sun is reflected in the image, the control prediction unit 505 predicts the photometric area control to be performed so that the area in the image where the sun is reflected is excluded from the photometric area. Control prediction information about the control predicted by the control prediction unit 505 is sent to the vehicle 10 via the communication unit 501.
[0217] Here, when the sun is reflected in the image, the area where the sun is reflected and the surroundings of the area in the image are too bright, and the area other than the overbright area is dark, which causes too thick shadows. When estimating the own position and posture in the own position estimation system 200 using such an image, the line of sight of the feature point in the image may be lost or the feature point in the image may be erroneously recognized.
[0218] On the other hand, in the present embodiment, the reflection of the sun is predicted in advance, and the area in the image where the sun is reflected is excluded from the photometry area where photometry is performed. This makes it possible to provide an appropriate image without excessively thick shadows. Therefore, when estimating the own position and posture using an image, an appropriate image in which the sight line of the feature point is less likely to be lost can be provided, and this improves the accuracy of estimating the own position and posture.
[0219] The controls performed on the sensing device in the self-position estimation system 200 include controls performed when estimating the self-position and posture and related to assigning weights to image information and vehicle status detection information, controls performed when estimating the self-position and posture and related to extracting masked areas of feature points, and controls performed when estimating the self-position and posture and related to assigning weights to individual image information from multiple cameras 300.
[0220] First, control related to assigning weights to image information and vehicle state detection information is described.
[0221] For example, when the sun is reflected in an image, the area where the sun is reflected and the surroundings of the area in the image are too bright, while areas other than the overly bright area are dark, which results in too thick shadows. When such an image is used to estimate the self-position and posture in the self-position estimation system 200, the sight of the feature point may be lost or the feature point may be erroneously recognized.
[0222] In this case, the control prediction unit 505 predicts the control to be performed so that the vehicle state detection information has a greater weight than the image information to estimate the own position and posture in the own position estimation system 200. Since the own position and posture are estimated in the vehicle 10 based on the information about such control prediction, the accuracy of estimating the own position and posture is improved.
[0223] Next, control of the feature point extraction mask area is described.
[0224] For example, when the sun is reflected in an image, due to the brilliance of the sun, the sight of a feature point in the image may be lost or the feature point in the image may be erroneously recognized in an area in the image where the sun is reflected.
[0225] In this case, the control prediction unit 505 predicts the control to be performed so that when the image is used to estimate the self-position and posture in the self-position estimation system 200, the area in the image where the sun is reflected is set as an area not used for extracting feature points (feature point extraction shielded area).
[0226] In the vehicle 10, based on the information about such control prediction, the area where the sun is reflected is first shielded to set an area from which feature points are not extracted, and then feature points are extracted to estimate the own position and posture. This improves the accuracy of estimating the own position and posture using images.
[0227] Next, control related to assigning weights to respective pieces of image information from the plurality of cameras 300 is described.
[0228] For example, the control prediction unit 505 predicts the control to be performed so that when using an image to estimate its own position and posture, image information from camera 300 that captures an image in which the sun is reflected is lightly weighted, while image information from cameras 300 other than camera 300 that captures an image in which the sun is reflected is heavily weighted.
[0229] In the vehicle 10, based on information about such control prediction, the image acquired by the camera 300 that captures the image in which the sun is not reflected is mainly used to estimate the own position and posture. This allows the accuracy of estimating the own position and posture using the image to be improved.
[0230] [Control prediction processing]
[0231] Figure 6 The flow of control prediction processing performed in the server device 500 to generate control prediction information about prediction of control performed on the sensing device is illustrated. S represents a step.
[0232] When the control prediction processing starts, the information acquisition unit 502 acquires information about the vehicle 10, such as parameter information about parameters of the camera 300, information about the position and posture of the vehicle 10, and information about the state of the vehicle 10, from the vehicle 10 through the communication unit 501 (S1).
[0233] Next, the unit 503 for predicting the position and posture at T+N predicts the position and posture of the vehicle 10 at T+N based on the information about the position and posture of the vehicle 10 at time T output from the information acquisition unit 502 and the vehicle state information of the vehicle 10 at time T (S2).
[0234] Next, the unit 504 for predicting the position of the sun in the image predicts the position of the sun in the image to be captured by the camera 300 at T+N based on the parameter information of the camera 300, the information about the position and posture of the vehicle at T+N, the information 506 about the date and time / weather, and the map information 507 (S3).
[0235] Next, based on the information on the predicted position of the sun in the image, the control prediction unit 505 predicts control to be performed on the sensing device and generates control prediction information (control prediction signal) ( S4 ).
[0236] Next, the communication unit 501 transmits the generated control prediction information to the vehicle 10 ( S5 ).
[0237] The server device 500 includes hardware necessary for the configuration of a computer, such as a central processing unit (CPU), a read only memory (ROM), a random access memory (RAM), and a hard disk drive (HDD).
[0238] In the server apparatus 500 , the above-described control prediction process is performed by loading a program stored in the ROM into the RAM and executing the program to generate control prediction information regarding prediction of control performed on the sensing device.
[0239] As described above, in the control system 1 according to the present embodiment, control performed on the camera 300 installed in the vehicle 10 and the self-position estimation system 200 so as to reduce the influence caused by the reflection of the sun in the image captured at T+N is predicted based on information about the position and posture of the vehicle 10 at time T, map information 507, and information 506 about the date and time / weather.
[0240] In the vehicle 10, control performed for the camera 300 and the self-position estimation system 200 installed in the vehicle 10 is performed based on information about such control prediction. Therefore, an image suitable for the state of the vehicle at T+N and with the influence due to reflection of the sun (interference factor) mitigated can be obtained without time lag at T+N. This enables a highly robust control system to be obtained.
[0241] <Second Embodiment>
[0242] [Example of configuration of control system]
[0243] In this embodiment, a tunnel is taken as an example of an interference factor for description.
[0244] Figure 1 1 is a block diagram of an example of a schematic functional configuration of a control system 1000 of a sensing device to which the present technology is applied.
[0245] Figure 8 It is a block diagram of the functional configuration of the server device (information processing device) in the control system 1000.
[0246] In the following description, the same structural elements as those of the first embodiment may be denoted by the same reference numerals, and description thereof may be omitted.
[0247] The control system 1000 includes a vehicle control system 100 installed in a vehicle 10 as a mobile object and a server device 1500 serving as an information processing device. The vehicle control system 100 and the server device 1500 can communicate with each other, for example, through a wireless communication network.
[0248] The server device 1500 includes a communication unit 501, an information acquisition unit 502, a unit 503 for predicting the position and posture of the vehicle at T+N, a unit 1504 for predicting the position of an interference factor (tunnel) in an image (hereinafter referred to as a unit for predicting the position of a tunnel in an image), and a control prediction unit 1505.
[0249] The information acquisition unit 502 acquires parameter information about parameters of the camera 300 , information about the position and posture of the vehicle 10 , and vehicle state information of the vehicle 10 from the vehicle 10 through the communication unit 501 .
[0250] Parameter information about the parameters of the camera 300 is output to a unit 504 for predicting the position of a tunnel in an image.
[0251] In this embodiment, the unit 1504 for predicting the position of the tunnel in the image predicts the position of the tunnel (interference factor) in the image.
[0252] The unit 1504 for predicting the position of the tunnel in the image predicts the position of the tunnel in the image captured at T+N based on the information about the predicted own position and posture of the vehicle 10 at T+N and the map information 507. The tunnel position prediction information is output to the control prediction unit 1505. The map information 507 includes the tunnel position information.
[0253] Based on the input information about the position of the tunnel in the image, the control prediction unit 1505 predicts the control to be performed for the sensing device. The control prediction information about the control predicted by the control prediction unit 1505 is transmitted to the vehicle 10 through the communication unit 501.
[0254] The control performed for the sensing device includes control performed for the camera 300 , control performed for the sensing device in the own position estimation system 200 , and control performed for both the camera 300 and the own position estimation system 200 .
[0255] The control performed for the camera 300 includes exposure control and photometry area control.
[0256] The control prediction unit 1505 predicts exposure control performed for the camera 300 at T+N based on the prediction result of the position of the tunnel in the image captured at T+N. Information about the control prediction is transmitted to the vehicle 10. Based on the transmitted information, exposure control for the camera 300 is performed in the vehicle 10. This is the exposure condition when image capturing is performed at T+N.
[0257] For example, exposure control such as reducing the shutter speed and increasing the gain is predicted so that a dark image is not obtained and the interior of the tunnel appears in a proper image because it becomes dark in the tunnel.
[0258] In addition, the control prediction unit 1505 predicts the photometric area control performed for the camera 300 at T+N based on the prediction result of the position of the tunnel in the image captured at T+N. Information about the control prediction is transmitted to the vehicle 10, and the photometric area control for the camera 300 is performed based on the transmitted information. This is the photometric area condition when image capturing is performed at T+N.
[0259] For example, when there is a certain distance between the entrance of the tunnel and the vehicle 10 before the vehicle 10 enters the tunnel, the control prediction unit 1505 predicts the control to be performed so that an area other than the area inside the tunnel is set as the photometric area and the area other than the area inside the tunnel appears in an appropriate image, but the area in the image where the tunnel is located shows a thickened shadow. In other words, the control prediction unit 1505 predicts the control to be performed so that an image based on the brightness outside the tunnel rather than the brightness inside the tunnel is obtained.
[0260] Similarly, when the exit of the tunnel appears in the image while the vehicle is in the tunnel and when the vehicle approaches the exit of the tunnel to some extent, the control prediction unit 1505 predicts the control to be performed so that an area other than the area inside the tunnel is set as a photometric area.
[0261] When the vehicle 10 approaches the entrance of the tunnel and when the vehicle 10 approaches the tunnel by more than a certain distance, the control prediction unit 1505 predicts the control to be performed so that the area inside the tunnel is set as the photometric area and the inside of the tunnel appears in the appropriate image. In other words, the control prediction unit 1505 predicts the control to be performed so that an image based on the brightness of the inside of the tunnel is obtained.
[0262] Similarly, when the exit of the tunnel has not yet appeared in the image while the vehicle is inside the tunnel, or when the exit of the tunnel appears in the image while the vehicle is inside the tunnel but the vehicle is still far away from the exit of the tunnel, the control prediction unit 1505 predicts the control to be performed so that the area inside the tunnel is set as the metering area.
[0263] Of the control performed so that the area outside the tunnel is set as the photometric area and the control performed so that the area inside the tunnel is set as the photometric area, which control is selected may be determined depending on, for example, the proportion of the area where the tunnel appears in the image.
[0264] In addition, for the image captured when the area outside the tunnel is set as the metering area and the image captured when the area inside the tunnel is set as the metering area, the control prediction unit 1505 predicts the control performed so that the two images are interpolated so that there is no sharp change between the images.
[0265] Note that when the area outside the tunnel is set as the photometry area, control according to the above-mentioned first embodiment is performed for the camera or the self-position estimation system based on the position of the sun, or control according to the third embodiment described later is performed for the camera or the self-position estimation system based on the shadow of the structure.
[0266] This makes it possible to perform image capturing in the vehicle 10 under a photometric condition or an exposure condition suitable for the state at T+N.
[0267] The control performed on the sensing device in the self-position estimation system 200 includes control performed when estimating the self-position and posture and related to assigning weights to image information and vehicle status detection information, and control performed when estimating the self-position and posture and related to assigning weights to image information acquired respectively from multiple cameras 300.
[0268] The control prediction unit 1505 predicts how to weight the image information and the vehicle state detection information respectively in the own position estimation system 200 for estimating the position of the vehicle 10 .
[0269] For example, since it is dark in a tunnel, the sight of a feature point may be lost or the feature point may be erroneously recognized when estimating the own position and posture using image information in the own position estimation system 200. In this case, the control prediction unit 1505 predicts the control to be performed so that when estimating the own position and posture in the own position estimation system 200, the result of the estimation performed using the image information is lightly weighted, while the result of the estimation performed using the vehicle state detection information is heavily weighted.
[0270] Since the own position and posture in the vehicle 10 are estimated based on information on such control prediction, the accuracy of estimating the own position and posture of the vehicle 10 is improved.
[0271] In addition, the control prediction unit 1505 predicts control for how to weight the respective image information acquired by the plurality of cameras 300 in the own position estimation system 200 for estimating the position and posture of the vehicle 10. Examples of control for assigning weights to the cameras 300 include selection of the cameras 300 used when estimating the own position and posture.
[0272] For example, it is predicted that control is performed so that image information about an image captured by the camera 300 directed toward the tunnel is not used or is lightly weighted.
[0273] Next, control performed on both the camera 300 and the self-position estimation system 200 is described.
[0274] The control prediction unit 1505 predicts the control to be performed so that the camera 300 performs image capture alternately in the first mode and the second mode for each frame. In addition, the control prediction unit 1505 predicts the control to be performed for which of the images captured in the first mode and the images captured in the second mode is used for estimating the own position at T+N in the own position estimation system 200.
[0275] The information on the control prediction is transmitted to the vehicle 10. In the vehicle 10, the own position and posture of the vehicle 10 are estimated in the own position estimation system 200 based on the information.
[0276] The first mode is an image capturing mode when an area other than the area inside the tunnel is set as a photometric area. In this mode, settings are performed so that the area other than the area inside the tunnel appears in an image captured with appropriate exposure, but the area where the tunnel is located in the image shows a thickened shadow.
[0277] When the area inside the tunnel is set as the photometric area, the second mode is an image capture mode. In this mode, settings are performed so that the inside of the tunnel appears in an image captured with sufficient exposure. In the second mode, controls such as reducing the shutter speed and increasing the gain are performed.
[0278] The modes of shutter speed and gain are switched between a first mode and a second mode.
[0279] In the vehicle 10, a process of estimating the own position and posture is performed in the vehicle 10 based on control prediction information including image information and information indicating which one of the images captured in the first mode and the images captured in the second mode is used when estimating the own position, and the image information is about an image obtained by alternately performing image capture in the first mode and in the second mode for each frame.
[0280] In the case of a process of estimating the own position and posture based on control prediction information indicating the use of an image captured in the first mode, the image captured in the first mode is extracted from the acquired image information in the own position estimation system 200, and a process of estimating the own position and posture is performed based on the extracted image.
[0281] On the other hand, in the case of a process of estimating the own position and posture based on control prediction information indicating the use of an image captured in the second mode, the image captured in the second mode is extracted from the acquired image information in the own position estimation system 200, and a process of estimating the own position and posture is performed based on the extracted image.
[0282] Note that, herein, an example has been described in which the control prediction information includes information indicating which of the images in the first mode and the images in the second mode is used to perform processing for estimating the own position and posture, and one of the images captured in the first mode and the images captured in the second mode is used when estimating the own position.
[0283] In addition, the control prediction information may include information indicating how the results of processing for estimating one's own position and posture performed using images captured in the first mode and the results of processing for estimating one's own position and posture performed using images captured in the second mode are respectively weighted to integrate each other.
[0284] In the case of such control prediction information, a process of estimating the own position and posture is performed for each mode in the own position estimation system 200, that is, a process of estimating the own position and posture is performed using image information about an image captured in the first mode, and a process of estimating the own position and posture is performed using image information about an image captured in the second mode. Then, a process of estimating the own position and posture is performed in the own position estimation system 200 using a result obtained by assigning weights to the processing results in the respective modes and integrating the weighted processing results.
[0285] [Control prediction processing]
[0286] Figure 8The flow of control prediction processing performed in the server apparatus 1500 to generate control prediction information regarding prediction of control performed on the sensing device is illustrated.
[0287] When the control prediction process starts, the information acquisition unit 502 acquires parameter information about parameters of the camera 300, information about the position and posture of the vehicle 10 at time T, and vehicle state information of the vehicle 10 at time T from the vehicle 10 through the communication unit 501 (S11).
[0288] Next, the unit 503 for predicting the position and posture at T+N predicts the position and posture of the vehicle 10 at T+N based on the information about the position and posture of the vehicle 10 at time T output from the information acquisition unit 502 and the vehicle state information of the vehicle 10 at time T (S12).
[0289] Next, the unit 1504 for predicting the position of the tunnel in the image predicts the position of the tunnel in the image to be captured by the camera 300 at T+N based on the parameter information of the camera 300, the information about the position and posture of the vehicle at T+N, and the map information 507, and predicts whether the tunnel will appear in the image (S13).
[0290] When the determination performed in S13 is "NO", the process returns to S11 to be repeatedly performed.
[0291] When the determination performed in S13 is “YES”, the process moves to S14 .
[0292] In S14 , based on the tunnel position information, the control prediction unit 1505 predicts control to be performed on the sensing device and generates control prediction information (control prediction signal).
[0293] Next, the communication unit 501 transmits the generated control prediction information to the vehicle 10 ( S15 ).
[0294] The server device 1500 includes hardware necessary for the configuration of a computer, such as a CPU, a ROM, a RAM, and a HDD.
[0295] In the server apparatus 1500 , the above-described control prediction process is performed by loading a program stored in the ROM into the RAM and executing the program to generate control prediction information regarding prediction of control performed on the sensing device.
[0296] As described above, in the control system 1000 according to the present embodiment, based on the information about the position and posture of the vehicle 10 at time T and the map information 507, it is predicted that control is performed on the camera 300 installed in the vehicle 10 and the own position estimation system 200 so as to reduce the impact caused by the presence of the tunnel in the image captured at T+N.
[0297] In the vehicle 10, control performed for the camera 300 and the self-position estimation system 200 installed in the vehicle 10 is performed based on information about such control prediction. Therefore, an image suitable for the vehicle state at T+N and in which the influence due to the presence of the tunnel (interference factor) is mitigated can be obtained without time lag at T+N. This enables a highly robust control system to be obtained.
[0298] <Third Embodiment>
[0299] In the present embodiment, a shadow of a structure (such as a building structure) which is a stationary object is described as an example of a disturbance factor. In the following description, a building is taken as an example of a structure.
[0300] Figure 1 2 is a block diagram of an example of a schematic functional configuration of a control system 2000 of a sensing device to which the present technology is applied.
[0301] Fig. 9 25 is a block diagram of a functional configuration of a server device 2500 serving as an information processing device in a control system 2000 .
[0302] In the following description, the same structural elements as those of the first embodiment may be denoted by the same reference numerals, and description thereof may be omitted.
[0303] The control system 2000 includes a vehicle control system 100 installed in a vehicle 10 as a mobile object and a server device 2500 serving as an information processing device. The vehicle control system 100 and the server device 2500 can communicate with each other, for example, through a wireless communication network.
[0304] The server device 2500 includes a communication unit 501, an information acquisition unit 502, a unit 503 for predicting the position and posture of the vehicle at T+N, a unit 2504 for predicting the position of an interference factor (shadow of a building) in an image (hereinafter referred to as a unit for predicting the position of the shadow of a building in an image), and a control prediction unit 2505.
[0305] The information acquisition unit 502 acquires parameter information about parameters of the camera 300 , information about the position and posture of the vehicle 10 , and vehicle state information of the vehicle 10 from the vehicle 10 through the communication unit 501 .
[0306] Parameter information about the parameters of the camera 300 is output to the unit 2504 for predicting the position of the shadow of the building in the image.
[0307] The unit 2504 for predicting the position of the shadow of the building in the image predicts the position of the shadow (interference factor) of the building in the image.
[0308] The unit 2504 for predicting the position of the shadow of a building in the image predicts the position of the shadow of a building in the image to be captured by the camera 300 at T+N based on the parameter information of the camera 300, the information about the vehicle 10's own position and posture at T+N, the information 506 about the date and time / weather, and the map information 507.
[0309] Specifically, first, the unit 2504 for predicting the position of the shadow of the building in the image calculates the altitude (elevation angle) and azimuth angle of the sun at T+N using the date and time information, the information about the predicted own position and posture of the vehicle 10 at T+N, and the map information 507. The map information 507 includes the building position information.
[0310] Next, the unit 2504 for predicting the position of the shadow of the building in the image determines whether the sun will appear based on the weather information about the weather at the position of the vehicle 10 at T+N.
[0311] For example, when the unit 2504 for predicting the position of the shadow of a building in an image has determined that the sun will appear in clear weather, the unit 2504 for predicting the position of the shadow of a building in an image predicts the position of the shadow of the building in the image captured by the camera 300 at T+N based on information about the altitude and azimuth of the sun at T+N, information about the vehicle 10's own position and posture, parameter information of the camera 300, and map information 507.
[0312] The result of the prediction performed by the unit 2504 for predicting the position of the shadow of the building in the image on the position of the shadow of the building in the image is output to the control prediction unit 2505 .
[0313] Based on input information about the position of the shadow of the building in the image, the control prediction unit 2505 predicts control to be performed on the sensing device. Control prediction information about the control predicted by the control prediction unit 2505 is transmitted to the vehicle 10 through the communication unit 501.
[0314] The control performed for the sensing device includes control performed for the camera 300 , control performed for the sensing device in the own position estimation system 200 , and control performed for both the camera 300 and the own position estimation system 200 .
[0315] The control performed for the camera 300 includes exposure control and photometry area control.
[0316] Based on the information about the position of the shadow of the building in the image at T+N, the control prediction unit 2505 predicts control to be performed for exposure, such as adjustment of the shutter speed and adjustment of the gain of the image signal.
[0317] For example, when the shadow of a building appears in the image, the control prediction unit 2505 predicts exposure control, such as reducing the shutter speed and increasing the gain, because the image is likely to become darker.
[0318] The information on the control prediction is transmitted to the vehicle 10. Based on the transmitted control prediction information, exposure control for the camera 300 is performed in the vehicle 10, and this is the exposure condition when image capturing is performed at T+N.
[0319] This enables the vehicle 10 to obtain an image that is captured with sufficient exposure and is appropriate for the conditions at T+N.
[0320] In addition, when using images to estimate the own position and posture in the own position estimation system 200, images captured with sufficient exposure and in which the line of sight of feature points is less likely to be lost can be used, and this enables improving the accuracy of estimating the own position and posture.
[0321] Based on the information about the position of the shadow of the building in the image at T+N, the control prediction unit 2505 predicts the control to be performed for the photometric area. Control prediction information about the control predicted by the control prediction unit 2505 is transmitted to the vehicle 10 through the communication unit 501. The photometric area control for the camera 300 is performed in the vehicle 10 based on the transmitted control prediction information, and this is the photometric condition when image capturing is performed at T+N.
[0322] For example, when the shadow of a building appears in an image, the control prediction unit 2505 predicts the photometric area control performed so that the area where the shadow of the building appears in the image is excluded from the photometric area because the area where the shadow of the building appears becomes darker.
[0323] Specifically, as long as there is a certain distance or more between the shadow of the building and the vehicle, the control prediction unit 2505 predicts the control to be performed so that the area outside the shadow area of the building in the image is set as the metering area, and the area outside the shadow area of the building appears in the appropriate image, but the shadow area of the building exhibits a thickened shadow.
[0324] On the other hand, when the shadow of the building and the vehicle 10 are closer than a certain distance to each other, the control prediction unit 2505 predicts the control to be performed so that the shadow area of the building is set as the photometric area and the shadow area appears in an appropriate image.
[0325] In addition, for an image captured when the shadow of a building is set as a metering area and an image captured when an area other than the shadow of a building is set as a metering area, the control prediction unit 2505 predicts the control performed so that the two images are interpolated so that there is no sharp change between the images.
[0326] This makes it possible to obtain an image suitable for the situation.
[0327] In addition, the own position and orientation can be estimated in the own position estimation system 200 using an image in which the line of sight of the feature point is less likely to be lost, and this enables improvement in the accuracy of estimating the own position and orientation.
[0328] The control performed on the sensing device in the self-position estimation system 200 includes control performed when estimating the self-position and posture and related to assigning weights to image information and vehicle status detection information, and control performed when estimating the self-position and posture and related to assigning weights to individual image information acquired from multiple cameras 300 respectively.
[0329] Based on the information about the position of the shadow of the building in the image at T+N, the control prediction unit 2505 predicts how to weight the image information and the vehicle state detection information respectively in the own position estimation system 200 for estimating the own position and posture of the vehicle 10.
[0330] For example, when the control prediction unit 2505 predicts that the screen will become darker due to the shadow of the building and the accuracy of extracting feature points will decrease, the control prediction unit 2505 predicts the control to be performed so that when estimating the own position and posture in the own position estimation system 200, the result of the estimation performed using the image information is lightly weighted, while the result of the estimation performed using the vehicle state detection information is heavily weighted.
[0331] The information on the control prediction is transmitted to the vehicle 10. Since the own position and posture are estimated in the vehicle 10 based on the information on such control prediction, the accuracy of estimating the own position and posture is improved.
[0332] In addition, the control prediction unit 2505 predicts control to be performed on how to weight the respective image information acquired by the plurality of cameras 300 in the own position estimation system 200 for estimating the position and posture of the vehicle.
[0333] For example, control of prediction execution is performed such that image information regarding an image captured by the camera 300 directed toward the shadow of a building is not used or is lightly weighted.
[0334] Next, control performed on both the camera 300 and the self-position estimation system 200 is described.
[0335] The control prediction unit 2505 predicts the control to be performed so that the camera 300 performs image capture alternately in the first mode and the second mode for each frame. In addition, the control prediction unit 2505 predicts the control to be performed as to which of the images captured in the first mode and the images captured in the second mode is used for estimating the own position at T+N in the own position estimation system 200, or how the result of the estimation of the own position at T+N performed using the image captured in the first mode and the result of the estimation of the own position at T+N performed using the image captured in the second mode are respectively weighted to be integrated with each other for estimating the own position at T+N in the own position estimation system 200.
[0336] The information on the control prediction is transmitted to the vehicle 10. In the vehicle 10, based on the information, an image is captured by the camera 300, and further, the own position and posture of the vehicle 10 are estimated in the own position estimation system 200.
[0337] The first mode is an image capturing mode when an area other than the shadow area of a building is set as a photometric area. In this mode, settings are performed so that an area other than the shadow area of a building appears in an image captured with appropriate exposure, but the shadow area of the building in the image shows a thickened shadow.
[0338] The second mode is an image capture mode when the shadow area of the building is set as the photometric area. In this mode, settings are performed so that the shadow area of the building appears in the image captured with appropriate exposure. In the second mode, exposure control such as reducing the shutter speed and increasing the gain is performed.
[0339] The modes of shutter speed and gain are switched between a first mode and a second mode.
[0340] A process of estimating the own position and posture of the vehicle 10 is performed in the vehicle 10 based on control prediction information, the control prediction information including image information and information indicating which of the image captured in the first mode and the image captured in the second mode is used when estimating the own position or indicating how to weight the results of estimating the own position and posture in each mode to integrate each other, the image information being information about an image obtained by alternately performing image capture in the first mode and in the second mode for each frame, the results of estimating the own position and posture in each mode being obtained using the images captured in the two modes.
[0341] In the case of a process of estimating the own position and posture based on control prediction information indicating the use of an image captured in the first mode, the image captured in the first mode is extracted from the acquired image information in the own position estimation system 200, and a process of estimating the own position and posture is performed based on the extracted image.
[0342] In the case of a process of estimating the own position and posture based on control prediction information indicating the use of an image captured in the second mode, the image captured in the second mode is extracted from the acquired image information in the own position estimation system 200, and a process of estimating the own position and posture is performed based on the extracted image.
[0343] In the case where the process of estimating the own position and posture is performed based on the control prediction information indicating that the process of estimating the own position and posture is performed using the result obtained by assigning weights to the result of estimating the own position and posture in each mode and integrating the weighted result, the process of estimating the own position and posture is performed for each mode in the own position estimation system 200, that is, the process of estimating the own position and posture is performed using the image information about the image captured in the first mode, and the process of estimating the own position and posture is performed using the image information about the image captured in the second mode. Then, the process of estimating the own position and posture is performed in the own position estimation system 200 using the result obtained by assigning weights to the processing results in each mode and integrating the weighted processing results.
[0344] [Control prediction processing]
[0345] Fig.10 The flow of control prediction processing performed in the server device 2500 to generate control prediction information regarding prediction of control performed on the sensing device is illustrated.
[0346] When the control prediction process is started, the information acquisition unit 502 acquires parameter information about parameters of the camera 300 , information about the position and posture of the vehicle 10 , and vehicle state information of the vehicle 10 from the vehicle 10 through the communication unit 501 ( S21 ).
[0347] Next, the unit 503 for predicting the position and posture at T+N predicts the position and posture of the vehicle 10 at T+N based on the information about the position and posture of the vehicle 10 at time T output from the information acquisition unit 502 and the vehicle state information of the vehicle 10 at time T (S22).
[0348] Next, the unit 2504 for predicting the position of the shadow of the building in the image predicts the position of the shadow of the building in the image to be captured by the camera 300 at T+N based on the parameter information of the camera 300, the information about the position and posture of the vehicle at T+N, the information 506 about the date and time / weather, and the map information 507, and predicts whether the shadow of the building will appear in the image (S23).
[0349] When the determination performed in S23 is “NO”, the process returns to S21 to be repeatedly performed.
[0350] When the determination performed in S23 is “YES”, the process moves to S24 .
[0351] In S24, based on the information about the position of the shadow of the building, the control prediction unit 2505 predicts control to be performed on the sensing device and generates control prediction information (control prediction signal).
[0352] Next, the communication unit 501 transmits the generated control prediction information to the vehicle 10 ( S25 ).
[0353] The server device 2500 includes hardware necessary for the configuration of a computer, such as a CPU, a ROM, a RAM, and a HDD.
[0354] In the server apparatus 2500 , the above-described control prediction processing is performed by loading a program stored in the ROM into the RAM and executing the program to generate control prediction information regarding prediction of control performed on the sensing device.
[0355] As described above, in the control system 2000 according to the present embodiment, the control performed on the camera 300 installed in the vehicle 10 and the self-position estimation system 200 so as to reduce the influence caused by the appearance of the shadow of the structure in the image captured at T+N is predicted based on the information about the position and posture of the vehicle 10 at time T, the map information 507, and the information 506 about the date and time / weather.
[0356] In the vehicle 10, control performed for the camera 300 and the self-position estimation system 200 installed in the vehicle 10 is performed based on information about such control prediction. Therefore, an image suitable for the state of the vehicle at T+N and in which the influence caused by the appearance of the shadow (interference factor) of the structure is mitigated can be obtained without time lag at T+N. This enables a highly robust control system to be obtained.
[0357] <Other embodiments>
[0358] The embodiments of the present technology are not limited to the above-described embodiments, and various modifications may be made thereto without departing from the spirit of the present technology.
[0359] For example, in the above-described embodiment, an example has been described in which the control prediction information generated by the server device 500 (1500, 2500) is transmitted to the vehicle 10 on which the camera for acquiring image information is installed. However, the control prediction information may be transmitted to another vehicle other than the vehicle 10. Here, in order to distinguish the own vehicle 10 from the other vehicle, the vehicle 10 is referred to as the own vehicle 10.
[0360] Another vehicle as the second vehicle follows the same route as the route traveled by the present vehicle 10 as the first vehicle, and the other vehicle passes a specific position at time T+N', which is the same position passed by the vehicle 10 at time T+N (N'>N), and time T+N' is a time only a short time after time T+N.
[0361] Control prediction information regarding prediction of control to be performed at T+N for vehicle 10 is transmitted to the other vehicle, the prediction of control being performed by server device 500 (1500, 2500).
[0362] When the other vehicle reaches the same position as the position where vehicle 10 is predicted to be present at T+N, processing for the sensing device similar to that performed in vehicle 10 and described in the above-described various embodiments is performed in the other vehicle based on the received control prediction information.
[0363] The server device 500 (1500, 2500) obtains information about the position and posture of the other vehicle only from the other vehicle. As control prediction information about the prediction of the control to be performed for the sensing device of the other vehicle at time T+N', the server device 500 (1500, 2500) sends control prediction information about the prediction of the control to be performed for the host vehicle 10 at T+N to the other vehicle.
[0364] In other words, based on the information about the position and posture of the vehicle 10 at time T acquired by the information acquisition unit 502, and based on the map information, the control prediction unit 505 (1505, 2505) sets the prediction of the control to be performed for the sensing device of the present vehicle 10 at T+N as the prediction of the control to be performed for the sensing device of the other vehicle, and the prediction of the control to be performed for the sensing device of the present vehicle 10 at T+N is predicted by the control prediction unit 505 (1505, 2505).
[0365] As described above, similar control prediction information can be shared by multiple vehicles.
[0366] In addition, in the above-mentioned embodiment, an example has been described in which the control prediction information includes control prediction information about the prediction of control to be performed for the camera, control prediction information about the prediction of control to be performed for the sensing device in the own position estimation system, and control prediction information about the prediction of control to be performed for both the camera and the own position estimation system. However, one of these control prediction information may be used, or a combination thereof may be used.
[0367] In addition, in the above-mentioned embodiment, an example has been described in which the present technology is applied to capture an image used in the self-position estimation system, but the application is not limited to this. For example, the present technology can be used to perform exposure control and light metering control performed for a camera used to capture a video stored in a drive recorder, and this makes it possible to obtain a video that is less affected by interference factors.
[0368] Furthermore, the control systems according to the above-described respective embodiments may be combined.
[0369] In addition, in the above-mentioned embodiment, the system refers to a collection of multiple structural elements such as devices and modules (components), and whether all structural elements are in a single housing is not the goal. Therefore, multiple devices housed in separate housings and connected to each other through a network and a single device in which multiple modules are housed in a single housing are both systems.
[0370] Note that the present technology can also adopt the following configurations.
[0371] (1) An information processing device comprising:
[0372] an information acquisition unit that acquires information about a position and a posture of a first moving object including a sensing device; and
[0373] A control prediction unit predicts control to be performed on the sensing device based on information on the position and posture acquired by the information acquisition unit and the map information.
[0374] (2) The information processing device according to (1), wherein
[0375] The sensing device includes an image capture device,
[0376] The information processing device also includes
[0377] a unit for predicting the position and posture of a mobile object, the unit predicting the position and posture of a first mobile object based on information on the position and posture, the information on the position and posture being acquired by the information acquisition unit, and
[0378] a unit for predicting the position of a disturbance factor, the unit predicting the position of the disturbance factor in an image captured by the image capturing device based on the map information and a result of the prediction performed by the unit for predicting the position and posture of the mobile object, and
[0379] The control prediction unit predicts control to be performed on the image capturing device based on a result of prediction performed by the unit for predicting the position of the disturbance factor.
[0380] (3) The information processing device according to (2), wherein
[0381] The control prediction unit predicts exposure control performed for the image capturing device.
[0382] (4) The information processing device according to (2) or (3), wherein
[0383] The control prediction unit predicts light-metering area control performed for the image capturing device.
[0384] (5) The information processing device according to any one of (1) to (4), wherein
[0385] The sensing device includes an image capture device,
[0386] The first mobile object includes a self-position estimation system that estimates the position and posture of the first mobile object using feature points extracted from image information from an image capture device,
[0387] The information processing device also includes
[0388] a unit for predicting the position and posture of a mobile object, the unit predicting the position and posture of a first mobile object based on information on the position and posture, the information on the position and posture being acquired by the information acquisition unit, and
[0389] a unit for predicting the position of a disturbance factor, the unit predicting the position of the disturbance factor in an image captured by the image capturing device based on the map information and a result of the prediction performed by the unit for predicting the position and posture of the mobile object, and
[0390] The control prediction unit predicts control to be performed for the own position estimation system based on a result of prediction performed by the unit for predicting the position of the disturbance factor.
[0391] (6) The information processing device according to (5), wherein
[0392] The control prediction unit predicts a region where extraction of feature points in the image is not performed in the own position estimation system based on a result of the prediction performed by the unit for predicting the position of the disturbance factor.
[0393] (7) The information processing device according to (5) or (6), wherein
[0394] The sensing device includes an image capturing device and a moving object state detection sensor that detects a state of a first moving object,
[0395] The first mobile object includes a self-position estimation system that estimates the position and posture of the first mobile object using at least one of image information and mobile object state information from a mobile object state detection sensor; and
[0396] The control prediction unit predicts how to weight image information and moving object state information respectively based on the result of the prediction performed by the unit for predicting the position of the interference factor, and the image information and moving object state information are used when estimating the position and posture of the first moving object in the own position estimation system.
[0397] (8) The information processing device according to any one of (5) to (7), wherein
[0398] The sensing device includes a plurality of image capture devices, and
[0399] The control prediction unit predicts how each image information from a plurality of image capturing devices is weighted based on the result of the prediction performed by the unit for predicting the position of the interference factor, and each image information is used when estimating the position and posture of the first mobile object in the own position estimation system.
[0400] (9) The information processing device according to any one of (5) to (8), wherein
[0401] The control prediction unit predicts control to be performed on the image capturing device based on a result of prediction performed by the unit for predicting the position of the disturbance factor.
[0402] (10) The information processing device according to any one of (2) to (9), wherein
[0403] The interfering factors are the sun, and
[0404] The unit for predicting the position of the interference factor predicts the position of the sun in the image captured by the image capturing device based on the map information, the result of the prediction performed by the unit for predicting the position and posture of the mobile object, and the sun position information.
[0405] (11) The information processing device according to any one of (2) to (9), wherein
[0406] The interfering factors are tunnels, and
[0407] The unit for predicting the position of the interference factor predicts the position of the tunnel in the image captured by the image capturing device based on the map information and a result of the prediction performed by the unit for predicting the position and posture of the mobile object.
[0408] (12) The information processing device according to any one of (2) to (9), wherein
[0409] The interfering factors are the shadow of the structure, and
[0410] The unit for predicting the position of the interference factor predicts the position of the shadow due to the structure in the image captured by the image capturing device based on the map information, the result of the prediction performed by the unit for predicting the position and posture of the mobile object, and the sun position information.
[0411] (13) The information processing device according to any one of (1) to (9), wherein
[0412] The information processing device according to claim 1, wherein
[0413] an information acquisition unit acquires information about a position and a posture of a second moving object that includes a sensing device and is different from the first moving object, and
[0414] The control prediction unit sets the prediction of the control performed by the sensing device for the first mobile object as the prediction of the control performed by the sensing device for the second mobile object, and the prediction of the control performed by the sensing device for the first mobile object is performed by the control prediction unit based on the information about the position and posture of the first mobile object and the map information, and the information about the position and posture of the first mobile object is acquired by the information acquisition unit.
[0415] (14) A moving object comprising:
[0416] Sensing equipment; and
[0417] An acquisition unit, the acquisition unit acquires information about the position and posture of the moving object, wherein
[0418] The sensing device is controlled according to control prediction information about a prediction of control to be performed on the sensing device, the control to be performed on the sensing device being predicted based on information about its own position and posture and map information, the information about its own position and posture being acquired by an acquisition unit.
[0419] (15) A control system comprising:
[0420] a mobile object, the mobile object comprising a sensing device;
[0421] an information acquisition unit, the information acquisition unit acquiring information about the position and posture of the moving object;
[0422] a control prediction unit that predicts control to be performed on the sensing device based on information about the position and posture and the map information, the information about the position and posture being acquired by the information acquisition unit; and
[0423] A control unit that performs control for the sensing device based on control prediction information regarding control prediction performed by the control prediction unit.
[0424] (16) An information processing method comprising:
[0425] obtaining information about the position and posture of a mobile object including a sensing device; and
[0426] Control performed on the sensing device is predicted based on the information about the position and posture and the map information.
[0427] (17) A program causing an information processing device to execute a process, the process comprising:
[0428] obtaining information about the position and posture of a mobile object including a sensing device; and
[0429] Control performed on the sensing device is predicted based on the information about the position and posture and the map information.
[0430] Reference numerals list
[0431] 1, 1000, 2000 control system
[0432] 10 Vehicle (first moving object)
[0433] 102 data acquisition unit (acquisition unit)
[0434] 200 Self-position estimation system
[0435] 201 Control unit of self-position estimation system (control unit)
[0436] 300 Camera (sensing device, image capture device)
[0437] 301 Camera control unit (control unit)
[0438] 400 Vehicle status detection sensor (sensing device, moving object status detection sensor)
[0439] 500, 1500, 2500 Server device (information processing device)
[0440] 502 Information Acquisition Unit
[0441] 503 Unit for predicting the position and posture of the vehicle at T+N (unit for predicting the position and posture of a moving object)
[0442] 504 Unit for predicting the position of the sun in an image (unit for predicting the position of a disturbance factor)
[0443] 505, 1505, 2505 Control prediction unit
[0444] 506 Information about date and time / weather
[0445] 507 Map Information
[0446] 1504 Unit for predicting the location of a tunnel in an image (unit for predicting the location of a disturbance factor)
[0447] 2504 Unit for predicting the position of the shadow of a building in an image (unit for predicting the position of interference factors)
Claims
1. An information processing device, comprising: an information acquisition unit that acquires information about a position and a posture of a first moving object including a sensing device; as well as a control prediction unit that predicts control performed on the sensing device at a second time after the first time based on information about the position and posture at the first time and the map information, the information about the position and posture being acquired by the information acquisition unit, Wherein, the sensing device comprises an image capturing device, the first mobile object includes a self-position estimation system that estimates the position and posture of the first mobile object using feature points extracted from image information from an image capture device, The information processing device also includes a unit for predicting the position and posture of a mobile object, the unit predicting the position and posture of a first mobile object at a second time based on information about the position and posture at a first time, the information about the position and posture at the first time being acquired by the information acquisition unit, and a unit for predicting the position of a disturbance factor, the unit predicting the position of the disturbance factor in the image captured by the image capturing device at the second time based on the map information and the result of the prediction performed by the unit for predicting the position and posture of the mobile object, and The control prediction unit predicts control to be performed for the own position estimation system based on a result of prediction performed by the unit for predicting the position of the disturbance factor, The control prediction unit predicts a region where extraction of feature points in the image is not performed in the own position estimation system based on a result of prediction performed by the unit for predicting the position of the disturbance factor.
2. The information processing device according to claim 1, wherein The control prediction unit predicts control to be performed on the image capturing device based on a result of prediction performed by the unit for predicting the position of the disturbance factor.
3. The information processing device according to claim 2, wherein The control prediction unit predicts exposure control performed for the image capture device.
4. The information processing device according to claim 2, wherein The control prediction unit predicts light-metering area control performed for the image capturing device.
5. The information processing device according to claim 1, wherein The sensing device includes an image capturing device and a moving object state detection sensor that detects a state of a first moving object, the first mobile object including a self-position estimation system that estimates a position and a posture of the first mobile object using at least one of image information and mobile object state information from a mobile object state detection sensor; and The control prediction unit predicts how to weight image information and moving object state information respectively based on the result of the prediction performed by the unit for predicting the position of the interference factor, and the image information and moving object state information are used when estimating the position and posture of the first moving object in the own position estimation system.
6. The information processing device according to claim 1, wherein The sensing device includes a plurality of image capture devices, and The control prediction unit predicts how the individual image information from the multiple image capture devices are weighted based on the results of the prediction performed by the unit for predicting the position of the interference factor, and the individual image information is used when estimating the position and posture of the first mobile object in the self-position estimation system.
7. The information processing device according to claim 1, wherein The control prediction unit predicts control to be performed on the image capturing device based on a result of prediction performed by the unit for predicting the position of the disturbance factor.
8. The information processing device according to claim 2, wherein The interfering factor is the sun, and The unit for predicting the position of the interference factor predicts the position of the sun in the image captured by the image capturing device based on the map information, the result of the prediction performed by the unit for predicting the position and posture of the mobile object, and the sun position information.
9. The information processing device according to claim 2, wherein The interfering factor is a tunnel, and The unit for predicting the position of the interference factor predicts the position of the tunnel in the image captured by the image capturing device based on the map information and a result of the prediction performed by the unit for predicting the position and posture of the mobile object.
10. The information processing apparatus according to claim 2, wherein The interfering factors are the shadow of the structure, and The unit for predicting the position of the interference factor predicts the position of the shadow due to the structure in the image captured by the image capturing device based on the map information, the result of the prediction performed by the unit for predicting the position and posture of the mobile object, and the sun position information.
11. The information processing device according to claim 1, wherein The information acquisition unit acquires information about a position and a posture of a second moving object that includes a sensing device and is different from the first moving object, and The control prediction unit sets the prediction of control performed by the sensing device for the first mobile object as the prediction of control performed by the sensing device for the second mobile object, and the prediction of control performed by the sensing device for the first mobile object is performed by the control prediction unit based on information about the position and posture of the first mobile object and map information, and the information about the position and posture of the first mobile object is acquired by the information acquisition unit.
12. A mobile object, comprising: Sensing equipment; as well as An acquisition unit, the acquisition unit acquires information about the position and posture of the moving object, wherein controlling the sensing device according to control prediction information regarding a prediction of control to be performed on the sensing device, the control to be performed on the sensing device at a second time after the first time being predicted based on information regarding the own position and posture at the first time and the map information, the information regarding the own position and posture being acquired by an acquisition unit, Wherein, the sensing device comprises an image capturing device, The mobile object includes a self-position estimation system that estimates the position and posture of the mobile object using feature points extracted from image information from an image capture device, The moving object also includes a unit for predicting the position and posture of the mobile object, the unit predicting the position and posture of the mobile object at a second time based on information about the position and posture at a first time, the information about the position and posture at the first time being acquired by the acquisition unit, and a unit for predicting the position of a disturbance factor, the unit predicting the position of the disturbance factor in the image captured by the image capturing device at the second time based on the map information and the result of the prediction performed by the unit for predicting the position and posture of the mobile object, and The mobile object predicts control to be performed for the own position estimation system based on a result of prediction performed by a unit for predicting the position of a disturbance factor, The mobile object predicts a region where extraction of feature points in the image is not performed in the own position estimation system based on a result of prediction performed by a unit for predicting the position of a disturbance factor.
13. A control system comprising: a mobile object, the mobile object comprising a sensing device; an information acquisition unit, the information acquisition unit acquiring information about the position and posture of the moving object; a control prediction unit that predicts control performed on the sensing device at a second time after the first time based on information about the position and posture at the first time and the map information, the information about the position and posture being acquired by the information acquisition unit; as well as a control unit that performs control for the sensing device based on control prediction information regarding control prediction performed by the control prediction unit, Wherein, the sensing device comprises an image capturing device, The mobile object includes a self-position estimation system that estimates the position and posture of the mobile object using feature points extracted from image information from an image capture device, The moving object also includes a unit for predicting the position and posture of a mobile object, the unit predicting the position and posture of the mobile object at a second time based on information about the position and posture at a first time, the information about the position and posture at the first time being acquired by the information acquisition unit, and a unit for predicting the position of a disturbance factor, the unit predicting the position of the disturbance factor in the image captured by the image capturing device at the second time based on the map information and the result of the prediction performed by the unit for predicting the position and posture of the mobile object, and The control prediction unit predicts control to be performed for the own position estimation system based on a result of prediction performed by the unit for predicting the position of the disturbance factor, The control prediction unit predicts a region where extraction of feature points in the image is not performed in the own position estimation system based on a result of prediction performed by the unit for predicting the position of the disturbance factor.
14. An information processing method, comprising: obtaining information about the position and posture of a mobile object including a sensing device; as well as predicting control performed on the sensing device at a second time after the first time based on the information about the position and the posture at the first time and the map information, Wherein, the sensing device comprises an image capturing device, The method further comprises: Estimate the position and posture of a moving object using feature points extracted from image information from an image capture device, predicting the position and posture of the moving object at a second time based on the information about the position and posture at a first time, predicting the position of the interference factor in the image captured by the image capture device at the second time based on the map information and the prediction result of the position and posture of the moving object, and Based on the prediction result of the position of the disturbance factor, a region where extraction of feature points in the image is not performed is predicted.
15. A computer-readable storage medium storing a program, the program causing an information processing device to execute a process, the process comprising: acquiring information about a position and a posture of a moving object including a sensing device, wherein the sensing device includes an image capture device; predicting control performed on the sensing device at a second time after the first time based on the information about the position and the posture at the first time and the map information; estimating a position and a posture of a moving object using feature points extracted from image information from an image capture device; predicting a position and a posture of the moving object at a second time based on information about the position and the posture at the first time; predicting a position of a disturbing factor in an image captured by the image capturing device at a second time based on the map information and a result of predicting the position and posture of the moving object; and Based on the prediction result of the position of the disturbance factor, a region where extraction of feature points in the image is not performed is predicted.
