WO2016016955A1 - 自律移動装置及び自己位置推定方法 - Google Patents
自律移動装置及び自己位置推定方法 Download PDFInfo
- Publication number
- WO2016016955A1 WO2016016955A1 PCT/JP2014/069989 JP2014069989W WO2016016955A1 WO 2016016955 A1 WO2016016955 A1 WO 2016016955A1 JP 2014069989 W JP2014069989 W JP 2014069989W WO 2016016955 A1 WO2016016955 A1 WO 2016016955A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- landmark
- self
- unit
- standard camera
- camera
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 15
- 238000000605 extraction Methods 0.000 claims description 17
- 239000000284 extract Substances 0.000 claims description 4
- 238000012545 processing Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 230000005484 gravity Effects 0.000 description 5
- 238000005286 illumination Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 125000002066 L-histidyl group Chemical group [H]N1C([H])=NC(C([H])([H])[C@](C(=O)[*])([H])N([H])[H])=C1[H] 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
- G01C21/1656—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments with passive imaging devices, e.g. cameras
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
- G05D1/0272—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means comprising means for registering the travel distance, e.g. revolutions of wheels
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/69—Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
- H04N7/185—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source from a mobile camera, e.g. for remote control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30244—Camera pose
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
Definitions
- the present invention relates to an autonomous mobile device and a self-position estimation method, for example, a device for estimating a self-position when a moving body such as a robot or an automobile moves autonomously.
- an internal sensor such as an encoder or a gyroscope and a camera
- a moving body such as a robot or an automobile
- Patent Document 1 Japanese Patent Laid-Open No. 2005-315746 discloses a method for self-localizing a moving body that autonomously runs in an environment in which a plurality of landmarks are arranged indoors, and measures the plurality of landmark positions in advance.
- a plurality of virtual points are set, and the self position is estimated from the two-dimensional coordinates of the landmarks at the virtual points and the candidate point coordinates of the landmarks extracted from the captured image of the wide-angle camera. Therefore, it is not necessary to identify individual landmarks, and the field of view range is unclear, and even when only a part of the landmarks can be extracted from the captured image of the wide-angle camera, it is stable and accurate. It is possible to estimate the self-position of the moving object. Furthermore, robust self-localization can be achieved against environmental disturbances such as lighting changes, and since the image above the ceiling is used, self-localization that is resistant to disturbances such as shielding can be performed. Since a wide-angle camera such as a fisheye lens or an omnidirectional camera is used, the field of view is wide, and self-position identification can be performed without requiring many landmarks.
- a conventional self-position estimation method using a camera detects landmark candidates in the surrounding environment from an image, associates the detected landmark candidates with landmarks on a map, and performs self-location based on the landmark arrangement. Although it was a method of estimating the position, the problem of losing sight of the self-position or deteriorating the accuracy of the self-position by losing or misrecognizing the landmark due to various disturbance elements existing in the surrounding environment There is.
- the self-position identification method and the apparatus disclosed in Patent Document 1 detect landmark candidates from a wide range above the ceiling or the like with a wide-angle camera, further set a plurality of virtual points, and perform two-dimensional landmarks at the virtual points.
- the self-position estimation that is robust against the shielding object and the illumination change can be performed.
- the driving environment is limited, such as an indoor ceiling where the landmark is above and approximately in the same plane.
- the disturbance elements are not robust.
- An object of the present invention is to provide an autonomous mobile device or the like that estimates the self-location based on the landmark arrangement of the surrounding environment while suppressing the influence of disturbance.
- a typical autonomous mobile device of the present invention is an autonomous mobile body including a wide-angle camera, a standard camera capable of attitude control, and an internal sensor, Imaging with the wide-angle camera with reference to the database, an odometry section that performs odometry of the autonomous mobile body, a database that stores image characteristics of disturbance factors that become disturbances when estimating the self-position of the autonomous mobile body
- a base information extraction unit that extracts the disturbance factor and a landmark used for self-position estimation from the captured image; and the information extracted by the base information extraction unit is used to influence the disturbance factor from the image captured by the standard camera.
- the landmark selection unit that selects the landmark that is not to be selected and the landmark selection unit that selects the landmark based on the odometry result calculated by the odometry unit.
- a landmark tracking unit that controls the attitude of the standard camera so as to track the landmark, and a self that estimates a self-position based on an arrangement of the landmark imaged by the standard camera that is track-controlled by the landmark tracking unit And a position estimation unit.
- an autonomous mobile device or the like that estimates its own position based on the landmark arrangement of the surrounding environment while suppressing the influence of disturbance.
- FIG. 1 It is a block diagram which shows the structure of the mobile body by the form of Example 1.
- FIG. It is a figure which shows an example of the base information by the form of Example 1.
- FIG. It is a figure which shows an example of the landmark selection part by the form of Example 1.
- FIG. It is a figure which shows an example of the landmark selection part by the form of Example 1.
- FIG. It is a block diagram which shows the structure of the mobile body by the form of Example 1.
- FIG. It is a figure which shows an example of the landmark selection part by the form of Example 1.
- FIG. It is a figure which shows an example of the landmark selection part by the form of Example 1.
- a wide-angle camera capable of imaging a wide range is mounted upward on the moving body, and a plurality of standard cameras capable of posture control are mounted.
- the autonomous mobile device detects disturbance elements and landmarks with a wide-angle camera, and tracks the landmarks that are difficult to lose sight with the camera according to the disturbance elements, thereby performing robust autonomous movement with respect to the disturbance elements.
- FIG. 1 shows a configuration of a moving body 200 according to the present embodiment.
- the moving body 200 includes a wide-angle camera 210, a standard camera 211, and an internal sensor 212, and includes an arithmetic processing unit that includes a CPU (not shown) and the like.
- a storage unit for storing the program is provided.
- the program executed by the arithmetic processing unit includes an odometry unit 100, a base information extraction unit 101, a landmark selection unit 102, a landmark tracking unit 103, and a self-position estimation unit 105.
- the wide-angle camera 210 is preferably a camera equipped with a super-wide-angle lens such as a fisheye camera or an omnidirectional camera, but may be a camera equipped with another wide-angle lens. In addition, an infrared camera is desirable because it can be used indoors with little illumination or outdoors at night.
- the wide-angle camera 210 is mounted upward on the moving body 200.
- the standard camera 211 is a high-resolution camera equipped with a standard lens, and the attitude of the standard camera 211 can be controlled by an external input and communicates with the landmark tracking unit 103.
- the mounting height of the standard camera 211 is such a height that the standard camera 211 is not captured in the captured image of the wide-angle camera 210 when the viewing direction of the standard camera 211 is the maximum in the elevation direction.
- the camera is a standard camera with a wrinkle such as a search camera.
- a standard camera equipped with a searchlight is desirable in order to support indoors with little illumination or outdoors at night, but an infrared camera may also be used.
- the inner world sensor 212 is a sensor for calculating the relative movement amount of the moving body 200, and includes, for example, a wheel encoder, a gyroscope, and an inertial measurement unit (IMU: Internal Measurement Unit).
- IMU Internal Measurement Unit
- the odometry unit 100 calculates a movement amount and a posture change from the previous position calculation by accumulating the wheel rotation speed, the movement acceleration, and the movement angular acceleration of the moving body 200 acquired from the internal sensor 212. Apply odometry that is
- the base information extraction unit 101 extracts, from the image captured by the wide-angle camera 210, base information composed of disturbance factor information that causes a loss of a landmark and landmark information of the surrounding environment. Details of the base information extraction unit 101 will be described with reference to FIG.
- the landmark selection unit 102 searches for a visible region that can be reliably seen in the surrounding environment regardless of the disturbance element, and from the visible region. Select a tracking landmark for use in self-location estimation. Details of the landmark selection unit will be described with reference to FIGS.
- the landmark tracking unit tracks the tracking landmark selected by the landmark selection unit while controlling the attitude of the standard camera 211.
- the conditional branch 104 moves to the base information extraction unit 101 when there are two or less tracking landmarks that can be tracked by the landmark tracking unit, and when there are three or more tracking landmarks that can be tracked. If there is, move to the self-position estimation unit 105.
- the self-position estimating unit 105 When there are three or more tracking landmarks that can be tracked by the landmark tracking unit, the self-position estimating unit 105 performs self-position estimation based on the tracking landmarks that can be tracked. It is desirable to use a map that describes the location information of each landmark as a method for self-location estimation based on the location of the landmark. For example, a method based on Bayes' theorem, Kalman filter, map creation and update And SLAM (Simultaneous Localization and Mapping), which is a technique for performing self-position estimation simultaneously, but other techniques may be used as long as the self-position can be estimated based on the arrangement of landmarks.
- the self-position estimation unit 105 performs self-position estimation based on the same tracking landmark arrangement until the landmark tracking unit 103 loses sight of the landmark. As a result, the calculation processing load can be reduced.
- FIG. 2 shows details of the base information extraction unit 101.
- D100 is the base information extracted by the base information extraction unit 101, and includes the information of the disturbance element D101 and the landmark D102.
- the disturbance element D101 includes, for example, the weather D103 and the moving object D104 present in the surrounding environment.
- an image of an attached portion when raindrops are attached to a lens is used as teacher data.
- the captured image of the wide-angle camera 210 As a result of comparing the captured image of the wide-angle camera 210 with the teacher data, pixels matching the teacher data are obtained. When there are a large number of pixels, it is rained, and when there are only a few pixels that match the teacher data, it is clear or cloudy. Further, if the sample average of the luminance values of all the pixels of the captured image is equal to or greater than a certain value, it is clear, and otherwise it is cloudy. In the case of clear weather, the direction of sunlight is further calculated based on the magnitude of the brightness gradient. The result of recognizing the weather is, for example, sunny: T (True), cloudy: F (False), and rain: False.
- FIG. 3 shows details of the landmark recognition operation in the landmark selection unit 102.
- the D200 is an image captured by the wide-angle camera 210 in fine weather.
- a lens flare D201 caused by sunlight and a moving object D202 are shown.
- the landmark selection unit first grasps the weather D103 and the moving object D104 from the captured image D200 on the basis of the base information D100 extracted by the base information extraction unit 101, and on the captured image.
- the gravity center position of the lens flare D201 and the gravity center position of the moving object D202 are detected.
- a circular area D203 centered on the position of the center of gravity is provided, and a landmark D204 as an image feature point outside the circular area is extracted. Then, the landmark D204 as the extracted feature point on the image is collated with the map on which the landmark is described, and the three-dimensional coordinates of the landmark D204 as the extracted feature point on the image are grasped. That is, the landmark D204 is recognized.
- the operation of recognizing the landmark D204 includes a direction D205 that is not affected by moving objects and an upward direction D206 and a downward direction D207 that are not affected by sunlight when the moving body 200 travels outdoors and the weather is clear. It is an operation to find out.
- the D300 is an image captured by the wide-angle camera 210 in the rain.
- the image D300 includes raindrops D301 and a moving body D202.
- the landmark selection unit 102 performs the same operation as the landmark recognition operation in the fine weather.
- the circular area centering on the gravity center position of the raindrop D301 and each standard camera are empty.
- a circular region D302 centered on the center of the image is provided so that raindrops do not adhere to the lens, and a landmark D303 as an image feature point outside the circular region is extracted.
- Subsequent operations are the same as those in fine weather, but the horizontal direction D304 and the downward direction D305 in which raindrops do not adhere are found by performing the above operations in rainy weather.
- FIG. 4 shows details of the tracking landmark determination operation in the landmark selection unit 102 when one standard camera 211 is mounted on each of the front, rear, left and right of the moving body 200.
- the D400 is an image obtained by dividing the captured image D200 and the landmark D204 in FIG. 3 into two equal parts in the front, rear, left, and right directions. Assigned to. That is, the standard camera 1 can track the front landmark, the standard camera 2 can track the left landmark, the standard camera 3 can track the rear landmark, and the standard camera 4 can track the right landmark.
- D401 is the two images in the center when the image divided into two is further divided into four equal parts, and the landmark shown in the image D401 is recommended as a tracking landmark.
- D402 is a table of the number of landmarks appearing in the bisected image 400 corresponding to each standard camera 211 and the number of landmarks recommended as tracking landmarks appearing in the central image D401.
- the number of landmarks in the image 401 corresponding to each standard camera 211 is 6 for the standard camera 1, 2 for the standard camera 2, 0 for the standard camera 3, and 4 for the standard camera 4.
- the standard camera 2 has the smallest number of landmarks except for the standard camera 3 having no mark. Therefore, the landmark tracked by the standard camera 2 is first determined. As a determination method, it is confirmed whether there is a landmark reflected in the central image D401. If there is the recommended landmark, the closest to the center of the image D401 is present (that is, the declination is closest to 90 degrees).
- a landmark is determined as a tracking landmark, and if there is no recommended landmark, a landmark closest to the center in the image D400 is determined as a tracking landmark. In this example, since there is no recommended landmark, the landmark D403 closest to the center of the image is determined as the tracking landmark of the standard camera 2.
- D404 is a table of the number of landmarks at the end of the tracking landmark determination operation of the standard camera 2 described above.
- the number of tracking landmark candidates of the standard camera 1 is changed from six to five, and the recommended number of landmarks is also increased from four to three.
- the standard camera with the smallest number of landmarks is selected again from the standard cameras whose tracking landmarks are not determined, and the selected standard is selected in the same manner as the tracking landmark determination operation.
- the standard camera 4 with the smallest number of landmarks is selected, and the landmark D405 closest to the center of the image is determined as the tracking landmark of the standard camera 4.
- the tracking landmark D406 is a table of the number of landmarks after the tracking landmark is determined.
- the tracking landmark D407 of the standard camera 1 is determined by the same method because the tracking landmark is not determined only for the standard camera 1 except for the standard camera 3 in which no landmark is shown. To do.
- the landmarks to be tracked by the standard camera 1, the standard camera 2, and the standard camera 3 are determined by the above tracking landmark determination operation, but the standard camera 3 is not determined.
- the standard camera whose tracking landmark is not determined by the tracking landmark determination operation fixes the posture with the line-of-sight direction facing the road surface, and applies visual odometry.
- the result of the visual odometry is used by the landmark tracking unit 103 together with the result of the odometry unit 100.
- the autonomous mobile device tracks landmarks that do not depend on disturbance elements by camera attitude control, and thus loses its own position in various environments unlike conventional autonomous mobile devices. You can move without
- the user can move without losing sight of his / her position in various environments, and the processing load can be reduced because the number of landmarks to be tracked is limited.
- the landmark is tracked with a high-precision camera, the self-position estimation accuracy can be improved.
- the self-position is estimated based on the same landmark arrangement until it is lost, the calculation processing load can be reduced.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Aviation & Aerospace Engineering (AREA)
- Theoretical Computer Science (AREA)
- Electromagnetism (AREA)
- Signal Processing (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
Description
210 広角カメラ
211 標準カメラ
212 内界センサ
201 自律移動機能ブロック
100 オドメトリ部
101 ベース情報抽出部
102 ランドマーク選択部
103 ランドマーク追跡部
105 自己位置推定部
Claims (6)
- 広角カメラと、姿勢制御可能な標準カメラと、内界センサと、を備える自律移動体であって、
前記内界センサで前記自律移動体のオドメトリを行うオドメトリ部と、
前記自律移動体の自己位置推定の際に外乱となる外乱要因の画像の特徴を記憶するデータベースと、
前記データベースを参照して、前記広角カメラで撮像した画像から前記外乱要因と自己位置推定に用いるランドマークとを抽出するベース情報抽出部と、
前記ベース情報抽出部で抽出した情報を用いて、前記標準カメラで撮像した画像から前記外乱要因に影響されない前記ランドマークを選択するランドマーク選択部と、
前記オドメトリ部で算出したオドメトリ結果をもとに、前記ランドマーク選択部で選択した前記ランドマークを追跡するよう前記標準カメラを姿勢制御するランドマーク追跡部と、
前記ランドマーク追跡部で追跡制御される前記標準カメラで撮像したランドマークの配置をもとに自己位置を推定する自己位置推定部と、
を有することを特徴とする自律移動装置。 - 請求項1において、
前記データベースは、前記外乱要因として、天候、または、移動物の画像特徴を記憶し、
前記ベース情報抽出部は、前記広角カメラで撮像した画像から前記外乱要因となる特徴点を排除し、前記ランドマーク候補となる画像上の特徴点を検出する
ことを特徴とする自律移動装置。 - 請求項1において、
前記標準カメラは、それぞれ異なる方向を撮像するよう複数備え、
前記ベース情報抽出部は、自己位置推定に用いる前記ランドマーク候補を複数抽出し、
前記ランドマーク選択部は、前記ベース情報抽出部で抽出した複数のランドマーク候補から、前記標準カメラごとに、各標準カメラでの追跡に適した前記ランドマークを選択する
ことを特徴とする自律移動装置。 - 請求項3において、
前記ランドマーク追跡部は、前記ランドマーク選択部で選択した前記ランドマークが前記標準カメラの撮像画像の中央に位置するように、前記オドメトリ部で算出したオドメトリ結果を用いて各標準カメラの姿勢を制御する
ことを特徴とする自律移動装置。 - 請求項1において、
前記自己位置推定部は、前記ランドマーク追跡部で追跡した前記ランドマークの配置をもとに自己位置を推定し、前記ランドマーク追跡部で前記標準カメラが前記ランドマークを見失うまで、同じ追跡用ランドマークの配置をもとに自己位置を推定する
ことを特徴とする自律移動装置。 - 広角カメラで撮像した画像から自己位置推定の際に外乱となる外乱要因と自己位置推定に用いるランドマークとを抽出するステップと、
抽出した情報を用いて、姿勢制御可能な標準カメラで撮像した画像から前記外乱要因に影響されない前記ランドマークを選択するステップと、
選択した前記ランドマークを追跡するよう前記標準カメラを姿勢制御するステップと、
追跡制御される前記標準カメラで撮像したランドマークの配置をもとに自己位置を推定するステップと、
を有する自己位置推定方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2014/069989 WO2016016955A1 (ja) | 2014-07-30 | 2014-07-30 | 自律移動装置及び自己位置推定方法 |
JP2016537645A JP6343670B2 (ja) | 2014-07-30 | 2014-07-30 | 自律移動装置及び自己位置推定方法 |
US15/326,294 US10061324B2 (en) | 2014-07-30 | 2014-07-30 | Autonomous moving device and self position estimation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2014/069989 WO2016016955A1 (ja) | 2014-07-30 | 2014-07-30 | 自律移動装置及び自己位置推定方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016016955A1 true WO2016016955A1 (ja) | 2016-02-04 |
Family
ID=55216900
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/069989 WO2016016955A1 (ja) | 2014-07-30 | 2014-07-30 | 自律移動装置及び自己位置推定方法 |
Country Status (3)
Country | Link |
---|---|
US (1) | US10061324B2 (ja) |
JP (1) | JP6343670B2 (ja) |
WO (1) | WO2016016955A1 (ja) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108506711A (zh) * | 2018-04-04 | 2018-09-07 | 中冶长天国际工程有限责任公司 | 烧结机台车车轮加脂轨迹检测装置、控制系统及控制方法 |
CN108781247A (zh) * | 2016-02-22 | 2018-11-09 | 凯特切普恩股份有限公司 | 自推进设备 |
EP3537249A1 (en) | 2018-03-09 | 2019-09-11 | Casio Computer Co., Ltd. | Autonomous mobile apparatus, autonomous move method, and program |
JP2021096731A (ja) * | 2019-12-19 | 2021-06-24 | 東芝デジタルソリューションズ株式会社 | 自律走行型自動搬送車両の制御装置及び搬送システム |
US11100675B2 (en) | 2017-10-24 | 2021-08-24 | Sony Corporation | Information processing apparatus, information processing method, program, and moving body |
US11481920B2 (en) | 2018-05-21 | 2022-10-25 | Sony Corporation | Information processing apparatus, server, movable object device, and information processing method |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2533295A (en) * | 2014-12-15 | 2016-06-22 | The Chancellor Masters And Scholars Of The Univ Of Oxford | Localising portable apparatus |
KR101772084B1 (ko) * | 2015-07-29 | 2017-08-28 | 엘지전자 주식회사 | 이동 로봇 및 그 제어방법 |
US10803600B2 (en) * | 2015-09-30 | 2020-10-13 | Sony Corporation | Information processing device, information processing method, and program |
EP3492870B1 (en) * | 2016-07-26 | 2020-07-15 | Nissan Motor Co., Ltd. | Self-position estimation method and self-position estimation device |
JP7257737B2 (ja) * | 2017-09-05 | 2023-04-14 | ソニーグループ株式会社 | 情報処理装置、自己位置推定方法、及び、プログラム |
US11158066B2 (en) | 2020-01-24 | 2021-10-26 | Ford Global Technologies, Llc | Bearing only SLAM with cameras as landmarks |
JP7221897B2 (ja) * | 2020-03-03 | 2023-02-14 | 株式会社東芝 | 推定装置、移動体、推定方法及びプログラム |
KR102225093B1 (ko) * | 2020-09-01 | 2021-03-09 | 주식회사 맥스트 | 카메라 포즈 추정 장치 및 방법 |
US12033390B2 (en) * | 2021-10-26 | 2024-07-09 | Hitachi, Ltd. | Method and apparatus for people flow analysis with inflow estimation |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6128884A (ja) * | 1984-07-19 | 1986-02-08 | Komatsu Ltd | 誘導標識装置 |
JPH0771978A (ja) * | 1993-09-03 | 1995-03-17 | Suzuki Motor Corp | 自己位置認識装置 |
JP2000337887A (ja) * | 1999-05-25 | 2000-12-08 | Mitsubishi Electric Corp | 移動体の自己位置標定装置 |
JP2005315746A (ja) * | 2004-04-28 | 2005-11-10 | Mitsubishi Heavy Ind Ltd | 自己位置同定方法及び該装置 |
WO2007113956A1 (ja) * | 2006-03-31 | 2007-10-11 | Murata Kikai Kabushiki Kaisha | 移動体位置の推定装置と推定方法及び推定プログラム |
JP2008070267A (ja) * | 2006-09-14 | 2008-03-27 | Canon Inc | 位置姿勢計測方法及び装置 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0854927A (ja) * | 1994-08-10 | 1996-02-27 | Kawasaki Heavy Ind Ltd | ランドマークの決定方法および装置 |
US8301325B2 (en) * | 2008-07-28 | 2012-10-30 | Precise Path Robotics, Inc. | System and method for autonomous vehicle localization |
JP6233706B2 (ja) * | 2013-04-02 | 2017-11-22 | パナソニックIpマネジメント株式会社 | 自律移動装置及び自律移動装置の自己位置推定方法 |
-
2014
- 2014-07-30 US US15/326,294 patent/US10061324B2/en active Active
- 2014-07-30 WO PCT/JP2014/069989 patent/WO2016016955A1/ja active Application Filing
- 2014-07-30 JP JP2016537645A patent/JP6343670B2/ja active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6128884A (ja) * | 1984-07-19 | 1986-02-08 | Komatsu Ltd | 誘導標識装置 |
JPH0771978A (ja) * | 1993-09-03 | 1995-03-17 | Suzuki Motor Corp | 自己位置認識装置 |
JP2000337887A (ja) * | 1999-05-25 | 2000-12-08 | Mitsubishi Electric Corp | 移動体の自己位置標定装置 |
JP2005315746A (ja) * | 2004-04-28 | 2005-11-10 | Mitsubishi Heavy Ind Ltd | 自己位置同定方法及び該装置 |
WO2007113956A1 (ja) * | 2006-03-31 | 2007-10-11 | Murata Kikai Kabushiki Kaisha | 移動体位置の推定装置と推定方法及び推定プログラム |
JP2008070267A (ja) * | 2006-09-14 | 2008-03-27 | Canon Inc | 位置姿勢計測方法及び装置 |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108781247A (zh) * | 2016-02-22 | 2018-11-09 | 凯特切普恩股份有限公司 | 自推进设备 |
US11100675B2 (en) | 2017-10-24 | 2021-08-24 | Sony Corporation | Information processing apparatus, information processing method, program, and moving body |
EP3537249A1 (en) | 2018-03-09 | 2019-09-11 | Casio Computer Co., Ltd. | Autonomous mobile apparatus, autonomous move method, and program |
US11662738B2 (en) | 2018-03-09 | 2023-05-30 | Casio Computer Co., Ltd. | Autonomous mobile apparatus, autonomous move method, and recording medium that use a selected environment map |
CN108506711A (zh) * | 2018-04-04 | 2018-09-07 | 中冶长天国际工程有限责任公司 | 烧结机台车车轮加脂轨迹检测装置、控制系统及控制方法 |
US11481920B2 (en) | 2018-05-21 | 2022-10-25 | Sony Corporation | Information processing apparatus, server, movable object device, and information processing method |
JP2021096731A (ja) * | 2019-12-19 | 2021-06-24 | 東芝デジタルソリューションズ株式会社 | 自律走行型自動搬送車両の制御装置及び搬送システム |
JP7162584B2 (ja) | 2019-12-19 | 2022-10-28 | 東芝情報システム株式会社 | 自律走行型自動搬送車両の制御装置及び搬送システム |
Also Published As
Publication number | Publication date |
---|---|
JP6343670B2 (ja) | 2018-06-13 |
US20170205832A1 (en) | 2017-07-20 |
JPWO2016016955A1 (ja) | 2017-04-27 |
US10061324B2 (en) | 2018-08-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6343670B2 (ja) | 自律移動装置及び自己位置推定方法 | |
CN110411441B (zh) | 用于多模态映射和定位的系统和方法 | |
US9881379B2 (en) | Self-localization device and movable body | |
CN107907131B (zh) | 定位系统、方法及所适用的机器人 | |
US10949712B2 (en) | Information processing method and information processing device | |
US9625912B2 (en) | Methods and systems for mobile-agent navigation | |
US20190080467A1 (en) | Pose determination with semantic segmentation | |
CN105644785B (zh) | 一种基于光流法和地平线检测的无人机着陆方法 | |
JP4978099B2 (ja) | 自己位置推定装置 | |
US20150235367A1 (en) | Method of determining a position and orientation of a device associated with a capturing device for capturing at least one image | |
TW202013251A (zh) | 在機器人設備上使用光流感測器進行vslam比例估計的系統和方法 | |
US20100074473A1 (en) | System and method of extracting plane features | |
CN109443348A (zh) | 一种基于环视视觉和惯导融合的地下车库库位跟踪方法 | |
Maier et al. | Vision-based humanoid navigation using self-supervised obstacle detection | |
CN108549376A (zh) | 一种基于信标的导航定位方法及系统 | |
CN208313291U (zh) | 一种基于ArUco标签的AGV机器人视觉定位系统 | |
Ren et al. | Real-time target tracking system for person-following robot | |
Williams et al. | Feature and pose constrained visual aided inertial navigation for computationally constrained aerial vehicles | |
CN108544494A (zh) | 一种基于惯性和视觉特征的定位装置、方法及机器人 | |
Springer et al. | Autonomous drone landing with fiducial markers and a gimbal-mounted camera for active tracking | |
Zhang et al. | The use of optical flow for UAV motion estimation in indoor environment | |
JP7273696B2 (ja) | 位置推定装置及びシステム | |
Sabatini et al. | Vision-based pole-like obstacle detection and localization for urban mobile robots | |
JP2020076714A (ja) | 位置姿勢推定装置 | |
Hernández et al. | Visual SLAM with oriented landmarks and partial odometry |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14898563 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2016537645 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15326294 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 14898563 Country of ref document: EP Kind code of ref document: A1 |