KR101303161B1 - Mobile robot and controlling method of the same - Google Patents

Abstract

A mobile robot and a control method thereof are disclosed. Embodiments of the present invention may recognize their location using image information and obstacle information. In particular, embodiments of the present invention use feature lines extracted from the image information and the obstacle information, respectively, according to the change in the illumination of the surroundings, or use a feature line extracted from the obstacle map and the obstacle information generated using the image information. The location can be recognized accurately. In addition, embodiments of the present invention by performing the absolute position recognition using the image information and the relative position recognition using the obstacle information in parallel to reduce the error of the position recognition in various lighting environments, improve the performance of the absolute position recognition, and improve the driving efficiency Increase.

Description

MOBILE ROBOT AND CONTROLLING METHOD OF THE SAME}

The present invention relates to a mobile robot and a control method thereof capable of precisely recognizing a position in various lighting conditions.

In general, robots have been developed for industrial use and have been a part of factory automation. In recent years, medical robots, aerospace robots, and the like have been developed, and household robots that can be used in ordinary homes are being developed.

A representative example of the domestic robot is a robot cleaner, which is a kind of electronic equipment that sucks dust and foreign matter around while driving a certain area by itself. Such a robot cleaner is generally equipped with a rechargeable battery and has an obstacle sensor capable of avoiding obstacles during traveling, so that it can run and clean by itself.

Recently, application technologies using mobile robots, especially robot cleaners, have been developed. For example, the development of a mobile robot with a networking function is progressing, so that a function of allowing a cleaning command from a remote location or monitoring a house situation is being implemented. In addition, mobile robots having magnetic location recognition and mapping functions have been developed using cameras or various sensors.

An embodiment of the present invention is to provide a mobile robot and its control method for recognizing its position using the image information and obstacle information.

Another embodiment of the present invention is to provide a mobile robot and a control method thereof capable of accurately recognizing its position by extracting and matching feature lines from image information and obstacle information, respectively.

Embodiments of the present invention provide a mobile robot and a control method thereof capable of precisely recognizing its position even in an environment where lighting changes using an obstacle map generated using image information and a feature line extracted from obstacle information. There is another purpose.

The mobile robot according to an embodiment may include extracting feature points from image information acquired from a surrounding, and extracting first feature lines using the feature points, and obstacle information about obstacles around the surroundings. And a second feature line extracting unit for extracting one or more second feature lines, and a position recognition unit for matching the first feature lines with the second feature line and recognizing a position based on the matching result. .

According to another embodiment of the present invention, a mobile robot includes an image detecting unit detecting image information by capturing a surrounding, an obstacle detecting unit configured to detect obstacles in the surrounding area, and output obstacle information by detecting the surrounding obstacle, and the image information. And a control unit extracting a plurality of first feature lines from the first feature line, extracting one or more second feature lines from the obstacle information, and matching the first feature lines with the second feature line to recognize a position. .

According to an embodiment of the present disclosure, a method of controlling a mobile robot may include detecting image information by photographing a surrounding, outputting obstacle information by detecting an obstacle around the surrounding, and generating a plurality of first feature lines from the image information. Extracting, extracting one or more second feature lines from the obstacle information, matching the first feature lines with the second feature line, and recognizing the position of the mobile robot using the matching result. It is configured to include.

Embodiments of the present invention may recognize their location using image information and obstacle information. In particular, embodiments of the present invention use feature lines extracted from the image information and the obstacle information, respectively, according to the change in the illumination of the surroundings, or use a feature line extracted from the obstacle map and the obstacle information generated using the image information. The location can be recognized accurately.

Embodiments of the present invention reduce the error of position recognition in various lighting environments, improve the performance of absolute position recognition, and increase driving efficiency by performing absolute position recognition using image information and relative position recognition using obstacle information in parallel. .

Embodiments of the present invention improve the user's convenience and the safety of the system by precisely moving the position or without cleaning.

1 is a block diagram schematically showing the configuration of a mobile robot according to one embodiment;
2 and 3 are block diagrams schematically showing the configuration of a mobile robot according to other embodiments;
4A and 4B are diagrams for describing an operation of extracting feature points and feature lines from image information, respectively, according to embodiments of the present disclosure;
5A to 5D are diagrams for describing an operation of matching feature lines extracted from image information and obstacle information, respectively, according to embodiments of the present disclosure;
6 is a perspective view of a robot cleaner according to an embodiment;
7 is a front view of the robot cleaner according to one embodiment; And
8 to 10 are flowcharts schematically illustrating a control method of a mobile robot according to embodiments.

Referring to FIG. 1, a mobile robot according to an exemplary embodiment includes a first feature line extractor 10, a second feature line extractor 20, and a position recognizer 40. The first feature line extractor 10 extracts feature points from image information acquired from the surroundings, and extracts first feature lines using the feature points. The second feature line extractor 20 extracts one or more second feature lines by using obstacle information on the surrounding obstacles. The position recognizing unit 40 matches the first feature lines with the second feature line, and recognizes a location based on the matching result.

The mobile robot further includes a map generator 30 that generates an obstacle map using the first feature lines. Here, the position recognizing unit 40 varies the position recognition according to the illuminance information. That is, the location recognition unit 40, when the surrounding illumination is less than a predetermined illumination, the second feature extracted by the first feature lines and the second feature line extracting unit 20 in the obstacle map generated by the map generator 30. Match the lines to recognize the location. On the other hand, if the peripheral illuminance is greater than the predetermined illuminance, the position recognizing unit 40 matches the first and second feature lines extracted from the image information and the obstacle information to recognize the position.

4 illustrates an operation of extracting a first feature line from image information. Referring to FIG. 4A, the mobile robot extracts a plurality of feature points by processing image information on a predetermined image. Then, the mobile robot matches a plurality of feature points based on two or more pieces of image information taken continuously. The plurality of feature points may be represented by three-dimensional coordinates. Referring to FIG. 4B, the mobile robot extracts first feature lines using feature points expressed in 3D coordinates and line components extracted from image information. Since the method of extracting the first feature lines from the image information varies according to an image processing technique, a detailed description of the image processing technique will be omitted. The map generator 30 may generate an obstacle map of the entire area by using the first feature lines. That is, the first feature lines are indicative of absolute position.

Referring to FIG. 5A, the map generator 30 may generate an obstacle map by using the first feature lines. That is, the mobile robot may express line components extracted from the image information using obstacle maps using three-dimensional feature points.

5B to 5C, the mobile robot generates obstacle information by detecting an obstacle around it and extracts a second feature line using the obstacle information. The obstacle information includes an obstacle detection position (or a position of the mobile robot at the time of obstacle detection), an obstacle detection period (time interval), and the like. The obstacle detection position may be displayed as shown in FIG. 5B, and when connected thereto, the second feature line may be extracted. The second feature line is the line component of the local obstacle.

Referring to FIG. 5D, the position recognizing unit 40 matches the first feature line with the second feature line and recognizes the position using the matching result. That is, the position recognizing unit 40 recognizes the position by matching the second feature line with the first feature line having the absolute position. Here, when the lighting is severely changed or the illuminance is a certain illuminance, the location recognition unit 40 may match the second feature line with the first feature lines in the obstacle map and use the matching result.

Referring to FIG. 2, a mobile robot according to another embodiment includes an image detecting unit 100 which photographs a surrounding and detects image information, and one or more sensors, and detects the surrounding obstacle to output obstacle information. The obstacle detection unit 200 and the control unit 300 is configured to include. The control unit 300 extracts a plurality of first feature lines from the image information, extracts one or more second feature lines from the obstacle information, and matches the first feature lines with the second feature lines. Recognize.

The image detection unit 100 detects image information by photographing a surrounding. As illustrated in FIG. 6, the image detection unit 100 is provided to face upwards or forwards, and includes a camera to capture the surroundings of the mobile robot to detect image information. 6 and 7 are a perspective view and a front view of a robot cleaner which is an example of a mobile robot. When the image detection unit 100 includes a plurality of cameras, the cameras may be formed on the top or side surfaces of the mobile robot at a predetermined distance or at an angle. The image detection unit 100 may include a lens connected to the camera to focus the subject. The lens uses a lens having a wide angle of view so that all the surrounding areas, for example, all areas of the ceiling can be photographed even at a predetermined position.

Referring to FIG. 3, the control unit 300 includes a feature point extractor 311, a coordinate calculator 312, and a first feature line extractor 310. The feature point extractor 311 extracts a plurality of points from the two image information, and matches the points between the two image information to extract the plurality of feature points. The coordinate calculator 312 calculates three-dimensional coordinates of the plurality of feature points. The first feature line extracting unit 310 extracts the plurality of first feature lines from the image information.

4 illustrates an operation of extracting a first feature line from image information. Referring to FIG. 4A, the feature point extractor 311 extracts a plurality of feature points by processing image information. Then, the control unit 300 matches a plurality of feature points based on two or more pieces of image information taken continuously. The plurality of feature points may be represented by three-dimensional coordinates. Referring to FIG. 4B, the first feature line extracting unit 310 extracts the first feature lines by using feature points expressed in 3D coordinates and line components extracted from image information. Since the method of extracting the first feature lines from the image information varies according to an image processing technique, a detailed description of the image processing technique will be omitted. The first feature lines are indicative of absolute position.

6 and 7, the obstacle detecting unit 200 includes a first sensor 210 installed at a predetermined interval on the front of the mobile robot, that is, on an outer circumferential surface thereof. In addition, the obstacle detecting unit 200 may include a second sensor 220 installed to have a surface protruding to the outside of the main body. The location and type of the first sensor and the second sensor may vary according to the type of the mobile robot, and the obstacle detecting unit may include more various sensors. The first sensor 210 detects an object in the moving direction of the mobile robot, in particular an obstacle, and transmits the obstacle information to the control unit 300. That is, the first sensor detects protrusions, household appliances, furniture, walls, wall edges, etc. existing on the movement path of the mobile robot and transmits the information to the control unit. The first sensor may be an infrared sensor, an ultrasonic sensor, a RF sensor, a geomagnetic sensor, or the like. The second sensor 220 detects an obstacle present in the front or side and transmits the obstacle information to the control unit. That is, the second sensor detects protrusions, household appliances, furniture, walls, wall edges, etc. existing on the movement path of the mobile robot and transmits the information to the control unit. The second sensor may be an infrared sensor, an ultrasonic sensor, an RF sensor, a position sensitive device (PSD) sensor, or the like.

The obstacle detecting unit 200 may be installed on a bottom surface (bottom surface) of the main body, and may further include a cliff sensor for detecting an obstacle on the bottom surface, for example, a cliff. The cliff sensor is configured to obtain a stable measurement value regardless of the reflectance and color difference of the bottom surface, and may be in the form of an infrared module such as a PSD sensor.

The control unit 300 may generate an obstacle map using the first feature lines. Referring to FIG. 3, the control unit 300 may further include a map generator 330 that expresses the first feature lines as the obstacle map using a plurality of feature points having the three-dimensional coordinates. In addition, the control unit 300 may further include a second feature line extracting unit 320 for extracting the at least one second feature line from the obstacle information.

Referring to FIG. 5A, the map generator 330 may generate an obstacle map by using the first feature lines. That is, the map generator 330 may express the line components extracted from the image information as obstacle maps using three-dimensional feature points.

5B to 5C, the second feature line extractor 320 generates obstacle information by detecting an obstacle around it and extracts the second feature line using the obstacle information. The obstacle information includes an obstacle detection position (or a position of the mobile robot at the time of obstacle detection), an obstacle detection period (time interval), and the like. The obstacle detection position may be displayed as shown in FIG. 5B, and when connected thereto, the second feature line may be extracted. The second feature line is the line component of the local obstacle.

Referring to FIG. 5D, the location recognizing unit 340 matches the first feature line with the second feature line and recognizes the location using the matching result. That is, the position recognition unit 340 recognizes the position by matching the second feature line with the first feature line having the absolute position. Here, when the lighting is severely changed or the illuminance is a certain illuminance, the location recognition unit 340 may match the second feature line with the first feature lines in the obstacle map and use the matching result.

Referring back to FIG. 2, the mobile robot further includes a storage unit 400 that stores the first feature lines, the one or more second feature lines, and the obstacle map. The storage unit 400 may further store at least one of image information, obstacle information, an area, and a path in addition to the first and second feature lines. The storage unit 400 stores a control program for controlling (driving) a mobile robot and data accordingly. In the case of the robot cleaner, the storage unit 400 may further store a cleaning method, a traveling method, a cleaning pattern, a cleaning area, and the like. As the storage unit 400, non-volatile memories (Non-Volatile Memory, NVM, NVRAM) such as a ROM and a flash memory may be used.

Referring back to FIG. 2, the mobile robot further includes an illuminance detecting unit 500 that detects the illuminance of the surroundings. The illuminance detecting unit 500 detects illuminance of a location where the mobile robot is located, that is, an area to be imaged by the image detecting unit 100. The illuminance detection unit 500 may sense light using, for example, a photo sensor, a photo transistor, or the like. Here, when the illuminance detected by the illuminance detecting unit 500 is greater than a predetermined illuminance, the control unit 300 uses the matching result of the first feature lines and the second feature lines extracted from the image information and the obstacle information, respectively, and detects the illuminance. When the illuminance sensed by the unit 500 is equal to or less than a predetermined illuminance, the position is recognized using the matching result of the first feature lines and the extracted second feature line in the obstacle map.

Referring to FIG. 3, the mobile robot may further include a driving unit 600, an input unit 700, and an output unit 800.

The mobile robot has left and right main wheels which are movable on both lower sides thereof. Handles may be installed on both sides of the main wheel to facilitate gripping by the user. The driving unit 600 is connected to the left and right main wheels 610 and includes a predetermined wheel motor for rotating the wheels to move the main body by driving the wheel motor. Each wheel motor is connected to the main wheels so that the main wheels rotate, and the wheel motors operate independently of each other and can rotate in both directions. In addition, the mobile robot is provided with one or more auxiliary wheels on the back to support the main body, to minimize the friction between the lower surface and the bottom surface of the main body and to facilitate the movement of the mobile robot.

The mobile robot may further include a motion detection unit (not shown) that detects a motion of the mobile robot according to the driving of the main body and outputs motion information. As a motion detection unit, a gyro sensor, a wheel sensor, an acceleration sensor, etc. are used.

The gyro sensor detects the rotation direction and detects the rotation angle when the mobile robot moves according to the driving mode. The gyro sensor detects the angular velocity of the mobile robot and outputs a voltage value proportional to the angular velocity. The control unit 300 calculates the rotation direction and the rotation angle using the voltage value output from the gyro sensor.

The wheel sensor is connected to the main wheels 610 on the left and the right to detect the rotation speed of the main wheels. Here, the wheel sensor may be a rotary encoder. The rotary encoder detects and outputs the number of revolutions of the main wheels on the left and right. The control unit 300 may calculate the rotation speed of the left and right wheels by using the rotation speed. In addition, the control unit 300 can calculate the rotation angle using the difference in the rotation speed of the left and right wheels.

An acceleration sensor detects a change in the moving speed due to a speed change of the mobile robot, for example, start, stop, change of direction, collision with an object, and the like. The acceleration sensor is attached to the adjacent position of the main wheel or the auxiliary wheel, and can detect slippage or idle of the wheel. In addition, the acceleration sensor may be embedded in the control unit 300 to detect a speed change of the mobile robot. That is, the acceleration sensor detects the impact amount according to the speed change and outputs a voltage value corresponding thereto. Thus, the acceleration sensor can perform the function of an electronic bumper.

The control unit 300 may calculate a change in position of the mobile robot based on the motion information output from the motion detection unit. This position becomes a relative position corresponding to the absolute position using the image information. The mobile robot can improve the performance of the position recognition using the image information and the obstacle information through the relative position recognition.

Referring to FIG. 6, the mobile robot further includes an input unit 700 that directly receives a control command. Further, the user or the like may input a command through the input unit to output one or more pieces of information stored in the storage unit. The input unit 700 may be formed of one or more buttons. For example, in the case of a robot cleaner, the input unit 700 may be provided with a button for setting or changing a cleaning mode. In addition, the input unit 700 may further include a button for receiving a command to return to the charging station. As illustrated in FIG. 6, the input unit 700 may be installed on the upper part of the mobile robot using a hard key, a soft key, a touch pad, or the like. In addition, the input unit 700 may have a form of a touch screen together with the output unit.

The output unit 800 is provided in the upper part of a mobile robot, as shown in FIG. Of course, the installation location and installation type may vary. For example, the output unit 800 displays reservation information, battery status, intensive cleaning, space expansion, cleaning method such as zigzag driving, or driving method on the screen. The output unit 800 may output the current state and the current cleaning state of each unit constituting the mobile robot. In addition, the output unit 800 may display obstacle information, location information, image information, obstacle map, area, route, and the like on the screen.

Referring to FIG. 3, the mobile robot further includes a power supply unit 900. The power supply unit 900 includes a rechargeable battery to supply power to the mobile robot. The power supply unit supplies driving power to each of the units, and operating power as the mobile robot travels or performs cleaning. When the remaining power is insufficient, the power supply unit is charged to receive a charging current. The mobile robot may further include a battery detection unit (not shown) that detects a charging state of the battery and transmits a detection result to the control unit 300. The battery remaining amount can be displayed on the screen of the output unit. The control unit 300 sets a reference value (battery remaining amount) in advance, and compares the remaining battery level with the reference value. As a result of the comparison, if the detection result is less than or equal to the reference value, the control unit 300 moves the mobile robot to the charging station to perform charging.

If the mobile robot is a robot cleaner, the mobile robot may further include a cleaning unit. The cleaning unit includes a dust container in which dust collected is stored, a suction fan providing power to suck dust in the cleaning area, and a suction motor rotating the suction fan to suck air, thereby removing surrounding dust or foreign matter. Inhale.

Referring to FIG. 8, a control method of a mobile robot according to an embodiment may include detecting image information by photographing a surrounding (S100), and detecting obstacles in the surroundings and outputting obstacle information (S200); Extracting a plurality of first feature lines from the image information (S300); extracting one or more second feature lines from the obstacle information (S400); and the first and second feature lines. And matching (S500) and recognizing the position of the mobile robot using the matching result (S600). Hereinafter, the configuration of the apparatus will be described with reference to FIGS. 1 to 7.

The extracting of the first feature lines (S300) may include extracting a plurality of points from two image informations, matching the points between the two image informations, and extracting a plurality of feature points (S310). Comprising a step (S320) for calculating a three-dimensional coordinates for a plurality of feature points, and the step (S330) for extracting the first feature line using a plurality of feature points having the three-dimensional coordinates.

4 illustrates an operation of extracting a first feature line from image information. The mobile robot detects image information by photographing a surrounding using a camera (S100). Referring to FIG. 4A, the mobile robot extracts a plurality of feature points by processing image information in a predetermined image (S310). Then, the mobile robot matches a plurality of feature points based on two or more pieces of image information taken continuously. The plurality of feature points may be represented by three-dimensional coordinates (S320). Referring to FIG. 4B, the mobile robot extracts first feature lines using feature points expressed in 3D coordinates and line components extracted from image information (S330). Since the method of extracting the first feature lines from the image information varies according to an image processing technique, a detailed description of the image processing technique will be omitted. The mobile robot may generate an obstacle map for the entire area using the first feature lines. That is, the first feature lines are indicative of absolute position.

Referring to FIG. 9, the control method may further include generating an obstacle map using the plurality of first feature lines (S340). The generating of the obstacle map (S340) may include extracting a plurality of points from two pieces of image information, matching the points between the two pieces of image information, and extracting a plurality of feature points. Comprising a step of calculating the three-dimensional coordinates for, and using the plurality of feature points having the three-dimensional coordinates to represent the first feature line to the obstacle map.

Referring to FIG. 5A, the mobile robot may generate an obstacle map using the first feature lines (S340). That is, the mobile robot may express line components extracted from the image information using obstacle maps using three-dimensional feature points.

The mobile robot detects nearby obstacles using obstacle detection units such as a PSD sensor or an ultrasonic sensor and generates obstacle information (S200). 5B to 5C, the mobile robot extracts the second feature line using the obstacle information (S400). The obstacle information includes an obstacle detection position (or a position of the mobile robot at the time of obstacle detection), an obstacle detection period (time interval), and the like. The obstacle detection position may be displayed as shown in FIG. 5B, and when connected thereto, the second feature line may be extracted. The second feature line is the line component of the local obstacle.

Referring to FIG. 5D, the mobile robot matches the first feature line with the second feature line (S500) and recognizes a position using the matching result (S600). That is, the mobile robot recognizes the position by matching the second feature line with the first feature line having the absolute position. Here, when the lighting change is severe or the illuminance is less than a certain illuminance, the mobile robot may match the second feature line with the first feature lines in the obstacle map and use the matching result.

Referring to FIG. 10, the control method may further include detecting an ambient illuminance (S700) and comparing the detected illuminance with a predetermined illuminance (S710). Here, in the step of recognizing the position (S600), the position is recognized using the comparison result. In the matching step S500, when the detected illuminance is equal to or less than the predetermined illuminance, the first feature lines and the second feature line in the obstacle map are matched. The mobile robot detects light using a photo sensor, a photo transistor, and the like, and senses illuminance using the photo sensor (S700). If the detected illuminance is greater than the predetermined illuminance, the mobile robot uses the matching result of the first and second feature lines extracted from the image information and the obstacle information, respectively (S520). The position is recognized using the matching result of the first feature lines and the extracted second feature line (S510) (S600).

As described above, the mobile robot and its control method according to the embodiments of the present invention can recognize their position using image information and obstacle information. In particular, embodiments of the present invention use feature lines extracted from the image information and the obstacle information, respectively, according to the change in the illumination of the surroundings, or use a feature line extracted from the obstacle map and the obstacle information generated using the image information. The location can be recognized accurately. In addition, embodiments of the present invention by performing the absolute position recognition using the image information and the relative position recognition using the obstacle information in parallel to reduce the error of the position recognition in various lighting environments, improve the performance of the absolute position recognition, and improve the driving efficiency Increase.

10: first feature line extracting unit 20: second feature line extracting unit
30: map generator 40: location recognizer
100: image detection unit 200: obstacle detection unit
300: control unit 400: storage unit
500: illuminance detection unit 600: drive unit

Claims (14)

A first feature line extracting unit extracting feature points from image information acquired from a surrounding, and extracting first feature lines using the feature points;
A second feature line extracting unit extracting one or more second feature lines using obstacle information on the surrounding obstacles;
A location recognizing unit matching the first feature lines with the second feature line and recognizing a location based on a matching result; And
A map generator generating an obstacle map using the first feature lines;
Including, but the location recognizing unit,
And if the peripheral illuminance is equal to or less than a predetermined illuminance, matching the first feature lines and the second feature line in the obstacle map to recognize the position. delete delete An image detection unit detecting an image by photographing a surrounding;
An obstacle detecting unit having one or more sensors and detecting obstacles in the vicinity and outputting obstacle information;
A control unit extracting a plurality of first feature lines from the image information, extracting one or more second feature lines from the obstacle information, and matching the first feature lines with the second feature lines to recognize a position; And
An illuminance detecting unit detecting the illuminance of the surroundings;
Including, the control unit,
Generate an obstacle map using the first feature lines, and if the illuminance detected by the illuminance sensing unit is greater than a predetermined illuminance, use a matching result of the first feature lines and the second feature line,
And when the illuminance sensed by the illuminance detecting unit is equal to or less than the predetermined illuminance, recognize the position by using a matching result of the first feature lines and the second feature line in the obstacle map. delete 5. The method of claim 4,
And a storage unit storing the first feature lines, the one or more second feature lines, and the obstacle map. delete delete The method of claim 4, wherein the control unit,
A feature point extracting unit extracting a plurality of points from two pieces of image information, and extracting a plurality of feature points by matching points between the two pieces of image information;
A coordinate calculator configured to calculate three-dimensional coordinates of the plurality of feature points;
A first feature line extracting unit extracting the plurality of first feature lines from the image information;
A map generation unit expressing the first feature lines as the obstacle map using a plurality of feature points having the three-dimensional coordinates; And
And a second feature line extracting unit which extracts the at least one second feature line from the obstacle information. Photographing the surroundings to detect image information;
Sensing obstacles in the vicinity to output obstacle information;
Extracting a plurality of first feature lines from the image information;
Generating an obstacle map using the plurality of first feature lines;
Extracting at least one second feature line from the obstacle information;
Detecting illuminance of the surroundings;
Comparing the detected illuminance with a predetermined illuminance;
If the detected illuminance is equal to or less than the predetermined illuminance, matching the first feature lines and the second feature line in the obstacle map; And
Recognizing a position of the mobile robot using the matching result; Control method of a mobile robot comprising a. delete delete delete The method of claim 10, wherein generating the obstacle map,
Extracting a plurality of points from two image informations;
Extracting a plurality of feature points by matching points between the two image information;
Calculating three-dimensional coordinates of the plurality of feature points; And
And expressing the first feature lines as the obstacle map using a plurality of feature points having the three-dimensional coordinates.

Images