JP2011238052A - Route determination system and moving device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a route determination system capable of determining a desired moving route, in a moving device which moves along a route consisting of a plurality of lines determined in advance.SOLUTION: The route determination system is installed in a moving device which moves along a route consisting of a plurality of lines. In the route determination system, the plurality of lines are stored and pictures of signs are taken with a camera (S11), contents of the signs are recognized (S12), and a movable route consisting of a plurality of lines is determined from line information and the recognized signs (S13).

Description

  The present invention relates to a route determination system and a mobile device, and more particularly to a route determination system and a mobile device capable of efficiently moving in a predetermined space.

  Conventionally, a system for recognizing a sign on a road using a camera and collecting sign information thereby is disclosed in, for example, Japanese Patent Application Laid-Open No. 2006-38558 (Patent Document 1). In this system, traffic signs and the like are recognized from image data captured by an in-vehicle camera and extracted as sign data.

JP 2006-38558 A (paragraph numbers 0009, 0024 to 0030, etc.)

  The system disclosed in Patent Document 1 is a so-called car navigation system in which a current location and a destination are input, and a recommended route from the current location to the destination can be selected arbitrarily.

  On the other hand, for a device that needs to move along a route constituted by a plurality of predetermined lines, such as a mobile cleaning robot, as to how to determine the route, There is no disclosure in conventional patent documents.

  The present invention has been made in view of the above problems, and in a mobile device that moves along a route configured by a plurality of predetermined lines, a route determination system that can determine a desired travel route, And it aims at providing the moving apparatus which has it.

  A route determination system according to the present invention is a route determination system that is provided in a moving device that moves along a route constituted by a plurality of lines and determines a moving route. The route determination system includes a line storage unit that stores a plurality of lines, a camera that captures a marker provided in the vicinity of the line, a marker recognition unit that recognizes the contents from the marker captured by the camera, and a storage unit Route determining means for determining a route to be moved based on the line information stored therein and the contents of the sign recognized by the sign recognition means.

  Preferably, the route determination unit includes a one-stroke route detection unit that detects a route that can be moved with a single stroke from routes formed by a plurality of lines.

  More preferably, the one-stroke writing route detection means includes an approximation means for approximating an area in which the moving device moves so that the moving area can be moved with one writing stroke.

  When the sign recognition unit recognizes that there is a line that cannot pass through any of the plurality of lines, the route determination unit preferably determines the route by excluding the line that cannot pass.

  In another aspect of the present invention, the moving device moves along a route constituted by a plurality of lines. The mobile device includes a line storage means for storing a plurality of lines, a camera for photographing a sign, a sign recognition means for recognizing the contents from the sign photographed by the camera, line information stored in the line storage means, Route determining means for determining a route to move based on the content of the sign recognized by the sign recognition means.

  In this invention, a plurality of lines are stored, a sign provided in the vicinity of the line is photographed with a camera, the contents thereof are recognized, and a route to be moved is determined based on the line information and the recognized sign contents. Therefore, it is possible to provide a route determination system and a moving device that can move a desired route simply by using a sign.

It is a block diagram which shows the principal part of the self-supporting traveling robot which has a route determination system. It is a figure which shows the structural example of the route detected by the route determination system. It is a flowchart which shows a route determination processing procedure. It is a flowchart which shows a label | marker recognition process procedure. It is a flowchart which shows a route determination processing procedure. It is a figure which shows the route | root in other embodiment. It is a flowchart which shows the route determination processing procedure in other embodiment.

  Hereinafter, a case where a route determination system according to an embodiment of the present invention is applied to a cleaning robot as a mobile device will be described with reference to the drawings. FIG. 1 is a block diagram showing a main part of a cleaning robot having a route determination system. Referring to FIG. 1, a cleaning robot 10 is recognized by a CPU 11 that controls the entire cleaning robot 10, a camera 20, a sign recognition unit 12 that recognizes a sign from an image captured by the camera 20, and a sign recognition unit 12. It includes a determination unit 13 that determines the meaning of the sign based on the sign, a storage unit 14 that stores area information and the like in which the cleaning robot 10 travels, and a traveling unit 15 that moves the cleaning robot 10.

  Here, the cleaning robot 10 is a line trace type robot that moves by tracing a line provided on a floor or the like with a tracing sensor (not shown). The storage unit (storage means) 14 stores map information of the area where the user travels, predetermined travel routes (directions) constituted by lines, passage times, and the like.

  FIG. 2 is a diagram illustrating an example of an area 40 where the cleaning robot 10 travels and a movement route within the area 40. Here, the area 40 has a pentagonal shape as a whole, and is composed of five vertices A to E and a plurality of lines connecting them. The cleaning robot 10 covers the area 40 by moving along a route composed of 10 lines a to j connecting these five vertices A to E.

  FIG. 3 is a flowchart showing a procedure for determining a travel route performed by the CPU 11. Referring to FIG. 3, first, cleaning robot 10 captures a sign with camera 20 if there is a sign on or near the travel route (step S <b> 11, hereinafter, “step” is omitted). Next, the photographed sign is recognized (S12). A travel route is determined according to the recognition result (S13). Therefore, the CPU 11 operates as a sign recognition unit and a route determination unit.

  Next, the label recognition procedure described in S12 will be described. FIG. 4 is a flowchart showing this procedure. First, the CPU 11 binarizes the photographed image (S121), cuts out the shape (S122), recognizes the shape and recognizes characters and numbers, and recognizes the color (S123). As a result, the image is judged and the sign is recognized (S124).

  Next, the route determination procedure described in S13 will be described. Here, a case where the vehicle travels in the area 40 with the regular pentagon shown in FIG. 2 will be described as an example. Therefore, the storage unit 14 indicates that the area 40 is a pentagon having points A to E as vertices, and that the entire area 40 can be covered by traveling on the lines a to j connecting the points A to E to each other. Is stored.

  First, the cleaning robot 10 is placed at the point A. This may be determined by the camera 20, or the start point may be input in advance. Here, for example, a condition that starts from the point A, passes through each passage once, and returns to the point A is one of the routes that efficiently pass through the ten passages a to j, a → b → c → A route moving in the order of d → e → f → g → h → i → j is stored in the storage unit 14. Thus, if it travels by "one stroke writing", it will be possible to cover all the passages from the point A and to return to the point A.

  Such a travel route may be displayed on a display unit (not shown) of the cleaning robot 10 and may be activated by a user turning on a switch (not shown). The cleaning robot 10 may recognize a sign indicating that the cleaning robot 10 is installed.

  As described above, according to this embodiment, a plurality of lines are stored, a sign provided in the vicinity of the line is photographed with a camera, and the contents thereof are recognized, and line information and recognized sign contents are obtained. Based on this, the route to be moved is determined, so that the desired route can be easily moved only by using the sign. Moreover, if it travels with a single stroke, it can move efficiently. In this case, the CPU 11 operates as a one-stroke writing route detection unit.

  Next, a case where a part of the passage cannot be passed due to construction or temporary blockage will be described. In this case, it is impossible to turn around the predetermined route, and the route must be changed. In order to change, the cleaning route 10 must be taught to the cleaning robot 10, which is very time consuming and may not be possible to operate if the technician is absent. Further, even if programmed in advance, the operator must perform the setting, and the more routes, the greater the number of possible combinations and the larger the system. However, in this embodiment, the following processing is possible using the label.

  Here, for example, a case where the passage e cannot pass will be described. In this case, the form of the sign Z that prohibits passage of the passage is stored in the storage unit 14 in advance, and the passage prohibition sign Z is installed at points E and A that are both ends of the passage E. The cleaning robot 10 recognizes the sign Z from the image from the camera 20 when passing the route of the passage e, so that the cleaning robot 10 itself is efficient by the route, the map information, and the sign recognition result. It is possible to detect the optimum route by using a one-stroke rule.

  FIG. 5 is a flowchart showing a route determination procedure performed by the CPU 11 of the cleaning robot 10 in this case. First, the cleaning robot 10 is placed at the point A. The cleaning robot 10 proceeds from the point A as a route in the order of lines a → b → c → d → e. When the camera 20 captures the sign Z at the point E, the image is recognized (S11, S12 in FIG. 3). Next, with reference to FIG. 5, an impassable line is detected according to the recognition result (S131, S132). Next, a past passing line is detected (S133), and a travel route is determined (S134).

  Specifically, it proceeds to h → i → j → f → g → and returns to the point E. Thereafter, in order to proceed to the original point A, the route h → a is followed.

  As described above, it is assumed that the one-stroke route information for passing through the points A to E and the shortest route information for returning from the stopped position to the original position are stored in the storage unit 14 in advance.

  In addition, "whether or not you can draw a stroke" is, according to the mathematics Euler, "if the total number of edges that go in and out of any point in the diagram (called local degree) is all even, the graph is I can write a stroke. " The definition of “one-stroke drawing” here means “do not trace the same line twice”, so here it means “pass all routes in a way that does not follow the same route as much as possible” .

  As described above, in this embodiment, when determining a route when a part of the passage cannot pass, it is possible to select a route that can be “drawn with one stroke”. Therefore, it is possible to determine a moving route more efficiently.

  Next, another embodiment of the present invention will be described. In the embodiment described above, the cleaning robot 10 determines a travel route so that the area can be efficiently covered with respect to the given travel area 40. For this purpose, the route is determined so as to cover the area 40 with a single stroke, such as a regular pentagon, for a given area.

  In this embodiment, first, the traveling area is approximated to a form in which one stroke can be written, and then the same processing as in the previous embodiment is performed. FIG. 6 is a diagram showing a travel route in this case, and FIG. 7 is a diagram corresponding to FIG. 3 in this case. In this case, the route determination procedure is as shown in FIG.

  With reference to FIG. 6 and FIG. 7, in this embodiment, the traveling area is approximated to be a one-stroke route in the hexagonal area (S21). That is, it consists of six vertices A to F and lines a to l connecting them. In this case, normally, one of the routes starting from the point A and returning to the point A travels by g → h → i → a → b → c → d → e → l → j → k → f. Therefore, the CPU 11 operates as approximation means.

  At this time, a case where traveling in the section a becomes impossible will be described. In this case, the signs Z are placed at the points A and B.

  The CPU 11 captures and recognizes the sign with the camera 20 (S22, S23), and determines the route (S24). At this time, the CPU 11 detects a route consisting of the line f → l as a method of arriving at the next point B.

  This is because the following contents are stored in the storage unit 14 as map information.

Route to point A: a (B → A), g (C → A), i (E → A), f (F → A)
Route to point B: a (A → B), l (F → B), j (D → B), b (C → B)
Route to point C: b (B → C), c (D → C), h (E → C), g (A → C)
Route to point D: c (C → D), d (E → D), j (B → D), k (F → D)
Route to point E: d (D → E), e (F → E), h (C → E), i (A → E)
Route to point F: e (E → F), f (A → F), k (D → F), l (B → F)

  Further, by storing the traveled route, a past passing line is detected, the current position is the point A, and the route to B is detected. From point A, there is a route that passes through lines a, g, i, and f, but line a cannot travel. When a route passing through the line g is used (the route of g is A → C), the route from the point C to the point B is detected based on the map information. As a result, the route passes through the line g → b.

  On the other hand, if the i route is used (the i route is from the point A to the point E), the route from the point E to the point B does not exist according to the map information. Bypass and connect. That is, the route is a route passing through the line i → e → l, a route passing through the line i → h → b, and a route passing through the line i → d → j.

  When the route passing through the line f is used (the route of f is from A to F), the route from the point F to the point B is detected by the map information. That is, a route passing through the line f → l is detected.

  From the above, a route passing through the line g → b or a route passing through the line f → l is detected. However, since the line g has passed first, a route passing through the line f → l is detected. As a result, a route passing through the lines g → h → i → f → l → b → c → d → e → l → j → k → f is determined.

  In addition, before the next run, since the route passing through the line a cannot be passed at the start point A, the optimum route is detected. New route detection uses a brute force detection method. This is because the combinations of routes are finite and can be executed.

  Specifically, it is as follows.

  The route from the point A includes g (A → C), i (A → E), and f (A → F). However, the route passing through the line a is deleted.

  The route from the point B includes l (B → F), j (B → D), and b (B → C). The route through line a is deleted.

  Routes from the point C include b (C → B), c (C → D), h (C → E), and g (C → A).

  The route from the point D includes c (D → C), d (D → E), j (D → B), and k (D → F).

  The route from the point E includes d (E → D), e (E → F), h (E → C), and i (E → A).

  The route from the point F includes e (F → E), f (F → A), k (F → D), and l (F → B).

  These search routes are sequentially searched from the point A. However, the route once passed is excluded from the search contents. In the above-described embodiment, the travel prohibition sign Z is provided at both ends of the route. In this case, when the sign is recognized, the cleaning robot 10 makes a U-turn and returns to the previous point to perform the same processing.

  Further, in the above embodiment, the case where the section represented by a certain line is approximated to the one-stroke route when the section cannot be traveled has been described. However, the present invention is not limited to this. You may approximate the writing root.

  The sign Z is not limited to one place, and may be provided at a plurality of places. As the sign Z, in addition to prohibiting traffic, “speed control”, “pause”, “direction control”, “ A “cleaning instruction” or the like may be instructed. Further, it may be a sign indicating “accessible direction”, “accessible time zone”, or the like.

  In addition, as another condition, a condition for turning around a predetermined passage within a predetermined time is added in advance. For example, in the case of a cleaning robot, a condition such as “cleaning each passage once within 4 hours” In the case of a patrol robot, a condition such as “pause each passage once within 2 hours” may be added. In this case, the CPU 11 determines a route so as to satisfy a predetermined condition using its own timer.

  In such a case, even if sudden construction or passage blocking is performed, the same processing can be performed only by installing a sign. That is, when the sign is recognized from the camera image, the optimum route can be detected by using the map information, the route that the robot itself has passed, and the time that the robot has passed, using the rule of writing the efficient route with one stroke.

  In the above description, the cleaning robot has been described as an example. However, the present invention is not limited to this, and the present invention may be applied to a patrol (security) robot, a factory transport robot, and the like.

As mentioned above, although embodiment of this invention was described with reference to drawings, this invention is not limited to the thing of embodiment shown in figure. Various modifications and variations can be made to the illustrated embodiment within the same range or equivalent range as the present invention.

  The route determination system according to the present invention can be advantageously used as a route determination system because a desired route can be determined simply by using a sign.

  DESCRIPTION OF SYMBOLS 10 Cleaning robot, 11 CPU, 12 Sign recognition part, 13 Determination part, 14 Storage part, 15 Traveling part, 20 Camera, 40 area

Claims (5)

A route determination system that is provided in a mobile device that moves along a route constituted by a plurality of lines and determines a route to be moved,
Storage means for storing the plurality of lines;
A camera for photographing a sign provided in the vicinity of the line;
A sign recognition means for recognizing the contents of the sign taken by the camera;
A route determination system comprising: route determination means for determining a route to move based on line information stored in the storage means and contents of the signs recognized by the sign recognition means. The route determination system according to claim 1, wherein the route determination unit includes a one-stroke route detection unit that detects a route that can be moved with a single stroke from routes constituted by a plurality of lines. The route determination system according to claim 1, wherein the one-stroke writing route detection unit includes an approximation unit that approximates a region in which the moving device moves with a one-stroke writing route. 4. When the sign recognition unit recognizes that there is a line that cannot pass through any of the plurality of lines, the route determination unit determines a route by excluding the line that cannot pass. A route determination system according to any of the above. A moving device that moves along a route constituted by a plurality of lines,
Line storage means for storing the plurality of lines;
A camera to shoot the sign,
A sign recognition means for recognizing the contents of the sign taken by the camera;
A moving apparatus comprising: route determination means for determining a route to move based on line information stored in the line storage means and the content of the sign recognized by the sign recognition means.

Images