JP7699349B2 - Automated Guided Vehicles and Automated Guided Vehicle Systems - Google Patents

Description

The present invention relates to an automated guided vehicle capable of autonomous driving, for example equipped with a map update function using 3D-SLAM (3-dimensional simultaneous localization and mapping), and an automated guided vehicle system including the automated guided vehicle.

Conventionally, as a method for guiding a rail-guided automatic guided vehicle (AGV), for example, the following method is known.
(1) A method in which an AGV detects radio waves from a guidance cable buried in the roadway. (2) A method in which guidance tape is attached to the roadway and the AGV detects magnetism or reflected light. (3) A method in which guidance signs are installed on the roadway and the AGV recognizes the images of the guidance signs.

However, these methods require the installation of guidance equipment on the travel path in advance.
In recent years, therefore, a method of autonomous transportation using a trackless system has been studied, in which an autonomous guided vehicle recognizes obstacles using sensors and travels autonomously. As obstacle avoidance path generation methods, the rule-based method, the (virtual) potential method, and the search method are mainly known. Patent Document 1 discloses an autonomous mobile device that employs the virtual potential method and can create multiple partial maps that constitute an environmental map of a moving area based on distance information and angle information of surrounding objects read from a laser range finder. In this autonomous mobile device, self-location estimation and environmental map creation are performed in real time using SLAM (Simultaneous Localization and Mapping).

JP 2010-92147 A

In the above guidance method (1), the cost of burying the guidance cable is high, and the travel path cannot be easily changed. In the above guidance method (2), guidance becomes impossible if the guidance tape installed on the travel path is damaged, so the guidance tape needs to be replaced periodically. In an environment such as a warehouse where the travel path of an automated guided vehicle and the traffic flow of a forklift overlap, there is an issue that the replacement span of the guidance tape is shorter than usual.

In the above guidance method (3), there is a problem that the accumulation of measurement errors causes inconsistencies in the created environmental map, and in particular, when creating a circular environmental map, the start and end parts do not match (circular route problem). In addition, there is a problem that when the layout around the driving road is changed, the entire environmental map needs to be recreated. Therefore, Patent Document 1 proposes that the environmental map be divided into multiple partial maps and managed, so that the range of measurement errors is limited to the partial maps, and the range that needs to be recreated when the layout is changed is limited to each partial map.
However, in an environment where manned guided vehicles and workers work in the same space, the layout of the work space changes constantly, which causes a problem that the accuracy of self-location estimation decreases due to unexpected environmental changes. There is also a need to minimize the changes in system settings that are required when changing the layout in a warehouse.

However, there is a need to use inexpensive sensors to replace expensive laser range finders (e.g., LiDAR (Light Detection and Ranging)) as a means of detecting surrounding objects. Although it is possible to use inexpensive image sensors such as stereo cameras as an alternative, if disturbance light enters the field of view of the automated guided vehicle, it becomes temporarily unable to detect surrounding objects, causing the automated guided vehicle to stop. In environments such as warehouses where disturbance light is constantly entering from receiving and shipping areas connected to the outdoors, there is a problem in that it is difficult to configure an automated guided vehicle using a stereo camera.

Therefore, the present invention aims to provide an automated guided vehicle and an automated guided vehicle system that can solve the above problems.

The automated guided vehicle system of the present invention is an automated guided vehicle system comprising: an automated guided vehicle that autonomously travels along a travel path based on an environmental map; a landmark image projection device that projects a landmark image of a specific shape or pattern along the travel path; and a server that transmits a projection command to the landmark image projection device to project the landmark image, wherein the automated guided vehicle comprises a color image sensor that captures an image of an object in the direction of travel; a drive unit that independently controls the drive of a plurality of wheels; a robot control unit that transmits a control command for the autonomous travel to the drive unit; and a wireless communication unit, and the robot control unit has a function of constantly updating the environmental map and route based on image information from the color image sensor; a function of linking the projected landmark image with coordinate information on the environmental map and registering it; and a function of recognizing feature points in the image information from the image sensor and calculating the current position against the environmental map. and a second current position estimation function that, when a landmark image is included in image information from a color image sensor, estimates the current position based on coordinate information of the landmark image, wherein the landmark image projection device has functions of projecting a floor line onto the boundary between the travel path and the work section, projecting a boundary line image of a color different from the floor line onto the boundary between the travel path and the work section which serves as an aisle, projecting a floor guide line having specific color information onto the travel path, and projecting a wall or ceiling guide line having specific color information onto a wall surface or a ceiling, and the unmanned guided vehicle includes a first unmanned guided vehicle and a second unmanned guided vehicle, and a robot control unit of the first unmanned guided vehicle performs first travel control based on the floor guide line, and a robot control unit of the second unmanned guided vehicle performs second travel control based on the wall or ceiling guide line .
In the above-described automated guided vehicle system , the drive unit may have a function of transmitting rotation information of the plurality of wheels to a robot control unit as odometry information, and the robot control unit may have a third current position estimation function of estimating a current position based on the odometry information and previously stored current position information.
In the above-mentioned automated guided vehicle system , the robot control unit may be characterized by having a function of dynamically generating a composite image by adding a virtual landmark image to image information from the color image sensor in an environment where disturbance light is present , and a function of performing driving control based on the virtual landmark image contained in the composite image.
In the above-mentioned automated guided vehicle system , the landmark image may include an image of an artificial code including a two-dimensional code.

In the above-mentioned automated guided vehicle system, the landmark image may include an image of a character string, a logo, or a character.
In the above-described automated guided vehicle system, the server may transmit a projection command to project an image for performing the first driving control during a first time period, and transmit a projection command to project an image for performing the second driving control during a second time period.

The present invention makes it possible to provide an automated guided vehicle and an automated guided vehicle system that can travel autonomously using inexpensive image sensors even in environments where disturbance light is present in indoor facilities such as warehouses. It is also possible to easily accommodate changes to the layout within the warehouse.

1 is a configuration diagram of an automated guided vehicle system according to an embodiment; FIG. 2 is a plan view of an automated guided vehicle according to an embodiment. FIG. 2 is a side view of an automated guided vehicle according to an embodiment. FIG. 2 is a plan view for explaining a running path in a warehouse according to an embodiment. 1A and 1B are diagrams illustrating a triangular cone with an AR marker and colored tape attached to a wall according to an embodiment of the present invention. 4A and 4B are diagrams for explaining a wall line recognition area and a floor line recognition area in the present embodiment. FIG. 13 is a diagram for explaining a travel control method using floor guide lines provided on the floor surface. 13 is a diagram for explaining a travel control method using a wall guide line provided on a wall. FIG. 13 is a diagram for explaining a travel control method using ceiling guide lines provided on the ceiling. FIG. 13 is a flowchart of route correction during driving. 13 is a flowchart of a process for acquiring a current position using complementary information. 11 is a diagram for explaining a composite image generating function for dynamically generating a composite image by adding a virtual image to a captured image. FIG.

In the following, a system configuration of an embodiment of the present invention will be described, and then a procedure for loading and unloading work will be described as an example of a transport work method of the present invention.
<System Configuration>
The automated guided vehicle system of the embodiment is configured to include an RM server 1, a WMS server 2, a management terminal 3, a handheld terminal 4, a wireless LAN master unit 5, a cart 6, a landmark image projection device 7, and a plurality of automated guided vehicles 10. The handheld terminal 4, the wireless LAN master unit 5, the cart 6, the landmark image projection device 7, and the plurality of automated guided vehicles 10 are installed in a work area of an indoor facility such as a warehouse.

The RM server 1 is a server capable of managing the automated guided vehicles 10, and is constructed by installing RM software and database software in a server device equipped with a CPU and a storage device. The RM software includes, as software modules for realizing the main functions, a vehicle management unit 1a, a work coordination unit 1b, a work place management unit 1c, and a billing information management unit 1d.
The guided vehicle management unit 1a manages information about a work site where the automated guided vehicle 10 is placed and operation information about the automated guided vehicle 10. In the guided vehicle management unit 1a, the vehicle ID of the automated guided vehicle 10 and the work site ID of the work target are linked and managed.
The work coordination unit 1b manages the operating times of multiple automated guided vehicles 10. The work coordination unit 1b manages the vehicle ID of the automated guided vehicle 10 in association with the work site ID of the work site where the work is to be performed, and these are input data for calculating billing information. Note that multiple automated guided vehicles 10 may operate in the same space in the same building, and there may be cases where only one vehicle is operated.
The work place management unit 1c manages a basic map for each work place and transmits the basic map to the automatic guided vehicle 10. In the basic map, passable routes and prohibited areas are set. Note that the basic map of the work place may not be managed by the RM server 1, but may be managed by the automatic guided vehicle 10 and a management terminal installed in the work place.
The billing information management unit 1d acquires operation information of the automatic guided vehicle 10 from the vehicle management unit 1a, and calculates billing information for each client by referring to a fee table.
The projection device management unit 1e transmits a projection command to project a specific image to a specific landmark image projection device 7. The projection device management unit 1e also has a function of transmitting a projection command to project different images in a first time zone and a second time zone.

The WMS server 2 is a server that enables the realization of a warehouse management system, and is constructed by installing WMS software and database software on a server device equipped with a CPU and a storage device. This WMS software includes an inventory management section 2a and an order processing section 2b as software modules that realize the main functions.

The inventory management unit 2a updates an inventory database that manages product IDs, storage addresses, statuses, etc. It also has a function of assigning storage addresses in accordance with storage information received from the management terminal 3, a function of sending storage instructions to the handheld terminal 4 and the automated guided vehicle 10, and a function of managing the quantity of products to be stored, the status of the delivery situation, etc.
The order processing unit 2b updates the order database that manages the order information received from the management terminal 3. The order processing unit 2b transmits a shipping instruction based on the order information to the handheld terminal 4 and the automatic guided vehicle 10, and updates the status of the order to completed when shipping information is received from the handheld terminal 4. The order processing unit 2b also has an allocation function that reserves inventory according to an order, and when an ordered quantity of inventory for an order is allocated, that quantity cannot be reserved for other orders, so that inventory is secured.

The landmark image projection device 7 is, for example, a laser beam irradiation device or a projector, and a plurality of units are installed on the ceiling, wall or floor along the travel path in the warehouse. The landmark image projection device 7 is configured to be able to communicate with the RM server 1, and projects an image of a specific shape or pattern that can be used as a landmark image onto the floor, wall or ceiling, etc., based on a projection command from the RM server 1. Examples of images of specific shapes or patterns projected by the landmark image projection device 7 include lines including dotted lines, circles and ellipses, polygons including triangles, geometric patterns, artificial codes, character strings, corporate logos, and characters. Different images may be projected by the landmark image projection device 7 depending on the time of day. The landmark image projection device 7 of the embodiment is equipped with a rotation device, and is capable of changing the projection position based on a command from the RM server 1.
As shown in FIG. 1, the automated guided vehicle 10 is configured to include a robot control unit 11, a display unit 12, a wireless communication unit 13, a speaker 14, a power supply unit 15, a drive system (21-23), and a group of sensors (31-33).

2 and 3, the drive system (21-23) of the automated guided vehicle 10 is disposed on the underside of the base 16, and the rest of the robot control unit 11 and the like are disposed on the upper side of the base 16. The wheels 19 are single wheels that do not have a drive unit, and are disposed on the underside of the base 16 via a rotating table 18.
A gate-shaped frame 17 is provided on the travel direction side of the base 16, and an arm for attaching the display unit 12, an emergency stop button 24, and a fixing device for hanging and fixing the image sensor 33 are provided on the upper pillar of the frame 17.
A coupling section 41 provided with a locking post 42 is disposed on the side opposite to the traveling direction of the base 16. In the illustrated example, a locking plate 53 of a trailer 50 capable of towing a container is attached to the locking post 42. The trailer 50 is a non-self-propelled cart that includes a block-shaped body section 51, a long plate-shaped support section 52, and a pair of wheels 54a, 54b. The trailer 50 can further couple other trailers.

The robot control unit 11 is a computer running transportation software constructed using ROS (Robot Operating System), a standard platform for robot development, and includes a map management unit 111, an operation management unit 112, a route generation unit 113, a sensor management unit 114, and a virtual image generation unit 115.
The map management unit 111 has a map update function using 3D-SLAM (3-dimensional Simultaneous Localization AND Mapping). The environmental map updated by the map update function is composed of a basic map for parts that do not change, such as floor plans and basic passageways, and multiple partial maps. The map management unit 111 grasps the position and shape information of objects that are constantly changing, such as carts and shipping boxes, based on signals from a group of sensors (31 to 33), and updates the partial maps (surrounding maps) around itself in real time while traveling.

The operation management unit 112 controls the drive system (21 to 23) of the automated guided vehicle 10 based on the entry/exit command, enabling autonomous driving. Information on the amount of rotation of the wheels 23a, 23b obtained by an encoder provided on the axle is stored as odometry information. The operation management unit 112 has a function of estimating its own position without communicating with the RM server 1 using image information, odometry information, an environmental map, and observation data from the sensor group (31 to 33) (first current position estimation function). Here, a separate 6-axis sensor may be provided, and information from the 6-axis sensor may also be used in combination. A known estimation method (for example, the Monte Carlo method) may be used to estimate the self-position. In addition, the automated guided vehicle 10 has a line following function, which will be described later. When multiple automated guided vehicles 10 are driven on the same driving route, a function of exchanging self-positions with each other and ensuring a certain inter-vehicle distance may be provided. The traffic management unit 112 has a second current position estimation function that, when the image information from the image sensor includes a landmark image (described later), estimates the current position based on the coordinate information of the landmark image.
The route generating unit 113 generates a route for autonomous driving without communicating with the RM server 1, using an environmental map stored in the storage device of the robot control unit 11. The address of the storage location of the product, which is the storage/return location, is managed by the inventory management unit 2a in association with the product ID. The cargo handling location where cargo is received and delivered from a transport vehicle such as a truck is managed by the address on the basic map. When a storage/return instruction is issued, the route generating unit 113 generates a route (global route) from the cargo handling location to the storage/return location based on the basic map and the partial map, and corrects the surrounding route (local route) of the automatic guided vehicle 10 as necessary when the partial map is updated while the automatic guided vehicle 10 is traveling.

The sensor management unit 114 detects observation signals from the forward sensors (31a-31c), the side sensors (32a, 32b) and the image sensor 33, and transmits them to the map management unit 111, the operation management unit 112, etc. The three forward sensors (31a-31c) installed in the front are distance sensors (e.g., ultrasonic sensors) that detect objects in front of the vehicle in a range of, for example, 180 degrees or more. The two side sensors (32a, 32b) installed on the sides are distance sensors (e.g., ultrasonic sensors) that detect objects in the sides in a range of, for example, 120 degrees or more. When the five sensors (31a-31c, 32a, 32b) installed in the front and sides detect an obstacle (including a person), the operation management unit 112, which receives the detection information from the sensor management unit 114, controls the vehicle to avoid the obstacle or temporarily halt driving if avoidance is difficult.

The virtual image generating unit 115 has a composite image generating function that dynamically generates a composite image by adding a virtual image to the image captured by the image sensor 33. For example, by dynamically generating a composite image by adding an image of a virtual line, it is possible to execute a line following function described later based on the added virtual line, or to dynamically generate a composite image by adding an image of a mark indicating a direction change position, it is possible to control direction changes based on the added virtual mark. In addition, in an environment where disturbance light is incident, it is also possible to control driving by dynamically generating a composite image by adding a virtual landmark image. In these cases, since it is assumed that the current position information held by the operation management unit 112 is correct, it is preferable to use supplementary information by artificial code information such as an AR marker, QR code (registered trademark), or barcode, whose coordinates are known, to acquire the current position.

12A is an image captured by the image sensor 33, (b) is a composite image in which a virtual image is added to the image captured by the image sensor 33, and (c) is a schematic plan view of (b).
In the composite image shown in Fig. 12(b), a virtual guide line 81 and a virtual control sign 82 are added to the captured image of the image sensor 33. The operation management unit 112 performs travel control based on the added virtual guide line 81 and virtual control sign 82. For example, the present invention discloses a travel control that performs line following so that the virtual guide line 81 is positioned at the center of the base 16, and turns right at 90 degrees at the virtual control sign 82. When the landmark image in the captured image changes due to the travel of the automated guided vehicle 10, the current position of the automated guided vehicle 10 is corrected in real time. Therefore, even if the drawing positions of the virtual guide line 81 and the virtual control sign 82 are inaccurate, the drawing positions are corrected as the automated guided vehicle 10 travels.

The image sensor 33 is configured with a stereo camera arranged at a distance to capture two-dimensional images. The stereo camera may be configured with two independent fixed cameras, or may be configured with two integrated lens mechanisms and shutter mechanisms. The image sensor 33 is preferably configured with a color camera so that color information can be recognized. The image sensor 33 is attached to the front side of the base 16, captures two-dimensional images in front of the automated guided vehicle 10, and transmits the images to the map management unit 111.
The map management unit 111 generates a three-dimensional image having distance information based on the captured image of the image sensor 33. The map management unit 111 also has a function of registering an image of an object having a specific shape or pattern or an image of a specific shape or pattern projected onto a floor or wall as a landmark image in association with coordinates. As a landmark consisting of a tangible object, a protective sign such as a triangular cone (safety cone) or a support pole can be registered, or a colored tape or a hanging sign can be registered, or an information sign such as an AR marker, a two-dimensional code such as a QR code (registered trademark), or an emergency exit plate can be registered. In addition, an image of a specific shape or pattern projected onto a floor, wall, or ceiling from the landmark image projection device 7 can be used as a landmark. The image from the landmark image projection device 7 can also be projected to a specified coordinate. A server that manages landmark images may be installed at the work site or on the cloud, and landmark information (image and coordinate information) may be shared among multiple automated guided vehicles 10 arranged in the work site. It is preferable that the protective sign and the information sign are colored to have a high contrast with the background of the work site.

The display unit 12 is configured with a touch screen and also serves as an information input unit. In the embodiment, the display unit 12 is configured with a tablet terminal on which a program capable of communicating with the robot control unit 11 runs. The display unit 12 displays a recommended route created by the route generation unit 113. When the worker approves the route, the route generation unit 113 converts the approved route into array data. If the recommended route is not desirable, a route change instruction can be issued, and a different route created by the route generation unit 113 is displayed.
The wireless communication unit 13 enables two-way communication via a wireless LAN (e.g., Wi-Fi) with the handy terminal 4 and the RM server 1. The communication modules of the handy terminal 4 and the RM server 1 may be configured as separate modules, and communication with the RM server 1 may be configured to be performed via a Low Power Wide Area Network (LPWA).
The speaker 14 is composed of a general-purpose speaker, and plays a melody to notify the user that the automated guided vehicle 10 is traveling while the automated guided vehicle 10 is traveling. If the automated guided vehicle 10 stops due to an abnormality, an alarm notifying the user of the abnormality is sounded from the speaker 14. Note that instead of sounding an alarm when the automated guided vehicle 10 stops due to an abnormality, an image notifying the user of the abnormality may be displayed on the display unit 12, or a configuration may be adopted in which an abnormality is notified by a separately provided indicator light.
The power supply unit 15 includes a rechargeable secondary battery, and enables the automated guided vehicle 10 to travel cable-free. In addition to a contact-type charging device, the power supply unit 15 includes a power receiving device on the bottom or side that enables non-contact charging by positioning the automated guided vehicle 10 in a charging area. Note that non-contact charging is not a required configuration, and the configuration may include only a contact-type charging device.

The drive system (21 to 23) is composed of a drive control device 21, drive devices 22a and 22b, and wheels 23a and 23b.
The drive control device 21 is a computer that independently controls the drive of each of the drive devices 22a and 22b based on instructions from the robot control unit 11. The direction of the automated guided vehicle 10 is changed by changing the rotational angular velocity of the wheels 23a driven by the right drive device 22a and the rotational speed of the wheels 23b driven by the left drive device 22b.
The driving devices 22a, 22b are configured with general-purpose motors such as direct current (DC) motors, alternating current (AC) motors, motors with encoders, geared motors, etc., and can rotate the wheels 23a, 23b at any rotational angular velocity. The driving devices 22a, 22b can transport a load of 500 kg at a speed of, for example, 50 m/min or less. Unlike the embodiment example, a steering device for steering the wheels 23a, 23b may be provided separately from the driving devices, and in this case, the odometry information described above also includes steering angle information.
In the embodiment, the wheels 23a, 23b are tires suitable for running on floor surfaces coated with epoxy resin, etc. The diameter, width, and presence or absence of a tread pattern of the wheels 23a, 23b can be optimally determined depending on the weight of the goods to be transported and the condition of the floor surface.

The management terminal 3 is a terminal such as a notebook PC, a desktop PC, or a tablet, and is used for managing the RM server 1 and the WMS server 2. The management terminal 3 may be configured to be able to directly send a projection command to the landmark image projection device 7.
The handheld terminal 4 is a portable terminal used for reading barcodes during picking operations. The handheld terminal 4 includes a display unit consisting of a liquid crystal screen or the like, a storage unit consisting of a storage device or the like, a control unit consisting of a processor and a built-in clock or the like, an operation unit consisting of buttons or the like, a barcode reader unit, a wireless communication unit, and a secondary battery. In this embodiment, the operation unit is provided separately from the display unit, but the display unit may be configured as a liquid crystal touch screen that allows information input. In a preferred embodiment, the handheld terminal 4 is capable of wireless communication with the robot control unit 11 of the automatic guided vehicle 10.
A wireless LAN base station 5 is placed on the floor of the work area, providing an environment in which access to a wireless LAN (eg, Wi-Fi) is possible anywhere on the floor.

FIG. 4 is a plan view for explaining the travel path of a warehouse according to an embodiment. In the figure, the shaded areas are the travel path. A floor line 71 is partially projected by the landmark image projection device 7 on the boundary between the travel path and the work area on the floor surface. In places where it is difficult to project the floor line 71, the floor line 71 may be formed by color tape (e.g., tiger-patterned tape) or painting. In the figure, the boundary line 72 shown by the dotted line is the boundary between the travel path and the work area, and indicates the part that becomes the passage for people and forklifts. It is preferable that an image of a different color, shape, or pattern from the floor line 71 is projected on the boundary line 72 by the landmark image projection device 7. In the embodiment, the floor line 71 and the boundary line 72 are made distinguishable by forming them with lines of different colors. The projected boundary line 72 does not deteriorate even if people or forklifts pass by it, and also contributes to people visually recognizing the work space. In addition, by making the boundary line 72 a landmark image, the landmark information on the travel path increases, making it possible to improve the accuracy of autonomous driving. Additionally, the landmark image projection device 7 may project floor guide lines 76, described below, onto the main parts of the running path.

As shown in FIG. 5, colored tape (e.g., tape with a tiger pattern) 75 is partially affixed to the wall along the travel path at a height that is reflected by the image sensor 33 (e.g., a height shorter than a person's height) to alert the worker. Instead of colored tape 75, colored lines may be formed by painting. Wall guide lines 77 and ceiling guide lines 78, described below, are projected by the landmark image projection device 7 at locations necessary for travel control.

In the illustrated example, any of areas A, B, and C can be set as the start point and the goal point. Reference numeral 73 denotes a support pillar at about waist height, which is colored (e.g., tiger-patterned tape). Reference numeral 74 denotes a color cone (registered trademark, omitted below). As shown in FIG. 5, a two-dimensional code 79 such as an AR marker is attached to a part of the color cone 74. Color tape 75 is attached to the corner of the pillar that contacts the running path in the vertical direction. The color tape 75 can be replaced by painting, or an image of a specific shape or pattern can be projected by the landmark image projection device 7. The support pillar 73, color cone 74, and color tape 75 also function as signs for the worker. In this way, since signs for the worker are installed in the space in which the automatic guided vehicle 10 runs, the automatic guided vehicle 10 uses them as feature point information to grasp its current position.

The automated guided vehicle 10 according to this embodiment also has a function of detecting guide lines 76, 77 provided on the floor or wall and traveling autonomously. Specifically, the automated guided vehicle 10 first recognizes the floor guide line 76 formed on the travel path on the floor surface and the wall guide line 77 formed on the wall surface in the captured image captured by the image sensor 33. Here, FIG. 6 is a diagram for explaining a method for recognizing whether the guide line detected in the area of the captured image is a line formed on the floor surface or a line formed on the wall surface in this embodiment. As shown in FIG. 6, in this embodiment, the operation management unit 112 of the automated guided vehicle 10 sets the area below the center of the screen of the captured image as the floor guide line recognition area, and sets the area excluding the lower center and upper part of the screen of the captured image as the wall guide line recognition area. Then, when the operation management unit 112 detects a line image having specific color information in the floor guide line recognition area, it recognizes that the line is the floor guide line 76 formed on the floor surface, and performs travel control based on the floor guide line 76. In addition, when the operation management unit 112 detects a line image having specific color information in the wall guide line recognition area, it recognizes that the line is a wall guide line 77 formed on the wall surface, and performs driving control based on the wall guide line 77.
As shown in FIG. 6, when both a floor guide line 76 formed on the running path on the floor surface and a wall guide line 77 formed on the wall surface are detected, running control can be performed in accordance with both lines 76, 77, or a specific vehicle can be made to perform a first running control based on the floor guide line 76 and other vehicles can be made to perform a second running control based on the wall guide line 77.

7 is a diagram for explaining a travel control method using a floor guide line 76 formed on the floor surface. For example, when the automated guided vehicle 10 detects a floor guide line 76 on the travel path on the floor surface, the automated guided vehicle 10 can be provided with a line follow function that performs travel control so that the automated guided vehicle 10 travels along the center line of the detected floor guide line 76 in the longitudinal direction, as shown in FIG. 7(A). Alternatively, the automated guided vehicle 10 can perform travel control so that the automated guided vehicle 10 does not pass the floor guide line 76 or travels a certain distance away from the floor guide line 76, regarding the detected floor guide line 76 as the end of the passage, as shown in FIG. 7(B). Here, the floor line 71 or the boundary line 72 may be used as the floor guide line 76.
8 is a diagram for explaining a travel control method using a wall guide line 77 formed on a wall surface. When the automated guided vehicle 10 detects a wall guide line 77 on a wall surface along the travel path, the automated guided vehicle 10 can perform travel control so that the automated guided vehicle 10 travels along the wall guide line 77 at a position a certain distance away from the detected wall guide line 77, as shown in Fig. 8(A) and Fig. 8(B). Here, a color tape 75 affixed to the wall may be used as the wall guide line 77.

Furthermore, in this embodiment, the unmanned guided vehicle 10 has the function of registering images of colored tape affixed to the ceiling, hanging signs, beams, lighting fixtures, etc. hung from the ceiling as landmark images by associating them with coordinates, and also has the function of detecting guide lines on the ceiling and traveling autonomously.
FIG. 9 is a diagram for explaining a travel control method using a ceiling guide line 78 provided on the ceiling. As shown in FIG. 9, the operation management unit 112 of the automatic guided vehicle 10 sets the area at the upper center of the screen of the captured image as the ceiling recognition area. When the operation management unit 112 detects a line image in the ceiling recognition area, it recognizes that the line is the ceiling guide line 78 formed on the ceiling, and performs travel control based on the ceiling guide line 78 formed on the ceiling. For example, the automatic guided vehicle 10 can be equipped with a line follow function that performs travel control so that the automatic guided vehicle 10 travels along the center line of the detected ceiling guide line 78 in the longitudinal direction along the ceiling guide line 78. Travel based on the ceiling guide line 78 can also be combined with ceiling landmark information (for example, a hanging signboard hung from the ceiling) to perform travel control so that the automatic guided vehicle 10 travels to a position where the hanging signboard is directly above. In particular, in facilities such as hospitals with low ceilings, it is useful to perform travel control based on the ceiling guide line 78 formed on the ceiling.

Note that the floor line recognition area and wall line recognition area shown in FIG. 6 and the ceiling recognition area shown in FIG. 9 are examples, and the ranges can be changed as appropriate. Also, when estimating the current position from each line (71, 72, 76-78) as feature point information, the automated guided vehicle 10 can estimate the current position by recognizing the line recognized in the floor line recognition area of the captured image as the floor line 71, boundary line 72, or floor guide line 76 formed on the floor surface, recognizing the line recognized in the wall line recognition area of the captured image as the wall guide line 77 formed on the wall surface, or recognizing the line recognized in the ceiling recognition area of the captured image as the ceiling guide line 78, as described above.

In the above example, in order to perform highly accurate and stable travel control on a travel path such as a narrow passage or a curve, the support pillar 73, the color cone 74, the color tape 75, and a signboard (not shown) attached to the ceiling are used as feature point information to estimate the current position, but the present invention is not limited to this. For example, the current position near a non-contact charging device can be estimated so that charging can be performed in close proximity to the non-contact charging device. For example, in FIG. 4, the symbol D is a charging area, the symbol E is an entrance/exit, and the symbol F is a cargo handling area. In the charging area of the symbol D, a power transmission device (not shown) for non-contact charging is arranged. However, in the charging area, charging cannot be performed unless the automatic guided vehicle 10 is guided with centimeter-order accuracy. For this reason, a floor guide line 76 for guiding the automatic guided vehicle 10 to the power transmission device is provided. The floor guide line 76 may be made of color tape, may be painted, or may be projected by the landmark image projection device 7. Here, the color tape may be any tape that is visible, and may include a translucent tape or a tape with a pattern. The floor guide line 76 may be a dotted line.
The operation management unit 112 has a line following function that guides the automated guided vehicle 10 along the line when the image sensor 33 detects a line image. As an implementation form of the line following function, for example, it is disclosed that the driving is controlled by extracting preset color information and recognizing the shape of the line. This line following function makes it possible to guide the automated guided vehicle 10 with centimeter-order accuracy so that the power receiving device is positioned above the power transmitting device.
The cargo handling area F is also a place where transport vehicles such as trucks arrive and depart, and so disturbance light is incident thereon.

The automated guided vehicle 10 travels while correcting its route at regular intervals. Fig. 10 is a flowchart of route correction while the automated guided vehicle 10 is traveling.
STEP 601: The robot control unit 11 acquires image information of the traveling direction and its surroundings by an image sensor, and performs feature point recognition in the image information. The feature point recognition will be described in detail later.
STEP 602: If the robot control unit 11 is able to acquire the current position, it proceeds to STEP 603, and if it is unable to acquire the current position, it proceeds to STEP 606.

STEP 603: The robot control unit 11 updates the partial map corresponding to the acquired current position based on the image information.
STEP 604: The robot control unit 11 judges whether or not the set route needs to be corrected. If it is necessary, the process proceeds to STEP 605, and if it is not necessary, the process returns to STEP 601.
STEP 605: The robot control unit 11 corrects the set route and stores it in the storage device.

STEP 606: The robot control unit 11 acquires the odometry information from the storage device, and calculates the current position based on the current position information and the odometry information most recently stored in the storage device.
STEP 607: If the robot control unit 11 is able to acquire the current position, it proceeds to STEP 608, and if it is unable to acquire the current position, it proceeds to STEP 609.
STEP 608: The robot control unit 11 updates the partial map corresponding to the acquired current position based on the image information.
STEP 609: The automatic guided vehicle 10 is stopped, and a screen informing the user of the abnormality is displayed on the display unit 12, or an alarm is sounded from the speaker 14 to inform the user of the stop.
STEP 610: The robot control unit 11 judges whether or not the set route needs to be corrected. If it is necessary, the process proceeds to STEP 605; if it is not necessary, the process returns to STEP 601.

A supplementary explanation will be given regarding the feature point recognition in STEP 601. In warehouses where surrounding objects are constantly changing, feature points are extracted including objects that are constantly being moved, such as carts and product boxes, making it easy for erroneous detections to occur. Therefore, in the example embodiment, when the current position cannot be obtained by extracting feature points based on image information, the current position is obtained by also using complementary information such as landmark information and artificial code information. Figure 11 is a flowchart of current position acquisition using complementary information.

STEP 701: The robot control unit 11 recognizes feature points in the image information of the traveling direction and its surroundings acquired by the image sensor, compares it with the basic map and the partial map, and attempts to acquire the current position.
STEP 702: If the current position can be acquired, proceed to STEP 706; if the current position cannot be acquired, proceed to STEP 703.
STEP 703: Based on the result of feature point recognition for the acquired image information, complementary information previously registered in association with coordinates is detected. For example, the coordinate information of a specific AR marker extracted from the image information is read, and the current position is calculated based on the position and size of the AR marker in the image.
STEP 704: If the current position can be acquired, proceed to STEP 706; if the current position cannot be acquired, proceed to STEP 705.
STEP 705: The automatic guided vehicle 10 is stopped, and a screen informing the user of the abnormality is displayed on the display unit 12, or an alarm is sounded from the speaker 14 to inform the user of the stop.
STEP 706: The robot control unit 11 stores the acquired current position in the storage device.

The automated guided vehicle 10 of the embodiment described above is capable of autonomous travel based on projected images, peripheral image information, and inexpensive obstacle sensors, without the need for guide cables or guide tapes. Therefore, even in existing warehouses, an automated guided vehicle system can be constructed with minimal capital investment.

In addition, by changing the projection position of the projected image of the landmark image projection device 7, it is possible to easily accommodate changes in the layout of the warehouse. In addition, by using a projected virtual landmark image in combination, it is possible to improve the accuracy of obtaining the current position even in an environment where disturbance light is present.

Although the preferred embodiment of the present invention has been described above, the technical scope of the present invention is not limited to the description of the above embodiment. Various modifications and improvements can be made to the above embodiment, and such modifications or improvements are also included in the technical scope of the present invention.
In the embodiment example, a configuration has been described in which the unmanned guided vehicle 10 receives inventory information and order information from the WMS server 2, but it is also possible to construct an unmanned guided vehicle system that does not link with the WMS server 2, and for example, inventory entry and exit instructions may be sent to the unmanned guided vehicle 10 from a handheld terminal 4 or a management terminal installed at the work site.
10, the robot control unit 11 can set any priority regarding which information is to be used for priority in obtaining the current position. For example, the priority of the distance sensor or the line following function may be given to obtaining the current position based on information from the image sensor 33.

Furthermore, in the above-described embodiment, a warehouse has been specifically described as an example of an indoor facility where GPS cannot be used, but the present invention is not limited to use in warehouses, and can also be used in indoor facilities other than warehouses where goods are transported (for example, factories and hospitals where GPS cannot be used).
The present invention is also an invention that prevents an automated guided vehicle from stopping when a camera cannot properly recognize surrounding objects, and has been described by taking an example of an environment where disturbance light is incident as such a situation. However, the situation where surrounding objects cannot be properly recognized is not limited to an environment where disturbance light is incident, and there are also environments where the arrangement of surrounding objects changes over time, such as when the amount and arrangement of transport fixtures such as carts and luggage such as goods changes depending on the season or time of day, or when people and forklifts are mixed in the same environment, and the present invention is also useful in such environments.

Furthermore, the work using the automated guided vehicle according to the present invention is not limited to loading and unloading work, but can be applied to various work that requires transporting luggage by the automated guided vehicle 10.

In addition, in the above-described embodiment, a configuration having an image sensor 33 is exemplified, but the number of image sensors 33 is not particularly limited, and a configuration having a single image sensor 33 or a configuration having multiple image sensors 33 may be used. In the case of a configuration having multiple image sensors 33, feature point information such as the support poles 73, color cones 74, color tape 75, and a signboard attached to the ceiling (not shown) is recognized based on images captured in multiple directions by the multiple image sensors 33, and the current position is recognized and driving control is performed, thereby improving the accuracy of current position recognition and driving control.

REFERENCE SIGNS LIST 1 RM server 2 WMS server 3 Management terminal 4 Handheld terminal 5 Wireless LAN master unit 6 Basket cart 7 Landmark image projection device 10 Automatic guided vehicle 11 Robot control unit 12 Display unit 16 Base 21 Drive control device 22 Drive device 23 Wheels 31 Front sensor 32 Side sensor 33 Image sensor 71 Floor line 72 Passage line 73 Support 74 Color cone 75 Color tape 76 Floor guide line 77 Wall guide line 78 Ceiling guide line 79 Two-dimensional code 81 Virtual guide line 82 Virtual control sign

Claims (6)

An automated guided vehicle that autonomously drives along a route based on an environmental map;
A landmark image projection device that projects a landmark image of a specific shape or pattern along the travel path;
a server that transmits a projection command to the landmark image projection device to project the landmark image,
The automated guided vehicle is
A color image sensor that captures an image of an object in the traveling direction;
A drive unit that independently controls the drive of a plurality of wheels;
A robot control unit that transmits a control command for the autonomous driving to a driving unit;
A wireless communication unit,
The robot control unit constantly updates an environmental map and a route based on image information from a color image sensor;
A function of registering the projected landmark image by linking it with coordinate information on an environmental map;
a first current position estimation function that performs feature point recognition in image information from a color image sensor and estimates a current position by comparing the image information with an environmental map;
a second current position estimation function that estimates a current position based on coordinate information of the landmark image when the image information from the color image sensor includes a landmark image;
Equipped with
the landmark image projection device has a function of projecting a floor line onto the boundary between the travel path and the work section, projecting a boundary line image of a different color from the floor line onto a portion of the boundary between the travel path and the work section that serves as an aisle, projecting a floor guide line having specific color information onto the travel path, and projecting a wall or ceiling guide line having specific color information onto a wall surface or a ceiling ,
The automated guided vehicles include a first automated guided vehicle and a second automated guided vehicle,
an automated guided vehicle system, characterized in that a robot control unit of the first automated guided vehicle performs a first driving control based on the floor guide line, and a robot control unit of the second automated guided vehicle performs a second driving control based on the wall or ceiling guide line . the driving unit has a function of transmitting rotation information of the plurality of wheels to a robot control unit as odometry information;
2. The automated guided vehicle system according to claim 1, wherein the robot control unit has a third current position estimation function for estimating a current position based on the odometry information and the immediately preceding stored current position information. a function of the robot control unit dynamically generating a composite image by adding a virtual landmark image to image information from a color image sensor in an environment where disturbance light is incident ;
3. The automated guided vehicle system according to claim 1, further comprising a function of performing travel control based on virtual landmark images included in the composite image. 4. The automated guided vehicle system according to claim 1 , wherein the landmark image includes an image of an artificial code including a two-dimensional code. 5. The automated guided vehicle system according to claim 1, wherein the landmark image includes an image of a character string, a logo, or a character. 6. The automated guided vehicle system according to claim 1, wherein the server transmits a projection command to project an image for performing the first driving control during a first time period, and transmits a projection command to project an image for performing the second driving control during a second time period.