KR102063891B1 - Following robot control method and system and computing device for executing the system - Google Patents

Abstract

Disclosed are a method and system for controlling a following robot and a computing device for executing the same. According to one embodiment of the present invention, the system for improving the efficiency of work comprises: a user terminal including a GPS module for obtaining GPS information; and a following robot receiving the GPS information from the user terminal and following a user by extracting position information of the user based on the GPS information. The following robot includes a control unit for calculating position information of the following robot and comparing the position information of the user and the position information of the following robot to control the following robot to maintain a predetermined distance from the user.

Description

Tracking robot control method and system, and a computing device for performing the same {FOLLOWING ROBOT CONTROL METHOD AND SYSTEM AND COMPUTING DEVICE FOR EXECUTING THE SYSTEM}

Embodiments of the present invention relate to following robotic technology.

Conventional user tracking robots measure distances from users using distance sensors such as ultrasonic distance sensors and travel when they are farther than a certain distance and stop when they are close.

However, if another person or object appears between the user following the robot and the conventional user, there is a problem that the user cannot be followed.

Republic of Korea Patent Publication No. 10-0877983 (2009.01.05.)

Embodiments of the present invention are to follow the robot while maintaining a certain distance from the user to improve the efficiency of the work.

In addition, embodiments of the present invention are to follow the user based on the GPS information of the user terminal to improve the tracking accuracy.

According to an exemplary embodiment of the present invention, a user terminal including a GPS module for obtaining GPS information; And a following robot that receives GPS information from the user terminal, extracts the location information of the user based on the GPS information, and follows the user, wherein the following robot calculates the location information of the following robot, A tracking robot system is provided that includes a controller configured to control the tracking robot so that the tracking robot maintains a predetermined distance from the user by comparing the location information of the user with the location information of the tracking robot.

The controller may set the location information of the user as a first target point, and control the following robot to reach the first target point by comparing the first target point with the position information of the following robot.

The controller extracts the next location information of the user from the first target point and sets the second target point, and calculates a direction vector of the following robot based on the first target point and the second target point. The following robot may be controlled to reach a second target point.

The following robot may include a photographing unit provided in the following robot to photograph the surroundings of the following robot; And a follower including a first preprocessing module that extracts a surrounding image from the image photographed by the photographing unit, and a first deep learning module that receives the surrounding image and detects an obstacle in the surrounding image.

When the surrounding image is input, the first deep learning module may use a convolutional neural network (CNN) trained to detect and output an obstacle in the input surrounding image.

The controller may control the following robot to follow the user by avoiding the obstacle when an obstacle is detected from the follower.

The following robot may include a photographing unit provided in the following robot to photograph the surroundings of the following robot; And a second preprocessing module for extracting a crop image from the image photographed by the photographing unit, a second deep learning module that receives the crop image and detects a suspected pest part in the crop image, and receives the crop image. The crop management unit may further include a crop management unit including a third deep learning module configured to detect a growth level of the crop in the image, wherein the crop management unit may provide at least one of the suspected pest or growth level of the harvest to the user terminal. have.

When the crop image is input, the second deep learning module may use a convolutional neural network (CNN) trained to detect and output a suspected pest portion in the input crop image.

When the crop image is input, the third deep learning module may use a convolutional neural network (CNN) trained to detect and output a growth level of a harvest from the input crop image.

The following robot may include a photographing unit provided in the following robot to photograph the surroundings of the following robot; A follower including a first preprocessing module for extracting a surrounding image from the image photographed by the photographing unit, and a first deep learning module that receives the surrounding image and detects an obstacle in the surrounding image; And a second preprocessing module that extracts a crop image from the image photographed by the photographing unit, a second deep learning module that receives the crop image and detects a suspected pest in the crop image, and receives the crop image. The crop management unit may further include a crop management unit including a third deep learning module configured to detect a growth level of the crop in the image, wherein the crop management unit may provide at least one of the suspected pest or growth level of the harvest to the user terminal. have.

According to another exemplary embodiment of the present invention, a computing device having one or more processors and a memory storing one or more programs executed by the one or more processors, the computing device comprising: a communication unit configured to receive GPS information from a user terminal; And extracting the location information of the user based on the GPS information and calculating the location information of the following robot, and comparing the location information of the user with the location information of the following robot to maintain the preset distance from the user. A computing device including a control unit for controlling the following robot is provided.

The controller may set the location information of the user as a first target point, and control the following robot to reach the first target point by comparing the first target point with the position information of the following robot.

The controller extracts the next location information of the user from the first target point and sets the second target point, and calculates a direction vector of the following robot based on the first target point and the second target point. The following robot may be controlled to reach a second target point.

The computing device may include a photographing unit provided in the following robot to photograph the surroundings of the following robot; And a follower including a first preprocessing module that extracts a surrounding image from the image photographed by the photographing unit, and a first deep learning module that receives the surrounding image and detects an obstacle in the surrounding image.

The computing device may include a photographing unit provided in the following robot to photograph the surroundings of the following robot; And a second preprocessing module for extracting a crop image from the image photographed by the photographing unit, a second deep learning module that receives the crop image and detects a suspected pest part in the crop image, and receives the crop image. The crop management unit may further include a crop management unit including a third deep learning module configured to detect a growth level of the crop in the image, wherein the crop management unit may provide at least one of the suspected pest or growth level of the harvest to the user terminal. have.

According to yet another exemplary embodiment of the present invention, a method performed in a computing device having one or more processors and a memory storing one or more programs executed by the one or more processors, the following method comprising: Receiving GPS information from the terminal; Extracting, by the tracking robot, location information of the user based on the GPS information and calculating location information of the tracking robot; Setting, by the tracking robot, location information of the user as a first target point and traveling to reach the first target point by comparing the first target point and the position information of the following robot; And extracting, by the following robot, the next position information of the user from the first target point, and setting the second target point, and setting the direction vector of the following robot based on the first target point and the second target point. A tracking robot control method is provided, which includes calculating and traveling to reach the second target point.

According to the embodiments of the present invention, the following robot may follow the user while maintaining a certain distance, thereby improving the efficiency of the work.

In addition, according to embodiments of the present invention, by following a user by applying a trajectory tracking technique based on GPS information of the user terminal, the tracking accuracy may be improved without being affected by the surrounding environment and obstacles.

1 is a configuration diagram for explaining a tracking robot system according to an embodiment of the present invention;
2 is a block diagram illustrating a tracking robot of a tracking robot system according to an exemplary embodiment of the present invention.
3 is a block diagram illustrating a follower and a crop management unit in a follower robot of a follower robot system according to an exemplary embodiment of the present invention;
4 is a flowchart illustrating a tracking robot control method of a tracking robot system according to an exemplary embodiment of the present invention.
5 is a block diagram illustrating and describing a computing environment including a computing device suitable for use in example embodiments.

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to assist in a comprehensive understanding of the methods, devices, and / or systems described herein. However, this is only an example and the present invention is not limited thereto.

In describing the embodiments of the present invention, when it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted. In addition, terms to be described below are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a user or an operator. Therefore, the definition should be made based on the contents throughout the specification. The terminology used in the description is for the purpose of describing embodiments of the invention only and should not be limiting. Unless expressly used otherwise, the singular forms “a,” “an,” and “the” include plural forms of meaning. In this description, expressions such as "comprises" or "equipment" are intended to indicate certain features, numbers, steps, actions, elements, portions or combinations thereof, and one or more than those described. It should not be construed to exclude the presence or possibility of other features, numbers, steps, actions, elements, portions or combinations thereof.

Meanwhile, an embodiment of the present invention may include a program for performing the methods described herein on a computer, and a computer readable recording medium including the program. The computer-readable recording medium may include program instructions, local data files, local data structures, etc. alone or in combination. The media may be those specially designed and constructed for the purposes of the present invention, or those conventionally available in the field of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical recording media such as CD-ROMs, DVDs, and specially configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Hardware devices are included. Examples of such programs may include high-level language code that can be executed by a computer using an interpreter as well as machine code such as produced by a compiler.

1 is a block diagram for explaining a tracking robot system according to an embodiment of the present invention, Figure 2 is a block diagram for explaining a tracking robot of the following robot system according to an embodiment of the present invention, Figure 3 In the following robot of the following robot system according to an embodiment of the present invention is a block diagram for explaining the follower and crop management unit.

As shown in FIGS. 1 to 3, the following robot system 1 according to an embodiment of the present invention may include a user terminal 100 and a following robot 200.

The user terminal 100 may be connected to the tracking robot 200 using a network. The user terminal 100 may include any smart device capable of using wireless communication such as a smart phone, a tablet PC, a smart watch, and the like. Here, the network is implemented as all kinds of wired / wireless networks such as a local area network (LAN), a wide area network (WAN), a mobile radio communication network, and a wireless broadband Internet (Wibro). Can be. In particular, a short-range communication technology such as Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), and ZigBee may be used. The user terminal 100 may include a GPS module for acquiring GPS information of the user terminal 100.

The user terminal 100 and the following robot 200 may perform data communication using a network, and the GPS (Global Position System) information of the user terminal 100 may be transmitted to the following robot 200.

Here, the current position of the user terminal 100 can be checked using the GPS information. The GPS information may calculate the current position in real time, and the speed information may be calculated using the GPS position. In addition, the GPS information may be updated in real time at predefined time intervals. In addition, in order to reduce power consumption of the user terminal 100, the transmission of the GPS information may be limited to being performed only when the GPS operation is ON.

In addition, the user terminal 100 may be installed with an application for providing a tracking robot service. The application may be stored in a computer readable storage medium of the user terminal 100. The application includes a predetermined set of instructions executable by the processor of the user terminal 100. The command may cause the processor of the user terminal 100 to perform an operation according to an exemplary embodiment. The computer readable storage medium of the user terminal 100 includes components of an operating system for executing the same set of instructions as the application on the user terminal 100. For example, such an operating system may be Apple's iOS or Google's Android.

Here, the application for providing the tracking robot service may provide crop information received from the tracking robot 200 on the screen. Here, the crop information may include a pest infection, the degree of growth of the harvest.

The tracking robot 200 may include a communication unit 202, a photographing unit 204, a follower 206, a crop manager 208, a controller 210, a driver 212, and a storage unit 214.

Here, the following robot 200 may be a transfer robot to follow the user in the crop facility. In addition, a space in which a predetermined tool, an object, a crop, or the like can be loaded while following the user may be formed. The following robot 200 may be applied to any known robot as long as it is an agricultural robot capable of transporting, harvesting, or the like.

The communication unit 202 may communicate with the user terminal 100 through a network. The communication unit 202 may receive GPS information from the user terminal 100. In addition, the communicator 202 may transmit crop information generated by the crop manager 208 to the user terminal 100. Crop information may include the presence of pests and the extent of crop growth.

The photographing unit 204 may use various cameras and the like to photograph the surroundings of the following robot 200. The photographing unit 204 may be installed on the following robot 200 so as to photograph the omnidirectional image.

The follower 206 extracts a surrounding image (eg, an obstacle image of a branch or leaf, a farm machine, a stone, a grass, a furrow, etc. of a crop) from an image captured by the photographing unit 204, and dips the extracted surrounding image. Obstacles can be identified using deep learning-based technology.

The follower 206 may include a first preprocessing module 221 and a first deep learning module 223.

The first preprocessing module 221 may extract a surrounding image (for example, an obstacle image of a branch or a leaf, a farm machine, a stone, a grass, a furrow, etc. of a crop) from an image captured by the photographing unit 204. The first preprocessing module 221 may transfer the extracted surrounding image to the first deep learning module 223.

The first deep learning module 223 may receive the extracted surrounding image and detect an obstacle in the surrounding image. When the surrounding image is input, the first deep learning module 223 may detect an obstacle in the input surrounding image by performing deep learning based on already learned images (that is, the obstacle image).

In an exemplary embodiment, the first deep learning module 223 may use a convolutional neural network (CNN) as a deep learning technique. In this case, when the surrounding image is input, the first deep learning module 223 may be a neural network learned to detect and output an obstacle from the input surrounding image. Since the multiplicative neural network is a known technique, a detailed description thereof will be omitted.

The crop manager 208 extracts a crop image (eg, a leaf image) from the image captured by the photographing unit 204, detects a pest using a deep learning based technology from the extracted crop image, and Diagnosis can be made.

In addition, the crop manager 208 extracts a crop image (eg, a crop image) from an image captured by the photographing unit 204 and grows a crop using a deep learning based technique from the extracted crop image. The degree can be detected and judged.

The crop manager 208 may include a second pretreatment module 231, a second deep learning module 233, and a third deep learning module 235.

The second preprocessing module 231 may extract a crop image (eg, a harvest image) from the image photographed by the photographing unit 204. The second preprocessing module 231 may transfer the extracted crop image to the second deep learning module 233 and the third deep learning module 235.

The second deep learning module 233 may receive the extracted crop image and detect a suspected pest part in the crop image. When the crop image is input, the second deep learning module 233 may detect a pest suspect part in the input crop image by performing deep learning based on already learned data (ie, pest information). have.

In an exemplary embodiment, the second deep learning module 233 may use a convolutional neural network (CNN) as a deep learning technique. In this case, when the crop image is input, the second deep learning module 233 may be a neural network trained to detect and output a suspected pest part in the input crop image.

The third deep learning module 235 may receive the extracted crop image and detect a growth level of the harvest from the crop image. When the crop image is input, the third deep learning module 235 performs deep learning based on already learned data (that is, harvest information) to detect a growth level of the crop in the input crop image. Can be.

In an exemplary embodiment, the third deep learning module 235 may use a convolutional neural network (CNN) as a deep learning technique. In this case, when the crop image is input, the third deep learning module 235 may be a neural network learned to detect and output a growth level of the harvest from the input crop image.

The controller 210 may control the driver 212 to follow the user by extracting the location information of the user based on the GPS information of the user terminal 100 received through the communication unit 202. The controller 210 may calculate the position information of the robot by fusing the GPS, the odometer, and the digital compass information of the following robot 200 with a Kalman filter, and compare the position information of the user with the position information of the robot. The robot 200 may control the driver 212 to follow the user by maintaining a predetermined distance from the user.

In this case, the controller 210 may use a trajectory following technique for following the user's movement trajectory based on the GPS information of the user terminal 100 to follow the user. Here, the trajectory following technique is a technique of sequentially setting and following each position of the user's moving trajectory as a target point.

That is, the controller 210 may determine whether the first target points X1 and Y1 have been reached based on the GPS information of the user terminal 100 from the position information of the follower robot 200. In this case, the controller 210 may determine whether the first target point is reached by using Equation 1 below.

Here, d is a distance between the position information of the following robot 200 and the first target point, and R is the angle of the square root of the covariance matrix with respect to the distance error between the current position information of the following robot 200 and the first target point. It is a diagonal component, and the square root of the covariance matrix can be calculated using the Cholesky decomposition method.

If the first position information of the following robot 200 does not reach the first target point, the controller 210 determines whether the first target point has been reached or not until the following robot reaches the first target point. 1 Can be controlled to maintain the target point. When the following robot 200 reaches the first target point, the controller 210 determines whether to reach the first target point, and extracts the next point from the movement trajectory of the user to determine the second target point (X2, Y2). Can be set. In this case, when the second target point is set, the controller 210 may calculate the direction vector D1 of the following robot 200 by using Equation 2 below to change the direction of the following robot 200. .

Meanwhile, the GPS information may be set to the same ground. That is, the Z coordinates of the GPS information may be set to be the same.

As such, the controller 210 may control the driving unit 212 to follow the user's trajectory by repeatedly performing the above process.

In addition, the controller 210 may control the driver 212 to drive the following robot 200 based on driving information stored from a trajectory following technique for following a user. When an obstacle is detected from the captured image, the controller 210 may control the driving unit 212 by changing the direction of the follower robot 200 to avoid the obstacle. That is, the controller 210 may drive based on the driving information, and control the driver 212 to avoid the obstacle based on the presence or absence of the obstacle based on the captured image. Accordingly, the tracking robot 200 system according to an embodiment of the present invention may not only follow the user but also travel based on the driving information and the captured image.

The driving unit 212 may allow the following robot 200 to follow the user and may drive the following. The driving unit 212 may be formed of various elements such as wheels, motors, shafts, and gears such that both linear and rotary motions are implemented. The driving unit 212 may operate according to a driving signal input from the control unit 210 to allow the following robot 200 to move along the back of the user. In addition, the driving unit 212 may be operated according to the driving signal input from the control unit 210 to allow the following robot 200 to travel according to the driving information stored in the storage unit 214.

The storage unit 214 may store the user terminal 100 information. The registered user terminal 100 may be authenticated using the stored user terminal 100 information. The storage unit 214 may store an image photographed by the photographing unit 204. The storage unit 214 may store driving information from a trajectory following technique for following a user.

4 is a flowchart illustrating a method for controlling a tracking robot 200 in a tracking robot 200 system according to an exemplary embodiment of the present invention. The method shown in FIG. 3 may be performed by the following robot 200 system described above, for example. In the illustrated flow chart, the method is divided into a plurality of steps, but at least some of the steps may be performed in a reverse order, in combination with other steps, omitted, divided into substeps, or not shown. One or more steps may be added and performed.

The tracking robot 200 extracts initial position information of the user based on the GPS information of the user terminal 100 and sets it as a first target point (S301).

Next, the following robot 200 calculates first position information of the following robot 200 (S302). In detail, the position information of the robot may be calculated by fusing GPS, traveling system, and digital compass information of the tracking robot 200 with a Kalman filter. Thereafter, the following robot 200 compares the first target point with the first position information (S303), and determines whether the following robot 200 has reached the first target point (S304).

Then, when the following robot 200 does not reach the first target point, the following robot 200 travels to the first target point until reaching the first target point (S305). When the following robot 200 reaches the first target point, the following robot 200 extracts the next position information of the user from the user's moving trajectory and sets it as the second target point (S306).

Next, the following robot 200 calculates a direction vector of the following robot 200 to move to the second target point (S307). Thereafter, the tracking robot 200 changes the direction of the tracking robot 200 according to the calculated direction vector and follows the movement trajectory of the user (S308).

Finally, the following robot 200 follows the user's movement trajectory, and determines whether the robot reaches the final target point (S309). The tracking robot 200 repeats the process of S306 to S308 to reach the final target point.

Accordingly, the tracking robot 200 system according to the present invention applies a trajectory tracking technique based on the GPS information of the user terminal 100 to follow the user, thereby improving the tracking accuracy without being affected by the surrounding environment and obstacles. have.

5 is a block diagram illustrating and describing a computing environment including a computing device suitable for use in example embodiments. In the illustrated embodiment, each component may have different functions and capabilities in addition to those described below, and may include additional components in addition to those described below.

The illustrated computing environment 10 includes a computing device 12. In one embodiment, computing device 12 may be user terminal 100. In addition, the computing device 12 may be a follower robot 200.

 Computing device 12 includes at least one processor 14, computer readable storage medium 16, and communication bus 18. The processor 14 may cause the computing device 12 to operate according to the example embodiments mentioned above. For example, processor 14 may execute one or more programs stored in computer readable storage medium 16. The one or more programs may include one or more computer executable instructions that, when executed by the processor 14, cause the computing device 12 to perform operations in accordance with an exemplary embodiment. Can be.

Computer readable storage medium 16 is configured to store computer executable instructions or program code, program data and / or other suitable forms of information. The program 20 stored in the computer readable storage medium 16 includes a set of instructions executable by the processor 14. In one embodiment, computer readable storage medium 16 includes memory (volatile memory, such as random access memory, nonvolatile memory, or a suitable combination thereof), one or more magnetic disk storage devices, optical disk storage devices, flash Memory devices, or any other form of storage medium that is accessible by computing device 12 and capable of storing desired information, or a suitable combination thereof.

The communication bus 18 interconnects various other components of the computing device 12, including the processor 14 and the computer readable storage medium 16.

Computing device 12 may also include one or more input / output interfaces 22 and one or more network communication interfaces 26 that provide an interface for one or more input / output devices 24. The input / output interface 22 and the network communication interface 26 are connected to the communication bus 18. The input / output device 24 may be connected to other components of the computing device 12 via the input / output interface 22. Exemplary input / output devices 24 may include pointing devices (such as a mouse or trackpad), keyboards, touch input devices (such as touchpads or touchscreens), voice or sound input devices, various types of sensor devices, and / or imaging devices. Input devices, and / or output devices such as display devices, printers, speakers, and / or network cards. The example input / output device 24 may be included inside the computing device 12 as one component of the computing device 12, and may be connected to the computing device 12 as a separate device from the computing device 12. It may be.

While the exemplary embodiments of the present invention have been described in detail above, those skilled in the art will appreciate that various modifications can be made to the above-described embodiments without departing from the scope of the present invention. . Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined by the claims below and equivalents thereof.

100: user terminal
200: following robot
202: communication unit
204: the photographing unit
206: follower
208: control unit
210: driving part
212: storage unit
221: first pretreatment module
223: first deep learning module
231: second pretreatment module
233: second deep learning module
235: third deep learning module

Claims (16)

A user terminal including a GPS module for obtaining GPS information; And
Receiving a GPS information from the user terminal, extracting location information of the user based on the GPS information, and including a following robot for following the user,
The following robot,
Calculating a position information of the following robot, comparing the position information of the user with the position information of the following robot, and controlling the following robot to control the following robot to maintain a preset distance from the user,
The control unit,
Setting the location information of the user as a first target point, controlling the following robot to reach the first target point by comparing the first target point with the position information of the following robot,
The next location information of the user is extracted from the first target point and is set as a second target point, and the direction vector of the following robot is calculated based on the first target point and the second target point and the second target point is obtained. Control the following robot to reach the point,
The following robot,
A photographing unit provided in the following robot to photograph the surroundings of the following robot;
A follower including a first preprocessing module for extracting a surrounding image from the image photographed by the photographing unit, and a first deep learning module that receives the surrounding image and detects an obstacle in the surrounding image; And
A second preprocessing module which extracts a crop image from the image photographed by the photographing unit, a second deep learning module that receives the crop image and detects a suspected pest from the crop image, and receives the crop image and the crop image Further comprising a crop management unit comprising a third deep learning module for detecting the growth of the harvest in,
The crop management unit provides the user terminal with at least one of the suspected pests or the degree of growth of the harvest,
The control unit,
The following robot is controlled based on driving information stored from a trajectory following technique for following the user, and when the obstacle is detected from the following unit, the following robot is controlled to avoid the obstacle and follow the user. Robotic system.
delete delete delete The method according to claim 1,
The first deep learning module,
And a convolutional neural network (CNN) trained to detect and output obstacles in the input peripheral image when the surrounding image is input.
delete delete The method according to claim 1,
The second deep learning module,
When the crop image is input, a tracking robot system using a convolutional neural network (CNN) trained to detect and output a suspected pest part in the input crop image.
The method according to claim 1,
The third deep learning module,
When the crop image is input, a tracking robot system using a convolutional neural network (CNN) trained to detect and output the growth of the harvest from the input crop image.
delete One or more processors, and
A computing device having a memory for storing one or more programs executed by the one or more processors, the computing device comprising:
Communication unit for receiving GPS information from the user terminal; And
Extract the location information of the user based on the GPS information, calculate the location information of the following robot, and compare the location information of the user with the location information of the following robot to maintain the preset distance from the user. It includes a control unit for controlling the following robot,
The control unit,
Setting the location information of the user as a first target point, controlling the following robot to reach the first target point by comparing the first target point with the position information of the following robot,
The next location information of the user is extracted from the first target point and is set as a second target point, and the direction vector of the following robot is calculated based on the first target point and the second target point and the second target point is obtained. Control the following robot to reach the point,
The computing device,
A photographing unit provided in the following robot to photograph the surroundings of the following robot;
A follower including a first preprocessing module for extracting a surrounding image from the image photographed by the photographing unit, and a first deep learning module that receives the surrounding image and detects an obstacle in the surrounding image; And
A second preprocessing module which extracts a crop image from the image photographed by the photographing unit, a second deep learning module that receives the crop image and detects a suspected pest from the crop image, and receives the crop image and the crop image Further comprising a crop management unit including a third deep learning module for detecting the growth level of the harvest in,
The crop management unit provides the user terminal with at least one of the suspected pests or the degree of growth of the harvest,
The control unit,
Computing the following robot based on the driving information stored from the trajectory tracking method for following the user, if the obstacle is detected from the following unit, the following robot is controlled to avoid the obstacle to follow the user, computing Device.
delete delete delete delete delete

Images