Method for dock security inspection robot to perform dock security inspection

By integrating mobile platforms, detection modules and image acquisition devices in the dock security patrol robot system, combining inertial navigation and extended Kalman filtering algorithm, the problem of robots accurately positioning and autonomous obstacle avoidance in the dock environment is solved, and the efficiency of the dock is achieved Security inspection and automatic charging improve safety and efficiency.

CN110103224BActive Publication Date: 2024-11-12EAST CHINA UNIV OF SCI & TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201910464773.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-05-30
Publication Date
2024-11-12
Estimated Expiration
2039-05-30

AI Technical Summary

Technical Problem

It is difficult to effectively realize unmanned security patrols of docks in the prior art, especially in the problem of robots accurately positioning and autonomous obstacle avoidance in complex outdoor environments.

Method used

A dock security inspection robot system was designed, including a mobile platform, detection module, image acquisition device, monitoring gimbal, remote control terminal and industrial control machine, using four-wheel drive differential steering, 360-degree rotating camera, inertial navigation unit, GPS module, lidar and ultrasonic detectors, combined with the extended Kalman filtering algorithm, realize autonomous robot navigation, obstacle avoidance and face recognition.

Benefits of technology

It realizes accurate positioning of robots, autonomous obstacle avoidance, face recognition and automatic charging in the dock environment, and can monitor and trigger alarms in real time, improving the safety and efficiency of the dock.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN110103224B_ABST
    Figure CN110103224B_ABST
Patent Text Reader

Abstract

The present invention discloses a dock security patrol robot and control system, which relates to the field of robot technology, including a mobile platform, a detection module, an image acquisition device, a monitoring platform, a remote control terminal and an industrial computer, wherein the monitoring platform, the detection module and the industrial computer are all installed on the mobile platform, the image acquisition device is installed on the monitoring platform, and the remote control terminal is connected to the industrial computer. The robot of the present invention can be used for dock security patrol, the robot can identify the uniforms of dock staff, can perform face recognition, can avoid obstacles when encountering obstacles during the movement, and when the patrol robot detects that it is low on power, it will automatically navigate to the charging pile to charge; when the robot detects that an illegal person has invaded, it will send a signal to the remote control terminal to trigger an alarm; using sensor data fusion positioning, the remote control terminal can observe the robot's position in real time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of robot technology, and in particular to a dock security inspection robot and a control system. Background Art

[0002] In recent years, China's port container terminal industry has made great progress. The production scale of port container terminals has remained the world's first for many years, playing an irreplaceable role in the development of my country's foreign economic and trade. Today, in the global port and shipping industry, cost is the lifeline of enterprises. All technological revolutions centered on cost saving and efficiency improvement can always find corresponding market demand. Therefore, the automation and intelligence of terminals have become one of the most important development trends.

[0003] The docks are stockpiled with important goods all year round. To prevent illegal personnel from stealing goods and stowaways from going ashore, security inspections have become an indispensable measure. In response to the development trend of smart docks, unmanned security inspections at docks have become an urgent problem to be solved. Using inspection robots to conduct security inspections at unmanned docks has become an important measure to ensure the safety of economic property and goods at docks.

[0004] The dock is an outdoor environment with complex container stacking environment. Accurate positioning of the robot is an important prerequisite to ensure that the robot patrols along the designated route. Summary of the invention

[0005] The object of the present invention is to provide a dock security inspection robot and a control system, so as to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] A dock security inspection robot comprises a mobile platform, a detection module, an image acquisition device, a monitoring platform, a remote control terminal and an industrial computer. The monitoring platform, the detection module and the industrial computer are all installed on the mobile platform, the image acquisition device is installed on the monitoring platform, and the remote control terminal is connected to the industrial computer.

[0008] Preferably, the mobile platform adopts four-wheel drive differential steering, and the mobile platform includes four wheels and a single-chip microcomputer control board. The four wheels are all equipped with a DC reduction motor and an odometer, and the single-chip microcomputer control board is installed in the center of the mobile platform.

[0009] Preferably, the image acquisition device comprises a camera that can rotate 360 ​​degrees and flip up and down, and the camera monitoring platform that can rotate 360 ​​degrees and flip up and down is installed on the monitoring platform through a camera installation mechanism.

[0010] Preferably, the robot further comprises an inertial navigation unit and a GPS module, and both the inertial navigation unit and the GPS module are connected to the industrial computer via a serial port.

[0011] Preferably, the detection module includes at least one of a laser radar and an ultrasonic detector, wherein the laser radar adopts SICK LMS111 and performs non-contact measurement. The ultrasonic detector can detect the distance information of obstacles around the robot and realize the robot's autonomous obstacle avoidance.

[0012] Preferably, the robot also includes an automatic charging system, which includes a charging module and a charging pile. The charging module is connected to a lithium battery installed on the mobile platform through an interface, and the charging pile is connected to any power interface.

[0013] Another object of the present invention is to provide a dock security inspection robot control system, including an autonomous navigation system, an image acquisition system, an industrial computer, a remote terminal operating system, and an automatic charging system; the autonomous navigation system and the automatic charging system are connected to the industrial computer, and the industrial computer and the image acquisition system are connected to the remote terminal operating system via a network.

[0014] Preferably, the control system further comprises a positioning system, and the positioning system is connected to the industrial computer.

[0015] The image acquisition system is composed of a monitoring pan-tilt platform and a camera. The image acquisition system can collect the real-time environmental conditions of the terminal and send them to the remote terminal operating system, and can perform face recognition. The remote terminal operating system provides users with a windows-based operating interface and an industrial computer that receives and processes instructions. Users can send instructions to the robot through the interface (such as starting the robot to start inspections and collecting images). The industrial computer receives instructions and processes and drives the robot to make corresponding actions. The automatic charging system includes an automatic charging module. When the inspection robot detects that it is out of power, it can automatically navigate to the charging pile position for automatic recharging. The positioning system is composed of an odometer (odom), an inertial navigation unit (imu), and a GPS module. After the robot is started, the odometer (odom), the inertial navigation unit (imu), and the GPS module publish data respectively. After data fusion, the robot's accurate position data can be obtained through extended Kalman filtering.

[0016] The last object of the present invention is to provide a method for a dock security inspection robot to perform a dock security inspection, comprising the following steps:

[0017] S1, the inspection robot receives the inspection task and arrives at the inspection task point according to the inspection path;

[0018] S2, the inspection robot starts to perform the inspection task and sends the inspection result to the remote control terminal;

[0019] S3, if the inspection robot finds an abnormal situation at the dock, it sends the coordinate information of the abnormal task point to the remote control terminal.

[0020] Preferably, in the process of reaching the task point, the robot in step S1 can use the detection module to detect obstacles, so as to realize autonomous obstacle avoidance of the robot.

[0021] Preferably, the detection module includes a laser radar and an ultrasonic detector. The laser radar adopts SICKLMS111 and performs non-contact measurement. The ultrasonic detector can detect the distance information of obstacles around the robot to enable the robot to avoid obstacles autonomously.

[0022] Preferably, step S2 specifically includes:

[0023] S21, using an image acquisition device to collect the real-time environmental conditions of the terminal and send them to the remote control terminal, and perform face recognition;

[0024] S22, when the remote control terminal finds that the inspection result is abnormal, the remote control terminal sends a command to the industrial computer of the robot;

[0025] S23, the industrial computer receives the instruction from the remote control terminal and processes and drives the robot to perform corresponding actions, and enters step S3.

[0026] Preferably, the inspection abnormality in step S22 includes an abnormality in the inspection environment or an intrusion of an illegal person.

[0027] Preferably, the positioning method in step S3 specifically includes:

[0028] The robot first obtains the rough posture information of the robot by integrating the inertial navigation unit, odometer, and GPS data; at the same time, the robot's self-built local map, the robot's self-built global map, and the artificial auxiliary map are used to fuse the global map to obtain the prior global map; after obtaining the rough posture information of the robot, the laser sensor is used to scan the surrounding environment for local positioning to obtain the local precise posture information of the robot. Finally, the rough posture information and local precise posture information are combined with the prior global map to obtain the precise position information of the robot. At the same time, the precise posture information obtained by the laser sensor is used to recalibrate the odometer and inertial navigation unit to reduce the cumulative error of the odometer and inertial navigation unit, and further obtain accurate robot posture information.

[0029] The extended Kalman filter algorithm used in the present invention refers to the process of observing the input data and output data of the system and estimating the state of the nonlinear system to obtain the optimal solution of the system. The algorithm can correct the measured value and make the measured value approach the true value.

[0030] The beneficial effects of the present invention are:

[0031] The present invention provides a dock security patrol robot and a control system. The robot of the present invention can be used for dock security patrol, the robot can recognize the uniforms of dock staff and perform face recognition, the robot can avoid obstacles encountered during movement, and when the patrol robot detects that it is low on power, it will automatically navigate to a charging pile for charging; when the robot detects an illegal intrusion, it will send a signal to a remote control terminal to trigger an alarm; using sensor data fusion positioning, the remote control terminal can observe the robot's position in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is the overall structure diagram of the terminal security inspection robot in Example 1;

[0033] Figure 2 is a structural diagram of the mobile platform of the terminal security inspection robot in Example 1;

[0034] Figure 3 is a structural diagram of the terminal security inspection robot control system in Example 2;

[0035] Figure 4 This is a flow chart of the inspection performed by the terminal security inspection robot in Example 3;

[0036] Figure 5 is a schematic diagram of the positioning system of the dock security inspection robot in Example 3;

[0037] Figure 6 is a flow chart of the extended Kalman filter algorithm used in Example 3;

[0038] 1 is the mobile platform, 2 is the monitoring gimbal, 3 is the camera, 4 is the industrial computer, 5 is the laser radar, 6 is the lithium battery, 7 is the camera installation mechanism, 8 is the wheel, 9 is the Arduino Mega 2560 single-chip microcomputer control board, and 10 is the DC reduction motor and odometer. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation methods described herein are only used to explain the present invention and are not used to limit the present invention.

[0040] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be an intermediate element at the same time.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. Example

[0042] This embodiment provides a terminal security inspection robot, such as Figure 1 As shown, it includes a mobile platform, a detection module, an image acquisition device, a monitoring platform, a remote control terminal, an automatic charging system and an industrial computer. The monitoring platform, the detection module and the industrial computer are all installed on the mobile platform. The image acquisition device is installed on the monitoring platform by bolts, and the remote control terminal is connected to the industrial computer. The automatic charging system includes a charging module and a charging pile. The charging module is connected to the lithium battery installed on the mobile platform through an interface, and the charging pile is connected to any power interface.

[0043] In this embodiment, the mobile platform adopts four-wheel drive differential steering. Figure 2 As shown, the mobile platform includes four wheels and a single-chip microcomputer control board. The four wheels are all equipped with a DC reduction motor and an odometer. The single-chip microcomputer control board is installed in the center of the mobile platform.

[0044] The image acquisition device in this embodiment includes a camera that can rotate 360 ​​degrees and flip up and down, and the camera monitoring platform that can rotate 360 ​​degrees and flip up and down is installed on the monitoring platform through a camera installation mechanism.

[0045] The robot further comprises an inertial navigation unit and a GPS module, and both the inertial navigation unit and the GPS module are connected to the industrial computer via a serial port.

[0046] The detection module includes a laser radar and an ultrasonic detector. The laser radar adopts SICK LMS111 and performs non-contact measurement. The ultrasonic detector can detect the distance information of obstacles around the robot and realize the robot's autonomous obstacle avoidance.

[0047] By using the above-mentioned dock security patrol robot, the robot can recognize the uniforms of dock staff and the facial features of dock staff. When the robot detects the facial features of non-staff members, it will send a signal to the remote control terminal to trigger an alarm.

[0048] The automatic charging module of the terminal security patrol robot also includes a power detection device. The industrial computer 4 can monitor the power of the patrol robot through the power detection device. When the power of the patrol robot is lower than a patrol cycle (a patrol cycle is when the patrol robot starts to inspect all instruments and equipment and returns to the initial position), the patrol robot will automatically navigate to the charging pile position for charging. Example

[0049] This embodiment provides a terminal security inspection robot control system, such as Figure 3 As shown, it includes an autonomous navigation system, an image acquisition system, an industrial computer, a remote terminal operating system, an automatic charging system and a positioning system; the autonomous navigation system, the positioning system and the automatic charging system are connected to the industrial computer, and the industrial computer and the image acquisition system are connected to the remote terminal operating system via a network.

[0050] The image acquisition system is composed of a monitoring pan-tilt and a camera. The image acquisition system can collect the real-time environmental conditions of the dock and send them to the remote control terminal, and can also perform face recognition. The remote terminal operating system provides the user with a windows-based operating interface, an industrial computer that receives and processes instructions, and the user can send instructions to the robot through the interface (such as starting the robot to start inspection and collecting images), and the industrial computer receives the instructions and processes and drives the robot to make corresponding actions. The automatic charging system includes an automatic charging module. When the inspection robot detects that it is out of power, it can automatically navigate to the charging pile position for automatic recharging. The positioning system includes software algorithms and hardware. The hardware equipment consists of an odometer (odom), an inertial navigation unit (imu), and a GPS module. The software algorithm is integrated on the industrial computer. After the robot is started, the odometer (odom), the inertial navigation unit (imu), and the GPS module publish data respectively. After data fusion, the robot's accurate position data can be obtained through the extended Kalman filter algorithm. Example

[0051] This embodiment provides a method for a dock security inspection robot to perform a dock security inspection, such as Figure 4 As shown, the following steps are included:

[0052] S1, the inspection robot receives the inspection task through the remote control terminal and arrives at the task point according to the set inspection path;

[0053] S2, after arriving at the task point, the inspection robot starts the inspection task and sends the inspection results to the remote control terminal;

[0054] S3, if the inspection robot finds an abnormal situation at the dock, it sends the position information of the abnormal task point to the remote control terminal.

[0055] S4, after receiving the position information, the remote control terminal notifies the staff and dispatches the staff to the designated location to handle the abnormal situation.

[0056] Specifically, in this embodiment, when the inspection robot moves for inspection, the detection module of the robot, including a laser radar and an ultrasonic detector, detects the distance information of obstacles around the robot to enable the robot to avoid obstacles autonomously.

[0057] Meanwhile, in this embodiment, when the robot is performing inspection, step S2 specifically includes the following steps:

[0058] S21, using the image acquisition system to collect the real-time environmental conditions of the terminal and send them to the remote control terminal, and can perform face recognition;

[0059] S22, when the remote control terminal finds that the inspection is abnormal, including an abnormal environment or an intrusion by an outsider, the remote control terminal sends further instructions to the robot;

[0060] S23, the industrial computer receives the command from the remote control terminal and processes it to drive the robot to make corresponding actions, and then enters step S3.

[0061] Specifically, the positioning method principle used in step S3 is as follows: Figure 5 As shown in the figure, the robot first obtains the rough posture information of the robot by integrating the inertial navigation unit, odometer, and GPS data; at the same time, the robot's self-built local map, the robot's self-built global map, and the artificial auxiliary map are used to fuse the global map to obtain the prior global map; after obtaining the rough posture information of the robot, the laser sensor is used to scan the surrounding environment for local positioning to obtain the local precise posture information of the robot. Finally, the rough posture information and local precise posture information are combined with the prior global map to obtain the precise position information of the robot. At the same time, the precise posture information obtained by the laser sensor is used to recalibrate the odometer and inertial navigation unit to reduce the cumulative error of the odometer and inertial navigation unit, and further obtain accurate robot posture information.

[0062] In this embodiment, when three sensors (inertial navigation unit, odometer, GPS) are used to locate the robot, the extended Kalman filter algorithm is used. This algorithm refers to the process of observing the input data and output data of the system and estimating the state of the nonlinear system to obtain the optimal solution of the system. This algorithm can correct the measured value and make the measured value approach the true value.

[0063] The flow chart of the extended Kalman filter algorithm used in this embodiment is as follows: Figure 6As shown in the figure, the specific process of the algorithm is as follows: first, create a data model for prediction and measurement update, then initialize the filter, and then confirm whether the robot's odometer (odom), inertial navigation unit (imu) and GPS module are operating normally and effectively. If they are operating effectively, update the filter according to the data they publish, and finally output the optimal estimate and covariance matrix; if invalid, further wait for the sensor data, and then judge again whether the status of the odometer (odom), inertial navigation unit (imu) and GPS is valid.

[0064] It is worth noting that before the entire inspection process begins, a facial database of dock staff can be established. When the robot recognizes facial features and uniforms that do not belong to the database, the industrial control machine will send a signal to the remote control terminal, thereby triggering the alarm.

[0065] By adopting the above technical solution disclosed in the present invention, the following beneficial effects are obtained:

[0066] The present invention discloses a dock security patrol robot and a control system. The robot can be used for dock security patrol. The robot can recognize the uniforms of dock staff and perform face recognition. The robot can avoid obstacles encountered during movement. When the patrol robot detects that it is low on power, it will automatically navigate to a charging pile for charging. When the robot detects an illegal intrusion, it will send a signal to a remote control terminal to trigger an alarm. Sensor data fusion positioning is used, and the remote control terminal can observe the robot's position in real time.

[0067] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be considered as the scope of protection of the present invention.

Claims

1. A method for performing dock security inspection by a dock security inspection robot, characterized in that: It includes a mobile platform, a detection module, an image acquisition device, a monitoring platform, a remote control terminal and an industrial computer. The monitoring platform, the detection module and the industrial computer are all installed on the mobile platform, the image acquisition device is installed on the monitoring platform, and the remote control terminal is connected to the industrial computer through a network; The robot also includes an automatic charging system, which includes a charging module and a charging pile. The charging module is connected to a lithium battery installed on the mobile platform through an interface. Connect to any power interface; the charging module also includes a power detection device, and the industrial computer detects The power of the inspection robot can be monitored. When the power of the inspection robot is lower than one inspection cycle, The inspection robot will automatically navigate to the charging station to charge. When the equipment returns to its initial position, it is considered an inspection cycle. The mobile platform adopts four-wheel drive differential steering, and the mobile platform includes four wheels and a single-chip microcomputer control board. The four wheels are equipped with a DC reduction motor and an odometer. Installed in the center of the mobile platform; The robot further includes an inertial navigation unit and a GPS module, and the inertial navigation unit and the GPS module are both connected to the industrial computer through a serial port; the detection module includes at least one of a laser radar and an ultrasonic detector; The method for performing dock security inspection using a dock security inspection robot comprises the following steps: S1, the inspection robot receives the inspection task and arrives at the task point according to the inspection path; S2, the inspection robot starts the inspection task and sends the inspection results to the remote control terminal; S3: If the inspection robot finds an abnormal situation at the dock, it will send the coordinate information of the abnormal task point to the remote Program control terminal; Step S2 specifically includes: S21, using an image acquisition device to collect the real-time environmental conditions of the terminal and send them to the remote control terminal, and Perform facial recognition; S22, when the remote control terminal finds that the inspection is abnormal, the remote control terminal sends a message to the machine People send instructions; S23, the industrial computer receives the command from the remote control terminal and processes it to drive the robot to make corresponding actions. Go to step S3; The positioning method in step S3 specifically includes: The robot first obtains its rough posture information by integrating the inertial navigation unit, odometer, and GPS data; at the same time, the robot's self-built local map, the robot's self-built global map, and the artificially assisted map are used to fuse the global maps to obtain a priori global map; after obtaining the robot's rough posture information, a laser sensor is used to scan the surrounding environment for local positioning to obtain the robot's local precise posture information; finally, the obtained rough posture information and local precise posture information are combined with the prior global map to finally obtain the robot's precise position information; at the same time, the precise posture information obtained by the laser sensor is used to recalibrate the odometer and inertial navigation unit to reduce the cumulative errors of the odometer and inertial navigation unit, and further obtain accurate robot posture information.

2. The method for performing dock security inspection by the dock security inspection robot according to claim 1, characterized in that: The image acquisition device comprises a camera capable of rotating 360 degrees and flipping up and down, and the camera monitoring platform capable of rotating 360 degrees and flipping up and down is installed on the monitoring platform through a camera installation mechanism.