Slope disease early warning and traffic management and control system based on intelligent road cone robot

Abstract

The invention relates to a slope disease early warning and traffic management and control system based on an intelligent road cone robot. The system comprises a slope monitoring module, a remote control center and the road cone robot. The side slope monitoring module monitors road side slope deformation and environment change to obtain side slope monitoring data; the road cone robot senses the slope state through a sensor to obtain slope monitoring data; the remote control center stores and processes the slope monitoring data obtained by the slope monitoring module and the road cone robot, makes a road slope disaster early warning and traffic control road cone arrangement scheme based on the slope monitoring data, converts a decision instruction of the traffic control road cone arrangement scheme into a control command, and sends the control command to the road cone robot; and dynamically deploying the road cone robot. The slope disease early warning and traffic management and control system has the beneficial effects that the slope disease early warning and traffic management and control system is established through cloud side-end cooperation and deep learning technologies, potential safety hazards caused by slope diseases are greatly reduced, the safety of passengers is guaranteed, and the traffic management and control efficiency is improved.

Description

Technical Field

[0001] This invention belongs to the field of disaster monitoring technology and transportation safety management, and in particular relates to a slope disease early warning and traffic control system based on an intelligent road cone robot. Background Technology

[0002] With the large-scale construction and operation of highway infrastructure, intelligent monitoring of slope stability and collaborative management of traffic emergencies have become core challenges in the field of road safety operation and maintenance. Current slope monitoring technologies mainly rely on fixed sensing terminals and periodic manual inspections, which suffer from technical defects such as high deployment costs, insufficient spatial coverage density, and discrete temporal data, resulting in insufficient real-time early warning capabilities for sudden slope instability. Although UAV remote sensing inspections have the advantages of flexibility and mobility, their limited endurance and poor resistance to severe weather conditions make it difficult to achieve all-weather, continuous slope condition perception, severely restricting the timeliness and reliability of disaster early warnings.

[0003] Traffic cones are widely used temporary warning devices in road traffic management. However, traditional traffic cones are limited to static physical isolation and cannot achieve dynamic traffic flow control. Furthermore, their reliance on manual deployment leads to poor response timeliness, making them unsuitable for rapid response to sudden slope disasters. Traffic management based on manual intervention lacks real-time data support. While current intelligent transportation systems attempt to improve monitoring capabilities through fixed monitoring equipment, the fixed deployment locations of these devices result in blind spots and equipment vulnerabilities. More importantly, existing systems lack an efficient "monitoring-decision-execution" closed-loop mechanism to ensure timely traffic control.

[0004] Existing slope monitoring systems are separated from traffic control equipment, relying on manual intervention and lacking a real-time linkage mechanism. While patent CN119399963A proposes dynamic early warning for intelligent traffic cones, it does not address the closed-loop execution of slope disease identification and traffic control. Patent CN218723923U's slope monitoring technology is limited to deformation sensing and cannot trigger automated traffic response. This invention, through a cluster of ROS intelligent traffic cone robots, achieves fully automated closed-loop management of the entire process from slope condition perception to disaster early warning to dynamic deployment of traffic cones. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a slope disease early warning and traffic control system based on an intelligent road cone robot.

[0006] This system, based on intelligent road cone robots for slope disease early warning and traffic control, includes a slope monitoring module, a remote control center, and road cone robots. The slope monitoring module monitors highway slope deformation and environmental changes to obtain slope monitoring data. The road cone robots sense the slope status through sensors and obtain slope monitoring data. The remote control center connects to the slope monitoring module and the road cone robots, stores and processes the slope monitoring data obtained by the module and robots, and makes road cone deployment plans for highway slope disaster early warning and traffic control based on the data. The decision instructions for the traffic control road cone deployment plan are converted into control commands and sent to the road cone robots. The road cone robots are dynamically deployed based on the control commands.

[0007] Preferably, the slope monitoring module includes sensors for slope deformation monitoring and sensors for slope environment monitoring; the sensors for slope deformation monitoring include displacement sensors, GPS monitoring stations, and inclinometers; the sensors for slope environment monitoring include rain gauges and humidity sensors.

[0008] Preferably, the traffic cone robot includes a sensor module, a power module, a motion module, a communication module, and a ROS software module. The sensor module is used to acquire the position data, motion status data, and slope surface image data of the traffic cone robot. The communication module is used for communication between traffic cone robots and between the traffic cone robot and a remote control center. The ROS software module analyzes the data acquired by the sensor module and feeds it back to the remote control center through the communication module. The ROS software module receives control commands from the remote control center through the communication module and converts the control commands into standardized control commands that the motion module can recognize. The motion module receives the standardized control commands and moves accordingly, driving the system to feed back motion status data to the ROS software module. The power module supplies power to the sensor module, motion module, communication module, and ROS software module.

[0009] Preferably, the ROS software module includes an execution module; the execution module receives control commands from the remote control center through the communication module and converts the control commands into standardized control commands that the motion module can recognize; the motion module includes a drive system and a mobile chassis; the drive system receives the standardized control commands and converts them into control signals for the motors of the mobile chassis to control the movement of the mobile chassis.

[0010] Preferably, the ROS software module includes a localization software module and a path planning and obstacle avoidance software module; the sensor module includes a LiDAR, a GPS receiver station, an IMU, and an odometer; the localization software module is used to process the data obtained from the LiDAR and GPS receiver station to obtain the location information data of the road cone robot; the path planning and obstacle avoidance software module is used to process the data from the IMU and odometer to obtain the motion state data of the road cone robot; the location information data and motion state data are fed back to the remote control center through the communication module.

[0011] Preferably, the ROS software module includes a slope disease image recognition module, and the sensor module includes a high-definition camera; the slope disease image recognition module is used to process slope surface image data obtained by the high-definition camera, identify slope disease features in the image, classify disease levels, and output structured disease information data and level assessment data.

[0012] As a preferred option, the ROS software module includes an edge decision module. The edge decision module adopts a cloud-edge-device collaborative architecture, deploys an intelligent algorithm system on edge nodes, performs autonomous early warning decisions based on structured disease information data and grade assessment data, and outputs early warning information. The edge decision module feeds back the early warning information, structured disease information data, and grade assessment data to the remote control center through the communication module.

[0013] Preferably, the ROS software module includes a communication module; the communication module includes a WiFi module and a Bluetooth module for short-range communication between the road cone robots and a 5G module for communication between the road cone robots and a remote control center.

[0014] Preferably, the remote control center includes a database, a human-computer interaction module, an intelligent decision-making module, and an instruction conversion and transmission module; the database is used to store slope monitoring data from the slope monitoring module; the intelligent decision-making module integrates machine learning prediction models and multi-objective optimization algorithms, and assesses slope stability risk and generates traffic control strategies based on location information data, motion state data, slope monitoring data, early warning information, structured disease information data, and grade assessment data, and outputs decision instructions; the instruction conversion and transmission module is used to convert the decision instructions from the intelligent decision-making module into control commands, and the control commands are sent to the road cone robot cluster.

[0015] Preferably, the human-computer interaction module includes a positioning information module, an autonomous navigation visualization module, and a disaster early warning module. The positioning information module displays the coordinates and motion status of the road cone robot based on the location information and motion status data fed back by the road obstacle robot. The autonomous navigation visualization module is used to adjust the preset path of the road cone robot and to perform collision detection and feasibility verification. The disaster early warning module displays the distribution of risk areas in the form of a heat map based on early warning information, structured disease information data, and level assessment data, and displays the control plan suggestions generated by the system.

[0016] The beneficial effects of this invention are:

[0017] 1) This invention integrates technologies such as sensors, robotics, edge computing, and machine learning, combining real-time monitoring of highway slopes, intelligent early warning of disasters, and automated and intelligent traffic control functions of road cone robots. It effectively overcomes the limitations of traditional manual inspections and fixed monitoring, significantly improves the reliability of slope disaster identification, and reduces safety hazards caused by slope disasters.

[0018] 2) The autonomous collaborative capability of the intelligent traffic cone robot cluster of the present invention enables rapid and accurate deployment of traffic control, significantly optimizes the emergency response process, and improves the efficiency and accuracy of traffic control. Attached Figure Description

[0019] Figure 1 This is an overall schematic diagram of the present invention;

[0020] Figure 2 This is the data flow diagram of the present invention;

[0021] Figure 3 This is a schematic diagram of the intelligent traffic cone robot's automated traffic control operation according to the present invention. Detailed Implementation

[0022] The present invention will be further described below with reference to embodiments. The description of the embodiments below is only for the purpose of helping to understand the present invention. It should be noted that those skilled in the art can make several modifications to the present invention without departing from the principle of the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

[0023] Example 1

[0024] As one embodiment, a slope disease early warning and traffic control system based on an intelligent road cone robot is proposed, such as... Figure 1 and 2As shown, the system includes a slope monitoring module, a remote control center, and road cone robots. The slope monitoring module monitors highway slope deformation and environmental changes to obtain slope monitoring data. Multiple road cone robots are deployed, sensing slope conditions through sensors to obtain slope monitoring data. The remote control center connects to the slope monitoring module and road cone robots, storing and processing the slope monitoring data. Based on the slope monitoring data, it formulates road cone deployment plans for highway slope disaster early warning and traffic control, converting the decision instructions for the traffic control road cone deployment plan into control commands and sending them to the road cone robots. The road cone robots dynamically deploy based on the control commands. Specifically, the slope monitoring... The system uses multi-source sensors to monitor changes in highway slope deformation and environmental factors online, acquiring real-time slope status and providing reliable data support for early warning of road defects. The road cone robot is equipped with ROS software module, achieving cloud-based collaborative decision-making through federated learning. Based on multi-sensor fusion data, it autonomously performs slope defect identification and traffic control tasks, forming a closed-loop management system from slope status perception and disaster early warning to dynamic deployment of road cones. The remote control center is used for storing and intelligently processing slope monitoring data obtained by the slope monitoring module and road cone robot. Based on the data, it makes early warnings of highway slope disasters, decides on road cone deployment schemes for traffic control, drives the road cone robot to complete traffic control, and provides a user interface for interaction with the ROS software module.

[0025] Example 2

[0026] As another embodiment, this embodiment two proposes, based on embodiment one, a more specific slope disease early warning and traffic control system based on intelligent road cone robot.

[0027] The slope monitoring module includes sensors for slope deformation monitoring and sensors for slope environmental monitoring; the sensors for slope deformation monitoring include displacement sensors, GPS monitoring stations, and inclinometers; the sensors for slope environmental monitoring include rain gauges and humidity sensors; specifically, such as Figure 2 As shown, the combined deployment of the GNSS displacement monitoring system and the inclinometer enables the coordinated monitoring of slope surface displacement and deep deformation. At the same time, combined with environmental monitoring equipment such as rain gauges and piezometers, a comprehensive monitoring network for factors affecting slope stability is formed. The data collected by each monitoring sensor is transmitted to the data collection box, and after centralized processing and standardization conversion, it is transmitted in real time to the database of the remote control center through the remote wireless communication system.

[0028] It should be noted that the parts in this embodiment that are the same as or similar to those in Embodiment 1 can be referred to each other, and will not be repeated in this application.

[0029] Example 3

[0030] As another embodiment, this embodiment three proposes, based on embodiment two, a more specific slope disease early warning and traffic control system based on intelligent road cone robot.

[0031] like Figure 2 As shown, the traffic cone robot includes a sensor module, a power module, a motion module, a communication module, and a ROS software module. The sensor module is used to acquire the traffic cone robot's position data, motion status data, and slope surface image data. The communication module is used for communication between traffic cone robots and between the traffic cone robot and the remote control center. The ROS software module analyzes the data acquired by the sensor module and feeds it back to the remote control center through the communication module. The ROS software module receives control commands from the remote control center through the communication module and converts the control commands into standardized control commands that the motion module can recognize. The motion module receives the standardized control commands and moves accordingly, driving the system to feed back motion status data to the ROS software module. The power module supplies power to the sensor module, motion module, communication module, and ROS software module.

[0032] Specifically, the sensor module includes a lidar, a GPS receiver station, a high-definition camera, an IMU, and an odometer. The lidar and GPS receiver station achieve centimeter-level positioning through a Kalman filter algorithm, and the high-definition camera acquires slope surface image data in real time based on the YOLOv7 model.

[0033] The motion module includes a mobile chassis for precisely performing forward, backward, turning, and climbing motion tasks, and a drive system that receives instructions from the ROS software module, converts them into precise control signals for each motor of the mobile chassis, and provides real-time feedback of motion status data.

[0034] The communication module includes a WiFi module and a Bluetooth module for short-range communication between the road cone robots, and a 5G module for communication between the road cone robots and the remote control center.

[0035] The ROS software module includes a positioning software module for multi-sensor fusion during the movement of the road cone robot; a path planning and obstacle avoidance software module for dynamic path planning; a slope disease image recognition module for automatic identification of slope diseases based on deep learning technology; an edge decision module for distributed optimization decision-making and formulating the best traffic control plan based on cloud-edge collaboration technology and federated learning; and an execution module for a precise execution control system that ensures the accurate implementation of control commands through real-time task decomposition and resource scheduling mechanisms.

[0036] It should be noted that the parts in this embodiment that are the same as or similar to those in Embodiment 2 can be referred to each other, and will not be repeated in this application.

[0037] Example 4

[0038] As another embodiment, this embodiment four proposes, based on embodiment three, a more specific slope disease early warning and traffic control system based on intelligent road cone robot.

[0039] The ROS software module includes an execution module; as the core instruction processing unit, the execution module receives control commands from the remote control center through the communication module, and converts the control commands into standardized control commands that the motion module can recognize through a dedicated communication protocol conversion interface; the motion module includes a drive system and a mobile chassis; the drive system receives standardized control commands and converts them into control signals for the motors of the mobile chassis, and adjusts the steering angle and travel speed of the mobile chassis through a closed-loop control mechanism to ensure that the road cone robot accurately reaches the target position according to the standardized control commands.

[0040] The ROS software module includes a localization software module and a path planning and obstacle avoidance software module. The road cone robot uses a multi-sensor fusion localization software module to achieve high-precision autonomous movement through the collaborative processing of various sensor data. The sensor module includes a lidar, a GPS receiver station, an IMU, and an odometer. The lidar and GPS receiver station work together. The GPS receiver station receives satellite signals, which provide a global position reference. The lidar constructs a local spatial model through real-time environmental scanning. The IMU and odometer work together. The odometer's Hall sensor monitors the changes in the magnetic field when the motor shaft of the mobile chassis rotates in real time, generating corresponding pulse signals. The IMU is an inertial measurement unit used to measure the road cone robot's attitude changes and acceleration information during its movement.

[0041] The positioning software module is used to process the data obtained by the lidar and GPS receiver. It processes the spatial data collected by the lidar, eliminates environmental interference factors, and establishes an accurate two-dimensional environmental map. Combined with satellite signals, the positioning software module obtains the location information data of the road cone robot from the data of the lidar and GPS receiver.

[0042] The path planning and obstacle avoidance software module processes data from the IMU and odometry, calculates the robot's actual movement distance based on the pulse signals generated by the odometry, and achieves precise control of the robot's position and speed. It also processes the attitude change and acceleration information of the IMU using filtering algorithms. The path planning and obstacle avoidance software module combines the data from the IMU and odometry to obtain the motion state data of the road cone robot, enabling the road cone robot to adjust its motion state in real time in complex environments, ensuring the accuracy and timeliness of obstacle avoidance actions.

[0043] Location information and motion status data are fed back to the remote control center through the communication module.

[0044] The ROS software module includes a slope disease image recognition module. Using high-definition camera images of the slope surface as raw images, it performs standardized preprocessing on the raw images, including denoising, enhancement, and geometric correction. Based on a feature extraction algorithm using a deep convolutional neural network, the slope disease image recognition module automatically identifies typical slope disease features such as cracks, seepage, and spalling in the processed images and classifies the disease level according to a preset evaluation model. The structured disease information data and level evaluation data after identification and analysis are transmitted in real time to the edge decision-making module of the ROS software module, providing data support for subsequent autonomous path planning and traffic control decisions.

[0045] The ROS software module includes a communication module; this module includes WiFi and Bluetooth modules for short-range communication between traffic cone robots, and a 5G module for communication between traffic cone robots and a remote control center; a highly efficient distributed collaborative network is built through the WiFi and Bluetooth dual-mode communication module, enabling real-time status interaction and motion coordination among individual traffic cone robot nodes through short-range communication, forming an autonomous intelligent cluster system; the communication module employs adaptive frequency hopping technology to ensure transmission stability in complex environments, supports real-time data sharing and collaborative decision-making among traffic cone robots, and achieves centimeter-level precision in collaborative movement and accurate deployment; the communication module achieves swarm intelligence through a distributed computing framework, enabling the traffic cone robot cluster to autonomously coordinate its movement trajectory, avoid path conflicts, and maintain information connectivity through neighboring nodes when communication conditions are limited.

[0046] The ROS software module includes an edge decision module, which adopts a cloud-edge-device collaborative architecture. It deploys an intelligent algorithm system on edge nodes to make autonomous early warning decisions based on structured disease information data and grade assessment data, and outputs early warning information. The edge decision module feeds back the early warning information, structured disease information data, and grade assessment data to the remote control center through the 5G module of the communication module.

[0047] It should be noted that the parts in this embodiment that are the same as or similar to those in Embodiment 3 can be referred to each other, and will not be repeated in this application.

[0048] Example 5

[0049] As another embodiment, this fifth embodiment proposes, based on the fourth embodiment, a more specific slope disease early warning and traffic control system based on an intelligent road cone robot.

[0050] like Figure 2As shown, the remote control center includes a database, a human-machine interaction module, an intelligent decision-making module, and an instruction conversion and sending module. The database stores slope monitoring data from the slope monitoring module. The human-machine interaction module allows users to interact with the ROS software module. The intelligent decision-making module integrates machine learning prediction models and multi-objective optimization algorithms to assess slope stability risks and generate traffic control strategies based on location information data, motion status data, slope monitoring data, early warning information, structured disease information data, and grade assessment data, and outputs decision instructions. The instruction conversion and sending module converts the decision instructions from the intelligent decision-making module into control commands, which are then sent to the road cone robot cluster.

[0051] The human-machine interaction module of the remote control center includes a positioning information module, an autonomous navigation visualization module, and a disaster early warning module. The positioning information module displays the coordinates and motion status of the road cone robot based on the location information and motion status data fed back by the road obstacle robot. The autonomous navigation visualization module is used to adjust the preset path of the road cone robot and to perform collision detection and feasibility verification. The disaster early warning module displays the distribution of risk areas in the form of a heat map based on early warning information, structured disease information data, and level assessment data, and displays the control plan suggestions generated by the system.

[0052] The disaster early warning module displays the early warning details on the interface of the human-computer interaction module based on the early warning information, structured disease information data and level assessment data fed back by the edge decision module of the ROS software module.

[0053] The positioning information module and the autonomous navigation visualization module perform 3D modeling and fusion processing based on the position information data fed back by the ROS software module's positioning software module, the path planning data from the ROS software module, and the motion status data fed back by the obstacle avoidance software module. This constructs a real-time situation map that includes elements such as the robot cluster distribution status, dynamic navigation path, environmental obstacle information, and a heat map of the warning area. The autonomous navigation visualization module supports multi-dimensional data display and interactive operation. Users can use the touch screen to perform functions such as precise positioning query of the road cone robot, dynamic path adjustment, task priority setting, and rapid issuance of emergency commands.

[0054] The human-machine interaction module features a highly integrated visual interface, enabling real-time monitoring and interactive control of traffic conditions. Adopting an event-driven architecture, the module incorporates a two-way communication mechanism, simultaneously displaying the real-time status of the traffic cone robot cluster and dynamic changes in traffic flow. The interface utilizes intelligent rendering technology to integrate and display multi-source data, supporting direct user control and parameter adjustment of the traffic cone robot cluster while ensuring low-latency transmission and execution feedback of control commands.

[0055] The intelligent decision-making module, based on real-time collected slope monitoring data, dynamically analyzes the slope stability status through a multi-dimensional risk assessment algorithm and establishes a disaster evolution prediction model. It employs a hybrid analysis method combining machine learning and geotechnical mechanics to assess the potential risk level of the slope in real time and dynamically displays the analysis results through a visual interface of the human-computer interaction module, including slope deformation trends, risk heat maps, and early warning level information. The intelligent decision-making module supports multi-terminal access, ensuring that managers can monitor the slope status in real time and respond promptly, forming a closed-loop management process from data collection to decision support.

[0056] The intelligent decision-making module integrates slope monitoring data obtained from multiple sensors by the slope monitoring module with high-definition camera visual recognition results from structured disease information data uploaded by the road cone robot. It also incorporates location information data, motion status data, early warning information, and level assessment data, and calls upon a pre-built scene knowledge base for multi-dimensional analysis to dynamically generate a complete decision-making plan that includes disaster level assessment, development trend prediction, and emergency response suggestions. The intelligent decision-making module automatically converts the optimized road cone robot deployment strategy into decision instructions and then converts the decision instructions from the intelligent decision-making module into control commands, which are then sent to the target robot cluster via a remote communication link, realizing intelligent handling of the entire process from disaster identification to the implementation of control measures.

[0057] It should be noted that the parts in this embodiment that are the same as or similar to those in Embodiment 4 can be referred to each other, and will not be repeated in this application.

[0058] Example 6

[0059] As another embodiment, this sixth embodiment, based on the fifth embodiment, proposes an automated working process for early warning and traffic control of slope landslide disasters using the present invention, such as... Figure 3 As shown:

[0060] A. When the road cone robot deployed in the slope area continuously monitors the slope surface cracks through high-definition cameras and finds that the crack expansion rate exceeds the threshold, its edge computing module will immediately start a multi-dimensional risk assessment algorithm; the edge decision module triggers an early warning and automatically generates early warning information, which is transmitted to the remote control center in real time through the communication module.

[0061] B. Upon receiving the early warning information sent by the road cone robot, the intelligent decision-making module of the remote control center immediately initiates the analysis process; it retrieves environmental parameters such as displacement monitoring data, pore water pressure data, and rainfall in the slope area in real time through the IoT data interface, and constructs a multi-dimensional slope stability assessment model; based on a hybrid algorithm of machine learning and geotechnical mechanics theory, the system automatically calculates the probability of slope instability and assesses the urgency of the disaster, generating an early warning report that includes risk level, impact range, and expected development trend. The early warning report is presented in real time through the three-dimensional visualization interface of the human-computer interaction module.

[0062] C. Based on real-time acquired multi-source monitoring data and risk assessment results, the intelligent decision-making module of the remote control center initiates the traffic control scheme generation algorithm; simultaneously, it generates a corresponding traffic guidance scheme, and the remote control center automatically generates a set of control commands, which are then sent to the road cone robot cluster for execution.

[0063] D. The traffic control plan is analyzed and decomposed into a sequence of executable machine instructions, including key control elements such as target coordinate set, priority path planning, and safety distance parameters; through a dedicated communication protocol conversion interface, the system converts the control strategy into control commands adapted to different models of traffic cone robots and distributes them to the corresponding traffic cone robots;

[0064] E. The execution module of the road cone robot decodes the control commands sent by the remote control center, extracts key parameters, and sends them to the drive system of the motion module;

[0065] The F. Road Cone Robot's positioning software module receives satellite signals from a GPS receiver station in real time. Simultaneously, a LiDAR performs a 3D scan of the environment. The collected point cloud data is processed by the path planning and obstacle avoidance software module in real time to eliminate noise interference and generate an environmental feature map with centimeter-level accuracy. This spatial data is transmitted back to the remote control center in real time through the communication module and is overlaid and merged with the basic data of the geographic information system to form a comprehensive situation map that includes the real-time position of the Road Cone Robot, the distribution of surrounding obstacles, and terrain features.

[0066] The sensor module of the G. Road Cone robot continuously collects multi-dimensional environmental data during its movement and achieves precise navigation through a fusion positioning algorithm. All navigation data is transmitted back to the remote control center in real time through the communication module, where it is spatiotemporally aligned and fused with geographic information system data. The 3D visualization platform of the remote control center dynamically renders this information, intuitively displaying the robot's real-time position, planned path, and environmental characteristics in the form of color coding and vector arrows.

[0067] H. During the placement of each traffic cone robot, the traffic cone robot cluster achieves efficient collaborative operation through a dual-mode wireless communication network; each robot node establishes a dynamic self-organizing network, uses WiFi to achieve high-speed data interaction, and at the same time maintains precise synchronization between near-field devices through Bluetooth, autonomously coordinates movement trajectories, ensures that the target area is blocked within 30 seconds, avoids path conflicts, implements traffic control in a timely manner, and reduces the safety hazards and economic losses that landslides may cause.

[0068] This invention presents a slope disease early warning and traffic control system based on intelligent road cone robots, constructing a closed-loop control system covering the entire process of "monitoring-decision-execution". The system utilizes a distributed cluster of intelligent road cone robots, integrating multi-source sensor data to achieve real-time monitoring of slope conditions. Relying on an intelligent decision-making mechanism combining edge computing and cloud collaboration, it rapidly generates optimal control plans when risks are detected. Furthermore, the road cone robots autonomously and collaboratively complete the precise deployment of traffic control facilities, significantly reducing the time required for traditional manual intervention. This greatly improves the timeliness and accuracy of slope disaster early warning, effectively reducing the risk of safety accidents caused by slope instability, and providing an innovative solution for the intelligent management and maintenance of highway infrastructure.

[0069] It should be noted that the parts in this embodiment that are the same as or similar to those in Embodiment 5 can be referred to each other, and will not be repeated in this application.

[0070] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

Claims

1. A system for slope disease early warning and traffic control based on an intelligent road cone robot, characterized in that, The system includes a slope monitoring module, a remote control center, and a road cone robot. The slope monitoring module monitors highway slope deformation and environmental changes to obtain slope monitoring data. The road cone robot senses the slope status through sensors and obtains slope monitoring data. The remote control center is connected to the slope monitoring module and the road cone robot, and stores and processes the slope monitoring data obtained by the slope monitoring module and the road cone robot. Based on the slope monitoring data, it makes road cone layout plans for highway slope disaster early warning and traffic control, and converts the decision instructions for the road cone layout plan for traffic control into control commands and sends them to the road cone robot. The road cone robot is dynamically deployed based on control commands.

2. The system for slope disease early warning and traffic control based on intelligent road cone robot according to claim 1, characterized in that, The slope monitoring module includes sensors for slope deformation monitoring and sensors for slope environment monitoring; the sensors for slope deformation monitoring include displacement sensors, GPS monitoring stations, and inclinometers; the sensors for slope environment monitoring include rain gauges and humidity sensors.

3. The system for slope disease early warning and traffic control based on intelligent road cone robot according to claim 2, characterized in that, The traffic cone robot includes a sensor module, a power module, a motion module, a communication module, and a ROS software module; the sensor module is used to acquire the position data, motion status data, and slope surface image data of the traffic cone robot; the communication module is used for communication between traffic cone robots and communication between the traffic cone robot and the remote control center; The ROS software module analyzes the data obtained by the sensor module and feeds it back to the remote control center through the communication module. The ROS software module receives control commands from the remote control center through the communication module and converts the control commands into standardized control commands that the motion module can recognize. The motion module receives the standardized control commands and moves, driving the system to feed back motion status data to the ROS software module. The power module is used to supply power to the sensor module, motion module, communication module and ROS software module.

4. The system for slope disease early warning and traffic control based on intelligent road cone robot according to claim 3, characterized in that, The ROS software module includes an execution module; the execution module receives control commands from the remote control center through the communication module and converts the control commands into standardized control commands that the motion module can recognize; the motion module includes a drive system and a mobile chassis; the drive system receives the standardized control commands and converts them into control signals for the mobile chassis motor, thereby controlling the movement of the mobile chassis.

5. The system for slope disease early warning and traffic control based on intelligent road cone robot according to claim 4, characterized in that, The ROS software module includes a localization software module and a path planning and obstacle avoidance software module; the sensor module includes a LiDAR, a GPS receiver station, an IMU, and an odometer; the localization software module processes the data obtained from the LiDAR and GPS receiver station to obtain the location information data of the road cone robot; the path planning and obstacle avoidance software module processes the data from the IMU and odometer, and the odometer obtains the motion state data of the road cone robot; the location information data and motion state data are fed back to the remote control center through the communication module.

6. The system for slope disease early warning and traffic control based on intelligent road cone robot according to claim 5, characterized in that, The ROS software module includes a slope disease image recognition module and a sensor module including a high-definition camera. The slope disease image recognition module is used to process slope surface image data obtained by the high-definition camera, identify slope disease features in the image, classify disease levels, and output structured disease information data and level assessment data.

7. The system for slope disease early warning and traffic control based on intelligent road cone robot according to claim 6, characterized in that, The ROS software module includes an edge decision module, which adopts a cloud-edge-device collaborative architecture. It deploys an intelligent algorithm system at the edge nodes, performs autonomous early warning decisions based on structured disease information data and grade assessment data, and outputs early warning information. The edge decision-making module feeds back early warning information, structured disease information data, and level assessment data to the remote control center through the communication module.

8. The system for slope disease early warning and traffic control based on intelligent road cone robot according to claim 7, characterized in that, The ROS software module includes a communication module; the communication module includes a WiFi module and a Bluetooth module for short-range communication between road cone robots, and a 5G module for communication between road cone robots and a remote control center.

9. The system for slope disease early warning and traffic control based on intelligent road cone robot according to claim 8, characterized in that, The remote control center includes a database, a human-computer interaction module, an intelligent decision-making module, and an instruction conversion and transmission module. The database stores slope monitoring data from the slope monitoring module. The intelligent decision-making module integrates machine learning prediction models and multi-objective optimization algorithms to assess slope stability risks and generate traffic control strategies based on location information data, motion status data, slope monitoring data, early warning information, structured disease information data, and grade assessment data, and outputs decision instructions. The instruction conversion and transmission module converts the decision instructions from the intelligent decision-making module into control commands, which are then sent to the road cone robot cluster.

10. The system for slope disease early warning and traffic control based on intelligent road cone robot according to claim 9, characterized in that, The human-computer interaction module includes a positioning information module, an autonomous navigation visualization module, and a disaster early warning module. The positioning information module displays the coordinates and motion status of the road cone robot based on the location information and motion status data fed back by the road obstacle robot. The autonomous navigation visualization module is used to adjust the preset path of the road cone robot and to perform collision detection and feasibility verification. The disaster early warning module displays the distribution of risk areas in the form of a heat map based on early warning information, structured disease information data, and level assessment data, and also presents the control plan suggestions generated by the system.

Images