Unmanned intelligent excavator system

Abstract

The invention relates to an unmanned intelligent excavator system which is composed of a plurality of functional modules and is characterized in that various sensors and actuators are integrated through a hardware design module to provide basic support for subsequent operation; the environment sensing and positioning module collects three-dimensional point cloud data of an operation area in real time by using a multi-sensor fusion technology, realizes accurate positioning and environment sensing, and transmits the information to the planning module; the planning module formulates a driving route of the excavator and an operation track of the mechanical arm according to the received data, and sends the driving route and the operation track to an upper computer or a mobile terminal through the central control communication module to allow remote monitoring and control; and the lower computer communication module is responsible for transmitting a planned path instruction to an execution mechanism and driving a machine to execute a predetermined task. According to the system, a closed-loop control mode is adopted, high efficiency and safety of the excavator in bulk cargo cabin cleaning and coal stacking operation are guaranteed, and the wide potential of the excavator in future power plants and bulk cargo wharfs is shown.

Description

Technical Field

[0001] The invention belongs to the field of intelligent engineering vehicle control, and in particular relates to an unmanned intelligent excavator system. Background Art

[0002] Excavators are key operating equipment in ship unloading and cargo clearing operations and coal stack loading and unloading operations at thermal power plants and medium and large bulk cargo terminals. However, the existing operation mode usually relies on manual operation, which not only leads to low efficiency but also poses high safety risks. The traditional manual operation mode requires operators to work in a small, closed cabin or coal shed. These environments are usually accompanied by high dust, high noise and low visibility, which seriously threatens the health and safety of operators. In addition, due to the limited freedom of the ship unloader, the remaining coal pile in the cabin often requires manual pushing and raking operations by excavators. This process is time-consuming and labor-intensive, and the operation effect depends on the experience and skill level of the operator.

[0003] The application of existing automation technology in ship unloading and tank cleaning operations mainly focuses on the control and operation optimization of ship unloaders, while there is little research on the automated control of excavators. Although some studies have attempted to improve operation efficiency by automating pushers or excavators, due to the lack of high-precision environmental perception and intelligent path planning technology, these systems have limited adaptability in complex environments and it is difficult to achieve true unmanned driving and efficient operation. In addition, the existing system's collaborative control capabilities are insufficient, making it difficult to effectively avoid conflicts between devices in multi-device collaborative operations, thereby limiting the overall operating efficiency of the system.

[0004] With the rapid development of industrial automation and intelligent technology, especially in the fields of artificial intelligence, sensor fusion, path planning and digital twins, new technical support has been provided for the realization of unmanned driving and intelligent operation of excavators. Through multi-sensor fusion technology, excavators can obtain high-precision three-dimensional data of the operating environment in real time and achieve comprehensive perception of the environment; using intelligent path planning and optimization algorithms, excavators can generate optimal travel and operation paths based on real-time environmental data, and dynamically adjust the path to adapt to environmental changes; the introduction of digital twin technology can simulate and predict the excavator and its operation process in real time, provide operation optimization and risk warning, and further improve the reliability and operation efficiency of the system.

[0005] Hu Xinhai proposed a method, device and equipment for dynamic target detection and tracking of unmanned excavators (Huaqiao University. Method, device and equipment for dynamic target detection and tracking of unmanned excavators: CN202310982930.0[P].2023-09-12.) By adopting a more real-time voxel partitioning method and using Mahalanobis distance as a metric, the time-consuming problem of point cloud downsampling is solved, and small targets are better tracked, which is suitable for detection and tracking of unstructured roads of construction machinery. Guo Xiangyu proposed a perception system and excavator for unmanned excavators (Qingdao Huituo Intelligent Machinery Co., Ltd. A perception system and excavator for unmanned excavators: CN202121954409.9[P].2022-01-28.), which obtains information on targets near the excavator body by four single-line laser radars horizontally arranged on the front, back, left and right sides of the excavator body, effectively avoiding potential collision risks. The above systems mainly involve dynamic perception of the working environment, and do not involve trajectory planning and automatic operation. Wang Yiqi proposed an unmanned excavator and its remote management and monitoring system (Nanjing University of Information Science and Technology. An unmanned excavator and its remote management and monitoring system: CN202021899818.9[P].2021-06-01.). The system designs data acquisition modules, data transmission modules and central control modules. Remote management and monitoring can batch process and manage mining data, monitor mining conditions in real time, and improve mining efficiency and acceptance quality. The system realizes remote management and data synchronization, and does not involve automatic operation.

[0006] In view of the deficiencies in the prior art, the present invention proposes an efficient and safe unmanned intelligent excavator system, which aims to improve the automation level and operation efficiency of ship unloading and transportation operations, while reducing safety risks during the operation process. Summary of the invention

[0007] The present invention aims to solve the above-mentioned technical problems existing in the prior art and provide an unmanned intelligent excavator system.

[0008] An unmanned intelligent excavator system includes a hardware design module, an environmental perception and positioning module, a planning module, a central control communication module, a lower computer communication module and a central control module. The hardware design module obtains information from each sensor and enables each actuator through hardware construction; the environmental perception and positioning module can obtain three-dimensional point cloud data of the working environment in real time and perform high-precision positioning and environmental perception through multi-sensor fusion such as solid-state laser radar, inertial navigation system, camera, etc., and transmit the information to the planning module; the planning module generates the excavator's travel path and the robot arm's operating path based on environmental data and real-time feedback information, and dynamically adjusts the path through an optimization algorithm, and transmits it to the central control device through the central control communication module, while the upper computer mobile phone and other central control devices can perform remote control operations based on the transmitted information; the lower computer communication module receives the travel planning and robot arm path planning information, encodes the data information into a protocol, and sends it to the actuator for execution;

[0009] The hardware design module includes a sensor unit and a motion execution unit. The sensor unit obtains environmental information through a combination of multiple sensors, including lidar, inertial navigation system (IMU) and camera, which is used to perceive the surrounding environment of the excavator in real time. The motion actuator unit includes a travel drive system and a mechanical arm control system. The travel drive system controls the movement and steering of the excavator, and the mechanical arm control system controls the excavation, grabbing, coal stacking and other operations of the excavator, and can dynamically adjust the operation according to sensor feedback.

[0010] The environment perception and positioning module includes an environment perception unit and a three-dimensional positioning unit. The environment perception unit obtains the three-dimensional point cloud data and visual information of the working environment through the solid-state laser radar, inertial navigation system and camera installed on the top of the excavator, tracks and predicts the motion state of the excavator in combination with the inertial navigation data, and performs high-precision semantic segmentation and object recognition by fusing multi-source perception data. Based on the perception results, the three-dimensional positioning unit downsamples the point cloud data and extracts semantic feature points, and uses the ICP (iterative closest point) algorithm to achieve real-time positioning and posture estimation of the excavator, and transmits it to the path planning module for further processing;

[0011] The planning module includes a travel path planning unit, a robot arm trajectory planning unit, and a collaborative control unit. It performs travel path planning and robot arm motion path planning by receiving map information and posture data provided by the environmental perception and positioning module. The travel path planning unit includes path generation and path optimization. The path generation unit generates a preliminary excavator travel path using the Theta* algorithm, and plans the travel direction and speed of each section of the path in combination with the coal pile height data and terrain changes to ensure the stability and safety of the excavator's travel. The path optimization is based on the real-time updated environmental map, and dynamically adjusts and optimizes the path through the D Lite algorithm to avoid dynamic obstacles and reduce travel energy consumption. At the same time, the working path of the robot arm is adjusted to ensure the coordination and safety of various mechanisms in multi-task operations.

[0012] The robot arm motion path planning unit realizes precise control of the excavator robot arm, and the unit includes posture solution, path tracking and motion control; the posture solution uses the rope encoder and position sensor on the excavator robot arm to obtain the real-time posture data of each joint, and compares these data with the target path to generate posture error information; the path tracking uses the artificial intelligence algorithm to analyze the posture error, optimize the motion path of the robot arm, and adjust the motion path online through the gradient descent method; the motion control calculates the expected position of each joint at each time point based on the inverse kinematics algorithm, and adjusts the hydraulic system in real time through the PID controller to ensure that the movement of the robot arm is accurate, smooth and efficient;

[0013] The collaborative control unit designs a collaborative scheduling scheme based on hierarchical reinforcement learning, so that the excavator and the ship unloader can perform different tasks in parallel, and finally achieve the best efficiency. First, according to the current cabin perception information (height and distribution of coal piles, etc.) and the status information of the equipment (position, posture, speed, etc. of the ship unloader and excavator), the target cabin for the ship unloader operation is selected. During the operation, the coal unloading port of the cabin is divided into N different areas, and the ship unloader chooses to operate in N different areas in turn, and the pusher and rake chooses other areas to operate. The two are effectively isolated by discretizing the cabin space to avoid collision between the two. In this way, efficient collaboration between the ship unloader and the excavator is achieved to ensure that no equipment collision occurs.

[0014] The central control communication module includes an encoding unit, a communication unit and a heartbeat detection unit, which are used to realize real-time data interaction with the central control module of the planning module. The encoding unit encodes the transmitted data to ensure the integrity and accuracy of the data; the communication unit publishes sensor data, path planning information, robot arm status, etc. through the Topic mechanism of ROS, and exchanges data between the central control system and the lower computer through the TCP / IP protocol; the heartbeat detection unit is used to monitor the stability of the communication link. When the heartbeat signal is abnormal, the backup communication channel is triggered or emergency measures are taken to ensure the continuity and safety of the system operation;

[0015] The lower computer communication module receives real-time data from the environmental perception and positioning module and the planning module, integrates the data and transmits it to each actuator control unit, and at the same time feeds back the operating status of the actuator to the planning module and the central control module. The lower computer communication module includes a network connection unit and a data processing unit. The network connection unit realizes high-speed data exchange between the lower computer and the actuator through the EtherCAT bus to ensure the synchronous operation of each actuator; the data processing unit parses and formats the data received from the perception and positioning module and the path planning module, and generates control instructions to send to each actuator unit;

[0016] The central control module, including the host computer control unit, the mobile phone remote control unit and the digital twin unit, is used to achieve comprehensive control and monitoring of the unmanned intelligent excavator system. Through the coordinated work of various units, it ensures the efficient and safe operation of the excavator in various operating scenarios.

[0017] The host control unit is the core control center of the central control module, located in the operation monitoring room, responsible for remote control of the excavator, task scheduling and data analysis. It communicates with the excavator in real time through an industrial-grade computer, receives real-time data from various sensors, including position, speed, robotic arm status, etc., and remotely controls and schedules the excavator's walking path and robotic arm movement in combination with the task requirements. The processed data is published to each related module through the ROS Topic mechanism, and exchanges data with the lower computer through the TCP / IP protocol to ensure the stability and efficient operation of the system. The host computer also supports multi-task parallel operation and can manage the collaborative operation of multiple excavator units at the same time.

[0018] The mobile phone remote control unit communicates with the excavator in real time through a mobile application to achieve on-site or remote manual control, which is suitable for emergency operations in emergency situations or scenarios that require fine on-site operations. The mobile phone connects to the host computer or directly to the excavator through a wireless network, displays the real-time status and environmental perception data of the excavator through the application, and directly controls the excavator's walking, mechanical arm operation, etc. through graphical interface instructions; in an emergency, the mobile phone remote control unit can quickly take over the control of the excavator through a preset emergency operation mode, and provide real-time status feedback and alarm notifications. All operation instructions and feedback information are transmitted through encrypted communication protocols to ensure the security and timeliness of data.

[0019] The digital twin unit is a virtual simulation platform in the central control module, which is used to simulate and predict the excavator and its working environment in real time, and provide operation optimization and risk warning. By synchronizing the physical entity of the excavator with the virtual model, the performance of the excavator in different working scenarios can be monitored and predicted in real time. The digital twin unit includes virtual modeling, data synchronization and simulation prediction; virtual modeling generates a high-precision virtual model through digital modeling of the excavator and its working environment, and updates the geometric and dynamic parameters of the model in real time; data synchronization synchronizes the real-time sensor data of the excavator with the virtual model through the Internet of Things technology to ensure that the virtual model is consistent with the actual working conditions; simulation prediction uses large model prediction technology to predict the operating performance of the excavator in the future, identify potential risks and provide optimization suggestions, thereby improving operating efficiency and safety; BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying creative labor, other drawings obtained based on these drawings still belong to the scope of the present invention.

[0021] Figure 1 It is a block diagram of the overall structure of the system of the present invention.

[0022] Figure 2 This is a rendering of the perception module of the present invention.

[0023] Figure 3 It is the upper computer interface of the present invention.

[0024] Figure 4 It is the mobile phone APP interface of the present invention.

[0025] Figure 5 It is the digital twin end interface of the present invention.

[0026] Figure 6 This is a scene diagram of the automatic operation of the unmanned intelligent excavator of the present invention. DETAILED DESCRIPTION

[0027] The present invention is further described in detail below with reference to the accompanying drawings.

[0028] The implementation of the embodiments of the present invention has the following beneficial effects:

[0029] like Figure 1 The structure block diagram of the unmanned intelligent excavator system is shown. The present invention proposes an unmanned intelligent excavator system, including: a hardware design module, an environment perception and positioning module, a planning module, a central control communication module, a lower computer communication module and a central control module.

[0030] The hardware design module includes a sensor unit and a motion execution unit. The entire system uses a combination of multiple sensors to perceive the working environment in real time, obtain information from radar, camera and inertial sensors, and pre-process and fuse the data. According to the instructions issued by the central control module, the motion execution unit is controlled to work, including: walking drive control, robotic arm operation control and power control.

[0031] The environmental perception and positioning module includes an environmental perception unit and a three-dimensional positioning unit. The environmental perception unit receives information from the sensor unit, obtains data from the solid-state laser radar, camera and inertial navigation system (IMU), performs semantic segmentation and object recognition on the working environment through algorithms, calculates the distance between the excavator and surrounding obstacles, and transmits the information to the path planning module and the central control module for processing. Based on the perception results, the three-dimensional positioning unit downsamples the point cloud data and extracts semantic feature points, and uses the ICP (iterative closest point) algorithm to iteratively estimate the real-time posture of the excavator to generate a high-precision three-dimensional environmental map. Finally, the generated map and the excavator's posture information are transmitted to the path planning module.

[0032] The planning module plans the travel path and the robot arm motion path by receiving the three-dimensional map and posture data provided by the environmental perception and positioning module. The path planning module includes a travel path planning unit, a robot arm path planning unit and a collaborative control unit. The travel path planning unit uses the Theta algorithm to generate a preliminary walking path, and plans a smooth and safe driving path based on terrain changes and obstacle distribution; the robot arm path planning unit uses the inverse kinematics algorithm and posture solution technology to generate the robot arm's operating path; the collaborative control unit designs a collaborative scheduling solution based on hierarchical reinforcement learning, so that the excavator and the ship unloader can perform different tasks in parallel, and ultimately achieve optimal efficiency.

[0033] The central control communication module is to realize data interaction and command transmission with the path planning module, the robot control module and the digital twin system. The module includes a coding unit, a communication unit and a heartbeat detection unit. The coding unit encodes the transmitted data to ensure the integrity and accuracy of the data; the communication unit publishes sensor data, path planning information, robot arm status, etc. through the Topic mechanism of ROS, and exchanges data between the central control system and the lower computer through the TCP / IP protocol; the heartbeat detection unit is used to monitor the stability of the communication link. When the heartbeat signal is abnormal, the backup communication channel is triggered or emergency measures are taken to ensure the continuity and safety of the system operation.

[0034] The lower computer communication module receives real-time data from the environment perception and positioning module and the path planning module, integrates the data and transmits it to each actuator control unit, and at the same time feeds back the operating status of the actuator to the path planning module and the central control system. The lower computer communication module includes a network connection unit and a data processing unit. The network connection unit realizes high-speed data exchange between the lower computer and the actuator through the EtherCAT bus to ensure the synchronous operation of each actuator; the data processing unit parses and formats the received data, and generates control instructions to send to each actuator unit.

[0035] The central control module includes a host control unit, a mobile phone remote control unit and a digital twin unit. The host control unit is the core of the central control module. It communicates with the excavator in real time through an industrial-grade computer and is responsible for remote control of the excavator, task scheduling and data analysis. The mobile phone remote control unit communicates with the excavator in real time through a mobile application to achieve on-site or remote manual control, which is suitable for emergency operations in emergency situations. The digital twin unit simulates and predicts the excavator and its operating environment in real time through virtual modeling and real-time data synchronization, providing operation optimization and risk warning.

[0036] Furthermore, the execution process of this system is as follows:

[0037] 1. Build hardware design modules to form an unmanned intelligent excavator system.

[0038] 2. After the unmanned excavator central control system is started, the environmental perception unit starts automatically and begins to detect the surrounding environment data; after the central control module receives the start signal, it turns on the automatic operation mode and sends the automatic mode command to the central control communication module.

[0039] 3. After receiving the automatic mode command, the central control communication module starts the perception and positioning module and the path planning module to obtain the excavator's posture information in real time and generate the walking path and the robotic arm operation path.

[0040] 4. The perception and positioning module performs three-dimensional modeling and posture estimation of the working environment, and transmits the generated three-dimensional map, excavator posture information and environmental perception data to the central control communication module in real time.

[0041] 5. The central control communication module transmits the walking path and robotic arm operation path generated by the path planning module to the host computer and mobile phone. The operator can perform remote control operations through the host computer or mobile phone. At the same time, the planned path is transmitted to the digital twin end, and combined with big data analysis and artificial intelligence algorithms, the operating status and potential faults of the excavator are predicted to provide decision support for remote operation and maintenance and operation strategy optimization.

[0042] 6. The path planning module dynamically adjusts the path planning according to the information fed back by the central control communication module, and sends the updated path information to the lower computer communication module through the central control communication module.

[0043] 7. After receiving the planning information of the travel path and the robot arm path, the lower computer communication module sends it to each actuator unit. The actuator unit performs the operation according to the control instructions and feeds back the operation status to the lower computer communication module.

[0044] 8. The lower computer communication module feeds back the operating status of the actuator to the path planning module and the central control module. At the same time, the central control communication module continuously monitors the stability of the communication link and the accuracy of data transmission.

[0045] 9. Repeat steps (4) to (8) until the task is completed and the system automatically exits the operation mode and closes all programs.

[0046] The unmanned intelligent excavator system of this embodiment realizes efficient and safe automated operation through multi-sensor perception fusion, precise path planning and intelligent control. It is suitable for ship unloading, cabin cleaning and coal stack loading and unloading operations in thermal power plants and medium and large bulk cargo terminals. It significantly improves operation efficiency and safety, solves the problems of low efficiency and high risk in existing manual operations, and has broad application prospects.

[0047] The contents described in the embodiments of this specification are merely an enumeration of the implementation forms of the inventive concept. The protection scope of the present invention should not be regarded as limited to the specific forms described in the embodiments. The protection scope of the present invention also extends to equivalent technical means that can be conceived by those skilled in the art based on the inventive concept.

Claims

1. An unmanned intelligent excavator system, characterized in that: It includes hardware design module, environment perception and positioning module, planning module, central control communication module, lower computer communication module and central control module. The hardware design module obtains information from each sensor and enables each actuator through hardware construction; the environment perception and positioning module can obtain the three-dimensional point cloud data of the working environment in real time and perform high-precision positioning and environment perception through multi-sensor fusion such as solid-state laser radar, inertial navigation system, camera, etc., and transmit the information to the planning module; the planning module generates the excavator's travel path and the robot's operating path based on environmental data and real-time feedback information, and dynamically adjusts the path through the optimization algorithm, and transmits it to the central control device through the central control communication module. At the same time, the upper computer mobile phone and other central control devices can be remotely controlled according to the transmitted information; the lower computer communication module receives the travel planning and robot arm path planning information, encodes the data information into a protocol, and sends it to the actuator for execution; The hardware design module includes a sensor unit and a motion execution unit. The sensor unit obtains environmental information through a combination of multiple sensors, including lidar, inertial navigation system (IMU) and camera, which is used to perceive the surrounding environment of the excavator in real time. The motion actuator unit includes a travel drive system and a mechanical arm control system. The travel drive system controls the movement and steering of the excavator, and the mechanical arm control system controls the excavation, grabbing, coal stacking and other operations of the excavator, and can dynamically adjust the operation according to sensor feedback. The environment perception and positioning module includes an environment perception unit and a three-dimensional positioning unit. The environment perception unit obtains the three-dimensional point cloud data and visual information of the working environment through the solid-state laser radar, inertial navigation system and camera installed on the top of the excavator, tracks and predicts the motion state of the excavator in combination with the inertial navigation data, and performs high-precision semantic segmentation and object recognition by fusing multi-source perception data. Based on the perception results, the three-dimensional positioning unit downsamples the point cloud data and extracts semantic feature points, and uses the ICP (iterative closest point) algorithm to achieve real-time positioning and posture estimation of the excavator, and transmits it to the path planning module for further processing; The path planning module includes a travel path planning unit, a robot arm trajectory planning unit, and a collaborative control unit. It performs travel path planning and robot arm motion path planning by receiving map information and posture data provided by the environmental perception and positioning module. The travel path planning unit includes path generation and path optimization. The path generation unit generates a preliminary excavator travel path using the Theta* algorithm, and plans the travel direction and speed of each section of the path in combination with the coal pile height data and terrain changes to ensure the stability and safety of the excavator's travel. The path optimization is based on the real-time updated environmental map, and dynamically adjusts and optimizes the path through the D Lite algorithm to avoid dynamic obstacles and reduce travel energy consumption. At the same time, the working path of the robot arm is adjusted to ensure the coordination and safety of various mechanisms in multi-task operations. The robot arm motion path planning unit realizes precise control of the excavator robot arm, and the unit includes posture solution, path tracking and motion control; the posture solution uses the pull rope encoder and position sensor on the excavator robot arm to obtain the real-time posture data of each joint, and compares these data with the target path to generate posture error information; Path tracking uses artificial intelligence algorithms to analyze posture errors, optimize the motion path of the robot, and adjust the motion path online through the gradient descent method; motion control calculates the expected position of each joint at each time point based on the inverse kinematics algorithm, and adjusts the hydraulic system in real time through the PID controller to ensure that the robot moves accurately, smoothly and efficiently; The collaborative control unit designs a collaborative scheduling scheme based on hierarchical reinforcement learning, so that the excavator and the ship unloader can perform different tasks in parallel, and finally achieve the best efficiency. First, according to the current cabin perception information (height and distribution of coal piles, etc.) and the status information of the equipment (position, posture, speed, etc. of the ship unloader and excavator), the target cabin for the ship unloader operation is selected. During the operation, the coal unloading port of the cabin is divided into N different areas, and the ship unloader chooses to operate in N different areas in turn, and the pusher and rake chooses other areas to operate. The two are effectively isolated by discretizing the cabin space to avoid collision between the two. In this way, efficient collaboration between the ship unloader and the excavator is achieved to ensure that no equipment collision occurs. The central control communication module includes an encoding unit, a communication unit, and a heartbeat detection unit, which are used to realize real-time data interaction with the central control module of the planning module. The encoding unit encodes the transmitted data to ensure the integrity and accuracy of the data; the communication unit publishes sensor data, path planning information, robot arm status, etc. through the Topic mechanism of ROS, and exchanges data between the central control system and the lower computer through the TCP / IP protocol; The heartbeat detection unit is used to monitor the stability of the communication link. When the heartbeat signal is abnormal, it triggers the backup communication channel or takes emergency measures to ensure the continuity and safety of system operation. The lower computer communication module receives real-time data from the environmental perception and positioning module and the planning module, integrates the data and transmits it to each actuator control unit, and at the same time feeds back the operating status of the actuator to the planning module and the central control module. The lower computer communication module includes a network connection unit and a data processing unit. The network connection unit realizes high-speed data exchange between the lower computer and the actuator through the EtherCAT bus to ensure the synchronous operation of each actuator; the data processing unit parses and formats the data received from the perception and positioning module and the path planning module, and generates control instructions to send to each actuator unit; The central control module, including the host computer control unit, the mobile phone remote control unit and the digital twin unit, is used to achieve comprehensive control and monitoring of the unmanned intelligent excavator system. Through the coordinated work of various units, it ensures the efficient and safe operation of the excavator in various operating scenarios. The host control unit is the core control center of the central control module, located in the operation monitoring room, responsible for remote control of the excavator, task scheduling and data analysis. It communicates with the excavator in real time through an industrial-grade computer, receives real-time data from various sensors, including position, speed, robotic arm status, etc., and remotely controls and schedules the excavator's walking path and robotic arm movement in combination with the task requirements. The processed data is published to each related module through the ROS Topic mechanism, and exchanges data with the lower computer through the TCP / IP protocol to ensure the stability and efficient operation of the system. The host computer also supports multi-task parallel operation and can manage the collaborative operation of multiple excavator units at the same time. The mobile phone remote control unit communicates with the excavator in real time through a mobile application to achieve on-site or remote manual control, which is suitable for emergency operations in emergency situations or scenarios that require fine on-site operations. The mobile phone connects to the host computer or directly to the excavator through a wireless network, displays the real-time status and environmental perception data of the excavator through the application, and directly controls the excavator's walking, mechanical arm operation, etc. through graphical interface instructions; in an emergency, the mobile phone remote control unit can quickly take over the control of the excavator through a preset emergency operation mode, and provide real-time status feedback and alarm notifications. All operation instructions and feedback information are transmitted through encrypted communication protocols to ensure the security and timeliness of data. The digital twin unit is a virtual simulation platform in the central control module, which is used to simulate and predict the excavator and its working environment in real time, and provide operation optimization and risk warning. By synchronizing the physical entity of the excavator with the virtual model, the performance of the excavator in different working scenarios can be monitored and predicted in real time. The digital twin unit includes virtual modeling, data synchronization and simulation prediction; virtual modeling generates a high-precision virtual model through digital modeling of the excavator and its working environment, and updates the geometric and dynamic parameters of the model in real time; data synchronization synchronizes the real-time sensor data of the excavator with the virtual model through the Internet of Things technology to ensure that the virtual model is consistent with the actual working conditions; simulation prediction uses large model prediction technology to predict the performance of the excavator in the future, identify potential risks and provide optimization suggestions, thereby improving work efficiency and safety.

2. The unmanned intelligent excavator system according to claim 1, characterized in that: The path generation unit of the path planning module performs preliminary path planning based on the three-dimensional map of the cabin or coal shed by combining the Theta* algorithm and the A algorithm, calculates the optimal movement trajectory in the walking path based on the morphological characteristics of the coal pile and the terrain elevation data, and identifies and avoids high-risk areas.

3. The unmanned intelligent excavator system according to claim 1, characterized in that: The posture calculation unit of the robotic arm control module obtains the posture information of each joint of the robotic arm in real time through the rope encoder, laser rangefinder and IMU sensor, generates real-time adjustment instructions based on the deviation between this information and the planned path, and dynamically adjusts the opening of the hydraulic cylinder through the feedback control system to ensure the smoothness and precision of the robotic arm movement.

4. The unmanned intelligent excavator system according to claim 1, characterized in that: The virtual modeling unit of the digital twin system uses multi-body dynamics modeling technology to build a high-precision virtual model of the excavator and updates its status through real-time data. The simulation prediction unit combines big data analysis with artificial intelligence algorithms to predict the operating status and potential failures of the excavator, providing decision support for remote operation and maintenance and operation strategy optimization.

5. The unmanned intelligent excavator system according to claim 1, characterized in that: The collaborative control module realizes collaborative control between the ship unloader and the excavator through a collaborative scheduling scheme based on hierarchical reinforcement learning, ensures the coordination of the operations of the two during the ship unloading process, and dynamically adjusts the operating rhythm of the equipment through an adaptive control algorithm to cope with the uncertainty in the operating environment.

6. The unmanned intelligent excavator system according to claim 1, characterized in that: The central control module realizes remote control operation through the host computer, on-site remote control operation through the mobile phone APP, and automatic operation through the controller and wireless communication equipment equipped on the excavator.

Images