Ship distribution robot position monitoring and distribution management system

Abstract

The application discloses a marine distribution robot position monitoring and distribution management system, comprising a multi-source positioning fusion module, a three-dimensional cabin map navigation module, a reinforcement learning path optimization module, a task scheduling cooperation module, a multi-device state monitoring module, a user interaction and management module and a multi-protocol communication and data encryption module. The application can significantly improve the material distribution efficiency in the ship environment, reduce the long-term labor cost by reducing the manual participation, improve the operation safety by dynamic obstacle avoidance and path optimization, and ensure the health and safety of materials by reducing the contact links.

Description

Technical Field

[0001] This invention belongs to the field of intelligent ship equipment and automated logistics distribution technology, specifically a location monitoring and distribution management system for ship delivery robots. Background Technology

[0002] Traditional shipboard supply delivery relies primarily on manual labor, especially on large cruise ships, ocean-going cargo ships, or research vessels. The enclosed and complex layout of the ship's cabins makes manual delivery routes long and inefficient. Labor costs are continuously rising, becoming even more pronounced during long voyages or when staff shortages occur. Simultaneously, frequent personnel movement increases collision and safety risks, and repeated contact during delivery poses hygiene hazards to food or supplies. Existing land-based and shipboard delivery robot systems largely depend on single GPS positioning and static maps, failing to address the shielding of satellite signals by the ship's metal structure, lacking real-time path adjustment capabilities for dynamic obstacles, and lacking multi-robot task collaboration and ship cabin adaptability.

[0003] Furthermore, whether in land-based hotels or on ships, current systems generally lack visualization capabilities for end users—users receiving deliveries cannot directly view the robot's real-time location, operating status, and estimated arrival time, resulting in a lack of information transparency and a positive experience during the waiting process. This problem is particularly prominent in long-distance, multi-floor, or multi-cabin deliveries.

[0004] Therefore, to address the above issues, a marine delivery robot location monitoring and delivery management system is provided. Summary of the Invention

[0005] To address the aforementioned problems in the existing technology, this invention provides a marine delivery robot location monitoring and delivery management system, which can significantly improve the efficiency of material delivery in a marine environment, reduce human intervention and lower long-term labor costs, improve operational safety through dynamic obstacle avoidance and path optimization, and ensure the hygiene and safety of materials by reducing contact links.

[0006] The technical solution to achieve the above objectives is: A marine delivery robot location monitoring and delivery management system, including: The multi-source positioning fusion module is used to fuse satellite positioning data with data from sensors inside the ship's cabin, and then output centimeter-level real-time positioning information to the three-dimensional ship's cabin map navigation module for position matching, and synchronize it to the multi-device status monitoring module to record the position status. The 3D cabin map navigation module provides environmental data support for the reinforcement learning path optimization module through positioning information and a built-in high-precision 3D cabin map. The reinforcement learning path optimization module is used to generate the optimal path strategy based on environmental information and task parameters allocated by the task scheduling and coordination module, and then feed it back to the task scheduling and coordination module. The task scheduling and coordination module is used to receive task information created by the user interaction and management module, combine it with the real-time robot status feedback from the multi-device status monitoring module, allocate tasks to the robot through intelligent scheduling algorithm, and send path strategies to the robot for execution. The multi-device status monitoring module is used to collect the robot's battery level, position, speed, network status, and task execution data in real time. When an anomaly occurs, it triggers an alarm and synchronizes the data to the task scheduling and coordination module and the user interaction and management module. The user interaction and management module provides PC and mobile interfaces, supports users to create tasks and send them to the task scheduling and collaboration module, and receives robot status data from the multi-device status monitoring module to enable path preview, status monitoring, alarm handling and historical record query. The multi-protocol communication and data encryption module is used to ensure the secure transmission of data and commands between the multi-source positioning fusion module, the 3D ship cabin map navigation module, the reinforcement learning path optimization module, the task scheduling and coordination module, the multi-device status monitoring module, and the user interaction and management module through AES / RSA encryption.

[0007] Preferably, the multi-source positioning fusion module includes: The satellite positioning receiving unit integrates BeiDou / GPS dual satellite system signal reception to provide absolute positioning data for ships in open-air environments. The cabin interior positioning unit integrates an inertial measurement unit and odometer data processing, and is used in conjunction with ultrasonic sensors to achieve environmental perception and relative positioning within the cabin. The data fusion and error correction unit is used to fuse multi-source data through the Kalman filter algorithm, correct positioning errors in real time, and finally output centimeter-level real-time positioning information.

[0008] Preferably, the three-dimensional ship cabin map navigation module includes: The map building unit is used to automatically build a high-precision 3D ship cabin map using SLAM (Simultaneous Localization and Mapping) technology, and then perform map updates, obstacle marking, and area division. The map visualization unit is used to enable map zooming, rotation, and layered display functions, and to display path previews and robot positions in real time. The navigation and guidance unit is used to provide the robot with real-time path planning and direction guidance, autonomous obstacle avoidance, and dynamic path adjustment.

[0009] The preferred reinforcement learning path optimization module includes: The environmental modeling unit is used to model the cabin environment as a Markov decision process and dynamically update environmental parameters and obstacle information. The reinforcement learning algorithm unit is used to continuously learn and optimize delivery route strategies through deep reinforcement learning algorithms. The path evaluation unit is used to evaluate path efficiency, distance, and safety metrics, generate optimal path strategies, and update them in real time.

[0010] Preferably, the task scheduling and coordination module includes: The task management unit is used for task creation, assignment, modification, and deletion, and enables task priority sorting and resource allocation; The robot scheduling unit is used to monitor the robot status in real time, realize multi-robot collaborative operation and load balancing. The robot status includes the robot's position, power level, and load. The dynamic adjustment unit is used to dynamically adjust task allocation based on task progress and robot status, and supports task pause, resumption and reallocation.

[0011] Preferably, the multi-device status monitoring module includes: The status acquisition unit is used to collect robot power, position, speed and other operating parameters in real time, and to monitor the robot's task execution status and environmental data. An abnormal alarm unit is used to set parameter thresholds and provide real-time alarms when abnormal situations occur. The alarm methods include audible and visual alarms and mobile notifications. The data analysis unit is used to analyze robot operation data, predict equipment failures, provide maintenance suggestions, and generate operation reports.

[0012] Preferably, the user interaction and management module includes: The task operation unit provides a task creation and management interface for PC and mobile devices, and supports batch import and export of tasks. The status monitoring unit is used to display the robot's position, status and task progress in real time, and provides historical task query and statistical analysis functions. The system management unit supports user permission management and system settings, and provides system log recording and backup and recovery functions.

[0013] Compared with the prior art, the beneficial effects of the present invention are: In a marine environment, this invention can significantly improve the efficiency of material distribution, reduce human intervention and lower long-term labor costs, improve operational safety through dynamic obstacle avoidance and path optimization, and ensure the hygiene and safety of materials by reducing contact links. This invention provides end users with a visual interface that allows them to view the location, operating status, and estimated arrival time of the delivery robot in real time on their mobile phones or terminal screens, effectively improving the waiting experience and service transparency. This invention is also scalable and can be applied to the distribution of medicines, spare parts and other materials. It also has full-process data traceability and visual operation analysis functions, which helps to improve the level of ship intelligence. Attached Figure Description

[0014] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a block diagram of the marine delivery robot location monitoring and delivery management system of the present invention; Figure 2 This is a detailed module diagram of the multi-source localization fusion module in this invention; Figure 3 This is a detailed module diagram of the three-dimensional ship cabin map navigation module in this invention; Figure 4 This is a specific module diagram of the reinforcement learning path optimization module in this invention; Figure 5 This is a detailed module diagram of the task scheduling and coordination module in this invention; Figure 6 This is a detailed module diagram of the multi-device status monitoring module in this invention; Figure 7 This is a specific module diagram of the user interaction and management module in this invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] like Figure 1 As shown, the marine delivery robot location monitoring and delivery management system includes: a multi-source positioning fusion module 1, a 3D cabin map navigation module 2, a reinforcement learning path optimization module 3, a task scheduling and collaboration module 4, a multi-device status monitoring module 5, a user interaction and management module 6, and a multi-protocol communication and data encryption module 7.

[0017] The multi-source positioning fusion module 1 is used to fuse satellite positioning data with data from sensors inside the ship's cabin, and then output centimeter-level real-time positioning information to the three-dimensional ship's cabin map navigation module 2 for position matching, and synchronize it to the multi-device status monitoring module 5 to record the position status.

[0018] like Figure 2As shown, the multi-source positioning fusion module 1 includes: a satellite positioning receiving unit 11, a cabin interior positioning unit 12, and a data fusion and error correction unit 13; Satellite positioning receiving unit 11 integrates Beidou / GPS dual satellite system signal reception and is used to provide absolute positioning data for ships in open-air environments; The cabin interior positioning unit 12 integrates an inertial measurement unit and odometer data processing, and is used to combine ultrasonic sensors to realize cabin environment perception and relative positioning. The data fusion and error correction unit 13 is used to perform multi-source data fusion through the Kalman filter algorithm, correct positioning errors in real time, and finally output centimeter-level real-time positioning information.

[0019] The 3D cabin map navigation module 2 is used to provide environmental data support for the reinforcement learning path optimization module 3 through positioning information and the built-in high-precision 3D cabin map.

[0020] like Figure 3 As shown, the 3D ship cabin map navigation module 2 includes: a map building unit 21, a map visualization unit 22, and a navigation guidance unit 23; Map building unit 21 is used to automatically build a high-precision three-dimensional ship cabin map using SLAM technology, and then perform map updates, obstacle marking, and area division. The map visualization unit 22 is used to realize map zooming, rotation, and layered display functions, and to display path preview and robot position in real time; The navigation and guidance unit 23 is used to provide the robot with real-time path planning and direction guidance, autonomous obstacle avoidance and dynamic path adjustment.

[0021] The reinforcement learning path optimization module 3 is used to generate the optimal path strategy based on environmental information and task parameters allocated by the task scheduling and coordination module 4, and then feed it back to the task scheduling and coordination module 4.

[0022] like Figure 4 As shown, the reinforcement learning path optimization module 3 includes: an environment modeling unit 31, a reinforcement learning algorithm unit 32, and a path evaluation unit 33; The environmental modeling unit 31 is used to model the cabin environment as a Markov decision process and dynamically update environmental parameters and obstacle information. The reinforcement learning algorithm unit 32 is used to continuously learn and optimize delivery route strategies through deep reinforcement learning algorithms. The path evaluation unit 33 is used to evaluate path efficiency, distance, and safety indicators, generate the optimal path strategy, and update it in real time.

[0023] The task scheduling and coordination module 4 is used to receive task information created by the user interaction and management module 6, combine it with the real-time robot status fed back by the multi-device status monitoring module 5, allocate tasks to the robot through an intelligent scheduling algorithm, and send the path strategy to the robot for execution.

[0024] like Figure 5 As shown, the task scheduling and coordination module 4 includes: a task management unit 41, a robot scheduling unit 42, and a dynamic adjustment unit 43; The task management unit 41 is used for task creation, assignment, modification and deletion, and implements task priority sorting and resource allocation; The robot scheduling unit 42 is used to monitor the robot status in real time and realize multi-robot collaborative operation and load balancing. The robot status includes the robot's position, power level, and load. The dynamic adjustment unit 43 is used to dynamically adjust the task allocation according to the task progress and robot status, and supports task pause, resumption and reallocation.

[0025] The multi-device status monitoring module 5 is used to collect the robot's power, position, speed, network status and task execution data in real time. When an abnormality occurs, it triggers an alarm and synchronizes it to the task scheduling and collaboration module 4 and the user interaction and management module 6.

[0026] like Figure 6 As shown, the multi-device status monitoring module 5 includes: a status acquisition unit 51, an abnormal alarm unit 52, and a data analysis unit 53; The status acquisition unit 51 is used to collect the robot's battery level, position, speed and operating parameters in real time, and to monitor the robot's task execution status and environmental data. An abnormal alarm unit 52 is used to set parameter thresholds and to issue a real-time alarm when an abnormal situation occurs. The alarm methods include audible and visual alarms and mobile terminal notifications. The data analysis unit 53 is used to analyze robot operation data, predict equipment failures, provide maintenance suggestions, and generate operation reports.

[0027] The user interaction and management module 6 provides PC and mobile interfaces, supports users to create tasks and send them to the task scheduling and collaboration module 4, and receives robot status data from the multi-device status monitoring module 5 to enable path preview, status monitoring, alarm handling and historical record query.

[0028] like Figure 7 As shown, the user interaction and management module 6 includes: a task operation unit 61, a status monitoring unit 62, and a system management unit 63; The task operation unit 61 is used to provide a task creation and management interface for PC and mobile terminals, and supports batch import and export of tasks. The status monitoring unit 62 is used to display the robot's position, status and task progress in real time, and provides historical task query and statistical analysis functions. System management unit 63 is used to support user permission management and system settings, and provides system log recording and backup and recovery functions.

[0029] The multi-protocol communication and data encryption module 7 is used to ensure the secure transmission of data and commands between the multi-source positioning fusion module 1, the 3D cabin map navigation module 2, the reinforcement learning path optimization module 3, the task scheduling and coordination module 4, the multi-device status monitoring module 5, and the user interaction and management module 6 through AES / RSA encryption. It supports communication protocols such as Wi-Fi, Bluetooth, and ZigBee.

[0030] Complete system operation steps: I. Preliminary Preparation Stage Step 1: System Deployment and Calibration Install delivery robots and related hardware equipment inside the ship; High-precision 3D ship cabin map constructed based on SLAM technology; Complete the initial robot positioning and parameter calibration; Step 2: User Permission Configuration Assign system operation permissions to different user roles (crew members, managers, maintenance personnel); Configure the user interface for PC and mobile devices; Step 3: Testing and Verification Conduct no-load and load tests on the robot; Verify navigation accuracy, obstacle avoidance capabilities, and mission execution efficiency; Optimize system parameters to adapt to the special environment of ships; II. Task Creation and Issuance Phase Step 1: User creates task Users can log in to the user interaction and management module 6 via PC or mobile device; Fill in the delivery task information, including origin, destination, type of goods, priority, etc.; Step 2: Task Information Transmission User interaction and management module 6 transmits task information to task scheduling and collaboration module 4 after encryption via multi-protocol communication and data encryption module 7. The multi-protocol communication and data encryption module 7 records task information and generates a unique task ID; Step 3: Task Preprocessing Task scheduling and coordination module 4 performs preliminary processing of tasks, confirming the completeness and rationality of task information; If the task information is incomplete, a request to complete the information is sent to the user interaction and management module 6. III. Task Allocation and Path Planning Phase Step 1: Robot Status Inquiry The task scheduling and coordination module 4 queries the multi-device status monitoring module 5 for the real-time status of all robots through the multi-protocol communication and data encryption module 7; The multi-device status monitoring module 5 provides feedback on information such as the robot's location, battery level, load, and network status; Step 2: Intelligent Task Allocation The task scheduling and coordination module 4 is based on an intelligent scheduling algorithm, which combines task priority and robot status to select the most suitable robot to execute the task; After identifying the robot to perform the task, bind the task information to the robot ID; Step 3: Environmental Data Acquisition Task scheduling and coordination module 4 requests 3D map data of the current task area from 3D cabin map navigation module 2; The 3D ship cabin map navigation module 2 returns a high-precision map and real-time environmental information; Step 4: Optimal Path Generation The 3D cabin map navigation module 2 sends environmental data to the reinforcement learning path optimization module 3; The reinforcement learning path optimization module 3 generates the optimal path strategy through deep reinforcement learning algorithms. The path strategy includes the main path and backup paths to deal with unexpected situations. Step 5: Route Confirmation and Distribution The reinforcement learning path optimization module 3 feeds back the path strategy to the task scheduling and coordination module 4; After the task scheduling and coordination module 4 confirms the rationality of the path, it sends the task information and path strategy to the execution robot through the multi-protocol communication and data encryption module 7. IV. Task Execution and Monitoring Phase Step 1: The robot receives the task. The robot receives task information and path strategy through the multi-protocol communication and data encryption module 7. The robot system analyzes the task and confirms its execution; Step 2: Real-time positioning and navigation The robot activates the multi-source positioning fusion module 1, which combines satellite positioning and data from sensors inside the ship's cabin to achieve centimeter-level real-time positioning. The 3D cabin map navigation module 2 provides real-time navigation guidance for the robot based on positioning information and path strategy; Step 3: Task Execution Process The robot executes delivery tasks according to a path strategy, automatically avoiding obstacles, taking elevators, and opening and closing doors. The multi-device status monitoring module 5 collects the robot's operating status and task execution data in real time; Step 4: Status Feedback and Monitoring The multi-device status monitoring module 5 feeds back the robot status and task progress to the task scheduling and collaboration module 4 and the user interaction and management module 6 through the multi-protocol communication and data encryption module 7; Users can monitor the robot's location, speed, battery level, and task execution status in real time through the user interaction and management module. Step 5: Exception Handling and Adjustment If the robot encounters an abnormal situation (such as insufficient power, inability to pass obstacles, or network interruption), the multi-device status monitoring module 5 will trigger an alarm and notify the task scheduling and collaboration module 4 and the user interaction and management module 6. The task scheduling and coordination module 4 automatically adjusts task allocation or generates new path strategies based on the type of exception to ensure that tasks continue to execute. V. Task Completion and Summary Phase Step 1: Task completion confirmation After the robot completes the delivery task, it sends a task completion signal to the task scheduling and coordination module 4. Task scheduling and coordination module 4 confirms the task completion status and updates the task record; Step 2: Data Summary and Analysis The multi-device status monitoring module 5 summarizes the task execution data and robot status data; Data is transmitted to the user interaction and management module 6 for storage and analysis via multi-protocol communication and data encryption module 7; Step 3: Task Recording and Query The User Interaction and Management Module 6 updates the task history, including information such as task time, executing robot, path, and time taken. Users can check task history at any time to conduct performance evaluation and optimization analysis; Step 4: System Optimization and Iteration The system periodically analyzes historical task data to optimize the algorithm model of reinforcement learning path optimization module 3; Based on user feedback and actual operation, system parameters were adjusted to improve overall delivery efficiency.

[0031] Finally, it should be noted that the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A location monitoring and delivery management system for marine delivery robots, characterized in that, include: The multi-source positioning fusion module is used to fuse satellite positioning data with data from sensors inside the ship's cabin, and then output centimeter-level real-time positioning information to the three-dimensional ship's cabin map navigation module for position matching, and synchronize it to the multi-device status monitoring module to record the position status. The 3D cabin map navigation module provides environmental data support for the reinforcement learning path optimization module through positioning information and a built-in high-precision 3D cabin map. The reinforcement learning path optimization module is used to generate the optimal path strategy based on environmental information and task parameters allocated by the task scheduling and coordination module, and then feed it back to the task scheduling and coordination module. The task scheduling and coordination module is used to receive task information created by the user interaction and management module, combine it with the real-time robot status feedback from the multi-device status monitoring module, allocate tasks to the robot through intelligent scheduling algorithm, and send path strategies to the robot for execution. The multi-device status monitoring module is used to collect the robot's battery level, position, speed, network status, and task execution data in real time. When an anomaly occurs, it triggers an alarm and synchronizes the data to the task scheduling and coordination module and the user interaction and management module. The user interaction and management module provides PC and mobile interfaces, supports users to create tasks and send them to the task scheduling and collaboration module, and receives robot status data from the multi-device status monitoring module to enable path preview, status monitoring, alarm handling and historical record query. The multi-protocol communication and data encryption module is used to ensure the secure transmission of data and commands between the multi-source positioning fusion module, the 3D ship cabin map navigation module, the reinforcement learning path optimization module, the task scheduling and coordination module, the multi-device status monitoring module, and the user interaction and management module through AES / RSA encryption.

2. The marine delivery robot location monitoring and delivery management system according to claim 1, characterized in that, The multi-source positioning fusion module includes: The satellite positioning receiving unit integrates BeiDou / GPS dual satellite system signal reception to provide absolute positioning data for ships in open-air environments. The cabin interior positioning unit integrates an inertial measurement unit and odometer data processing, and is used in conjunction with ultrasonic sensors to achieve environmental perception and relative positioning within the cabin. The data fusion and error correction unit is used to fuse multi-source data through the Kalman filter algorithm, correct positioning errors in real time, and finally output centimeter-level real-time positioning information.

3. The marine delivery robot location monitoring and delivery management system according to claim 1, characterized in that, The 3D ship cabin map navigation module includes: The map building unit is used to automatically build a high-precision 3D ship cabin map using SLAM technology, and then perform map updates, obstacle marking, and area division. The map visualization unit is used to enable map zooming, rotation, and layered display functions, and to display path previews and robot positions in real time. The navigation and guidance unit is used to provide the robot with real-time path planning and direction guidance, autonomous obstacle avoidance, and dynamic path adjustment.

4. The marine delivery robot location monitoring and delivery management system according to claim 1, characterized in that, The reinforcement learning path optimization module includes: The environmental modeling unit is used to model the cabin environment as a Markov decision process and dynamically update environmental parameters and obstacle information. The reinforcement learning algorithm unit is used to continuously learn and optimize delivery route strategies through deep reinforcement learning algorithms. The path evaluation unit is used to evaluate path efficiency, distance, and safety metrics, generate optimal path strategies, and update them in real time.

5. The marine delivery robot location monitoring and delivery management system according to claim 1, characterized in that, The task scheduling and coordination module includes: The task management unit is used for task creation, assignment, modification, and deletion, and enables task priority sorting and resource allocation; The robot scheduling unit is used to monitor the robot status in real time, realize multi-robot collaborative operation and load balancing. The robot status includes the robot's position, power level, and load. The dynamic adjustment unit is used to dynamically adjust task allocation based on task progress and robot status, and supports task pause, resumption, and reallocation.

6. The marine delivery robot location monitoring and delivery management system according to claim 1, characterized in that, The multi-device status monitoring module includes: The status acquisition unit is used to collect robot power, position, speed and other operating parameters in real time, and to monitor the robot's task execution status and environmental data. An abnormal alarm unit is used to set parameter thresholds and provide real-time alarms when abnormal situations occur. The alarm methods include audible and visual alarms and mobile notifications. The data analysis unit is used to analyze robot operation data, predict equipment failures, provide maintenance suggestions, and generate operation reports.

7. The marine delivery robot location monitoring and delivery management system according to claim 1, characterized in that, The user interaction and management module includes: The task operation unit provides a task creation and management interface for PC and mobile devices, and supports batch import and export of tasks. The status monitoring unit is used to display the robot's position, status and task progress in real time, and provides historical task query and statistical analysis functions. The system management unit supports user permission management and system settings, and provides system log recording and backup and recovery functions.

Images