Disinfection robot dynamic path planning embedded system for complex environment

Abstract

This invention discloses an embedded system for dynamic path planning of a disinfection robot in complex environments, belonging to the field of path planning technology. It utilizes a data acquisition module to collect environmental data in real time, a dynamic map building module to construct a dynamic map using real-time positioning and mapping technology, an intelligent planning module to perform optimal global path planning based on the constructed dynamic map, calculating the optimal global path from the starting point to the target point, an obstacle avoidance module to avoid sudden dynamic obstacles while maintaining the original path, and dynamically adjusting the robot's route, using a local obstacle avoidance algorithm. An intelligent adjustment module adjusts the robot's speed and direction in real time based on the optimal global path and the dynamic adjustment results. By combining global path planning with intelligent control, the robot can not only plan an initial path but also adjust the path in real time according to the dynamic environment during execution, effectively improving the robot's adaptability in dynamic environments.

Description

Technical Field

[0001] This invention relates to the field of path planning technology, and more specifically to an embedded system for dynamic path planning of disinfection robots in complex environments. Background Technology

[0002] With the development of intelligent technology, robots are increasingly used in fields such as medical care, industry, and public places. Especially in epidemic prevention and control and environmental cleaning, disinfection robots, as a highly efficient automated device, are gradually gaining popularity. Disinfection robots need to work in complex environments, including densely populated areas, narrow corridors, and furniture of different shapes. All of these require the robot to have strong dynamic path planning capabilities to ensure the smooth completion of the task.

[0003] The existing technology has the following drawbacks: Traditional path planning algorithms typically rely on static maps. When encountering dynamic obstacles (such as pedestrians, other equipment, or sudden obstacles), the path planning is difficult to adjust in real time. This limits the operation of disinfection robots in complex and dynamic environments. For example, when the robot is operating in an environment full of obstacles, its path planning may fail quickly, causing the robot to stall or deviate from its target. In addition, traditional path planning methods often ignore real-time responses to environmental changes, making the robot lack flexibility and adaptability when encountering unknown or unpredictable environmental changes.

[0004] Based on this, the present invention proposes an embedded system for dynamic path planning of disinfection robots in complex environments. By combining global path planning with intelligent control, the robot can not only plan a preliminary path, but also adjust the path in real time according to the dynamic environment during execution, effectively improving the robot's adaptability in dynamic environments. Summary of the Invention

[0005] The purpose of this invention is to provide an embedded system for dynamic path planning of disinfection robots in complex environments, in order to address the shortcomings of the prior art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an embedded system for dynamic path planning of a disinfection robot for complex environments, comprising a data acquisition module, a dynamic map building module, an intelligent planning module, an obstacle avoidance module, and an intelligent adjustment module; Data acquisition module: used to collect environmental data in real time; Dynamic map creation module: Constructs dynamic maps using real-time positioning and mapping technologies; Intelligent planning module: Performs optimal global path planning based on the constructed dynamic map, and calculates the optimal global path from the starting point to the target point; Obstacle avoidance module: By using a local obstacle avoidance algorithm, the robot avoids sudden dynamic obstacles while maintaining the original path, and dynamically adjusts the robot's travel route. Intelligent adjustment module: Adjusts the robot's movement speed and direction in real time based on the optimal global path and dynamic adjustment results.

[0007] Preferably, the obstacle avoidance module simulates a force field using an artificial potential field method, where the target point is considered as an attraction source and the obstacle is considered as a repulsion source, and the robot is subjected to two forces. Based on the robot's current position, the combined force of the target point and obstacles is calculated, and an obstacle avoidance path is generated, with the forward direction adjusted in real time. By monitoring the dynamic changes of obstacles through real-time sensor data and calculating new obstacle avoidance paths through obstacle avoidance algorithms, the robot adjusts its movement direction based on real-time data.

[0008] Preferably, the obstacle avoidance module simulates the force field using the artificial potential field method, with the following steps: Let the robot's current position be... The target point is located at The location of the obstacle is Then the total force on the robot Represented as: ,in: It's attraction. It is a repulsive force; Calculate a new obstacle avoidance path using an obstacle avoidance algorithm. : ,in: It's the angle that the robot needs to adjust. This is the current direction of the robot's movement.

[0009] Preferably, the intelligent planning module uses a constructed dynamic map to assess obstacles and free space in the environment, and calculates the optimal global path from the starting point to the target point using the Dijkstra algorithm; The system assesses the impact of dynamic obstacles in real time and adjusts the path planning accordingly.

[0010] Preferably, the optimal global path from the starting point to the target point is calculated using Dijkstra's algorithm, and the expression is: ,in: Indicates the distance from the starting point to the node. The shortest path distance, From the starting point to the node The known shortest path distance, From node To the node The weight of the edges.

[0011] Preferably, the dynamic map building module uses real-time positioning and mapping technology to simultaneously construct a dynamic map and determine the robot's position; The location is estimated based on control inputs and sensor data, and a dynamic map is built based on the current location and environmental information acquired by the sensors. Point cloud data of the surrounding environment is acquired using lidar. The point cloud is a three-dimensional dataset composed of measurement points, each of which contains its spatial position (x, y, z) and reflection intensity.

[0012] Preferably, the dynamic map building module utilizes real-time positioning and mapping technology to simultaneously construct a dynamic map, as shown below: ,in: Indicates the robot's time State estimation, including position and attitude. Is it the robot in time? The control input, It is process noise, representing the error generated during actual motion.

[0013] Preferably, the impact of dynamic obstacles is assessed in real time, expressed as: ,in: It is the first in the path The optimal distance function for each point These are the weighting coefficients for dynamic obstacles. This represents the influence of dynamic obstacles on node i.

[0014] Preferably, the intelligent adjustment module acquires the robot's motion state and performs real-time analysis to obtain the robot's position and posture; Based on the robot's real-time motion status, the intelligent adjustment module uses motion control algorithms to dynamically adjust the robot's speed and direction. Through PID control, it adjusts the robot's speed in real time according to the deviation between the robot and the target path. and rotational speed .

[0015] Preferably, the embedded system further includes an evaluation module: when the robot travels along the optimal global path, it synchronously performs the disinfection task, monitors the disinfection effect in real time, and adjusts the disinfection intensity and duration according to the disinfection effect.

[0016] The technical effects and advantages provided by the present invention in the above technical solution are as follows: This invention employs a data acquisition module to collect environmental data in real time, a dynamic map building module to construct a dynamic map using real-time positioning and mapping technology, an intelligent planning module to perform optimal global path planning based on the constructed dynamic map, calculating the optimal global path from the starting point to the target point, an obstacle avoidance module to avoid sudden dynamic obstacles while maintaining the original path, and dynamically adjusting the robot's route, using a local obstacle avoidance algorithm, and an intelligent adjustment module to adjust the robot's speed and direction in real time based on the optimal global path and the dynamic adjustment results. By combining global path planning with intelligent control, the robot can not only plan an initial path but also adjust the path in real time according to the dynamic environment during execution, effectively improving the robot's adaptability in dynamic environments. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0018] Figure 1 This is a framework diagram of the embedded system of the present invention.

[0019] Figure 2 This is a flowchart illustrating the operation of the embedded system of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0021] Example 1: Please refer to Figure 1 As shown in this embodiment, the embedded system for dynamic path planning of a disinfection robot for complex environments includes a data acquisition module, a dynamic map building module, an intelligent planning module, an obstacle avoidance module, and an intelligent adjustment module.

[0022] Data Acquisition Module: The disinfection robot first needs to perceive its environment and acquire information about surrounding obstacles, people, and objects. By integrating multiple sensors (LiDAR, ultrasonic sensors, infrared sensors, cameras, etc.), the robot can collect environmental data in real time and perform preliminary analysis. The information collected by the sensors will provide the foundation for subsequent path planning, intelligent control, and obstacle avoidance. The environmental data is sent to the dynamic map building module.

[0023] Dynamic map building module: The robot will use real-time localization and mapping technologies (such as SLAM) to build a dynamic map. Through real-time analysis of environmental data, the system can perceive dynamic changes and update the map in a timely manner to ensure that the map accurately reflects obstacles, people, and other changing factors in the environment. The dynamic map is then sent to the intelligent planning module.

[0024] Intelligent Planning Module: Based on the constructed dynamic map, the robot will perform optimal global path planning, calculating the optimal global path from the starting point to the target point. In this process, path planning is not only based on static obstacles but also considers the potential impact of real-time dynamic obstacles. The intelligent control module dynamically adjusts the path planning to adapt to environmental changes, ensuring the robot can move continuously and efficiently in complex environments. The planned optimal global path is then sent to the obstacle avoidance module and the intelligent control module.

[0025] Obstacle avoidance module: During the robot's execution of the optimal global path, it needs to avoid any new obstacles encountered in real time. Through local obstacle avoidance algorithms (such as the artificial potential field method), the robot can avoid sudden dynamic obstacles while maintaining its original path. The intelligent correction system can dynamically adjust the robot's route based on real-time sensor data, and the dynamic adjustment results are sent to the intelligent adjustment module.

[0026] Intelligent Adjustment Module: After completing path planning, the robot will precisely execute the task through the motion control system based on the optimal global path and dynamic adjustments. The intelligent motion control algorithm will adjust the robot's speed and direction in real time according to the robot's actual motion state and environmental feedback, ensuring path accuracy and task execution efficiency.

[0027] The embedded system also includes an evaluation module: the disinfection task is executed synchronously as the robot travels along the optimal global path. The disinfection system monitors the disinfection effect in real time through sensors, such as ultraviolet sensors and air quality monitoring, and adjusts parameters such as disinfection intensity and duration based on the disinfection effect. An intelligent feedback mechanism ensures that the quality of the disinfection task meets the expected standards. This intelligent feedback control mechanism dynamically adjusts the disinfection strategy based on real-time data to ensure optimal disinfection performance under different environments.

[0028] The specific workflow of an embedded system is as follows: The first step for a disinfection robot is to perceive its environment and acquire information about surrounding obstacles, people, and objects. By integrating multiple sensors (LiDAR, ultrasonic sensors, infrared sensors, cameras, etc.), the robot can collect environmental data in real time and perform preliminary analysis. The information collected by the sensors will provide the foundation for subsequent path planning, intelligent control, and obstacle avoidance.

[0029] The robot will utilize real-time localization and mapping technologies (such as SLAM) to construct dynamic maps. Through real-time analysis of environmental data, the system can perceive dynamic changes and update the map in a timely manner, ensuring that the map accurately reflects obstacles, people, and other changing factors in the environment.

[0030] Based on the constructed dynamic map, the robot will perform optimal global path planning, calculating the optimal global path from the starting point to the target point. In this process, path planning is not only based on static obstacles but also considers the potential impact of real-time dynamic obstacles. The intelligent control module will dynamically adjust the path planning to adapt to environmental changes, ensuring the robot can move forward continuously and efficiently in complex environments.

[0031] During the process of a robot executing the optimal global path, it needs to avoid any new obstacles it encounters in real time. Through local obstacle avoidance algorithms (such as the artificial potential field method), the robot can avoid sudden dynamic obstacles while maintaining its original path. The intelligent correction system can dynamically adjust the robot's route based on real-time sensor data.

[0032] After path planning is completed, the robot will precisely execute the task through the motion control system based on the optimal global path and dynamic adjustments. The intelligent motion control algorithm will adjust the robot's speed and direction in real time according to the robot's actual motion state and environmental feedback, ensuring the accuracy of the path and the efficiency of task execution.

[0033] As the robot travels along the optimal global path, the disinfection task is executed simultaneously. The disinfection system monitors the disinfection effect in real time through sensors such as ultraviolet sensors and air quality monitoring, adjusting parameters such as disinfection intensity and duration based on the disinfection results. An intelligent feedback mechanism ensures that the quality of the disinfection task meets the expected standards. This mechanism dynamically adjusts the disinfection strategy based on real-time data to ensure optimal disinfection performance under different environments.

[0034] This application employs a data acquisition module to collect environmental data in real time, a dynamic map building module to construct a dynamic map using real-time positioning and mapping technology, an intelligent planning module to perform optimal global path planning based on the constructed dynamic map, calculating the optimal global path from the starting point to the target point, an obstacle avoidance module to avoid sudden dynamic obstacles while maintaining the original path, and dynamically adjusting the robot's route, and an intelligent adjustment module to adjust the robot's speed and direction in real time based on the optimal global path and the dynamic adjustment results. By combining global path planning with intelligent control, the robot can not only plan a preliminary path but also adjust the path in real time according to the dynamic environment during execution, effectively improving the robot's adaptability in dynamic environments.

[0035] Data Acquisition Module: The disinfection robot first needs to perceive its environment and acquire information about surrounding obstacles, people, and objects. By integrating multiple sensors (LiDAR, ultrasonic sensors, infrared sensors, cameras, etc.), the robot can collect environmental data in real time and perform preliminary analysis. The information collected by the sensors will provide the foundation for subsequent path planning, intelligent control, and obstacle avoidance. The environmental data is sent to the dynamic map building module.

[0036] The data acquisition module is one of the core components of the disinfection robot system. It aims to integrate multiple sensors to perceive environmental information in real time, providing foundational data for subsequent path planning, intelligent control, and obstacle avoidance decisions. Through environmental perception and data acquisition, the robot can obtain information about key elements such as obstacles, people, and objects, and then send this data to the subsequent dynamic map building module for further processing.

[0037] First, the disinfection robot needs to perceive the structure and dynamic changes of its surrounding environment. To achieve this, the robot integrates multiple sensors, including LiDAR, ultrasonic sensors, infrared sensors, and cameras. Different types of sensors each have unique advantages and can complement each other.

[0038] LiDAR (Light Detection and Ranging) Sensors: LiDAR is widely used to acquire high-precision 3D data of the surrounding environment, particularly suitable for environmental mapping and obstacle detection. LiDAR calculates distance by emitting a laser beam and measuring the time it takes for the light to return (i.e., time of flight), acquiring detailed point cloud data of the environment. Its output is a 3D dataset consisting of a large number of points, each containing position (x, y, z) and reflection intensity information. This point cloud data provides the foundation for dynamic map creation.

[0039] Ultrasonic sensors: Ultrasonic sensors measure distances to objects by emitting high-frequency sound waves and receiving the echoes. These sensors are suitable for short-range obstacle detection, especially in confined spaces. Due to their low cost and small size, ultrasonic sensors are often used to supplement the limitations of LiDAR at short distances.

[0040] Infrared sensors: Infrared sensors are primarily used to measure the thermal radiation of objects, helping robots identify and detect heat sources, such as the human body or other objects with high temperatures. The advantage of infrared sensors is their ability to operate effectively in low light or adverse weather conditions, making them suitable for environments with significant variations in lighting.

[0041] Camera (visual sensor): Cameras provide visual information about the environment through image acquisition. Computer vision technology can be used to detect and identify complex environmental features (such as people, equipment, obstacles, etc.), providing important support for subsequent path planning and obstacle avoidance.

[0042] After data acquisition, the data from various sensors must be preprocessed and fused for further use. Due to the differences in data type and accuracy among different sensors, preprocessing and fusion are crucial steps in the data acquisition module.

[0043] Data filtering and denoising: Since sensors are susceptible to environmental interference, such as reflected light, temperature changes, or electromagnetic noise, the raw data may contain noise. Filtering algorithms (such as Kalman filtering or median filtering) can remove noise and smooth the data, thereby improving its accuracy.

[0044] Sensor data fusion: Sensor fusion combines information from different sensors to create a more comprehensive and accurate environmental description. For example, combining 3D point cloud data from LiDAR with image data from a camera can provide more precise environmental perception. Commonly used algorithms in this process include weighted average fusion and Extended Kalman Filter (EKF). Assume the LiDAR data at a certain moment is... Camera data is The merged data This can be expressed by the following weighted formula: ,in, and These are weighting coefficients, representing the reliability of the data from each sensor. The fused data provides a comprehensive input, facilitating subsequent processing.

[0045] The collected data is transmitted to the central processing unit or computing platform via high-speed bus or wireless network (such as Wi-Fi or Bluetooth) to ensure data real-time performance and integrity. The data acquisition module collaborates with other modules (such as the dynamic map building module and intelligent planning module) through inter-module communication protocols to ensure that all components of the system work synchronously. The real-time data provided by the sensor modules directly affects the accuracy of map building and route planning.

[0046] The data acquisition module, through the collaborative work of multiple sensors, provides the disinfection robot with high-precision environmental perception data. Through effective data preprocessing and fusion, obstacle detection, and other steps, the robot can understand its surrounding environment in real time, providing essential foundational data for subsequent dynamic map updates, path planning, and obstacle avoidance decisions. The accuracy and real-time performance of the data acquisition module directly impact the performance of the entire robot system, ensuring that the robot can autonomously perform disinfection tasks in complex and dynamic environments.

[0047] Dynamic map building module: The robot will use real-time localization and mapping technologies (such as SLAM) to build a dynamic map. Through real-time analysis of environmental data, the system can perceive dynamic changes and update the map in a timely manner to ensure that the map accurately reflects obstacles, people, and other changing factors in the environment. The dynamic map is then sent to the intelligent planning module.

[0048] The dynamic map building module is a key component of the disinfection robot's navigation system. It aims to construct and update a dynamic map of the robot's surroundings using real-time localization and mapping (SLAM) technologies. Through real-time analysis of sensor data, this module can perceive and respond to dynamic changes in the environment, ensuring that the map always reflects obstacles, people, and other potentially changing factors. The dynamic map not only provides accurate information for path planning but also offers real-time data support for obstacle avoidance and task execution. The core objective of this module is to maintain the robot's high degree of autonomy and adaptability in complex environments through efficient real-time processing and map updates.

[0049] During the dynamic map creation process, the disinfection robot utilizes Simultaneous Localization-and-Mapping (SLAM) technology to simultaneously construct a dynamic map and determine the robot's position. The key to SLAM technology is that, during exploration, the robot simultaneously estimates its own position and continuously updates the environmental map. The basic principle of SLAM can be represented as follows: ,in: Indicates the robot's time State estimation, including position and attitude (e.g. , Is it the robot in time? Control inputs (such as speed, steering angle, etc.). This refers to process noise, representing errors that may occur during actual motion. Through SLAM, the robot can adjust its behavior based on control inputs. The robot estimates its position using sensor data (such as LiDAR or visual data) and builds a dynamic map based on its current location and environmental information acquired by the sensors. At any given moment, the robot's position information and map data are continuously updated to adapt to changes in the environment.

[0050] To build accurate dynamic maps during SLAM, the robot uses LiDAR or other sensors to acquire point cloud data of its surroundings. A point cloud is a three-dimensional dataset composed of a large number of measurement points, each containing its spatial location (x, y, z) and possibly other attributes (such as reflectance). In a real-time environment, point cloud data is the basis for map updates.

[0051] For each frame of laser scan results, the robot extracts valid obstacle points using real-time point cloud processing algorithms, and then filters and denoises them to ensure data accuracy. Common point cloud filtering methods include: VoxelGridFilter: Reduces data density and removes redundant points by dividing the space into small grids.

[0052] Ground profile extraction and removal: By identifying ground points, point cloud data on the ground is removed, focusing on obstacle detection.

[0053] Using this processed point cloud data, the SLAM algorithm can efficiently update the robot's position and mark the location and shape of obstacles on the map.

[0054] Unlike traditional static mapping techniques, dynamic map building modules require special attention to the detection and updating of dynamic obstacles in the environment. Dynamic obstacles (such as pedestrians and mobile devices) are constantly changing in the environment and must be detected and updated from the dynamic map in a timely manner.

[0055] To this end, the robot employs motion detection algorithms to identify dynamic objects. By comparing point cloud data from consecutive frames, the robot can determine which points originate from dynamic objects and which are static obstacles. This process can be described by the following formula: ,in: It is the current time. Compared to the previous time Differences in point cloud data. and These represent the point cloud data for the current frame and the previous frame, respectively. By calculating the differences between the point clouds in each frame, the robot can identify moving obstacles, remove them from the static dynamic map, or mark them separately as dynamic obstacles, preventing them from being mistakenly identified as fixed obstacles during path planning.

[0056] To improve the efficiency and accuracy of map updates, disinfection robots typically maintain both a global map and a local map. The global map represents the general structure of the entire environment, while the local map represents detailed environmental information in the robot's current vicinity. As the robot moves, the local map is continuously updated and periodically merged with the global map. Local map updates are achieved through the following methods: ,in: It is a local map at the current moment. This refers to the new environmental data acquired from the sensors at the current moment. The global map is updated based on the accumulation of local maps and changes in the environment. The changes in multiple local maps are merged through map stitching algorithms (such as graph optimization or consistency algorithms) to update the global map.

[0057] Once the dynamic map is updated in real time, the system will transmit the updated map information to the intelligent planning module. Based on the latest dynamic map, the intelligent planning module will recalculate the global path and obstacle avoidance path to ensure the robot can perform its tasks efficiently and safely in the current environment.

[0058] The dynamic map building module utilizes SLAM technology and sensor data fusion to achieve efficient and accurate environmental perception and map updates. Through real-time environmental analysis, the robot can flexibly respond to the influence of obstacles, people, and other factors in dynamically changing environments, ensuring that the map always reflects the true environmental state. This module not only provides accurate basic data for path planning but also provides real-time feedback for obstacle avoidance and task execution, making it a core component for enabling the disinfection robot to operate efficiently and autonomously.

[0059] Intelligent Planning Module: Based on the constructed dynamic map, the robot will perform optimal global path planning, calculating the optimal global path from the starting point to the target point. In this process, path planning is not only based on static obstacles but also considers the potential impact of real-time dynamic obstacles. The intelligent control module dynamically adjusts the path planning to adapt to environmental changes, ensuring the robot can move continuously and efficiently in complex environments. The planned optimal global path is then sent to the obstacle avoidance module and the intelligent control module.

[0060] The intelligent planning module is a core component of the disinfection robot's autonomous navigation system. Its main task is to calculate and execute optimal global path planning based on a constructed dynamic map and real-time sensed data. In complex environments, path planning needs to consider not only static obstacles but also the impact of dynamic obstacles in real time to ensure the robot can move efficiently and safely from the starting point to the target point. The goal of the intelligent planning module is to enable the robot to continuously move forward in complex and changing environments, while constantly optimizing the path, avoiding collisions, and ensuring the successful completion of the task.

[0061] Global path planning is the primary task of the intelligent planning module, aiming to find the optimal path from the starting point to the target point. In this step, the robot needs to utilize a constructed dynamic map to evaluate obstacles and free space in the environment and calculate the optimal global path from the starting point to the target point. Commonly used global path planning algorithms include the A* algorithm and Dijkstra's algorithm, both of which can find a path with the shortest distance within a known environmental map.

[0062] Dijkstra's Algorithm: Dijkstra's algorithm is a classic graph search algorithm used to find the shortest path from a starting point to a target point. It relies solely on calculating the shortest distance from the starting point to each node, making it suitable for scenarios where the target information is not explicitly stated. Its path distance formula is: ,in: Indicates the distance from the starting point to the node. The shortest path distance. From the starting point to the node The known shortest path distance. From node To the node The weight of the edge (e.g., time).

[0063] In practical applications, robots often need to operate in dynamic environments where dynamic obstacles (such as moving people, other equipment, etc.) may appear or change position at any time. To ensure the real-time performance and effectiveness of path planning, the intelligent planning module needs to evaluate and incorporate the impact of these dynamic obstacles in real time during the global path planning process. This process typically involves continuous monitoring of the environment and prediction of dynamic obstacles.

[0064] The real-time impact of dynamic obstacles can be quantified using the following formula: ,in: It is the first in the path The optimized distance function for each point (i.e., the path distance considering dynamic obstacles). Indicates the distance from the starting point to the node. The shortest path distance. These are the weighting coefficients for dynamic obstacles, controlling the degree to which dynamic obstacles affect the path planning distance. This represents the impact of a dynamic obstacle on node i, typically calculated using the distance between the obstacle and the current node. Based on this formula, the intelligent planning module can update the obstacle's impact using real-time sensor data and dynamically adjust the path planning to prevent the robot from encountering unforeseen obstacles.

[0065] After calculating the optimal global path, the intelligent planning module considers not only the effects of static and dynamic obstacles but also optimizes the path based on task requirements, robot state, and environmental changes. The core objective of path optimization is to maximize task efficiency while ensuring robot stability and safety. For example, path smoothness and executability are two important optimization metrics. Path optimization can be performed using the following methods: Path smoothing: Using methods such as curve fitting or Bézier curves, sharp turns and unnecessary path segments are smoothed to ensure robot stability during actual movement. Dynamic path adjustment: During execution, the robot may encounter new obstacles or environmental changes. In this case, the intelligent control module re-evaluates the path based on the new environmental information and adjusts the path in real time to avoid collisions or path failure. The mathematical expression for path optimization can be described using a distance function: ,in: It is the total optimized distance of the path. It is the first in the path Optimization distance function for points. It is the first in the path The weight of each point indicates its importance in the optimization process. Using this distance function, path optimization can comprehensively consider multiple factors, ensuring that the optimal path is not only the path with the lowest distance but also the most stable and feasible during execution.

[0066] Once the intelligent planning module calculates and optimizes the optimal global path, the planning results are transmitted to the obstacle avoidance module and the intelligent adjustment module. The obstacle avoidance module adjusts the robot's obstacle avoidance strategy based on the optimal path and real-time obstacle information to ensure collision-free path execution. The intelligent adjustment module dynamically adjusts the robot's speed and acceleration based on its current state (such as position, speed, and direction) to guarantee accurate path execution and efficient task completion.

[0067] The intelligent planning module combines global path planning, dynamic obstacle assessment, and path optimization technologies to enable the robot to navigate efficiently and safely in complex and dynamically changing environments. The module's core task is to calculate and adjust the optimal path based on real-time dynamic maps and obstacle information, while simultaneously optimizing the path's feasibility, smoothness, and efficiency. Working in collaboration with the obstacle avoidance and intelligent adjustment modules, the intelligent planning module ensures that the robot can flexibly and accurately complete disinfection tasks in varied environments.

[0068] Obstacle avoidance module: During the robot's execution of the optimal global path, it needs to avoid any new obstacles encountered in real time. Through local obstacle avoidance algorithms (such as the artificial potential field method), the robot can avoid sudden dynamic obstacles while maintaining its original path. The intelligent correction system can dynamically adjust the robot's route based on real-time sensor data, and the dynamic adjustment results are sent to the intelligent adjustment module.

[0069] The obstacle avoidance module is a key component of the disinfection robot's autonomous navigation system. Its main task is to detect and avoid any new obstacles in real time while the robot is executing the optimal global path, ensuring the robot can move safely and smoothly in complex and dynamic environments. By using local obstacle avoidance algorithms and an intelligent correction system, the obstacle avoidance module can dynamically adjust the path based on real-time sensor data to avoid collisions and optimize path execution. This module not only ensures the robot's path safety but also improves overall task execution efficiency.

[0070] Local obstacle avoidance algorithms are the core technology of obstacle avoidance modules. Their main function is to calculate local paths to avoid new obstacles in real time during the robot's global path execution, ensuring that the robot can bypass dynamic obstacles without deviating from the globally planned path. Common local obstacle avoidance algorithms include artificial potential field methods, Voronoi diagram methods, and dynamic window methods. Among them, the artificial potential field method is widely used in obstacle avoidance systems due to its simple calculation and strong real-time performance.

[0071] The artificial potential field method simulates a hypothetical force field, where the target point is considered an attraction source and obstacles are considered repulsion sources. The robot is subjected to two forces: an attractive force from the target point and a repulsive force from the obstacles. Based on the robot's current position, the combined force of these two forces is calculated, and an obstacle avoidance path is generated. Assume the robot's current position is... The target point is located at The location of the obstacle is Then the total force on the robot It can be represented as: ,in: It is the attraction force, usually the gravitational force between the target point and the robot, calculated using the following formula: ,in, It is a repulsive force, originating from the obstacle, and usually decreases as the distance increases. The calculation formula is: ,in: and It is the coefficient of attraction and repulsion, and the magnitude of control. It is the minimum safe distance to ensure the robot does not collide with obstacles. Through a synthesized force field, the robot can avoid collisions with obstacles and adjust its direction of travel in real time without deviating from the global path.

[0072] In actual operation, the robot will constantly encounter new obstacles, especially in complex environments or densely populated areas. The obstacle avoidance module monitors the dynamic changes of obstacles through real-time sensor data (such as LiDAR, ultrasound, and cameras) and calculates new obstacle avoidance paths using obstacle avoidance algorithms. The robot adjusts its movement direction based on real-time data to avoid collisions.

[0073] The key to real-time obstacle avoidance and dynamic path adjustment is to quickly calculate a new travel route based on sensor data. Assume the robot's current position is... The perception distance of the new obstacle is The angle between the robot and the obstacle is The robot's adjusted path can be calculated using the following formula: ,in: It is the angle that the robot needs to adjust, which is dynamically calculated based on the current relative position and distance of the obstacle. This indicates the current direction of the robot's movement. This dynamic path adjustment ensures that the robot can respond to new obstacles in real time and optimize its route to avoid deviating from the mission objective.

[0074] The role of the intelligent correction system is to finely adjust the robot's trajectory based on real-time sensor data during path execution. The intelligent correction system not only adjusts the robot's direction based on the results of local obstacle avoidance algorithms, but also comprehensively considers the robot's state (such as speed, acceleration, and energy consumption) to ensure that the robot's movement is both safe and efficient during path execution. For example, suppose the robot's current speed is... The target speed is The robot's current location is The intelligent correction system will then dynamically adjust the speed and direction based on the real-time position of the obstacle and the robot's motion state. ,in: This is the speed adjustment coefficient, used to control the dynamic adjustment of the robot's speed. Simultaneously, the correction system also appropriately adjusts the robot's acceleration to prevent excessive speed changes due to sudden obstacles, ensuring smoothness and stability during movement.

[0075] After the obstacle avoidance module completes the dynamic path adjustment, the adjusted obstacle avoidance path and motion control commands are transmitted to the intelligent adjustment module. The intelligent adjustment module will further adjust the robot's motion based on its state (such as current position, speed, and direction) to ensure efficient and accurate path execution. Simultaneously, the intelligent adjustment module will also adjust the robot's motion strategy and control parameters in real time according to task requirements and environmental changes to ensure the achievement of task objectives.

[0076] The obstacle avoidance module, through the collaboration of local obstacle avoidance algorithms and an intelligent correction system, can effectively handle new obstacles encountered by the robot while executing its global path. Utilizing obstacle avoidance algorithms such as the artificial potential field method, the robot can dynamically adjust its movement path to avoid collisions with obstacles, while maintaining smooth progress along the globally planned path. Through the intelligent correction system, the obstacle avoidance module further optimizes the robot's motion trajectory and speed control, improving the robot's motion stability and task execution efficiency.

[0077] Intelligent Adjustment Module: After completing path planning, the robot will precisely execute the task through the motion control system based on the optimal global path and dynamic adjustments. The intelligent motion control algorithm will adjust the robot's speed and direction in real time according to the robot's actual motion state and environmental feedback, ensuring path accuracy and task execution efficiency.

[0078] The intelligent adjustment module is a key component of the disinfection robot's autonomous navigation system. Its main function is to ensure that the robot can execute tasks through a precise motion control system based on the optimal global path and real-time dynamic adjustments. The intelligent adjustment module not only handles the robot's motion control but also dynamically adjusts its speed, direction, acceleration, and other control parameters in real time based on the robot's current motion state and environmental feedback, ensuring task execution efficiency and path accuracy. Through intelligent motion control algorithms, the robot can flexibly adapt to changes in complex environments, ensuring successful task completion.

[0079] The primary task of the intelligent adjustment module is to monitor and provide feedback on the robot's current motion state in real time. The robot's motion state typically includes parameters such as position, velocity, orientation, and acceleration. The intelligent adjustment module acquires this information through sensor data (such as encoders, IMU sensors, and LiDAR) and performs real-time analysis. This data serves as input to guide subsequent motion adjustments and control. The robot's current position can be represented as... ,in Let be the robot's planar coordinates. This is the robot's orientation (direction angle) relative to the reference coordinate system. The robot's velocity can be expressed as its linear velocity. and angular velocity , representing the robot's forward speed and rotational speed, respectively. Through real-time monitoring of these motion states, the intelligent adjustment module can obtain the robot's precise position and posture, and provide data support for subsequent motion control algorithms.

[0080] Based on the robot's real-time motion state, the intelligent adjustment module uses motion control algorithms to dynamically adjust the robot's speed and direction. The core objective of the motion control algorithm is to calculate the required speed and direction based on the deviation between the robot's current position and the target path, enabling the robot to move smoothly along the optimal path. Commonly used control algorithms include PID control (Proportional-Integral-Derivative) and fuzzy control. PID control calculates the control quantity to adjust the robot's motion state by weighting position error, velocity error, and acceleration error. The output of the PID controller can be expressed as: ,in: It is the current position error, defined as the difference between the target position and the actual position. These are the proportional, integral, and derivative coefficients, which determine the response speed of the control system to errors. This refers to the control variable, specifically the speed or direction the robot needs to adjust. Through PID control, the intelligent adjustment module can adjust the robot's speed in real time based on the deviation between the robot and the target path. and rotational speed This is to ensure that the robot travels along the optimal path as accurately as possible.

[0081] In addition to adjusting speed and direction, the intelligent adjustment module also needs to dynamically adjust the robot's acceleration to ensure smooth path execution. Excessive acceleration may cause the robot to lose balance or make sharp turns during path adjustment, while insufficient acceleration will prevent the robot from responding to environmental changes or dynamic obstacles in a timely manner.

[0082] The robot's acceleration can be expressed as This refers to the rate of change of velocity over time. The intelligent adjustment module adjusts the acceleration in real time based on the robot's motion state to ensure smooth movement that meets task requirements. For example, suppose the robot needs to move from its current speed... Accelerate to target speed The acceleration can then be calculated using the following formula. The expression is: ,in: This is the current speed. It is the target speed. This is a time interval, representing the time required to reach the target speed. By adjusting the acceleration, the intelligent adjustment module can ensure that the robot moves at an appropriate speed and direction, while avoiding instability caused by sudden changes in acceleration.

[0083] In actual task execution, robots often need to face changes in the environment, such as encountering new obstacles, changing the location of the task target, or changing the path. The intelligent adjustment module can dynamically correct the robot's path and movement strategy based on real-time environmental feedback, ensuring that the robot can move steadily in a constantly changing environment.

[0084] The intelligent adjustment module corrects the path based on data from the obstacle avoidance module. If the robot encounters new obstacles or other unexpected situations during execution, the intelligent adjustment module dynamically calculates new speed and direction based on the obstacle's position and the need for dynamic path adjustment, ensuring that the robot bypasses the obstacle and returns to the optimal path.

[0085] The ultimate goal of the intelligent adjustment module is to ensure that the robot can complete tasks efficiently through precise motion control. In complex environments, the robot may need to adjust its motion strategy in a timely manner according to changes in task priority and target location. For example, when the robot approaches the task target area, it can appropriately reduce its speed to improve execution accuracy; while when the task area is far away, it can increase its speed to save time.

[0086] The intelligent adjustment module adjusts motion parameters, comprehensively considering task objectives, robot status, and environmental factors to ensure efficient task execution. After task completion, the intelligent adjustment module transmits feedback information to other system modules, providing support for task evaluation and subsequent task planning.

[0087] The intelligent adjustment module precisely controls the robot's movement in complex environments by monitoring its motion status in real time and combining motion control algorithms and acceleration adjustment strategies. Through algorithms such as PID control, the intelligent adjustment module ensures the robot can perform tasks smoothly and efficiently, avoiding path deviations caused by environmental changes or dynamic obstacles. The flexibility and accuracy of this module are key to ensuring the disinfection robot's efficient and autonomous task execution, guaranteeing path accuracy and task performance efficiency in complex and changing environments.

[0088] The embedded system also includes an evaluation module: the disinfection task is executed synchronously as the robot travels along the optimal global path. The disinfection system monitors the disinfection effect in real time through sensors, such as ultraviolet sensors and air quality monitoring, and adjusts parameters such as disinfection intensity and duration based on the disinfection effect. An intelligent feedback mechanism ensures that the quality of the disinfection task meets the expected standards. This intelligent feedback control mechanism dynamically adjusts the disinfection strategy based on real-time data to ensure optimal disinfection performance under different environments.

[0089] The evaluation module is a crucial component of the disinfection robot's embedded system. It is responsible for real-time monitoring of the disinfection task's effectiveness and dynamically adjusting the disinfection strategy based on the actual results. This module utilizes various sensors (such as ultraviolet sensors and air quality monitoring sensors) to acquire key data during the disinfection process. Through an intelligent feedback mechanism, it precisely adjusts parameters such as disinfection intensity and duration to ensure that the disinfection effect meets the expected standards under different environments. The evaluation module not only optimizes disinfection efficiency but also guarantees the quality of the disinfection process based on real-time feedback, ensuring that each area receives thorough and effective disinfection.

[0090] During the disinfection process, the disinfection system monitors the disinfection effect in real time using various sensors. For example, ultraviolet (UV) sensors can monitor the intensity of ultraviolet radiation in real time, ensuring that the robot provides sufficient UV irradiation for disinfection within the target area. Air quality sensors can detect changes in the concentration of microorganisms in the air during disinfection, thereby indirectly assessing the disinfection effect. Through these sensors, the evaluation module can acquire data during the disinfection process in real time and determine the completion status of the disinfection task accordingly.

[0091] For ultraviolet disinfection, there is usually a certain relationship between ultraviolet intensity and disinfection effectiveness. Assume the intensity measured by the ultraviolet sensor is... Its relationship with disinfection effect The relationship between them can be described by the following formula: ,in: The measurement represents the effectiveness of ultraviolet disinfection, expressed as sterilization rate or degree of disinfection. The intensity of ultraviolet radiation measured by the ultraviolet sensor. This is a proportionality coefficient between ultraviolet (UV) intensity and disinfection effectiveness, representing the relationship between UV intensity and sterilization rate. Through this real-time monitoring, the evaluation module can determine the UV irradiation effect on the current disinfection area and, based on preset standards, decide whether to adjust the disinfection intensity or duration.

[0092] After monitoring the disinfection effect in real time, the evaluation module adjusts the disinfection strategy through an intelligent feedback mechanism. This mechanism dynamically adjusts various parameters during the disinfection process, including ultraviolet light intensity and disinfection duration, based on real-time data and the system's set disinfection standards. This mechanism automatically optimizes the disinfection process according to environmental changes and actual feedback, ensuring that the disinfection effect consistently meets the expected standards under different environments. For example, in air quality monitoring, suppose the robot measures the bacterial concentration in the air of the current area using an air quality sensor... Its target concentration is The intelligent feedback mechanism can then adjust the disinfection intensity or time based on concentration differences. The adjustment strategy can be optimized using the following formula: ,in: It is the amount of change that adjusts the duration of disinfection. This is the current concentration of bacteria in the air as monitored. It is the predetermined target bacterial concentration. This is an adjustment coefficient that reflects the relationship between changes in bacterial concentration and disinfection time. If the current bacterial concentration is higher than the target concentration, the intelligent feedback mechanism will automatically extend the disinfection time. This ensures that the disinfection effect meets expectations.

[0093] Based on real-time monitoring data, the evaluation module can flexibly adjust the disinfection intensity and duration. In dynamic environments, the complexity of disinfection areas and disinfection requirements can vary significantly. For example, some areas may have higher bacterial concentrations, requiring longer UV irradiation or stronger disinfection intensity; while other areas may only require shorter irradiation times. The intelligent feedback mechanism continuously adjusts these parameters to ensure efficient execution of disinfection tasks and optimal disinfection effects. The adjustment of disinfection intensity and duration is typically achieved through the following formula: ,in: This is the adjusted disinfection time. This is the default disinfection time (the disinfection time under standard conditions). This is the current measured concentration of bacteria in the air. It is the concentration of the target bacteria. It is an adjustment coefficient that controls the non-linear relationship between disinfection time and changes in bacterial concentration. By adjusting the disinfection time, the evaluation module can ensure optimal disinfection performance in different environments and avoid over-disinfection or under-disinfection.

[0094] During task execution, the evaluation module continuously assesses the disinfection effectiveness of each area and optimizes it based on real-time data. For example, in complex environments, some areas may suffer from insufficient lighting or obstruction, leading to less than expected disinfection results. The evaluation module can dynamically adjust the disinfection strategy based on sensor feedback data and environmental factors (such as light intensity and obstacle distribution) to ensure that all areas are adequately disinfected.

[0095] The intelligent feedback control mechanism provides precise adjustment plans through comprehensive analysis of real-time data and environmental factors, thereby ensuring optimal effectiveness during the disinfection process. Optimization results typically include adjustments to factors such as disinfection intensity, time, and pathways to ensure the desired disinfection effect is consistently achieved under different environmental conditions.

[0096] Once the disinfection task is completed, the evaluation module generates a task report based on the final feedback data on the disinfection effect and transmits the report data to the upper-level system or user. The report includes key information such as the disinfected area, disinfection time, disinfection intensity, and disinfection effect. This data provides a basis for subsequent task evaluation, optimization, and system upgrades.

[0097] The evaluation module monitors disinfection effectiveness in real time and dynamically adjusts disinfection intensity and duration using an intelligent feedback mechanism to ensure optimal performance under varying environmental conditions. By adjusting key parameters such as UV intensity and air quality in real time, the evaluation module guarantees the quality of disinfection tasks and optimizes disinfection efficiency. The intelligent feedback mechanism ensures the disinfection process can flexibly respond to environmental changes, thereby improving task completion and optimizing disinfection strategies, providing the robot with a precise and efficient disinfection solution.

[0098] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0099] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. An embedded system for dynamic path planning of a disinfection robot in complex environments, characterized by: It includes a data acquisition module, a dynamic map creation module, an intelligent planning module, an obstacle avoidance module, and an intelligent adjustment module; Data acquisition module: used to collect environmental data in real time; Dynamic map creation module: Constructs dynamic maps using real-time positioning and mapping technologies; Intelligent planning module: Performs optimal global path planning based on the constructed dynamic map, and calculates the optimal global path from the starting point to the target point; Obstacle avoidance module: By using a local obstacle avoidance algorithm, the robot avoids sudden dynamic obstacles while maintaining the original path, and dynamically adjusts the robot's travel route. Intelligent adjustment module: Adjusts the robot's movement speed and direction in real time based on the optimal global path and dynamic adjustment results; The intelligent planning module uses a constructed dynamic map to assess obstacles and free space in the environment, and calculates the optimal global path from the starting point to the target point using the Dijkstra algorithm. Real-time assessment of the impact of dynamic obstacles and dynamic adjustment of path planning; The effect of dynamic obstacles can be assessed in real time, expressed as: ,in: It is the first in the path The optimal distance function for each point Indicates the distance from the starting point to the node. The shortest path distance, These are the weighting coefficients for dynamic obstacles. This represents the amount of influence of a dynamic obstacle on node i; The mathematical expression for path optimization can be described using a distance function: ,in: It is the total optimized distance of the path. It is the first in the path The optimal distance function for each point It is the first in the path The weight of each point indicates its importance in the optimization.

2. The embedded system for dynamic path planning of a disinfection robot in complex environments according to claim 1, characterized in that: The obstacle avoidance module simulates a force field using an artificial potential field method, where the target point is considered as an attraction source and the obstacle as a repulsion source, and the robot is subjected to two forces. Based on the robot's current position, the combined force of the target point and obstacles is calculated, and an obstacle avoidance path is generated, with the forward direction adjusted in real time. By monitoring the dynamic changes of obstacles through real-time sensor data and calculating new obstacle avoidance paths through obstacle avoidance algorithms, the robot adjusts its movement direction based on real-time data.

3. The embedded system for dynamic path planning of a disinfection robot in complex environments according to claim 2, characterized in that: The obstacle avoidance module simulates the force field using the artificial potential field method. The steps are as follows: Let the robot's current position be... The target point is located at The location of the obstacle is Then the total force on the robot Represented as: ,in: It's attraction. It is a repulsive force; Calculate a new obstacle avoidance path using an obstacle avoidance algorithm. : ,in: It's the angle that the robot needs to adjust. This is the current direction of the robot's movement.

4. The embedded system for dynamic path planning of a disinfection robot in complex environments according to claim 1, characterized in that: The optimal global path from the starting point to the target point is calculated using Dijkstra's algorithm, and the expression is: ,in: From the starting point to the node The known shortest path distance, From node To the node The weight of the edges.

5. The embedded system for dynamic path planning of a disinfection robot in complex environments according to claim 4, characterized in that: The dynamic map building module uses real-time positioning and mapping technology to simultaneously construct a dynamic map and determine the robot's position; The location is estimated based on control inputs and sensor data, and a dynamic map is built based on the current location and environmental information acquired by the sensors. Point cloud data of the surrounding environment is acquired using lidar. The point cloud is a three-dimensional dataset composed of measurement points, each of which contains its spatial position (x, y, z) and reflection intensity.

6. The embedded system for dynamic path planning of a disinfection robot in complex environments according to claim 5, characterized in that: The dynamic map building module utilizes real-time positioning and mapping technologies to simultaneously construct a dynamic map, represented as follows: ,in: Indicates the robot's time State estimation, including position and attitude. Is it the robot in time? The control input, It is process noise, representing the error generated during actual motion.

7. The embedded system for dynamic path planning of a disinfection robot for complex environments according to claim 1, characterized in that: The intelligent adjustment module acquires the robot's motion state and performs real-time analysis to obtain the robot's position and posture; Based on the robot's real-time motion status, the intelligent adjustment module uses motion control algorithms to dynamically adjust the robot's speed and direction. Through PID control, it adjusts the robot's speed in real time according to the deviation between the robot and the target path. and rotational speed .

8. The embedded system for dynamic path planning of a disinfection robot in complex environments according to claim 7, characterized in that: The embedded system also includes an evaluation module: when the robot travels along the optimal global path, it synchronously performs the disinfection task, monitors the disinfection effect in real time, and adjusts the disinfection intensity and duration according to the disinfection effect.

Images