Path planning method and device for 5G nursing robot

Abstract

The invention discloses a path planning method and device for a 5G nursing robot, and relates to the field of path planning. In the method, map information, first sensor data and first image data dynamically updated in a hospital are received in real time through a 5G network, and a three-dimensional space model in the hospital is constructed according to the map information and the first sensor data; analyzing the first image data to determine a human traffic mode and a static obstacle distribution condition in the hospital, and predicting a dynamic obstacle distribution state in a future preset time according to the human traffic mode and the static obstacle distribution condition; determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the emergency degree of the work demand; and in the process of moving according to the initial path, identifying the pedestrian and the movement trend of the pedestrian by using a second sensor and a second camera, and adjusting the initial path according to the movement trend. By implementing the technical scheme provided by the invention, the path planning efficiency and safety are improved.

Description

Technical Field

[0001] The present application relates to the technical field of path planning, and specifically to a path planning method and device for a 5G nursing robot. Background Art

[0002] With the rapid development and popularization of 5G technology, the application of nursing robots has gradually become an important part of the modern medical system.

[0003] At present, in order to cope with the complex environment inside the hospital and enable the mobile medical station to reach the designated location safely and quickly, common solutions include the use of traditional navigation systems and manual operations. Traditional navigation systems usually rely on pre-drawn static maps and fixed path planning algorithms. Although they can achieve basic path navigation functions, they are difficult to make timely and effective adjustments when facing dynamic changes in the hospital, such as temporary obstacles and sudden peaks in traffic. In addition, although manual operations can flexibly respond to emergencies, they require a lot of human resources and are prone to errors in emergency situations.

[0004] Therefore, how to realize real-time dynamic path planning of nursing robots is a technical problem that needs to be solved urgently. Summary of the invention

[0005] This application provides a path planning method and device for a 5G nursing robot, which significantly improves the working efficiency and safety of the 5G nursing robot in the hospital through real-time information acquisition, three-dimensional space modeling, prediction and optimization, urgency consideration, and dynamic adjustment. It helps to reduce the waste of medical resources and improve the response speed and quality of medical services.

[0006] In a first aspect of the present application, a path planning method for a 5G nursing robot is provided, which is applied to the 5G nursing robot, and the method comprises: receiving in real time through a 5G network dynamically updated map information in the hospital, first sensor data collected by a first sensor, and first image data collected by a first camera, and constructing a three-dimensional space model inside the hospital according to the map information and the first sensor data, wherein the first sensor and the first camera are installed at preset positions inside the hospital; Analyze the first image data to determine the flow pattern of people and the distribution of static obstacles in the hospital, and predict the obstacle distribution state within a preset time in the future according to the flow pattern of people and the distribution of static obstacles; Determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand; In the process of moving along the preliminary path, a second sensor and a second camera are used to identify pedestrians and their movement trends, and the preliminary path is adjusted according to the movement trends. The second sensor and the second camera are installed on the 5G nursing robot.

[0007] Optionally, the predicting of the obstacle distribution state within a preset future time according to the pedestrian flow pattern and the static obstacle distribution includes: Parsing the first image data to obtain current crowd flow data and static obstacle data, wherein the crowd flow data includes the number, movement direction and speed of pedestrians in different areas inside the hospital, and the static obstacle data includes the size and location of the obstacle; Based on the historical crowd flow data and the current crowd flow data, predict the changing trend of the crowd flow in each area within a preset time period in the future; According to the change trend and the static obstacle data, the distribution status of the dynamic obstacles in the future preset time period is determined, the hospital is divided into crowded areas, dense areas and general areas according to the distribution status, and the traffic bottleneck areas are determined in the crowded areas and the dense areas.

[0008] Optionally, determining the traffic bottleneck area in the congested area and the dense area includes: Determine the pedestrian flow restricted area by comparing the predicted pedestrian density change with the preset threshold; The duration and impact of the pedestrian restricted flow area are predicted based on the historical crowd flow data and the change trend, and the target area with the greatest impact on the overall crowd flow is determined as the traffic bottleneck area based on the area, duration and impact of the pedestrian restricted flow area.

[0009] Optionally, determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand includes: When the urgency of the work requirement is greater than or equal to a first threshold, a preliminary path with the shortest time is determined, and a warning message is sent to mobile devices in the target area involved in the preliminary path through the 5G network, prompting the user of the mobile device to avoid it, and turning on the sound warning unit on the 5G nursing robot.

[0010] Optionally, determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand includes: When the urgency of the work demand is less than a second threshold, determining whether a complete path can be formed based on the general area, and the first threshold is greater than the second threshold; When a complete path cannot be constructed based on the general area, multiple first candidate paths are constructed based on the general area and the dense area, and a first path that passes through the least dense area is selected from the multiple first candidate paths. When there are multiple first paths, a second path with the shortest time is selected from the first paths as a preliminary path.

[0011] Optionally, determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand includes: When the urgency of the work demand is greater than or equal to the second threshold and less than the first threshold, constructing a plurality of second candidate paths according to the departure place and the destination; The interference weights of passing through a crowded area, a dense area, and a general area are set to be a first sub-weight, a second sub-weight, and a third sub-weight, respectively; the interference score of the second candidate path is calculated according to the number of times of passing through the crowded area, the dense area, and the general area and the first sub-weight, the second sub-weight, and the third sub-weight, wherein the first sub-weight is greater than the second sub-weight, and the second sub-weight is greater than the third sub-weight; Calculate the congestion coefficient of each area according to the predicted crowd flow density, determine the time of each area according to the congestion coefficient, and calculate the total time of the second candidate path according to the time; The interference score and the total time are weightedly summed to obtain a total score, and the second candidate path with the smallest total score is selected as the preliminary path.

[0012] Optionally, adjusting the preliminary path according to the movement trend includes: Dividing the preliminary path into multiple sub-paths, and setting a break point between two adjacent sub-paths; Based on the identified pedestrian movement trends, predict the intersection point and intersection time with pedestrians; Slows down movement and reroutes from the current point to the next break point based on predicted junctions and times.

[0013] In a second aspect of the present application, a path planning system for a 5G nursing robot is provided, including a map module, a prediction module, a path module, and an adjustment module, wherein: a map module configured to receive in real time through a 5G network dynamically updated map information in the hospital, first sensor data collected by a first sensor, and first image data collected by a first camera, and construct a three-dimensional space model inside the hospital according to the map information and the first sensor data, wherein the first sensor and the first camera are installed at preset positions inside the hospital; a prediction module configured to analyze the first image data to determine a human flow pattern and a distribution of static obstacles in the hospital, and predict a distribution state of obstacles within a preset time in the future according to the human flow pattern and the distribution of static obstacles; A path module, configured to determine a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand; The adjustment module is configured to use a second sensor and a second camera to identify pedestrians and their movement trends during the movement along the preliminary path, and adjust the preliminary path according to the movement trends. The second sensor and the second camera are installed on the 5G nursing robot.

[0014] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0015] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0016] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Receive dynamically updated map information, sensor data, and camera image data in the hospital in real time through the 5G network, ensuring that the information used for path planning is up to date, thereby improving the real-time and accuracy of path planning; 2. Use map information and sensor data to build a three-dimensional spatial model inside the hospital, so that path planning can more accurately reflect the actual environment inside the hospital, including floors, rooms, corridors and other structures, providing a basis for subsequent path planning; 3. Determine the flow pattern and static obstacle distribution in the hospital by analyzing the image data collected by the camera, and predict the distribution of dynamic obstacles (such as pedestrians, medical equipment, etc.) within a preset time in the future. This prediction capability helps to avoid potential obstacles in advance, optimize path planning, and reduce waiting and conflicts during movement; 4. Path planning not only takes into account space and environmental factors, but also the urgency of work needs. This means that in emergency situations, path planning can be more flexible and efficient to meet the urgency of medical work; 5. While moving along the preliminary path, the sensors and cameras installed on the 5G nursing robot are used to identify pedestrians and their movement trends in real time, and the path is dynamically adjusted based on this information. This dynamic adjustment capability improves the flexibility and adaptability of path planning, helping to avoid potential collisions and delays. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a flow chart of a path planning method for a 5G nursing robot disclosed in an embodiment of the present application; Figure 2 It is a module schematic diagram of the path planning system of the 5G nursing robot disclosed in the embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0018] Explanation of the reference numerals: 201, map module; 202, prediction module; 203, path module; 204, adjustment module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0019] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0020] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0021] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0022] This embodiment discloses a path planning method for a 5G nursing robot, which is applied to the 5G nursing robot. Figure 1 is a flow chart of the path planning method of the 5G nursing robot disclosed in the embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps: S110, receiving in real time through a 5G network dynamically updated map information in the hospital, first sensor data collected by a first sensor, and first image data collected by a first camera, and constructing a three-dimensional space model inside the hospital according to the map information and the first sensor data, wherein the first sensor and the first camera are installed at preset positions inside the hospital; The first sensor and the first camera are installed at preset locations inside the hospital. These locations may be determined based on the needs and monitoring requirements within the hospital to ensure that various information inside the hospital can be fully obtained. The types and quantities of sensors may be configured according to specific needs to cover different areas and scenes inside the hospital. The camera is used to capture image information inside the hospital in real time to provide intuitive visual support for monitoring and management. 5G network, the fifth generation of mobile communication technology, has the characteristics of high speed, large capacity and low latency. In this system, the 5G network is used as a medium for data transmission, which can transmit various information inside the hospital in real time and efficiently. The system receives three types of data in real time through the 5G network: dynamically updated map information in the hospital, first sensor data collected by the first sensor, and first image data collected by the first camera. The dynamically updated map information may include layout changes inside the hospital, department location adjustments, etc. The first sensor data may include environmental parameters such as temperature, humidity, light intensity, or the operating status of medical equipment. The first image data is a video or image captured in real time by a camera installed inside the hospital, which is used to monitor the situation inside the hospital. The system constructs a three-dimensional spatial model inside the hospital based on the received map information and first sensor data. This model is a virtual, three-dimensional representation of the internal environment of a hospital, which can intuitively display the internal layout of the hospital, the location of departments, environmental parameters and other information. The construction process of a three-dimensional spatial model may involve related technologies such as geographic information systems (GIS), computer graphics and virtual reality (VR).

[0023] S120, analyzing the first image data to determine the flow pattern of people and the distribution of static obstacles in the hospital, and predicting the obstacle distribution state within a preset time in the future according to the flow pattern of people and the distribution of static obstacles; The first image data collected in real time by the first camera inside the hospital is received. The first image data contains various visual information inside the hospital, such as personnel flow and medical equipment. The first image data is analyzed to extract the flow pattern and static obstacle distribution in the hospital. The flow pattern refers to the flow pattern of personnel inside the hospital in a specific time period, such as peak hours, flow direction, etc. This can be obtained by analyzing the number of pedestrians, speed and trajectory in the image. The static obstacle distribution refers to obstacles that are fixed or slowly changing inside the hospital, such as medical equipment and walls. These obstacles appear in relatively stable shapes and positions in the image. After obtaining the flow pattern and static obstacle distribution, the system can use this information to predict the obstacle distribution state in the hospital within a preset time in the future. The prediction process may involve artificial intelligence technologies such as machine learning and deep learning, and predict the changing trend of the internal environment of the hospital in the future time period by learning and analyzing historical data. In the prediction, the system needs to consider multiple factors, such as the changing pattern of personnel flow, the use of medical equipment, and the activity patterns of patients and medical staff. These factors may affect the obstacle distribution state inside the hospital. The prediction result can be a dynamic three-dimensional model or two-dimensional image, showing the expected changes in the distribution status of obstacles inside the hospital within a preset time in the future.

[0024] Optionally, the predicting of the obstacle distribution state within a preset future time according to the pedestrian flow pattern and the static obstacle distribution includes: Parsing the first image data to obtain current crowd flow data and static obstacle data, wherein the crowd flow data includes the number, movement direction and speed of pedestrians in different areas inside the hospital, and the static obstacle data includes the size and location of the obstacle; Based on the historical crowd flow data and the current crowd flow data, predict the changing trend of the crowd flow in each area within a preset time period in the future; According to the change trend and the static obstacle data, the distribution status of the dynamic obstacles in the future preset time period is determined, the hospital is divided into crowded areas, dense areas and general areas according to the distribution status, and the traffic bottleneck areas are determined in the crowded areas and the dense areas.

[0025] By analyzing the image data collected by the first camera, the system can extract the number of pedestrians, movement direction and speed in different areas of the hospital. This information is key to understanding the current flow pattern. The system can also identify static obstacles inside the hospital, such as medical equipment and walls, from the image data, and record their size and location. This information is crucial for the subsequent determination of the distribution status of dynamic obstacles. The system not only considers the current flow data, but also combines historical flow data (such as pedestrian flow patterns in the past period of time) to predict the change trend of the flow of people in each area in the future preset time period. This prediction may involve advanced technologies such as time series analysis and machine learning. The prediction results will show the increase or decrease of the flow of people in the hospital in the future. The trend of changes in the flow direction. Based on the predicted flow change trend and the known static obstacle data, the system can determine the distribution status of dynamic obstacles in the future preset time period. This includes pedestrians, mobile equipment (such as wheelchairs, beds) and other objects that may hinder passage. Based on the distribution status of dynamic obstacles, the system divides the hospital into different areas: Crowded areas: areas where dense crowds and a large number of dynamic obstacles are expected.

[0026] Dense Area: An area that is not as crowded as a congested area but still has a high density of people flow and dynamic obstacles.

[0027] General area: an area with relatively few pedestrians and dynamic obstacles and smoother traffic.

[0028] Bottleneck areas: In congested and dense areas, the system will further identify possible bottlenecks, that is, areas where the speed of travel may drop significantly due to small spaces, many obstacles or the intersection of people.

[0029] By parsing the first image data, the system can accurately obtain the number of pedestrians, movement direction and speed in different areas of the current hospital, as well as the size and location of static obstacles. This information provides a solid foundation for subsequent predictions. Based on historical and current crowd flow data, the system can predict the changing trend of the flow of people in each area within a preset time period in the future. This prediction capability helps hospitals understand the changes in the flow of people in advance, so as to make reasonable plans and arrangements. Based on the predicted trend of the flow of people and the static obstacle data, the system can determine the distribution of dynamic obstacles within a preset time period in the future. This distribution reflects the degree of congestion in different areas of the hospital. The system further divides the hospital into crowded areas, dense areas and general areas. In crowded and dense areas, the system can also determine the bottleneck areas. These areas are places where people flow densely and traffic is difficult, such as corridor intersections, elevator entrances, etc.

[0030] Optionally, determining the traffic bottleneck area in the congested area and the dense area includes: Determine the pedestrian flow restricted area by comparing the predicted pedestrian density change with the preset threshold; The duration and impact of the pedestrian restricted flow area are predicted based on the historical crowd flow data and the change trend, and the target area with the greatest impact on the overall crowd flow is determined as the traffic bottleneck area based on the area, duration and impact of the pedestrian restricted flow area.

[0031] According to the predicted trend of pedestrian flow in the future time period, the pedestrian density in different areas of the hospital is calculated. Pedestrian density refers to the number of pedestrians per unit area, which reflects the degree of congestion in the area. The predicted pedestrian density is compared with the preset threshold. This preset threshold is set according to the actual situation and safety management requirements inside the hospital, and it represents the critical value at which pedestrian flow begins to be restricted. If the predicted pedestrian density in a certain area exceeds the preset threshold, then the area is considered to be a pedestrian flow restricted area. This means that in this area, the flow of pedestrians may be hindered and the traffic efficiency will be reduced. For areas determined as pedestrian flow restricted, the system also needs to further predict the duration and impact of these areas. The duration refers to how long the pedestrian flow restriction state is expected to last, and the impact refers to how much impact this restriction has on the overall flow of people. These predictions are based on historical flow data and current change trends. The system predicts the future state of the pedestrian flow restricted area by analyzing similar situations in historical data and combining them with the current change trend. After determining the pedestrian flow restricted area and its duration and impact, the system needs to find the target area with the greatest impact on the overall flow of people as the bottleneck area. This target area is determined by comprehensively considering the area, duration, and impact of the restricted pedestrian flow area. The larger the area, the longer the duration, and the greater the impact, the more likely it is to be a bottleneck area. When the bottleneck area is determined, the system can try to avoid passing through the bottleneck area in subsequent route planning, thereby reducing interference with the existing crowd.

[0032] By comparing the predicted changes in pedestrian density with the preset threshold, the areas with restricted pedestrian flow can be accurately identified. This comparison method can quickly lock in those areas that may cause difficulty in passing due to excessively high pedestrian density, providing a basis for subsequent path planning. According to historical pedestrian flow data and change trends, the duration and impact of the areas with restricted pedestrian flow are predicted. This prediction not only takes into account the current pedestrian flow conditions, but also combines historical data to make the evaluation results more comprehensive and accurate. By evaluating the area, duration and impact of restricted areas, the method can deeply understand the impact of these areas on the overall pedestrian flow, providing strong support for subsequent decision-making. According to the evaluation results of the impact of restricted areas on the overall pedestrian flow, the target area with the greatest impact on the overall pedestrian flow is determined as the bottleneck area. This positioning method not only takes into account the congestion level of the area, but also combines its impact on the overall pedestrian flow, making the determined bottleneck area more accurate and meaningful.

[0033] S130, determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand; The three-dimensional space model is a virtual representation of the internal environment of the hospital, including key elements such as the layout of the hospital, department locations, corridors, stairs, elevators, etc. This model provides a basic spatial framework for path planning. Dynamic obstacles refer to obstacles that change their position over time inside the hospital, such as personnel, medical equipment, temporary facilities, etc. Information such as the location, quantity, and movement speed of these obstacles is crucial for path planning. Through real-time monitoring and analysis, the system can obtain the distribution status of dynamic obstacles in the current and future period, including areas that may become crowded or impassable due to dense traffic or equipment movement. Work requirements may include patient transfer, medical staff rounds, emergency rescue, and other situations. Each requirement has its own specific urgency. For example, emergency rescue usually requires the highest priority path planning. The system needs to adjust the priority of path planning according to the urgency of the work requirements to ensure that the optimal path can be quickly found in an emergency. In the three-dimensional space model, the system needs to use path planning algorithms to search for the optimal path from the starting point to the end point. These algorithms usually consider multiple factors such as obstacles in the space, path length, and travel speed. In terms of obstacle avoidance, the system needs to adjust the path in real time according to the distribution status of obstacles to avoid collisions with people or equipment. According to the urgency of work needs, the system needs to adjust the priority of path planning. Urgent needs should be given higher priority to ensure that the optimal path is found within a limited time. This may involve adjusting the algorithm parameters, such as increasing the search speed, reducing the path length, etc., to meet the needs in emergency situations. After comprehensively considering the three-dimensional space model, the distribution status of obstacles and the urgency of work needs, the system can determine a preliminary path. This path should be as short, safe and meet the requirements of urgency as possible. After the preliminary path is determined, the system needs to monitor the changes of dynamic obstacles in real time to ensure that the path is still feasible. If the path is blocked or becomes unsafe, the system needs to adjust the path immediately. Based on the results of real-time monitoring, the system can optimize the preliminary path. This may include adjusting the path length, avoiding more crowded areas, or choosing a safer way of passing. After verification and optimization, the system can output the final path. This path should meet the requirements of work needs while ensuring safety and efficiency.

[0034] Optionally, determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand includes: When the urgency of the work requirement is greater than or equal to a first threshold, a preliminary path with the shortest time is determined, and a warning message is sent to mobile devices in the target area involved in the preliminary path through the 5G network, prompting the user of the mobile device to avoid it, and turning on the sound warning unit on the 5G nursing robot.

[0035] An urgency value will be set for each work requirement. When the urgency of the work requirement is greater than or equal to the preset first threshold, the current task is considered to be an emergency task. After confirming that the task is an emergency task, the system will plan a preliminary path with the shortest time based on the three-dimensional space model and the dynamic obstacle distribution status. This path is designed to ensure that the emergency task can be completed as quickly as possible while avoiding possible obstacles. In order to ensure the smooth and safe preliminary path, the system will use the 5G network to send warning information to mobile devices in the target area involved in the preliminary path. These mobile devices may be mobile phones of staff within the hospital, communication modules on medical equipment, etc. The content of the warning information will prompt the user of the mobile device to pay attention to avoidance, that is, inform them that there is an emergency task in progress and they need to cooperate in avoidance to ensure the smooth flow of the path. At the same time, the system will also turn on the sound warning unit on the 5G nursing robot. This unit will emit a sound signal to further remind the surrounding personnel to pay attention to avoidance and ensure that the emergency task can proceed smoothly.

[0036] When the urgency of the work demand is greater than or equal to the first threshold, the system can quickly determine the shortest preliminary path. This is crucial for emergency tasks that require a quick response (such as medical emergency, disaster relief, etc.) because it can minimize the response time and improve the efficiency of task execution. By sending warning information in advance to mobile devices in the target area involved in the preliminary path through the 5G network, the corresponding user of the mobile device can be reminded to avoid. This real-time communication capability not only improves the safety of path planning, but also reduces delays caused by path conflicts or obstacles. At the same time, turning on the sound warning unit on the 5G nursing robot can further alert the surrounding personnel to ensure that no accidents occur due to negligence when performing emergency tasks. The 5G network has the characteristics of high speed and low latency, which enables the system to transmit large amounts of data (such as three-dimensional space models, dynamic obstacle information, warning information, etc.) in real time and respond quickly. This is crucial for application scenarios that require real-time updates and precise control.

[0037] Optionally, determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand includes: When the urgency of the work demand is less than a second threshold, determining whether a complete path can be formed based on the general area, and the first threshold is greater than the second threshold; When a complete path cannot be constructed based on the general area, multiple first candidate paths are constructed based on the general area and the dense area, and a first path that passes through the least dense area is selected from the multiple first candidate paths. When there are multiple first paths, a second path with the shortest time is selected from the first paths as a preliminary path.

[0038] Determine whether the urgency of the work demand is less than the second threshold. The second threshold is also a preset parameter used to distinguish between urgent tasks and non-urgent tasks. The first threshold is greater than the second threshold, indicating that a task with a higher urgency will trigger another set of path planning logic (such as the shortest path planning in emergency situations mentioned earlier). If the urgency of the work demand is less than the second threshold, the system first tries to build a complete path in the general area. The general area refers to an area in the hospital that is relatively open, has less traffic, and has higher traffic efficiency. The system checks whether a complete path can be built based on the general area. This includes checking whether the path is continuous, whether there are obstacles that cannot be crossed, etc. If a complete path cannot be built based on the general area (possibly because some key locations belong to dense areas or crowded areas), the system considers building multiple first candidate paths in the general area and dense areas. Dense areas refer to areas with more traffic and lower traffic efficiency. The system selects the first path that passes through the least dense areas from multiple first candidate paths. This is because in non-emergency situations, reducing the number of dense areas passed through helps reduce the cost of travel (such as reducing waiting time, avoiding congestion, etc.). If there are multiple first paths that pass through the same number of dense areas, the system further selects the second path with the shortest time from these paths as the preliminary path. This is to optimize traffic efficiency while ensuring route feasibility.

[0039] When the urgency of the work demand is less than the second threshold, the system first tries to form a complete path in the general area. This strategy helps to avoid occupying resources in dense or crowded areas when the urgency is not high, thereby optimizing the allocation and utilization of resources within the hospital. If a complete path cannot be formed in the general area, the system can flexibly adjust the strategy and build multiple first candidate paths in combination with general and dense areas. This flexibility ensures that feasible path solutions can be found in different scenarios. When selecting the first candidate path, the system gives priority to the path that passes through the least dense area. This helps to reduce the obstacles and delays that may be encountered due to crossing crowded areas, as well as interference with personnel, and improves the efficiency and safety of the path. When there are multiple paths that pass through the least dense areas, the system further selects the path with the shortest time as the preliminary path. This strategy ensures the optimality of the selected path in terms of time and efficiency, and helps to improve the efficiency and effectiveness of the overall task execution.

[0040] Optionally, determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand includes: When the urgency of the work demand is greater than or equal to the second threshold and less than the first threshold, constructing a plurality of second candidate paths according to the departure place and the destination; The interference weights of passing through a crowded area, a dense area, and a general area are set to be a first sub-weight, a second sub-weight, and a third sub-weight, respectively; the interference score of the second candidate path is calculated according to the number of times of passing through the crowded area, the dense area, and the general area and the first sub-weight, the second sub-weight, and the third sub-weight, wherein the first sub-weight is greater than the second sub-weight, and the second sub-weight is greater than the third sub-weight; Calculate the congestion coefficient of each area according to the predicted crowd flow density, determine the time of each area according to the congestion coefficient, and calculate the total time of the second candidate path according to the time; The interference score and the total time are weightedly summed to obtain a total score, and the second candidate path with the smallest total score is selected as the preliminary path.

[0041] When the urgency of the work demand is between the second threshold and the first threshold (i.e., general urgency), the system starts to build a path planning. Based on the location information of the departure and destination, the system uses the three-dimensional space model and the dynamic obstacle distribution status (such as personnel flow, equipment location, etc.) to build multiple possible second candidate paths. In order to evaluate the potential impact of different areas on the path, the system sets interference weights for passing through crowded areas, dense areas, and general areas. These weights reflect the relative importance of different areas to path planning, among which the weight of crowded areas is the highest (first sub-weight), followed by dense areas (second sub-weight), and the general area is the lowest (third sub-weight). For each second candidate path, the system calculates an interference score based on the number of times it passes through different areas and the corresponding weights. The higher this score, the greater the potential interference to the path. The system uses historical data and real-time information to predict the density of people flow in each area. Based on the predicted density of people flow, the system determines a congestion coefficient for each area. This coefficient reflects the speed of travel and possible delays in the area in the current and future period. For each second candidate path, the system calculates a total time based on the congestion coefficient and path length of each area it passes through. This time includes the extra time that may be caused by congestion. For each second candidate path, the system weights and sums its interference score and total time to obtain a total score. This total score combines the potential interference and actual time of the path. The system selects the second candidate path with the smallest total score as the preliminary path. This path achieves the best balance between potential interference and actual time. For example, the interference weight (first sub-weight) of the crowded area is set to the highest, such as 5 points, the interference weight (second sub-weight) of the dense area is set to the medium, such as 3 points, and the interference weight (third sub-weight) of the general area is set to the lowest, such as 1 point. Assuming that there are paths A and B that can reach the destination, for path A, assuming that it only passes through the general area three times, then its interference score is the number of general areas multiplied by the third sub-weight, that is, 3*1=3 points; for path B, assuming that it passes through a crowded area once and a dense area twice, then its interference score is 1*5+2*3=11 points. According to the predicted crowd density, the congestion coefficient of each area can be calculated. For example, a congested area may have a congestion factor of 2.0 (indicating half the normal speed), while a normal area may have a congestion factor of 1.0 (indicating normal speed). The total time for each path is calculated based on the congestion factor and the distance of each area. For example, path A may only take 5 minutes, while path B may take 10 minutes. Finally, the interference score and total time of each path are weighted and summed to get the total score.Assuming that the weights of interference score and total time are both 0.5 (i.e., both are equally important), the total score of path A is 0.5*3+0.5*5=4 points, and the total score of path B is 0.5*11+0.5*10=10.5 points. Obviously, the total score of path A is lower, so path A should be selected as the preliminary path.

[0042] When the urgency of the work demand is at a medium level (greater than or equal to the second threshold and less than the first threshold), the system can construct multiple second candidate paths and calculate the interference score of each path by setting the interference weights of different areas. This refined path planning strategy helps to find the optimal path that takes into account both traffic efficiency and traffic difficulty when the urgency is moderate. By setting the interference weights (first sub-weight, second sub-weight and third sub-weight) of passing through crowded areas, dense areas and general areas, the system can perform differentiated evaluations on paths according to the traffic difficulty of different areas. This processing method helps to avoid over-reliance on a single factor (such as the shortest distance) during path planning, thereby ensuring the feasibility and efficiency of the selected path in actual traffic. The system can calculate the congestion coefficient of each area based on the predicted crowd density and determine the time required for each area accordingly. This processing method fully considers the impact of dynamic obstacles (such as crowd flow) on path planning, so that the selected path can more accurately reflect the actual traffic situation. By weighted summing the interference score and the total time to obtain the total score, the system can comprehensively evaluate the pros and cons of each second candidate path. This comprehensive evaluation method helps to select the best path from multiple feasible paths and ensure the scientificity and rationality of path planning. It combines multiple factors such as the three-dimensional space model, dynamic obstacle distribution status, and the urgency of work needs, and improves the efficiency and accuracy of path planning through refined path planning and comprehensive evaluation strategies. This helps to quickly find the best path in practical applications, reduce travel time and costs, and improve overall operational efficiency.

[0043] S140. In the process of moving along the preliminary path, a second sensor and a second camera are used to identify pedestrians and their movement trends, and the preliminary path is adjusted according to the movement trends. The second sensor and the second camera are installed on the 5G nursing robot.

[0044] The second sensor may include radar sensors, infrared sensors, etc., which are used to sense obstacles and pedestrian dynamics in the surrounding environment. These sensors can provide information such as the location and speed of pedestrians in real time. The second camera is used to capture image information of the surrounding environment and identify pedestrians and their movement trends through image recognition technology. The camera can capture high-definition video and analyze pedestrians' walking direction, speed and other characteristics through algorithms. The second sensor and the second camera collect data of the surrounding environment in real time, including information such as the location, speed, and movement direction of pedestrians. The system processes and analyzes the collected data and identifies the movement trends of pedestrians through algorithms, such as whether they are about to enter the path, whether the walking speed is accelerating, etc. According to the movement trends of pedestrians, the system dynamically adjusts the preliminary path. For example, if it is detected that a pedestrian is about to enter the path, the system can adjust the path to avoid the pedestrian; if the pedestrian walks faster, the system can predict its possible movement trajectory and adjust the path in advance. The adjusted path information is fed back to the control system of the 5G nursing robot in real time, and the control system controls the movement of the vehicle according to the new path information. By sensing and identifying pedestrians and their movement trends in real time, the system can detect potential dangers in advance and adjust the path to avoid collisions with pedestrians and improve safety during movement. Dynamically adjusting the path can reduce delays caused by avoiding pedestrians and improve the mobility efficiency of the 5G nursing robot. The 5G nursing robot will first use the pre-loaded internal map of the hospital for initial positioning. By comparing the second sensor data of the 5G nursing robot with the map information, the initial position of the robot relative to the map is determined. During the initial positioning stage, the 5G nursing robot will also calibrate the installed second sensor to ensure the accuracy of the second sensor data. This includes the calibration of multiple sensors such as lidar, infrared sensors, and cameras. During the movement of the 5G nursing robot, it will continue to collect data from lidar, infrared sensors, etc. These data include distance information, obstacle information, direction information, etc. At the same time, the 5G nursing robot will also use the second camera to capture real-time images and extract feature information in the image, such as edges, corners, etc. through image processing algorithms. The sensor data and camera data are fused and processed to obtain more comprehensive environmental information. Based on the real-time collected data, the robot will use a positioning algorithm (such as a SLAM algorithm) to estimate the position. This step will comprehensively consider the sensor data and camera data, as well as the robot's motion model, to obtain an accurate estimate of the robot's current position.

[0045] Optionally, adjusting the preliminary path according to the movement trend includes: Dividing the preliminary path into multiple sub-paths, and setting a break point between two adjacent sub-paths; Based on the identified pedestrian movement trends, predict the intersection point and intersection time with pedestrians; Slows down movement and reroutes from the current point to the next break point based on predicted junctions and times.

[0046] The preliminary path is divided into multiple sub-paths, each of which represents a stage or area in the movement process. Interruption points are set between two adjacent sub-paths, which serve as key nodes for path adjustment. When an interruption point is triggered, the system will re-evaluate and adjust the subsequent path. The position and movement trend of pedestrians are identified in real time using sensors and cameras installed on the 5G nursing robot. Based on the identified pedestrian movement trend, the system predicts the possible intersection point and intersection time between the mobile workstation and the pedestrian. This prediction takes into account the speed and direction of the pedestrian and the current speed and path of the mobile workstation. When the intersection point and intersection time with the pedestrian are predicted, the system first slows down the speed of the mobile workstation to ensure that there is enough time for path adjustment. While slowing down, the system re-determines the path from the current point to the next interruption point. This path adjustment is intended to avoid the predicted intersection point, or at least reduce the risk of conflict with pedestrians. The adjusted path information is fed back to the control system of the mobile workstation in real time, and the control system controls the movement of the vehicle based on the new path information.

[0047] The preliminary path is divided into multiple sub-paths, and interruption points are set between two adjacent sub-paths, so that the system can quickly adjust the path when necessary. This division method improves the flexibility of path adjustment, allowing the system to better adapt to the dynamically changing pedestrian environment. By predicting the intersection point and intersection time with pedestrians based on the identified pedestrian movement trend, the system can perceive potential dangers in advance and take measures such as deceleration to avoid collisions with pedestrians. This predictive ability significantly enhances safety during movement. Based on the predicted intersection point and intersection time, the system can intelligently adjust the movement speed to avoid unnecessary waiting and delays. At the same time, redefining the path from the current point to the next interruption point can ensure a smoother movement process, thereby improving overall movement efficiency. Through intelligent path adjustment and speed control, the system can provide users with a safer and more efficient mobile experience. This helps to improve users' satisfaction and trust in medical services.

[0048] This embodiment also discloses a path planning system for a 5G nursing robot. Figure 2 is a module schematic diagram of the path planning system of the 5G nursing robot disclosed in the embodiment of the present application, such as Figure 2 As shown, the system includes a map module 201, a prediction module 202, a path module 203 and an adjustment module 204, wherein: A map module 201 is configured to receive in real time through a 5G network dynamically updated map information in the hospital, first sensor data collected by a first sensor, and first image data collected by a first camera, and construct a three-dimensional space model inside the hospital according to the map information and the first sensor data, wherein the first sensor and the first camera are installed at preset positions inside the hospital; A prediction module 202, configured to analyze the first image data to determine a human flow pattern and a distribution of static obstacles in the hospital, and predict an obstacle distribution state within a preset time in the future according to the human flow pattern and the distribution of static obstacles; A path module 203, configured to determine a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand; The adjustment module 204 is configured to use a second sensor and a second camera to identify pedestrians and their movement trends during the movement along the preliminary path, and adjust the preliminary path according to the movement trends. The second sensor and the second camera are installed on the 5G nursing robot.

[0049] Optionally, the prediction module 202 is configured to: Parsing the first image data to obtain current crowd flow data and static obstacle data, wherein the crowd flow data includes the number, movement direction and speed of pedestrians in different areas inside the hospital, and the static obstacle data includes the size and location of the obstacle; Based on the historical crowd flow data and the current crowd flow data, predict the changing trend of the crowd flow in each area within a preset time period in the future; According to the change trend and the static obstacle data, the distribution status of the dynamic obstacles in the future preset time period is determined, the hospital is divided into crowded areas, dense areas and general areas according to the distribution status, and the traffic bottleneck areas are determined in the crowded areas and the dense areas.

[0050] Optionally, the prediction module 202 is configured to: Determine the pedestrian flow restricted area by comparing the predicted pedestrian density change with the preset threshold; The duration and impact of the pedestrian restricted flow area are predicted based on the historical crowd flow data and the change trend, and the target area with the greatest impact on the overall crowd flow is determined as the traffic bottleneck area based on the area, duration and impact of the pedestrian restricted flow area.

[0051] Optionally, the path module 203 is configured to: When the urgency of the work requirement is greater than or equal to a first threshold, a preliminary path with the shortest time is determined, and a warning message is sent to mobile devices in the target area involved in the preliminary path through the 5G network, prompting the user of the mobile device to avoid it, and turning on the sound warning unit on the 5G nursing robot.

[0052] Optionally, the path module 203 is configured to: When the urgency of the work demand is less than a second threshold, determining whether a complete path can be formed based on the general area, and the first threshold is greater than the second threshold; When a complete path cannot be constructed based on the general area, multiple first candidate paths are constructed based on the general area and the dense area, and a first path that passes through the least dense area is selected from the multiple first candidate paths. When there are multiple first paths, a second path with the shortest time is selected from the first paths as a preliminary path.

[0053] Optionally, the path module 203 is configured to: When the urgency of the work demand is greater than or equal to the second threshold and less than the first threshold, constructing a plurality of second candidate paths according to the departure place and the destination; The interference weights of passing through a crowded area, a dense area, and a general area are set to be a first sub-weight, a second sub-weight, and a third sub-weight, respectively; the interference score of the second candidate path is calculated according to the number of times of passing through the crowded area, the dense area, and the general area and the first sub-weight, the second sub-weight, and the third sub-weight, wherein the first sub-weight is greater than the second sub-weight, and the second sub-weight is greater than the third sub-weight; Calculate the congestion coefficient of each area according to the predicted crowd flow density, determine the time of each area according to the congestion coefficient, and calculate the total time of the second candidate path according to the time; The interference score and the total time are weightedly summed to obtain a total score, and the second candidate path with the smallest total score is selected as the preliminary path.

[0054] Optionally, the adjustment module 204 is configured to: Dividing the preliminary path into multiple sub-paths, and setting a break point between two adjacent sub-paths; Based on the identified pedestrian movement trends, predict the intersection point and intersection time with pedestrians; Slows down movement and reroutes from the current point to the next break point based on predicted junctions and times.

[0055] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0056] This embodiment also discloses an electronic device, referring to Figure 3 The electronic device may include: at least one processor 301 , at least one communication bus 302 , a user interface 303 , a network interface 304 , and at least one memory 305 .

[0057] The communication bus 302 is used to realize the connection and communication between these components.

[0058] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0059] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0060] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0061] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be optionally at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a path planning method for a 5G nursing robot.

[0062] exist Figure 3 In the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 301 can be used to call the application program of the path planning method of the 5G nursing robot stored in the memory 305. When executed by one or more processors 301, the electronic device executes one or more methods in the above-mentioned embodiments.

[0063] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0064] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0065] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0066] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0067] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0068] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory 305 and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory 305 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk.

[0069] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A path planning method for a 5G nursing robot, characterized in that: Applied to a 5G nursing robot, the method comprises: receiving in real time through a 5G network dynamically updated map information in the hospital, first sensor data collected by a first sensor, and first image data collected by a first camera, and constructing a three-dimensional space model inside the hospital according to the map information and the first sensor data, wherein the first sensor and the first camera are installed at preset positions inside the hospital; Analyze the first image data to determine the flow pattern of people and the distribution of static obstacles in the hospital, and predict the obstacle distribution state within a preset time in the future according to the flow pattern of people and the distribution of static obstacles; Determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand; In the process of moving along the preliminary path, a second sensor and a second camera are used to identify pedestrians and their movement trends, and the preliminary path is adjusted according to the movement trends. The second sensor and the second camera are installed on the 5G nursing robot.

2. The path planning method of the 5G nursing robot according to claim 1 is characterized in that: The predicting of the obstacle distribution state within a preset time in the future according to the pedestrian flow pattern and the static obstacle distribution includes: Parsing the first image data to obtain current crowd flow data and static obstacle data, wherein the crowd flow data includes the number, movement direction and speed of pedestrians in different areas inside the hospital, and the static obstacle data includes the size and location of the obstacle; Based on the historical crowd flow data and the current crowd flow data, predict the changing trend of the crowd flow in each area within a preset time period in the future; According to the change trend and the static obstacle data, the distribution status of the dynamic obstacles in the future preset time period is determined, the hospital is divided into crowded areas, dense areas and general areas according to the distribution status, and the traffic bottleneck areas are determined in the crowded areas and the dense areas.

3. The path planning method of the 5G nursing robot according to claim 2 is characterized in that: Determining the traffic bottleneck area in the congested area and the dense area comprises: Determine the pedestrian flow restricted area by comparing the predicted pedestrian density change with the preset threshold; The duration and impact of the pedestrian restricted flow area are predicted based on the historical crowd flow data and the change trend, and the target area with the greatest impact on the overall crowd flow is determined as the traffic bottleneck area based on the area, duration and impact of the pedestrian restricted flow area.

4. The path planning method of the 5G nursing robot according to claim 1 is characterized in that: Determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand includes: When the urgency of the work requirement is greater than or equal to a first threshold, a preliminary path with the shortest time is determined, and a warning message is sent to mobile devices in the target area involved in the preliminary path through the 5G network, prompting the user of the mobile device to avoid it, and turning on the sound warning unit on the 5G nursing robot.

5. The path planning method of the 5G nursing robot according to claim 4 is characterized in that: Determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand includes: When the urgency of the work demand is less than a second threshold, determining whether a complete path can be formed based on the general area, and the first threshold is greater than the second threshold; When a complete path cannot be constructed based on the general area, multiple first candidate paths are constructed based on the general area and the dense area, and a first path that passes through the least dense area is selected from the multiple first candidate paths. When there are multiple first paths, a second path with the shortest time is selected from the first paths as a preliminary path.

6. The path planning method of the 5G nursing robot according to claim 5, characterized in that: Determining a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand includes: When the urgency of the work demand is greater than or equal to the second threshold and less than the first threshold, constructing a plurality of second candidate paths according to the departure place and the destination; The interference weights of passing through a crowded area, a dense area, and a general area are set to be a first sub-weight, a second sub-weight, and a third sub-weight, respectively; the interference score of the second candidate path is calculated according to the number of times of passing through the crowded area, the dense area, and the general area and the first sub-weight, the second sub-weight, and the third sub-weight, wherein the first sub-weight is greater than the second sub-weight, and the second sub-weight is greater than the third sub-weight; Calculate the congestion coefficient of each area according to the predicted crowd flow density, determine the time of each area according to the congestion coefficient, and calculate the total time of the second candidate path according to the time; The interference score and the total time are weightedly summed to obtain a total score, and the second candidate path with the smallest total score is selected as the preliminary path.

7. The path planning method of the 5G nursing robot according to claim 1, characterized in that: The adjusting the preliminary path according to the movement trend comprises: Dividing the preliminary path into multiple sub-paths, and setting a break point between two adjacent sub-paths; Based on the identified pedestrian movement trends, predict the intersection point and intersection time with pedestrians; Slows down movement and reroutes from the current point to the next break point based on predicted junctions and times.

8. A path planning system for a 5G nursing robot, characterized in that: It includes map module, prediction module, path module and adjustment module, among which: a map module configured to receive in real time through a 5G network dynamically updated map information in the hospital, first sensor data collected by a first sensor, and first image data collected by a first camera, and construct a three-dimensional space model inside the hospital according to the map information and the first sensor data, wherein the first sensor and the first camera are installed at preset positions inside the hospital; a prediction module configured to analyze the first image data to determine a human flow pattern and a distribution of static obstacles in the hospital, and predict a distribution state of obstacles within a preset time in the future according to the human flow pattern and the distribution of static obstacles; A path module, configured to determine a preliminary path according to the three-dimensional space model, the obstacle distribution state and the urgency of the work demand; The adjustment module is configured to use a second sensor and a second camera to identify pedestrians and their movement trends during the movement along the preliminary path, and adjust the preliminary path according to the movement trends. The second sensor and the second camera are installed on the 5G nursing robot.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images