An airport terminal environment autonomous inspection vehicle monitoring system

Abstract

The present invention discloses an airport terminal environment autonomous patrol vehicle monitoring system, comprising: autonomous patrol vehicles, the number of which is multiple, for performing environmental monitoring of the airport terminal and acquiring secondary data according to a planned path; wherein the autonomous patrol vehicle comprises a navigation positioning guidance unit; a data acquisition module, for acquiring monitoring data of relevant monitoring equipment in the airport terminal, and generating primary data according to the monitoring data; a central control module, for acquiring secondary data and primary data, and updating the driving path of each autonomous patrol vehicle based on a cost function and a non-zero-sum game model, and sending the data to the corresponding autonomous patrol vehicle; the present invention combines non-zero-sum game theory and an improved cost function to adjust the path costs of multiple autonomous patrol vehicles, reduce the probability of a falsely low path cost of each patrol vehicle, and prevent waste of resources caused by multiple autonomous patrol vehicles concentrating on the same area, and at the same time reasonably plan the inspection path of each patrol vehicle to improve monitoring efficiency.

Description

Technical Field

[0001] The invention belongs to the technical field of path planning, and in particular relates to an airport terminal environment autonomous inspection vehicle monitoring system. Background Art

[0002] China's civil aviation is vigorously promoting the development strategy of a strong civil aviation country, emphasizing the construction of a new type of large-scale international modern airport in the new era. The future aviation field has broad development space. With the continuous construction and expansion of super-large civil transport hub airports, airports will usher in a development stage of safety, digitization, informatization, visualization, and intelligence. From small and medium-sized airports with an annual passenger throughput of hundreds of thousands to large airports with more than 10 million passengers, safety is always the primary consideration. Environmental monitoring of the terminal is one of the important measures to ensure the personal safety of passengers and staff and the safe and stable operation of the terminal.

[0003] The airport terminal has a huge building area. Traditional manual inspections not only have problems such as unstable inspection quality, low monitoring accuracy and efficiency, and monitoring blind spots, but also the monitoring information is often not reflected in a timely manner, which can easily cause safety hazards. The currently commonly used environmental fixed-point monitoring devices require a lot of infrastructure to be laid, with high maintenance costs and fixed-point monitoring. In order to solve this technical problem, the existing technology proposes an autonomous patrol vehicle monitoring system for autonomous monitoring of the environment in the airport terminal, replacing manual inspections with patrol vehicles, and conducting targeted environmental monitoring of different areas of the airport terminal, which greatly reduces the number of airport security and inspection personnel and improves the quality of environmental monitoring and operation and maintenance efficiency.

[0004] However, the existing technology only uses the cost function method to plan the driving path of the autonomous patrol vehicle. When multiple autonomous patrol vehicles are deployed in the same area, the improved A* path planning algorithm based on the cost function usually only returns the optimal path once when the minimum cost is calculated. Therefore, multiple autonomous patrol vehicles in the same area will go to the same area due to the returned optimal path, resulting in a falsely low path cost, waste of resources, and reduced monitoring efficiency. Summary of the invention

[0005] In view of this, the purpose of the present invention is to provide an airport terminal environment autonomous patrol vehicle monitoring system, which is used to combine non-zero-sum game theory and improved cost function to adjust the path costs of multiple autonomous patrol vehicles, reduce the probability of false low path costs of each autonomous patrol vehicle, and prevent the waste of resources caused by multiple autonomous patrol vehicles concentrating on the same area. At the same time, the inspection path of each autonomous patrol vehicle is reasonably planned to improve monitoring efficiency.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] An airport terminal environment autonomous inspection vehicle monitoring system, comprising:

[0008] A plurality of autonomous inspection vehicles are used to monitor the environment of the airport terminal and obtain secondary data according to the planned path; wherein the autonomous inspection vehicle includes a navigation positioning guidance unit;

[0009] The navigation positioning and guidance unit is used to determine the initial position of the autonomous inspection vehicle according to the RSSI ranging positioning algorithm, and automatically determine and update the real-time relative position of the autonomous inspection vehicle based on the initial position. At the same time, the path of the autonomous inspection vehicle is planned according to the cost function and the minimum cost target to obtain the planned path;

[0010] The data acquisition module is used to obtain the monitoring data of the relevant monitoring equipment of each regional node in the airport terminal and generate the main data based on the monitoring data;

[0011] The central control module is used to obtain secondary data and primary data to calculate the real-time pedestrian density of each regional node, determine the real-time monitoring importance level of each regional node according to the pedestrian density, generate the standard number of patrol vehicles for the corresponding regional node according to the real-time monitoring importance level, and obtain the number of autonomous patrol vehicles to be inspected at each regional node, determine whether the number of autonomous patrol vehicles to be inspected at each regional node meets the standard number of patrol vehicles for the corresponding regional node, determine multiple autonomous patrol vehicles for paths to be updated according to the judgment results and the retention principle, and update the driving path of each autonomous patrol vehicle for the path to be updated based on the cost function and the non-zero-sum game model, and send it to the corresponding autonomous patrol vehicle.

[0012] As an embodiment of the present invention, the autonomous inspection vehicle includes:

[0013] Communication unit, used for data exchange with the central control module and various fixed environmental monitoring devices in the airport terminal;

[0014] A mobile control unit is used to control the movement of the autonomous inspection vehicle according to the planned path and to avoid obstacles;

[0015] A comparison unit, used to compare whether the driving path received by the communication unit is the same as the planned path, and if not, update the planned path according to the driving path;

[0016] The mobile control unit is also used to perform mobile control operations on the autonomous inspection vehicle according to the updated planned path.

[0017] As an embodiment of the present invention, path planning is performed on the autonomous inspection vehicle according to the cost function and the minimum cost target to obtain a planned path, including:

[0018] Get the cost function :

[0019]

[0020] in, Indicated in i From the initial node to the path node under the path selection p The total cost of the next node, Indicated in i From the initial node to the path node under the path selection p The actual cost, Indicated in i Select the path node from the p The estimated cost to reach the next node, Indicates that at the next node j The weight of the environmental data, Indicates the total number of types of environmental data monitored at the next node. represents the pedestrian density at the next node, Indicates the pedestrian density safety value of each node;

[0021]

[0022] in, For the j Preset monitoring thresholds for various environmental data, Indicates the first node monitored at the next node j The actual values ​​of the environmental data;

[0023] According to the cost function and the minimum cost target, the minimum cost problem of the path is generated:

[0024]

[0025] The heuristic algorithm is used to solve the minimum path cost problem, obtain several optimal path nodes, and generate a planned path.

[0026] As an embodiment of the present invention, the autonomous inspection vehicle further includes:

[0027] The visual unit is used to collect information about buildings and pedestrians around the autonomous inspection vehicle;

[0028] The secondary positioning unit is used to determine the current location of the autonomous inspection vehicle based on the comparison of building information and built-in airport terminal building information;

[0029] The environmental monitoring unit is used to monitor the environmental data of the area where the autonomous inspection vehicle is currently located according to the preset environmental monitoring standards, and receive the interactive data between the communication unit and the fixed environmental monitoring equipment in the airport terminal, compare it with the monitoring data, and feed back the comparison data to the central control module;

[0030] The secondary data sorting unit is used to obtain the pedestrian information collected by the visual unit, and estimate the pedestrian density of the node in the area where the current autonomous inspection vehicle is currently located based on the pedestrian information. At the same time, it generates an area identifier and a time identifier to mark the corresponding pedestrian density to obtain secondary data.

[0031] As an embodiment of the present invention, the environment monitoring unit performs the following operations:

[0032] Obtaining preset environmental monitoring standards, and determining preset monitoring thresholds for each type of environmental data based on the preset environmental monitoring standards;

[0033] Acquire monitoring data of the environment in the area where the autonomous inspection vehicle is currently located, generate first comparison data according to the corresponding preset monitoring threshold, and if the first comparison data is abnormal, feed back the corresponding abnormal data to the central control module;

[0034] Receiving interactive data between the communication unit and each fixed environment monitoring device in the airport terminal; wherein the interactive data includes second monitoring data and device operation data of each fixed environment monitoring device on the corresponding environment data;

[0035] If there is any abnormality in the equipment operation data, the corresponding abnormal data will be fed back to the central control module;

[0036] If there is no abnormality in the equipment operation data, second comparison data is generated according to the monitoring data and the second monitoring data. If there is an abnormality in the second comparison data, the corresponding abnormal data is fed back to the central control module.

[0037] As an embodiment of the present invention, the data acquisition module performs the following operations:

[0038] Obtain monitoring data of relevant monitoring equipment at each regional node in the airport terminal; the relevant monitoring equipment includes security cameras and crowd counters;

[0039] Perform data preprocessing and feature extraction on the monitoring data to obtain the pedestrian density contained in the monitoring data;

[0040] Generate the area identification of each area node and the time identification of the monitoring data collection time, mark the corresponding pedestrian density contained in the monitoring data, and obtain the main data.

[0041] As an embodiment of the present invention, the central control module performs the following operations:

[0042] Obtain primary and secondary data, and calculate the real-time pedestrian density of each regional node based on the weighted sum method;

[0043] According to the real-time pedestrian density of each regional node, based on the preset pedestrian density and monitoring importance level comparison table, the real-time monitoring importance level of the corresponding regional node is obtained; wherein, the higher the pedestrian density in the preset pedestrian density and monitoring importance level comparison table, the higher the monitoring importance level;

[0044] According to the real-time monitoring importance level of each regional node, based on the preset monitoring importance level and patrol vehicle quantity arrangement table, the standard number of patrol vehicles for the corresponding regional node is obtained; wherein, the higher the preset monitoring importance level, the more standard patrol vehicles for the corresponding regional node;

[0045] Obtain the driving nodes included in the planned paths of all autonomous inspection vehicles, and determine the number of autonomous inspection vehicles to be inspected in each regional node based on all driving nodes;

[0046] If the number of autonomous inspection vehicles to be inspected at each regional node is greater than the number of standard inspection vehicles, according to the retention principle, the autonomous inspection vehicles whose number of autonomous inspection vehicles to be inspected at each regional node is equal to the number of standard inspection vehicles are retained and continue to drive according to the original planned path; among which, the retention principle is the principle of minimum total cost;

[0047] Send the path update information to the other L autonomous inspection vehicles participating in the retention principle screening;

[0048] After waiting for a node driving time, the autonomous inspection vehicles that obtain all the path information to be updated form a game model; in the game model, the participants are L autonomous inspection vehicles that request to update the path planning, and the strategy set is the set of recommended planning paths returned by the central control module to each participant;

[0049] Based on the game model and cost function, according to the non-zero-sum game principle, the updated driving path is returned to the corresponding autonomous inspection vehicle.

[0050] As an embodiment of the present invention, based on the game model and the cost function, according to the non-zero-sum game principle, returning an updated driving path to the corresponding autonomous inspection vehicle includes:

[0051] Get the strategy set of the game model ;in, Indicates L The recommended planning path for each participant, ,in, Indicates L Participant's c Recommended planning paths;

[0052] Based on the cost function and strategy set, generate the cost model of the game model:

[0053]

[0054] in, Indicates L Participants choose c The total cost of the path when recommending the planning path, Indicates c Each node selection strategy in the recommended planning path, Indicates c A first node selection strategy in the recommended planning path. Indicated in The next node after the node selection strategy is u The weight of the environmental data, Indicated in The total number of types of environmental data monitored when the next node is selected after the secondary node selects the strategy. Indicated in The pedestrian density of the next node after the secondary node selection strategy, represents the pedestrian density safety value of each node, Indicated in The overflow coefficient of the number of autonomous inspection vehicles at the next node after the secondary node selection strategy, Indicated in The estimated cost of traveling from the current node to the next node after the secondary node selection strategy;

[0055]

[0056] in, For the u Preset monitoring thresholds for various environmental data, Indicates the first node monitored at the next node u The actual value of the environmental data;

[0057]

[0058] in, Indicated in The next node after the secondary node selection strategy does not belong to the planning node of other autonomous inspection vehicles. Indicated in The next node after the secondary node selection strategy belongs to the planning node of other autonomous inspection vehicles;

[0059]

[0060] in, Indicated in The number of autonomous inspection vehicles belonging to the next node after the secondary node selection strategy is equal to the number of standard inspection vehicles, and the other autonomous inspection vehicles belonging to the node are not participants in the game model; Indicated in The number of autonomous inspection vehicles that belong to the next node after the secondary node selection strategy is equal to the number of standard inspection vehicles, but the other autonomous inspection vehicles that belong to the node include participants in the game model; Indicated in The number of autonomous inspection vehicles that belong to the next node after the secondary node selection strategy is less than the number of standard inspection vehicles;

[0061]

[0062] in, Indicated in The estimated cost of the participants in the game model of the next node to which they belong after the secondary node selection strategy, traveling from the previous node to the node to which they belong;

[0063] In the game model, the path planning decision of each autonomous inspection vehicle is expressed by minimizing its own total cost. L The selected driving route is , while the set of driving paths selected by other autonomous inspection vehicles is , then the autonomous inspection vehicle L Optimal driving path node selection strategy It is expressed as:

[0064]

[0065] in, It means that given the driving path of other autonomous inspection vehicles is In the case of autonomous inspection vehicles L The total path cost calculated by the cost model, Indicates that The driving route selection with the minimum cost;

[0066] The optimal driving path node selection strategy of each autonomous inspection vehicle is obtained to generate an updated driving path, and the updated driving path is returned to the corresponding autonomous inspection vehicle.

[0067] The beneficial effects of the present invention are:

[0068] The present invention proposes an airport terminal environment autonomous patrol vehicle monitoring system, which is used to combine non-zero-sum game theory and improved cost function to adjust the path costs of multiple autonomous patrol vehicles, reduce the probability of false low path cost of each autonomous patrol vehicle, and prevent the waste of resources caused by multiple autonomous patrol vehicles concentrating on the same area. At the same time, the inspection path of each autonomous patrol vehicle is reasonably planned to improve the monitoring efficiency.

[0069] Other advantages, objectives and features of the present invention will be described in the following description and will be apparent to those skilled in the art to some extent, or they may be taught from the practice of the present invention. The purposes and other advantages of the present invention may be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0070] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0072] Figure 1 This is a module schematic diagram of an airport terminal environment autonomous inspection vehicle monitoring system according to an embodiment of the present invention;

[0073] Figure 2 It is a schematic diagram of the modules of an autonomous inspection vehicle in an airport terminal environment autonomous inspection vehicle monitoring system in an embodiment of the present invention;

[0074] Figure 3 It is a schematic diagram of another module of an autonomous inspection vehicle in an airport terminal environment autonomous inspection vehicle monitoring system in an embodiment of the present invention;

[0075] Figure 4 This is a flowchart of the execution process of an environment monitoring unit of an airport terminal environment autonomous inspection vehicle monitoring system in an embodiment of the present invention;

[0076] Figure 5 The present invention is a flowchart of the execution process of a central control module of an airport terminal environment autonomous inspection vehicle monitoring system in an embodiment of the present invention. DETAILED DESCRIPTION

[0077] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0078] See also Figure 1 The present invention proposes an airport terminal environment autonomous inspection vehicle monitoring system, comprising:

[0079] A plurality of autonomous inspection vehicles are used to monitor the environment of the airport terminal and obtain secondary data according to the planned path; wherein the autonomous inspection vehicle includes a navigation positioning guidance unit;

[0080] The navigation positioning and guidance unit is used to determine the initial position of the autonomous inspection vehicle according to the RSSI ranging positioning algorithm, and automatically determine and update the real-time relative position of the autonomous inspection vehicle based on the initial position. At the same time, the path of the autonomous inspection vehicle is planned according to the cost function and the minimum cost target to obtain the planned path;

[0081] The data acquisition module is used to obtain the monitoring data of the relevant monitoring equipment of each regional node in the airport terminal and generate the main data based on the monitoring data;

[0082] The central control module is used to obtain secondary data and primary data to calculate the real-time pedestrian density of each regional node, determine the real-time monitoring importance level of each regional node according to the pedestrian density, generate the standard number of patrol vehicles for the corresponding regional node according to the real-time monitoring importance level, and obtain the number of autonomous patrol vehicles to be inspected at each regional node, determine whether the number of autonomous patrol vehicles to be inspected at each regional node meets the standard number of patrol vehicles for the corresponding regional node, determine multiple autonomous patrol vehicles for paths to be updated according to the judgment result and the retention principle, and update the driving path of each autonomous patrol vehicle for the path to be updated based on the cost function and the non-zero-sum game model, and send it to the corresponding autonomous patrol vehicle;

[0083] The working principle of the above technical solution is as follows: the present invention provides an airport terminal environment autonomous patrol vehicle monitoring system, which is used to perform targeted autonomous environmental monitoring of different areas of the airport terminal. Compared with manual inspections, it is beneficial to improve inspection efficiency and monitoring quality. The system includes an autonomous patrol vehicle, a data acquisition module and a central control module, wherein the number of autonomous patrol vehicles is multiple, which are pre-placed at various predetermined points in the airport terminal, and are used to perform environmental monitoring and secondary data acquisition of the airport terminal based on the planned paths generated by the various equipment units integrated therein. Since pedestrian density directly affects the severity of an accident when it occurs, the secondary data is preferably pedestrian density in this application; the data acquisition module integrates various types of monitoring equipment, including but not limited to security cameras, temperature and humidity sensors, air quality monitors Detectors, crowd counters, etc., but in this application, only security cameras and crowd counters are integrated, and other environmental monitors are preferably directly associated with the central control module. The data acquisition module is mainly used to obtain monitoring data of relevant monitoring equipment in the airport terminal, and generate primary data based on the monitoring data. As mentioned above, since the density of pedestrians directly affects the severity of an accident, the primary data is preferably the density of pedestrians in this application, and data alignment is performed with the secondary data; the central control module is preferably a central server, which is mainly used to obtain secondary data and primary data, and update the driving path of each autonomous inspection vehicle based on the cost function and the non-zero-sum game model, and send it to the corresponding autonomous inspection vehicle, that is, combining the non-zero-sum game theory and the improved cost function to adjust the path of the autonomous inspection vehicle during driving;

[0084] The beneficial effects of the above technical scheme are: through the above technical scheme, combined with non-zero-sum game theory and improved cost function, the path costs of multiple autonomous patrol vehicles are adjusted, which is beneficial to reduce the probability of false low path costs of each autonomous patrol vehicle, and prevent the waste of resources caused by multiple autonomous patrol vehicles concentrating on the same area. At the same time, the inspection path of each autonomous patrol vehicle is reasonably planned to improve monitoring efficiency.

[0085] See also Figure 2 In one embodiment, the autonomous inspection vehicle includes:

[0086] The navigation positioning and guidance unit is used to determine the initial position of the autonomous inspection vehicle according to the RSSI (Received Signal Strength Indication) ranging positioning algorithm, and automatically determine and update the real-time relative position of the autonomous inspection vehicle based on the initial position. At the same time, the path of the autonomous inspection vehicle is planned according to the cost function and the minimum cost target to obtain the planned path;

[0087] Communication unit, used for data exchange with the central control module and various fixed environmental monitoring devices in the airport terminal;

[0088] A mobile control unit is used to control the movement of the autonomous inspection vehicle according to the planned path and to avoid obstacles;

[0089] A comparison unit, used to compare whether the driving path received by the communication unit is the same as the planned path, and if not, update the planned path according to the driving path;

[0090] The mobile control unit is also used to perform mobile control operations on the autonomous inspection vehicle according to the updated planned path;

[0091] The working principle of the above technical solution is as follows: the system includes an autonomous inspection vehicle for autonomous environmental monitoring of the airport terminal. In order to realize autonomous environmental monitoring of the airport terminal, the autonomous inspection vehicle includes a navigation positioning guidance unit, a communication unit, a mobile control unit and a comparison unit; wherein the navigation positioning guidance unit preferably includes a WiFi (WIreless Fidelity-wireless communication technology) positioning subunit, a visual SLAM (Simultaneous Localization and The WiFi positioning subunit obtains the location information of the autonomous inspection vehicle through the RSSI ranging positioning algorithm, and provides the initial position for the visual SLAM subunit, so that the visual SLAM subunit can automatically calibrate and update the real-time relative position of the autonomous inspection vehicle according to the initial position provided by the WiFi positioning subunit, realize the directional positioning and local mapping of the autonomous inspection vehicle, and provide data support for the subsequent path planning of the autonomous inspection vehicle according to the cost function and the minimum cost target, and obtain the planned path; the communication unit preferably uses the built-in WiFi positioning subunit of the navigation positioning guidance unit to exchange data with the central control module and various fixed environmental monitoring equipment in the airport terminal, which is beneficial to reduce redundant components Installation to improve the versatility of the WiFi positioning subunit; the mobile control unit preferably adopts a crawler form for mobile control, which is easy to turn and has the characteristics of not easy to fall, and is specifically used to perform mobile control operations on the autonomous inspection vehicle according to the planned path. At the same time, the mobile control unit also has the function of obstacle avoidance operations, and preferably uses ultrasonic sensors to avoid moving passengers or fixed obstacles; the function of the comparison unit is preferably integrated into the integrated processor of the autonomous inspection vehicle, which is used to compare whether the driving path sent by the central control module received by the communication unit is the same as the planned path. If not, the planned path is updated according to the driving path; after the planned path is updated, the mobile control unit is also used to perform mobile control operations on the autonomous inspection vehicle according to the updated planned path;

[0092] The beneficial effect of the above technical solution is: through the above technical solution, the autonomous inspection vehicle can move autonomously in the airport terminal, providing reliable hardware support for the autonomous inspection vehicle's environmental monitoring activities in the airport terminal.

[0093] In one embodiment, the path planning of the autonomous inspection vehicle is performed according to the cost function and the minimum cost target to obtain the planned path, including:

[0094] Get the cost function :

[0095]

[0096] in, Indicated in i From the initial node to the path node under the path selection p The total cost of the next node, Indicated in i From the initial node to the path node under the path selection p The actual cost, Indicated in i Select the path node from the p The estimated cost to reach the next node, Indicates that at the next node j The weight of the environmental data, Indicates the total number of types of environmental data monitored at the next node. represents the pedestrian density at the next node, Indicates the pedestrian density safety value of each node;

[0097]

[0098] in, For the j Preset monitoring thresholds for various environmental data, Indicates the first node monitored at the next node j The actual values ​​of the environmental data;

[0099] According to the cost function and the minimum cost target, the minimum cost problem of the path is generated:

[0100]

[0101] Use heuristic algorithms to solve the minimum cost problem of the path, obtain several optimal path nodes, and generate a planned path;

[0102] The working principle of the above technical solution is as follows: In order to realize the key monitoring planning of the entire terminal by the autonomous inspection vehicle, this solution designs a path planning method based on the improved cost function, calculates the optimal driving path of the autonomous inspection vehicle to inspect the airport terminal, which is beneficial to improve the inspection efficiency and reduce the driving of invalid paths;

[0103] in, Indicates that at the next node j The weight of the environmental data is the weight of the first j The larger the actual value of the environmental data is, the smaller its weight is, that is, the smaller the cost of driving to the target node is, which makes it easier for the autonomous inspection vehicle to quickly determine the target node;

[0104] It indicates the pedestrian density weight at the next node. The greater the pedestrian density monitored at the next node, the greater the impact when a risk occurs. The smaller the pedestrian density weight, the lower the cost of driving to the target node, which makes it easier for the autonomous inspection vehicle to quickly determine the target node.

[0105] Indicated in i Select the path node from the p The estimated cost of reaching the next node. In the present application, the calculation of the estimated cost preferably includes the distance between the two nodes, the time required for the autonomous inspection vehicle to reach the target node according to the unit driving speed, and the path complexity between the two nodes. Furthermore, the crowd density between the two nodes can also be added to assist in calculating the path complexity between the two nodes, which is beneficial to improve the calculation accuracy of the estimated cost;

[0106] The beneficial effects of the above technical solution are as follows: compared with the improved cost function in the prior art, this solution simplifies the selection method of positively correlated and negatively correlated environmental weights, and transfers the selection of the main cost weights to the pedestrian density. Since the pedestrian density in each area is significantly positively correlated with the severity of the accident after the accident, adding pedestrian density to calculate the total cost of each area is beneficial to improving the reliability of the cost function for path planning and improving the accuracy of path planning.

[0107] See also Figure 3 In one embodiment, the autonomous inspection vehicle further includes:

[0108] The visual unit is used to collect information about buildings and pedestrians around the autonomous inspection vehicle;

[0109] The secondary positioning unit is used to determine the current location of the autonomous inspection vehicle based on the comparison of building information and built-in airport terminal building information;

[0110] The environmental monitoring unit is used to monitor the environmental data of the area where the autonomous inspection vehicle is currently located according to the preset environmental monitoring standards, and receive the interactive data between the communication unit and the fixed environmental monitoring equipment in the airport terminal, compare it with the monitoring data, and feed back the comparison data to the central control module;

[0111] The secondary data sorting unit is used to obtain the pedestrian information collected by the visual unit, and estimate the pedestrian density of the node in the area where the current autonomous inspection vehicle is currently located based on the pedestrian information, and at the same time generate an area identifier and a time identifier to mark the corresponding pedestrian density to obtain secondary data;

[0112] The working principle of the above technical solution is as follows: the system includes an autonomous patrol vehicle for autonomous environmental monitoring of airport terminals, in order to realize autonomous environmental monitoring of airport terminals; the autonomous patrol vehicle also includes a visual unit, a secondary positioning unit, an environmental monitoring unit and a secondary data sorting unit; wherein the visual unit preferably takes the form of a camera to collect data on building information and pedestrian information around the autonomous patrol vehicle, and further, pedestrian behavior detection can be added to prevent malicious damage to the autonomous patrol vehicle and theft, etc.; there are differences in the functions of the secondary positioning unit and the navigation positioning and guidance unit. The secondary positioning unit is mainly used to assist in positioning the current area of ​​the autonomous patrol vehicle according to the surrounding environment, and is mainly used to determine the current area of ​​the autonomous patrol vehicle according to the comparison of building information and built-in airport terminal building information. The built-in airport terminal building information is pre-stored in the corresponding equipment of the autonomous patrol vehicle. For example, taking the boarding gate as an example, the license plate of each boarding gate can be an autonomous patrol vehicle. The inspection vehicle provides positioning assistance; the environmental monitoring unit preferably integrates various types of environmental monitoring equipment, including humidity, smoke concentration and other sensor equipment. During the execution of the task, the environmental monitoring unit monitors the environmental data of the area where the autonomous inspection vehicle is currently located according to the preset environmental monitoring standards. At the same time, it can also receive the interactive data between the communication unit and the fixed environmental monitoring equipment in the airport terminal, compare it with the monitoring data, and feed back the comparison data to the central control module to realize autonomous environmental monitoring of the airport terminal; the function of the secondary data sorting unit is preferably integrated into the integrated processor of the autonomous inspection vehicle, which is mainly used to obtain the pedestrian information collected by the visual unit, and estimate the pedestrian density of the node in the area where the autonomous inspection vehicle is currently located based on the pedestrian information. There are many specific estimation methods in the prior art, which are not limited here. The method with high estimation accuracy is given priority. At the same time, the area identifier and time identifier are generated to mark the corresponding pedestrian density to obtain secondary data, which is used to provide reliable data support for subsequent path planning;

[0113] The beneficial effect of the above technical solution is: through the above technical solution, the autonomous inspection vehicle can perform precise positioning environmental monitoring in the airport terminal, providing reliable hardware support for the autonomous inspection vehicle's environmental monitoring activities in the airport terminal.

[0114] See also Figure 4 In one embodiment, the environment monitoring unit performs the following operations:

[0115] S101, obtaining a preset environmental monitoring standard, and determining a preset monitoring threshold for each type of environmental data based on the preset environmental monitoring standard;

[0116] S102, obtaining monitoring data of the environment in the area where the autonomous inspection vehicle is currently located, generating first comparison data according to the corresponding preset monitoring threshold, and if the first comparison data is abnormal, feeding back the corresponding abnormal data to the central control module;

[0117] S103, receiving interactive data between the communication unit and each fixed environment monitoring device in the airport terminal; wherein the interactive data includes second monitoring data of each fixed environment monitoring device on corresponding environment data and device operation data;

[0118] S104: If there is an abnormality in the equipment operation data, the corresponding abnormal data is fed back to the central control module;

[0119] S105. If there is no abnormality in the equipment operation data, generate second comparison data according to the monitoring data and the second monitoring data. If there is an abnormality in the second comparison data, feed back the corresponding abnormal data to the central control module;

[0120] The working principle of the above technical solution is as follows: In order to improve the reliability of the environmental monitoring unit, this solution adopts three methods to jointly monitor the environmental monitoring data of each area. First, the preset environmental monitoring standard is obtained. The preset environmental monitoring standard is preferably formulated according to relevant official documents. Then, based on the preset environmental monitoring standard, the preset monitoring threshold of each type of environmental data is determined. The preset monitoring threshold is specified by the airport management personnel and is usually 70% of the preset environmental monitoring standard.

[0121] After determining the monitoring threshold, first, obtain the monitoring data of the environment in the area where the autonomous inspection vehicle is currently located, and generate the first comparison data according to the corresponding preset monitoring threshold. If there is an abnormality in the first comparison data, the corresponding abnormal data is fed back to the central control module. The abnormality preferably refers to judging whether the monitoring data is greater than the corresponding preset monitoring threshold. If it is greater, it is judged that there is an abnormality. This method is used to judge whether there is an abnormality in the current environmental data;

[0122] Then, the interactive data between the communication unit and each fixed environmental monitoring device in the airport terminal is received; wherein the interactive data includes the second monitoring data of each fixed environmental monitoring device on the corresponding environmental data and the equipment operation data. If there is an abnormality in the equipment operation data, the corresponding abnormal data is fed back to the central control module. It is preferred to judge whether there is an abnormality in the equipment operation data by performing a conventional judgment on the received equipment operation data, that is, judging whether the equipment abnormality instruction is 1, and if it is 1, the equipment is abnormal. This method is used to judge whether there is an abnormality in the current fixed monitoring device;

[0123] Finally, when there is no abnormality in the equipment operation data, the second comparison data is generated according to the monitoring data and the second monitoring data. If there is an abnormality in the second comparison data, the corresponding abnormal data is fed back to the central control module. The abnormality preferably refers to whether the difference between the monitoring data and the second monitoring data belongs to the preset error range. If it does, there is no abnormality, and if it does not, there is an abnormality. The selection of the preset error range is preferably customized by the management personnel according to the equipment model and the type of monitoring data. This method is used to determine whether the autonomous inspection vehicle has an abnormality.

[0124] In summary, when the central control module receives the first comparison data with an abnormality, it initially determines that the corresponding area environmental data has an abnormality. If the equipment operation data received at the same time has an abnormality, the relevant maintenance personnel are dispatched to maintain the equipment. If the equipment operation data is not received with an abnormality, but the second comparison data with an abnormality is received, when the equipment is normal, if the second monitoring data is abnormal, the equipment will send an alarm signal to the central control module. Therefore, at this time, it is determined that the environmental monitoring equipment of the autonomous inspection vehicle has an abnormality, and a return instruction is sent to the autonomous inspection vehicle, or a pull-over instruction is sent to the autonomous inspection vehicle to wait for maintenance personnel to perform maintenance.

[0125] The beneficial effect of the above technical solution is: through the above technical solution, the environmental monitoring data is jointly monitored to prevent the reliability of the environmental monitoring data from being reduced due to abnormalities in the monitoring equipment, which is beneficial to improving the environmental monitoring efficiency of the autonomous inspection vehicle.

[0126] In one embodiment, the data acquisition module performs the following operations:

[0127] Obtain monitoring data of relevant monitoring equipment at each regional node in the airport terminal; the relevant monitoring equipment includes security cameras and crowd counters;

[0128] Perform data preprocessing and feature extraction on the monitoring data to obtain the pedestrian density contained in the monitoring data;

[0129] Generate the area identification of each area node and the time identification of the monitoring data collection time, mark the corresponding pedestrian density contained in the monitoring data, and obtain the main data;

[0130] The working principle of the above technical solution is as follows: the system also includes a data acquisition module. In order to obtain the main data in the airport terminal, the data acquisition module obtains the monitoring data of the relevant monitoring equipment of each regional node in the airport terminal; wherein the relevant monitoring equipment includes but is not limited to security cameras and crowd counters; and performs data preprocessing and feature extraction on the monitoring data to obtain the pedestrian density contained in the monitoring data. Since the main data in the present application is preferably the pedestrian density, during feature extraction, the extracted image features and data features are related to the pedestrian density, which is beneficial to improving the accuracy of pedestrian density acquisition. Finally, the area identifier of each regional node and the time identifier of the monitoring data acquisition time are generated, and the corresponding pedestrian density contained in the monitoring data is marked to obtain the main data, so that each pedestrian density can be guaranteed to be real-time according to its acquisition time and area, which is beneficial to provide reliable real-time data support for subsequent path planning.

[0131] The beneficial effect of the above technical solution is: through the above technical solution, the acquisition of main data is completed, which is beneficial to provide reliable data support for subsequent path planning.

[0132] See also Figure 5 In one embodiment, the central control module performs the following operations:

[0133] S201, obtaining primary data and secondary data, and calculating the real-time pedestrian density of each regional node based on a weighted summation method;

[0134] S202, according to the real-time pedestrian density of each regional node, based on a preset pedestrian density and monitoring importance level comparison table, obtain the real-time monitoring importance level of the corresponding regional node; wherein the higher the pedestrian density in the preset pedestrian density and monitoring importance level comparison table, the higher the monitoring importance level;

[0135] S203, according to the real-time monitoring importance level of each regional node, based on the preset monitoring importance level and patrol vehicle quantity arrangement table, obtain the number of standard patrol vehicles for the corresponding regional node; wherein, the higher the preset monitoring importance level, the more standard patrol vehicles for the corresponding regional node;

[0136] S204, obtaining the driving nodes included in the planned paths of all autonomous inspection vehicles, and determining the number of autonomous inspection vehicles to be inspected in each regional node according to all the driving nodes;

[0137] S205. If the number of autonomous inspection vehicles to be inspected at each regional node is greater than the number of standard inspection vehicles, according to the retention principle, autonomous inspection vehicles whose number of autonomous inspection vehicles to be inspected at each regional node is equal to the number of standard inspection vehicles are retained and continue to travel according to the original planned path; wherein the retention principle is the principle of minimum total cost;

[0138] S206, sending the path update information to the other L autonomous inspection vehicles participating in the retention principle screening;

[0139] S207, after waiting for a node driving time, the autonomous inspection vehicles that obtain all the path information to be updated form a game model; wherein, in the game model, the participants are L autonomous inspection vehicles that request to update the path planning, and the strategy set is the set of recommended planning paths returned by the central control module to each participant;

[0140] S208, based on the game model and the cost function, according to the non-zero-sum game principle, returning an updated driving path to the corresponding autonomous inspection vehicle;

[0141] The working principle of the above technical solution is as follows: the system includes a central control module, which is used to obtain secondary data and primary data, and update the driving path of each autonomous patrol vehicle based on the cost function and the non-zero-sum game model, and send it to the corresponding autonomous patrol vehicle; specifically, first obtain the primary data and secondary data, and calculate the real-time pedestrian density of each regional node based on the weighted sum method. Preferably, the weight of the secondary data is preferably 30%, and the weight of the primary data is preferably 70%. The pedestrian density is calculated in two directions, which is beneficial to improve the calculation accuracy of the pedestrian density; then, according to the real-time pedestrian density of each regional node, based on the preset pedestrian density and monitoring importance level comparison table, the real-time monitoring importance level of the corresponding regional node is obtained; wherein, the higher the pedestrian density in the preset pedestrian density and monitoring importance level comparison table, the higher the monitoring importance level, and the preset pedestrian density and monitoring importance level comparison table is preferably determined according to the hazard impact range in the airport disaster drill, and according to the real-time monitoring importance level of each regional node, based on the preset monitoring importance Obtain a table of levels and number of patrol vehicles to obtain the number of standard patrol vehicles for corresponding regional nodes; wherein, the higher the preset monitoring importance level, the more standard patrol vehicles for corresponding regional nodes, and the table of preset monitoring importance level and number of patrol vehicles is preferably customized by management personnel, the more patrol vehicles there are, the higher the inspection efficiency for the same area; then obtain the driving nodes included in the planned paths of all autonomous patrol vehicles, each driving node preferably corresponds to a monitoring node in an area, each area includes several monitoring area nodes, the node preferably refers to a range, not specifically a coordinate, for example, the area range to which boarding gate G21 belongs, determine the number of autonomous patrol vehicles to be inspected for each regional node based on all driving nodes, and then judge the number of autonomous patrol vehicles to be inspected for each regional node, if the number of autonomous patrol vehicles to be inspected for each regional node is greater than the number of standard patrol vehicles, according to the retention principle, retain the autonomous patrol vehicles whose number of autonomous patrol vehicles to be inspected for each regional node is equal to the number of standard patrol vehicles, and continue to drive according to the original planned path;Among them, the retention principle is the principle of minimum total cost, that is, each regional node is regarded as a set, and each planned path includes the autonomous patrol vehicle of the regional node as an element in the set. The total cost of each element from the current autonomous patrol vehicle traveling according to the initial planned path to the target regional node is calculated. Finally, according to the size of the set (that is, the number of standard patrol vehicles), according to the order of total cost from low to high, the corresponding number of elements are selected to join the set. All elements in the set continue to travel according to the original planned path. Other elements kicked out of the set wait for the new planned path while traveling according to the original planned path, that is, the path update information is sent to the other L autonomous patrol vehicles participating in the retention principle screening, etc. After a node driving time, the node driving time is not fixed for each autonomous patrol vehicle, but uniformly represents the time from one node to another, that is, when the autonomous patrol vehicle reaches the next node of the original planned path, the autonomous patrol vehicle stops running and waits for the updated path information. During the waiting process, the central control module obtains all autonomous patrol vehicles whose path information is to be updated to form a game model, wherein, in the game model, the participants are L autonomous patrol vehicles requesting to update the path planning, and the strategy set is the set of recommended planned paths returned by the central control module to each participant; finally, based on the game model and the cost function, according to the non-zero-sum game principle, the updated driving path is returned to the corresponding autonomous patrol vehicle;

[0142] The beneficial effect of the above technical scheme is: through the above technical scheme, when multiple patrol vehicles conduct autonomous inspections, the dynamic planning path generated by the non-zero-sum game model and the cost function is used, which is beneficial to achieve reasonable monitoring of each area of ​​the airport terminal, realize the diversion of patrol vehicles, maximize the inspection efficiency of patrol vehicles, and prevent the waste of resources caused by multiple autonomous patrol vehicles concentrating on the same area.

[0143] In one embodiment, based on the game model and the cost function, according to the non-zero-sum game principle, an updated driving path is returned to the corresponding autonomous inspection vehicle, including:

[0144] Get the strategy set of the game model ;in, Indicates L The recommended planning path for each participant, ,in, Indicates L Participant's c Recommended planning paths;

[0145] Based on the cost function and strategy set, generate the cost model of the game model:

[0146]

[0147] in, Indicates LParticipants choose c The total cost of the path when recommending the planning path, Indicates c Each node selection strategy in the recommended planning path, Indicates c A first node selection strategy in the recommended planning path. Indicated in The next node after the node selection strategy is u The weight of the environmental data, Indicated in The total number of types of environmental data monitored when the next node is selected after the secondary node selects the strategy. Indicated in The pedestrian density of the next node after the secondary node selection strategy, represents the pedestrian density safety value of each node, Indicated in The overflow coefficient of the number of autonomous inspection vehicles at the next node after the secondary node selection strategy, Indicated in The estimated cost of traveling from the current node to the next node after the secondary node selection strategy;

[0148]

[0149] in, For the u Preset monitoring thresholds for various environmental data, Indicates the first node monitored at the next node u The actual value of the environmental data;

[0150]

[0151] in, Indicated in The next node after the secondary node selection strategy does not belong to the planning node of other autonomous inspection vehicles. Indicated in The next node after the secondary node selection strategy belongs to the planning node of other autonomous inspection vehicles;

[0152]

[0153] in, Indicated in The number of autonomous inspection vehicles belonging to the next node after the secondary node selection strategy is equal to the number of standard inspection vehicles, and the other autonomous inspection vehicles belonging to the node are not participants in the game model; Indicated in The number of autonomous inspection vehicles that belong to the next node after the secondary node selection strategy is equal to the number of standard inspection vehicles, but the other autonomous inspection vehicles that belong to the node include participants in the game model; Indicated in The number of autonomous inspection vehicles that belong to the next node after the secondary node selection strategy is less than the number of standard inspection vehicles;

[0154]

[0155] in, Indicated in The estimated cost of the participants in the game model of the next node to which they belong after the secondary node selection strategy, traveling from the previous node to the node to which they belong;

[0156] In the game model, the path planning decision of each autonomous inspection vehicle is expressed by minimizing its own total cost. L The selected driving route is , while the set of driving paths selected by other autonomous inspection vehicles is , then the autonomous inspection vehicle L Optimal driving path node selection strategy It is expressed as:

[0157]

[0158] in, It means that given the driving path of other autonomous inspection vehicles is In the case of autonomous inspection vehicles L The total path cost calculated by the cost model, Indicates that The driving route selection with the minimum cost;

[0159] Obtain the optimal driving path node selection strategy for each autonomous inspection vehicle to generate an updated driving path, and return the updated driving path to the corresponding autonomous inspection vehicle;

[0160] The working principle of the above technical solution is as follows: In order to realize reasonable monitoring of each monitoring point in the airport terminal, this solution proposes an autonomous patrol vehicle path update method, which reasonably monitors each area of ​​the airport terminal, realizes patrol vehicle diversion, maximizes the patrol vehicle inspection efficiency, and prevents multiple autonomous patrol vehicles from concentrating on the same area, resulting in resource waste;

[0161] in, Indicates L Participant's c The recommended planning path is c The selection of each node in the recommended planning path has been fixed, which is The end point of the recommended planning path is preferably a storage point or maintenance point of the autonomous inspection vehicle;

[0162] It represents the weight of the jth environmental data at the next node. When selecting a node, the larger the actual value of the uth environmental data monitored at the next node, the smaller its weight value, that is, the smaller the cost of driving to the target node, which is convenient for the autonomous inspection vehicle to quickly determine the target node. However, in the cost model, since the next node is fixed, this weight is used to calculate the cost of reaching the next node, which is used for the subsequent calculation of the total path cost.

[0163] Indicated in The overflow coefficient of the number of autonomous inspection vehicles at the next node after the secondary node selection strategy. The larger the overflow coefficient, the greater the cost of selecting the node. It is used to prevent multiple autonomous inspection vehicles from selecting the same node, resulting in multiple autonomous inspection vehicles concentrating on the same area.

[0164] Therefore, this plan is for The selection of sets the multi-level weight distribution. Indicated in The next node after the second node selection strategy belongs to the planning node of other autonomous inspection vehicles, that is, the next node is in the planning of other autonomous inspection vehicles. Since, in addition to the elements in the aforementioned set, other autonomous inspection vehicles are uniformly planned after the game model is established, then when there is a When the next node after the secondary node selection strategy belongs to the planning node of other autonomous inspection vehicles, there are cases where all other autonomous inspection vehicles are elements in the set, and cases where not all other autonomous inspection vehicles are elements in the set;

[0165] According to the above situation, Again, the weights are assigned. Indicated in The number of autonomous patrol vehicles belonging to the next node after the secondary node selection strategy is equal to the number of standard patrol vehicles, but the other autonomous patrol vehicles belonging to the node include participants in the game model, that is, the situation described above where other autonomous patrol vehicles are not all elements in the set. Finally, the number of autonomous patrol vehicles is determined according to the actual situation. The specific value of is beneficial to improving the ability to minimize the total cost of each inspection vehicle in the non-zero-sum game model;

[0166] Finally, in the game model, the path planning decision of each autonomous inspection vehicle can be expressed by minimizing its own total cost. L The selected driving route is , while the set of driving paths selected by other autonomous inspection vehicles is When the autonomous inspection vehicleL Optimal driving path node selection strategy ; Through this method, the driving path of each autonomous inspection vehicle is determined on the basis of minimizing its total cost;

[0167] The beneficial effect of the above technical solution is: through the above technical solution, it is beneficial to improve the real-time performance of the autonomous patrol vehicle's driving route change. Compared with modifying the route after multiple autonomous patrol vehicles have concentrated on the same area, this solution can minimize the impact of such information delay, so that the route combination selected by the autonomous patrol vehicle is most effective and coordinated with each other, thereby achieving the purpose of maximizing the monitoring efficiency of the autonomous patrol vehicle.

[0168] Finally, it should be noted that the above preferred embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made in form and details without departing from the scope defined by the claims of the present invention.

Claims

1. An airport terminal environment autonomous inspection vehicle monitoring system, characterized in that: include: A plurality of autonomous inspection vehicles are used to monitor the environment of the airport terminal and obtain secondary data according to the planned path; wherein the autonomous inspection vehicle includes a navigation positioning guidance unit; The navigation positioning and guidance unit is used to determine the initial position of the autonomous inspection vehicle according to the RSSI ranging positioning algorithm, and automatically determine and update the real-time relative position of the autonomous inspection vehicle based on the initial position. At the same time, the path of the autonomous inspection vehicle is planned according to the cost function and the minimum cost target to obtain the planned path; The data acquisition module is used to obtain the monitoring data of the relevant monitoring equipment of each regional node in the airport terminal and generate the main data based on the monitoring data; The central control module is used to obtain secondary data and primary data to calculate the real-time pedestrian density of each regional node, determine the real-time monitoring importance level of each regional node according to the pedestrian density, generate the standard number of patrol vehicles for the corresponding regional node according to the real-time monitoring importance level, and obtain the number of autonomous patrol vehicles to be inspected at each regional node, determine whether the number of autonomous patrol vehicles to be inspected at each regional node meets the standard number of patrol vehicles for the corresponding regional node, determine multiple autonomous patrol vehicles for paths to be updated according to the judgment result and the retention principle, and update the driving path of each autonomous patrol vehicle for the path to be updated based on the cost function and the non-zero-sum game model, and send it to the corresponding autonomous patrol vehicle; wherein the retention principle is the principle of minimum total cost; The driving path of each autonomous inspection vehicle to be updated is updated based on the cost function and the non-zero-sum game model, including: Get the strategy set of the game model ;in, Indicates L The recommended planning path for each participant, ,in, Indicates L Participant's c Recommended planning paths; Based on the cost function and strategy set, generate the cost model of the game model: in, Indicates L Participants choose c The total cost of the path when recommending the planning path, Indicates c Each node selection strategy in the recommended planning path, Indicates c A first node selection strategy in the recommended planning path. Indicated in The next node after the node selection strategy is u The weight of the environmental data, Indicated in The total number of types of environmental data monitored when the next node is selected after the secondary node selects the strategy. Indicated in The pedestrian density of the next node after the secondary node selection strategy, represents the pedestrian density safety value of each node, Indicated in The overflow coefficient of the number of autonomous inspection vehicles at the next node after the secondary node selection strategy, Indicated in The estimated cost of traveling from the current node to the next node after the secondary node selection strategy; in, For the u Preset monitoring thresholds for various environmental data, Indicates the first node monitored at the next node u The actual value of the environmental data; in, Indicated in The next node after the secondary node selection strategy does not belong to the planning node of other autonomous inspection vehicles. Indicated in The next node after the secondary node selection strategy belongs to the planning node of other autonomous inspection vehicles; in, Indicated in The number of autonomous inspection vehicles belonging to the next node after the secondary node selection strategy is equal to the number of standard inspection vehicles, and the other autonomous inspection vehicles belonging to the node are not participants in the game model; Indicated in The number of autonomous inspection vehicles that belong to the next node after the secondary node selection strategy is equal to the number of standard inspection vehicles, but the other autonomous inspection vehicles that belong to the node include participants in the game model; Indicated in The number of autonomous inspection vehicles that belong to the next node after the secondary node selection strategy is less than the number of standard inspection vehicles; in, Indicated in The estimated cost of the participants in the game model of the next node to which they belong after the secondary node selection strategy, traveling from the previous node to the node to which they belong; In the game model, the path planning decision of each autonomous inspection vehicle is expressed by minimizing its own total cost. L The selected driving route is , while the set of driving paths selected by other autonomous inspection vehicles is , then the autonomous inspection vehicle L Optimal driving path node selection strategy It is expressed as: in, It means that given the driving path of other autonomous inspection vehicles is In the case of autonomous inspection vehicles L The total path cost calculated by the cost model, Indicates that The driving route selection with the minimum cost; The optimal driving path node selection strategy of each autonomous inspection vehicle is obtained to generate an updated driving path, and the updated driving path is returned to the corresponding autonomous inspection vehicle.

2. The airport terminal environment autonomous inspection vehicle monitoring system according to claim 1 is characterized in that: Autonomous inspection vehicles include: Communication unit, used for data exchange with the central control module and various fixed environmental monitoring devices in the airport terminal; A mobile control unit is used to control the movement of the autonomous inspection vehicle according to the planned path and to avoid obstacles; A comparison unit, used to compare whether the driving path received by the communication unit is the same as the planned path, and if not, update the planned path according to the driving path; The mobile control unit is also used to perform mobile control operations on the autonomous inspection vehicle according to the updated planned path.

3. The airport terminal environment autonomous inspection vehicle monitoring system according to claim 2 is characterized in that: According to the cost function and the minimum cost target, the path of the autonomous inspection vehicle is planned to obtain the planned path, including: Get the cost function : in, Indicated in i From the initial node to the path node under the path selection p The total cost of the next node, Indicated in i From the initial node to the path node under the path selection p The actual cost of Indicated in i Select the path node from the p The estimated cost to reach the next node, Indicates that at the next node j The weight of the environmental data, Indicates the total number of types of environmental data monitored at the next node. represents the pedestrian density at the next node, Indicates the pedestrian density safety value of each node; in, For the j Preset monitoring thresholds for various environmental data, Indicates the first node monitored at the next node j The actual values ​​of the environmental data; According to the cost function and the minimum cost target, the minimum cost problem of the path is generated: The heuristic algorithm is used to solve the minimum path cost problem, obtain several optimal path nodes, and generate a planned path.

4. The airport terminal environment autonomous inspection vehicle monitoring system according to claim 2 is characterized in that: The autonomous inspection vehicle also includes: The visual unit is used to collect information about buildings and pedestrians around the autonomous inspection vehicle; The secondary positioning unit is used to determine the current location of the autonomous inspection vehicle based on the comparison of building information and built-in airport terminal building information; The environmental monitoring unit is used to monitor the environmental data of the area where the autonomous inspection vehicle is currently located according to the preset environmental monitoring standards, and receive the interactive data between the communication unit and the fixed environmental monitoring equipment in the airport terminal, compare it with the monitoring data, and feed back the comparison data to the central control module; The secondary data sorting unit is used to obtain the pedestrian information collected by the visual unit, and estimate the pedestrian density of the node in the area where the current autonomous inspection vehicle is currently located based on the pedestrian information. At the same time, it generates an area identifier and a time identifier to mark the corresponding pedestrian density to obtain secondary data.

5. The airport terminal environment autonomous inspection vehicle monitoring system according to claim 4 is characterized in that: The environmental monitoring unit performs the following operations: Obtaining preset environmental monitoring standards, and determining preset monitoring thresholds for each type of environmental data based on the preset environmental monitoring standards; Acquire monitoring data of the environment in the area where the autonomous inspection vehicle is currently located, generate first comparison data according to the corresponding preset monitoring threshold, and if the first comparison data is abnormal, feed back the corresponding abnormal data to the central control module; Receiving interactive data between the communication unit and each fixed environment monitoring device in the airport terminal; wherein the interactive data includes second monitoring data and device operation data of each fixed environment monitoring device on the corresponding environment data; If there is any abnormality in the equipment operation data, the corresponding abnormal data will be fed back to the central control module; If there is no abnormality in the equipment operation data, second comparison data is generated according to the monitoring data and the second monitoring data. If there is an abnormality in the second comparison data, the corresponding abnormal data is fed back to the central control module.

6. The airport terminal environment autonomous inspection vehicle monitoring system according to claim 1 is characterized in that: The data acquisition module performs the following operations: Obtain monitoring data of relevant monitoring equipment at each regional node in the airport terminal; the relevant monitoring equipment includes security cameras and crowd counters; Perform data preprocessing and feature extraction on the monitoring data to obtain the pedestrian density contained in the monitoring data; Generate the area identification of each area node and the time identification of the monitoring data collection time, mark the corresponding pedestrian density contained in the monitoring data, and obtain the main data.

7. The airport terminal environment autonomous inspection vehicle monitoring system according to claim 1 is characterized in that: The central control module performs the following operations: Obtain primary and secondary data, and calculate the real-time pedestrian density of each regional node based on the weighted sum method; According to the real-time pedestrian density of each regional node, based on the preset pedestrian density and monitoring importance level comparison table, the real-time monitoring importance level of the corresponding regional node is obtained; wherein, the higher the pedestrian density in the preset pedestrian density and monitoring importance level comparison table, the higher the monitoring importance level; According to the real-time monitoring importance level of each regional node, based on the preset monitoring importance level and patrol vehicle quantity arrangement table, the standard number of patrol vehicles for the corresponding regional node is obtained; wherein, the higher the preset monitoring importance level, the more standard patrol vehicles for the corresponding regional node; Obtain the driving nodes included in the planned paths of all autonomous inspection vehicles, and determine the number of autonomous inspection vehicles to be inspected in each regional node based on all driving nodes; If the number of autonomous inspection vehicles to be inspected at each regional node is greater than the number of standard inspection vehicles, according to the retention principle, the autonomous inspection vehicles whose number of autonomous inspection vehicles to be inspected at each regional node is equal to the number of standard inspection vehicles are retained and continue to drive according to the original planned path; among which, the retention principle is the principle of minimum total cost; Send the path update information to the other L autonomous inspection vehicles participating in the retention principle screening; After waiting for a node driving time, the autonomous inspection vehicles that obtain all the path information to be updated form a game model; in the game model, the participants are L autonomous inspection vehicles that request to update the path planning, and the strategy set is the set of recommended planning paths returned by the central control module to each participant; Based on the game model and cost function, according to the non-zero-sum game principle, the updated driving path is returned to the corresponding autonomous inspection vehicle.

Images