Baggage transportation path tracking and correction system and method based on RFID and multi-sensor fusion

Abstract

The present invention discloses a baggage transport path tracking and correction system and method based on RFID and multi-sensor fusion, which relates to the field of baggage sorting technology. The system comprises the following steps: arranging multiple sensors and RFID tags on each baggage transport vehicle to obtain real-time data and the terminal location of each baggage during transportation; using a path planning method to avoid environmental obstacles based on the real-time data and the terminal location, planning the transport path of each baggage transport vehicle to obtain a first planned path; optimizing the first planned path using a local optimization method to obtain an optimized path; and controlling each baggage transport vehicle to move to a corresponding terminal location based on the optimized path, so that each user can arrive at the corresponding terminal location to collect the baggage. The present invention realizes comprehensive monitoring of the baggage transport process by combining the RFID tags and multiple sensors. By planning and optimizing the transport paths of the baggage transport vehicles, the efficiency and safety of baggage transportation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of baggage sorting, and in particular to a baggage transport path tracking and correction system and method based on RFID and multi-sensor fusion. Background Art

[0002] In baggage transportation systems, RFID tags are typically attached to luggage and connected to the baggage handling system via a reader. When luggage passes through the reader, the information on the RFID tag is automatically read and transmitted to the baggage handling system, enabling automated baggage identification. However, currently, luggage is typically transported en masse via large transport vehicles to specific sorting areas for manual sorting. This can lead to the risk of crushing valuable items, and users needing to find their own luggage, which can easily lead to the risk of misplacing it, severely reducing the user experience.

[0003] For example, Chinese patent application CN112258133B discloses a luggage tracking and identification system and method based on RFID technology, including a conveying mechanism, a logic control system, a luggage position detection device, and an RFID identification system. The conveying mechanism is used to convey luggage with RFID tags; the logic control system is used to drive the conveying mechanism to convey the luggage, receive the position information obtained by the luggage position detection device, track and control the luggage, and communicate with the RFID identification system in real time to realize automatic identification of the luggage barcode information; the luggage position detection device is used to detect the position information of the luggage on the conveying mechanism and send the position information to the logic control system; the RFID identification system is used to receive the luggage tracking signal transmitted by the logic control system, scan the RFID tag on the luggage, and complete the marking of the luggage tag information.

[0004] The above patents have the problem raised by this background technology: only using RFID tags to track the luggage transportation path, the collected data is relatively simple and cannot provide comprehensive and complete luggage transportation information, which may lead to inaccurate identified luggage transportation paths. The traditional luggage transportation path is fixed, resulting in low luggage transportation efficiency. To solve the above problems, the present invention proposes a luggage transportation path tracking and correction system and method based on RFID and multi-sensor fusion. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the main purpose of the present invention is to provide a baggage transportation path tracking and correction system and method based on RFID and multi-sensor fusion, which can effectively solve the problems in the background technology. The specific technical solutions of the present invention are as follows:

[0006] The baggage transportation path tracking and correction method based on RFID and multi-sensor fusion includes:

[0007] By installing multiple sensors and RFID tags on each baggage transport vehicle, real-time data and the final location of each baggage during transportation are obtained;

[0008] Based on the real-time data and the destination location, a path planning method is used to avoid environmental obstacles and plan a transportation path for each luggage transport vehicle to obtain a first planned path;

[0009] Optimizing the first planned path by a local optimization method to obtain an optimized path;

[0010] According to the optimized path, each luggage transport vehicle is controlled to move to a corresponding terminal position, so that each user arrives at the corresponding terminal position to collect the luggage, wherein the terminal position corresponding to each luggage transport vehicle is different.

[0011] Specifically, based on the real-time data and the destination location, a path planning method is used to avoid environmental obstacles and plan the transportation path of each luggage transport vehicle to obtain a first planned path, including:

[0012] The action space of the luggage transport vehicle is divided by using the grid division method to obtain multiple space grids;

[0013] According to the position of the obstacle in the action space, the space grid occupied by the obstacle is used as the obstacle grid;

[0014] According to the terminal position, a path planning method is used to plan the transportation path of the luggage transport vehicle within a non-obstacle grid to obtain a first planned path.

[0015] Specifically, the method of planning the transport path of the luggage transport vehicle within a non-obstacle grid using a path planning method according to the destination position to obtain a first planned path includes:

[0016] By using the population optimization method, the non-obstacle grids that the luggage transport vehicle needs to pass through to reach the destination are found, and multiple intermediate grids are obtained;

[0017] The intermediate grids are connected using a path connection method to form a first planning path.

[0018] Specifically, the population optimization method is used to find the non-obstacle grids that the luggage transport vehicle needs to pass through to reach the terminal location, and multiple intermediate grids are obtained, including:

[0019] Initialize the population, where each individual in the population represents a set of non-obstacle grids that the luggage transport vehicle must pass through to reach the destination;

[0020] Calculate the fitness value of each individual according to the preset fitness function;

[0021] According to the fitness value, individuals whose fitness value is greater than a preset fitness threshold are selected as initial elite individuals;

[0022] Performing a mutation operation on the initial elite individuals to generate mutant individuals;

[0023] Performing a crossover operation on the mutant individual and the initial elite individual to generate a crossover individual;

[0024] Select the elite individuals of the next generation according to the fitness values ​​corresponding to the crossover individuals;

[0025] Until the preset number of iterations is reached, the set of non-obstacle grids that the luggage transport vehicle needs to pass through to reach the destination position, corresponding to the individual with the best fitness value among the final elite individuals, is used as the intermediate grid.

[0026] Specifically, the use of a path connection method to connect the intermediate grids to form a first planning path includes:

[0027] Starting from the current grid position of the luggage transport vehicle, searching for adjacent grids in the middle grid, wherein the adjacent grids include adjacent grids in four directions: up, down, left, and right;

[0028] According to the preset evaluation function, the grid with the best evaluation result among the adjacent grids is selected as the next grid;

[0029] Connect the grid center of the current grid to the grid center of the next grid;

[0030] Repeat the grid selection and connection process until it is connected to the grid corresponding to the end position, and obtain the first planned path.

[0031] Specifically, optimizing the first planned path by a local optimization method to obtain an optimized path includes:

[0032] Set the safety distance threshold between the baggage transport vehicle and the obstacle boundary;

[0033] Using the local optimization method, redundant grid nodes in the first planned path are deleted to obtain the optimized path.

[0034] Specifically, setting the safety distance threshold between the luggage transport vehicle and the obstacle boundary includes:

[0035] Calculate the shortest distance between the obstacle coordinates and the first planned path as the safety distance;

[0036] The sum of the radius of the obstacle's circumscribed circle and the length of the luggage transport vehicle is used as the safety distance threshold.

[0037] Specifically, the method of using the local optimization method to delete redundant grid nodes in the first planned path to obtain the optimized path includes:

[0038] Starting from the end grid, select three grid nodes A1, A2, and A3 in order;

[0039] When the slopes of line A1A2 and line A2A3 are the same, the middle node A2 is a redundant node and is deleted.

[0040] When the slopes of straight line A1A2 and straight line A2A3 are different, and the safety distance between straight line A1A3 and the obstacle is greater than the safety distance threshold, the intermediate node A2 is deleted;

[0041] The screening process of redundant nodes is repeated until the middle node is the starting point of the luggage transport vehicle, and the optimized path is obtained.

[0042] Specifically, by setting multiple sensors and RFID tags on each luggage transport vehicle, real-time data and the final location of each luggage during transportation are obtained, including:

[0043] Perform outlier correction and filtering on the raw data collected by multiple sensors;

[0044] Perform data cleaning and data compression on RFID tag data.

[0045] The baggage transport path tracking and correction system based on RFID and multi-sensor fusion is used to implement the baggage transport path tracking and correction method based on RFID and multi-sensor fusion, including:

[0046] The data acquisition module acquires the real-time data and final location of each piece of luggage during transportation by installing multiple sensors and RFID tags on each luggage transport vehicle;

[0047] A baggage transport path planning module, which plans a transport path for each baggage transport vehicle based on the real-time data and the destination location using a path planning method to avoid environmental obstacles and obtain a first planned path;

[0048] A baggage transport path optimization module, which optimizes the first planned path by a local optimization method to obtain an optimized path;

[0049] The luggage transport module controls each luggage transport vehicle to move to a corresponding terminal position according to the optimized path, so that each user can arrive at the corresponding terminal position to collect the luggage, wherein the terminal position corresponding to each luggage transport vehicle is different.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The present invention uses a combination of RFID tags and multiple sensors to comprehensively monitor the baggage transportation process, monitor the location and status of luggage in real time, and fully utilize information collected from different data sources to improve data accuracy and reliability. A path planning method can be used to plan an optimal transportation route while avoiding obstacles, thereby improving luggage transportation efficiency. A local optimization algorithm can further simplify the transportation route, further shortening luggage transportation time and finding a more efficient luggage transportation route. A control system precisely controls the movement of each luggage transport vehicle, ensuring that it travels along the optimized route to ensure that luggage arrives accurately at its destination, improving the reliability of luggage transportation. This allows for precise tracking and management of luggage transportation, improving its efficiency and safety. Furthermore, since each luggage transport vehicle carries a user's luggage and each destination location is different, the destination location can be serially numbered and notified to specific users via text messages, allowing users to go directly to the corresponding destination location to wait for their luggage to arrive, eliminating the possibility of users taking the wrong luggage. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a workflow diagram of the baggage transport path tracking and correction method based on RFID and multi-sensor fusion in Example 1 of the present invention;

[0053] Figure 2 This is a schematic diagram of a path planned by the path connection method in Example 1 of the present invention;

[0054] Figure 3 This is a schematic diagram of the optimization path of the local optimization method in Example 1 of the present invention;

[0055] Figure 4 This is a structural diagram of a baggage transport path tracking and correction system based on RFID and multi-sensor fusion in Example 2 of the present invention. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0059] Example 1

[0060] This embodiment provides a baggage transport path tracking and correction method based on RFID and multi-sensor fusion, such as Figure 1 As shown, the baggage transport path tracking and correction method based on RFID and multi-sensor fusion includes:

[0061] S101, by setting multiple sensors and RFID tags on each luggage transport vehicle, obtaining real-time data and terminal location of each luggage during transportation;

[0062] S102. Plan a transport path for each luggage transport vehicle based on the real-time data and the destination location using a path planning method to avoid environmental obstacles and obtain a first planned path.

[0063] S103, optimizing the first planned path by a local optimization method to obtain an optimized path;

[0064] S104. Control each luggage transport vehicle to move to a corresponding terminal location according to the optimized path, so that each user arrives at the corresponding terminal location to collect the luggage, wherein the terminal location corresponding to each luggage transport vehicle is different.

[0065] To achieve intelligent luggage transportation at the airport, passengers' luggage is placed on luggage transport vehicles. By controlling the transportation trajectory of each luggage transport vehicle, the luggage can be transported quickly and accurately to the corresponding destination. Specifically, the destination is in a planned destination area. Each destination is equipped with a conspicuous sign. For example, if the destination is a 0.3 square meter rectangular waiting area grid, the luggage will move to the rectangular waiting area grid and stop. The user can receive the number of the rectangular waiting area grid through the mobile phone, and then reach the rectangular waiting area grid through the conspicuous sign to collect his or her luggage.

[0066] In this embodiment, an RFID tag for each piece of luggage is attached to the corresponding luggage transport vehicle. Each RFID tag stores information about each piece of luggage, such as the luggage tag number, flight number, departure airport, arrival airport, and take-off and landing times. By obtaining the luggage's flight information, the luggage's final location is determined. Multiple sensors, such as position sensors and speed sensors, are installed on the luggage transport vehicle to monitor the luggage's dynamic information in real time, collect information such as the luggage's location and speed, and send it to a backend database. The combined use of RFID tags and multiple sensors enables comprehensive monitoring of the luggage transport process, ensuring data accuracy and integrity. The data collected by multiple sensors can provide a more detailed understanding of the luggage's transportation status, providing data support for identifying the luggage's transportation route.

[0067] Specifically, due to the complex airport environment, the large number of passengers and airport facilities, luggage transport vehicles need to avoid these obstacles when moving through the airport to ensure safe arrival at their destination. This invention designs a path planning method that can effectively avoid obstacles in the airport environment, such as walls, pedestrians, and other luggage transport vehicles, thereby ensuring that the luggage transport vehicles arrive safely and smoothly at their destination. Currently, path planning algorithms include the Dijkstra algorithm and the A* algorithm. This invention creatively combines the genetic optimization algorithm and the A* algorithm to plan the travel path of the luggage transport vehicle. While avoiding obstacles, it can plan a more optimal transportation path, resulting in a first planned path, thereby improving luggage transportation efficiency.

[0068] Specifically, based on the first planned path, a local optimization method is used to further optimize the first planned path. Currently, local optimization methods include simulated annealing algorithms and ant colony algorithms. In this embodiment, the local optimization algorithm is used to further simplify the path while ensuring a safe distance between the luggage transport vehicle and obstacles, further shortening the luggage transport time and improving luggage transport efficiency. By adjusting the path, a more efficient transport path is found. Based on the optimized path, the central control system precisely controls the movement of each luggage transport vehicle through the control system. The control system sends instructions to the transport vehicle, guiding it to travel along the optimized path. At the same time, the position and status of the transport vehicle are continuously monitored through real-time sensor data to ensure that it can accurately reach the corresponding destination and that the luggage can accurately reach the destination. By continuously monitoring the position and status of the transport vehicle, the reliability of luggage transportation can be improved.

[0069] The present invention uses a combination of RFID tags and multiple sensors to comprehensively monitor the baggage transportation process, monitor the location and status of luggage in real time, and fully utilize information collected from different data sources to improve data accuracy and reliability. A path planning method can be used to plan an optimal transportation route while avoiding obstacles, thereby improving luggage transportation efficiency. A local optimization algorithm can further simplify the transportation route, further shortening luggage transportation time and finding a more efficient luggage transportation route. A control system precisely controls the movement of each luggage transport vehicle, ensuring that it travels along the optimized route to ensure that luggage arrives accurately at its destination, improving the reliability of luggage transportation. This allows for precise tracking and management of luggage transportation, improving its efficiency and safety. Furthermore, since each luggage transport vehicle carries a user's luggage and each destination location is different, the destination location can be serially numbered and notified to specific users via text messages, allowing users to go directly to the corresponding destination location to wait for their luggage to arrive, eliminating the possibility of users taking the wrong luggage.

[0070] Furthermore, based on the real-time data and the destination location, a path planning method is used to avoid environmental obstacles and plan the transportation path of each luggage transport vehicle to obtain a first planned path, including:

[0071] S201, using a grid division method to divide the action space of the luggage transport vehicle to obtain multiple space grids;

[0072] S202: Based on the position of the obstacle in the action space, the space grid occupied by the obstacle is used as the obstacle grid;

[0073] S203 : Based on the destination position, a path planning method is used to plan a transportation path of the luggage transport vehicle within a non-obstacle grid to obtain a first planned path.

[0074] In this embodiment, a grid partitioning method is first used to divide the luggage transport vehicle's movement space into multiple grids of equal or similar size. Each grid represents a discrete spatial unit. This discretization of the continuous space into multiple spatial grids reduces environmental complexity and improves path planning efficiency. Based on the spatial grid partitioning, the spatial grids occupied by obstacles are marked as obstacle grids based on the location information of obstacles in the environment. This marking of obstacle grids clearly indicates the location of obstacles in the movement space. During path planning, obstacle grids are considered impassable and must be avoided when planning the luggage transport vehicle's transportation route. For example, there are fixed obstacles in the luggage transport area of ​​an airport, such as pillars and seats. Based on their location information, the spatial grids occupied by these obstacles can be marked as obstacle grids. For example, if a pillar is located in the grid in row 3 and column 5, the grid coordinates corresponding to this grid are marked as obstacle grid coordinates, and the obstacle grid corresponding to these obstacle grid coordinates must be avoided during path planning.

[0075] In this embodiment, a radio frequency device is configured in each spatial grid, and the radio frequency range is adjusted to the area defined in the spatial grid, so that the location of each piece of luggage can be determined by RFID radio frequency technology.

[0076] Specifically, after all obstacle grids are determined, the path planning method is used to plan the transportation path of the luggage transport vehicle within the non-obstacle grid according to the destination position of the luggage, and an optimal path from the starting point to the destination position is obtained; through path planning, environmental obstacles can be avoided, and a shorter transportation path can be planned, reducing the time and cost of luggage transportation and improving transportation efficiency; using a combination of grid division method, obstacle grid marking and path planning method, the transportation path of the luggage transport vehicle can be accurately planned, which not only improves the efficiency and accuracy of path planning, but also ensures the safety and efficiency of luggage transportation.

[0077] Furthermore, the method of planning the transport path of the luggage transport vehicle within a non-obstacle grid using a path planning method based on the destination position to obtain a first planned path includes:

[0078] S301. Using a population optimization method, find non-obstacle grids that the luggage transport vehicle must pass through to reach the destination, and obtain multiple intermediate grids.

[0079] S302: Using a path connection method, connect the intermediate grids to form a first planned path.

[0080] In this embodiment, a population optimization algorithm is used to search for feasible paths from the starting point to the destination based on the baggage transport vehicle's starting and ending locations. By evaluating the fitness of each feasible path, a path with high fitness is selected from multiple feasible paths, and the grids it passes through are used as intermediate grids. The population optimization algorithm can search the entire non-obstacle grid space to find a globally optimal or near-optimal path. The algorithm can be adjusted based on different fitness functions and constraints to accommodate different transportation needs and scenarios, offering high flexibility. For example, in an airport baggage transport area, there is a starting grid and a destination grid, as well as several non-obstacle grids and obstacle grids. Using the population optimization algorithm, multiple possible paths from the starting point to the destination can be generated. By evaluating the fitness of each path, the optimal path can be selected as the intermediate grid sequence for the first planned path.

[0081] Specifically, the path connection method connects multiple intermediate grid points to form a continuous, smooth path. Using the A* algorithm with a four-neighborhood strategy, each grid point can only connect to its four adjacent grid points above, below, and to the left and right. During the connection process, the evaluation function value from each intermediate grid point to the destination is calculated. Combined with the evaluation function values ​​of the paths already traversed, the optimal adjacent grid points are selected for connection. This path connection method can quickly find the shortest path, improving the efficiency and flexibility of path planning. For example, given three intermediate grid points C, D, and E, located between starting point A and destination B, the A* algorithm with a four-neighborhood strategy can connect these three intermediate grid points to form a path from A to B. The A* algorithm calculates the estimated cost from each intermediate grid point to B and, based on the costs of the paths already traversed, selects the path with the lowest cost for expansion. For example, if the cost from C to D is less than the cost from C to E, and the estimated cost from D to B is also low, the algorithm will select path CDB, resulting in the shortest path from A to B. By combining the population optimization method with the A* algorithm of the four-neighborhood strategy, the transportation path of the luggage transport vehicle can be effectively planned to obtain a path that is both safe and efficient.

[0082] Furthermore, the population optimization method is used to find the non-obstacle grids that the luggage transport vehicle needs to pass through to reach the terminal location, and multiple intermediate grids are obtained, including:

[0083] S401: Initialize a population, where each individual in the population represents a non-obstacle grid that a luggage transport vehicle must pass through to reach the destination.

[0084] S402, calculating the fitness value of each individual according to a preset fitness function;

[0085] S403. Select multiple individuals with relatively better fitness values as the initial elite individuals according to the fitness values;

[0086] S404. Perform mutation operations on the initial elite individuals to generate mutant individuals;

[0087] S405. Perform crossover operations on the mutant individuals and the initial elite individuals to generate crossover individuals;

[0088] S406. Select the elite individuals of the next generation according to the fitness values corresponding to the crossover individuals;

[0089] S407. Until the preset number of iterations is reached, use the non-obstacle grids that the individual corresponding to the optimal fitness value in the final elite individuals needs to pass through to reach the end position as the intermediate grids.

[0090] In this embodiment, according to the starting position and the end position of the luggage transport vehicle, the individuals in the population are initialized, and multiple transport paths are randomly generated. Each transport path includes multiple non-obstacle grids required to travel from the starting position to the end position. According to the preset fitness function, the fitness value of each individual is calculated. In this embodiment, the fitness function is:

[0091]

[0092] In the formula, F is the fitness of each individual, L is the path length of each individual, j is the number of non-obstacle grids in the individual, x n and x n+1 represent the x-axis coordinates of the nth and (n + 1)th grids, y n and y n+1 represent the y-axis coordinates of the nth and (n + 1)th grids, S represents the number of inflection points in the individual's planned path, α and β are the weights of L and S, and c is a parameter that can be set by oneself. Calculate the fitness value of each individual in the population according to the fitness function, set the fitness threshold, and select the individuals with fitness values greater than the fitness threshold as the initial elite individuals. The selection formula for the initial elite individual set is as follows:

[0093] E0 = {x i 丨F i > F *}

[0094] In the formula, E0 represents the initial elite individual set, x i represents the state value of the ith individual in the population, F i represents the fitness value of the ith individual, F *Represents the fitness threshold. Based on the fitness threshold, excellent individuals are selected from the population. By selecting elite individuals, we can prevent the loss of excellent solutions during the algorithm optimization process and improve the quality of the optimization results. Add a small random perturbation to the initial elite individuals and perform a mutation operation to generate mutant individuals. The mutation formula is as follows:

[0095] x′ i =x i +∈×rand()

[0096] Where x′ i is the individual state value after mutation, ∈ is the mutation intensity, which can be set according to computational needs, and rand() is a random number uniformly distributed in the range [-1, 1]. Mutated individuals are generated through mutation, which increases population diversity and avoids falling into local optimal solutions. Mutated individuals are cross-pollinated with the initial elite individuals to generate crossover individuals. This crossover operation combines the advantages of different individuals to generate better individuals, facilitating the algorithm's optimization process. After the crossover operation, the fitness values ​​of the newly generated crossover individuals are calculated and the next generation of elite individuals are selected based on their fitness values. Selecting crossover individuals with higher fitness values ​​as the next generation of elite individuals preserves excellent solutions and accelerates the algorithm's convergence. The algorithm iterates and updates the population and elite individuals until the preset number of iterations is reached. At the end of the iteration, the individual with the highest fitness value among the final elite individuals is selected as the optimal solution. The non-obstacle grid that the luggage transport vehicle must pass through to reach the destination, corresponding to the individual with the highest fitness value among the final elite individuals, is used as the intermediate grid. Through continuous iteration and selection of excellent individuals, the algorithm gradually approaches the optimal solution, improving the quality of the optimization results.

[0097] Furthermore, the method of connecting the intermediate grids using a path connection method to form a first planning path includes:

[0098] S501: Starting from the current grid position of the luggage transport vehicle, search for adjacent grids in the middle grid, wherein the adjacent grids include adjacent grids in four directions: up, down, left, and right;

[0099] S502: Selecting the grid with the best evaluation result among the adjacent grids as the next grid according to a preset evaluation function;

[0100] S503, connecting the grid center of the current grid with the grid center of the next grid;

[0101] S504 , repeating the grid selection and connection process until connecting to the grid corresponding to the end position, thereby obtaining a first planned path.

[0102] In this embodiment, if Figure 2The shaded grid is the obstacle grid. Starting from the current grid position of the luggage transport, the target grid must be the upper right corner. Using the four-neighborhood A* algorithm, starting from the current grid, we search for adjacent grids in the four directions of up, down, left, and right. These adjacent grids constitute the neighborhood of the current grid. This four-neighborhood search reduces search complexity and ensures the continuity of the path between grids.

[0103] Specifically, according to a preset evaluation function, the grid with the best evaluation result among the adjacent grids is selected as the next grid. The evaluation function in this embodiment is:

[0104] f(n)=g(n)+h(n)

[0105] Where f(n) is the evaluation value, g(n) is the actual cost from the starting grid to the current grid, and h(n) is the estimated cost from the current grid to the final grid, using Euclidean distance for evaluation. The evaluation function value is calculated for each adjacent grid, and the grid with the smallest evaluation function value is selected as the next grid. By selecting the grid with the smallest evaluation function value, the shortest path can be gradually selected. A line segment is used to connect the grid center point of the current grid with the grid center point of the next grid, ensuring the continuity of the path between grids and facilitating the movement of the luggage transport vehicle along the path.

[0106] Specifically, steps S501-S503 are repeated to continuously select the optimal adjacent grids and connect them. Each selection is based on the neighborhood of the current grid and the evaluation function value. When the destination grid is reached, the iteration is stopped. At this time, a complete path from the starting point to the destination has been formed. The path connection method can ensure the integrity of the path from the starting point to the destination. By gradually selecting the optimal grids and connecting them, the optimal path can be found. By using the four-neighborhood search strategy and the selection of the evaluation function, an efficient and continuous path can be found for the luggage transport vehicle in the grid environment, such as Figure 2 , through the path connection method, the driving path in the right figure is obtained as the optimal driving path.

[0107] Furthermore, the optimizing the first planned path by a local optimization method to obtain an optimized path includes:

[0108] S601: Setting a safety distance threshold between the baggage transport vehicle and the obstacle boundary;

[0109] S602: Using a local optimization method, delete redundant grid nodes in the first planned path to obtain an optimized path.

[0110] In this embodiment, in order to ensure that the luggage transport vehicle can safely avoid obstacles, a safety distance threshold is set. The safety distance threshold defines the minimum safe distance between the transport vehicle and the obstacle boundary, ensuring that no collision occurs during driving due to excessive distance, thereby improving the safety of the luggage transport vehicle during operation.

[0111] Specifically, the first planned path only considers the driving path between neighboring grids during the design process, resulting in a longer driving path. The local optimization method optimizes the path by deleting redundant nodes or adjusting the node positions on the basis of the first planned path. By checking each grid node in the first planned path, it is determined whether the grid straight line composed of it meets the requirements of the safety distance threshold, and those redundant nodes that do not affect the path connectivity and are far away from obstacles are deleted to shorten the path length: by deleting redundant nodes, the path length can be significantly shortened and the transportation efficiency can be improved. The optimized path will be smoother, reducing the sharp turns of the luggage transport vehicle during driving. By optimizing the first planned path through the local optimization method, the safety and efficiency of the luggage transportation path can be improved.

[0112] Furthermore, the setting of the safety distance threshold between the luggage transport vehicle and the obstacle boundary includes:

[0113] S701, calculating the shortest distance between the obstacle coordinates and the first planned path as a safety distance;

[0114] S702: The sum of the radius of the circumscribed circle of the obstacle and the length of the luggage transport vehicle is used as a safety distance threshold.

[0115] In this embodiment, the precise coordinates of the obstacle are obtained from the sensor, and the shortest distance between the obstacle and the planned path is calculated in real time to ensure the real-time update and accuracy of the safety distance. The shortest distance is used as the safety distance. By calculating the shortest distance between the obstacle coordinates and the first planned path, the direction of the path and the position of the obstacle are taken into consideration to ensure that a certain safety margin is maintained between the transport vehicle and the obstacle.

[0116] Specifically, the radius of the obstacle's circumscribed circle is determined based on its shape and size. The safety distance threshold is then calculated by adding the length of the luggage transport vehicle and the radius of the obstacle's circumscribed circle. By setting the safety distance threshold, a certain safety margin can be maintained between the luggage transport vehicle and the obstacle during travel, thereby improving the safety and efficiency of the transportation process.

[0117] Furthermore, the method of using a local optimization method to delete redundant grid nodes in the first planned path to obtain an optimized path includes:

[0118] S801, starting from the end grid, select three grid nodes A1, A2, and A3 in order;

[0119] S802: When the slopes of straight lines A1A2 and A2A3 are the same, the intermediate node A2 is a redundant node and is deleted.

[0120] S803: When the slopes of straight line A1A2 and straight line A2A3 are different, and when the safety distance between straight line A1A3 and the obstacle is greater than the safety distance threshold, delete the intermediate node A2.

[0121] S804: Repeat the screening process of redundant nodes until the intermediate node is the starting point of the luggage transport vehicle, and obtain the optimized path.

[0122] In this embodiment, a local optimization method is used to further optimize the luggage transport vehicle's transport path, removing redundant nodes to achieve more efficient luggage transport. Starting from the destination grid, three grid nodes A1, A2, and A3 are sequentially selected. Lines A1A2 and A2A3 are analyzed separately. When the slopes of lines A1A2 and A2A3 are the same, node A2 is on line A1A3 and does not contribute to the shape or length of the path. In this case, node A2 is redundant. Removing this redundant node simplifies the path and reduces the number of unnecessary nodes. When the slopes of lines A1A2 and A2A3 differ, the minimum distance between line A1A3 and an obstacle is calculated. If this minimum distance exceeds a safety distance threshold, A1A3 can meet collision-free transport requirements. In this case, intermediate node A2 can be removed, further shortening the transport path.

[0123] Specifically, repeat steps S801-S803, and gradually filter out redundant nodes from the end point to the starting point. This process will continue until the intermediate node becomes the starting point of the luggage transport vehicle. The path obtained at this time is the optimized path. By sequential calculation, the entire path is optimized, and efficiency and safety are maintained from the starting point to the end point. Through step-by-step optimization, the complexity of global re-planning of the path is avoided. By using the local optimization method to delete the redundant grid nodes in the first planned path, the path can be simplified, efficiency and safety can be improved, and the optimized path is finally obtained. Under the premise of ensuring the safety of the luggage transport vehicle, the transportation efficiency is improved. Figure 3 , the path in the left figure is optimized by the local optimization method, and the path in the right figure is obtained, making the luggage transport vehicle's travel path shorter.

[0124] Furthermore, by setting multiple sensors and RFID tags on each luggage transport vehicle, real-time data and the final location of each luggage during transportation are obtained, including:

[0125] S901, performing outlier correction and filtering on raw data collected by multiple sensors;

[0126] S902: Clean and compress the RFID tag data.

[0127] In this embodiment, the raw data collected by each sensor is preprocessed, including outlier correction and filtering. Outliers are detected, found, and their locations are determined, including missing data, type errors, timestamp errors, etc. The abnormal data point is corrected by interpolation method with reference to the data before and after the abnormal data point to ensure that information is not missing and maintain the continuity of the original collected data. The corrected data is filtered to eliminate noise and interference, thereby improving the accuracy of the data.

[0128] Specifically, RFID tag data is preprocessed, including data cleaning and data compression. RFID technology may generate a large amount of redundant data during data collection. Data cleaning can remove these redundant data. The reader may miss readings when reading RFID tag data. When missed readings are found, the data is padded based on the previous and next data to improve data integrity. In order to reduce storage and transmission overhead, RFID tag data can be compressed. RFID data can be compressed from the data layer to the logical area layer to remove redundant data, and there is a certain tolerance for missed data readings.

[0129] Example 2

[0130] In this embodiment, if Figure 4 , providing a baggage transport path tracking and correction system based on RFID and multi-sensor fusion, for implementing the baggage transport path tracking and correction method based on RFID and multi-sensor fusion, including:

[0131] The data acquisition module acquires the real-time data and final location of each piece of luggage during transportation by installing multiple sensors and RFID tags on each luggage transport vehicle;

[0132] A baggage transport path planning module, which plans a transport path for each baggage transport vehicle based on the real-time data and the destination location using a path planning method to avoid environmental obstacles and obtain a first planned path;

[0133] A baggage transport path optimization module, which optimizes the first planned path by a local optimization method to obtain an optimized path;

[0134] The luggage transport module controls each luggage transport vehicle to move to a corresponding terminal position according to the optimized path, so that each user can arrive at the corresponding terminal position to collect the luggage, wherein the terminal position corresponding to each luggage transport vehicle is different.

[0135] In this embodiment, the data acquisition module includes an RFID tag, an RFID reader / writer, and multiple sensors. The RFID tag is used to store the unique identification information of the luggage, and the RFID reader / writer is used to read and write this information, reading the user identity information and flight information corresponding to the luggage, thereby identifying the final location of the luggage. The multiple sensors include position sensors, humidity sensors, acceleration sensors, etc., which are used to collect environmental parameters and dynamic information during the luggage transportation process. Through the collection of multiple sensors and RFID tags, real-time data and the final location of the luggage during transportation are obtained.

[0136] Specifically, the baggage transport route planning module includes a central processing unit (CPU) and a path planning unit. The CPU processes and analyzes real-time data and destination location information transmitted by the data acquisition module. The path planning unit uses path planning methods based on the real-time data and destination location to avoid environmental obstacles and plan the transport path for each baggage transport vehicle. This results in a first planned path, and through dynamic planning of the optimal path, transport efficiency is improved. The baggage transport route optimization module includes an optimization algorithm processor and a communication interface. The optimization algorithm processor executes a local optimization algorithm to refine and optimize the first planned path, removing redundant nodes and avoiding unnecessary turns and waiting. The communication interface communicates with the baggage transport route planning module and the baggage transport module, improving the flexibility and responsiveness of baggage transport.

[0137] Specifically, the luggage transport module comprises a drive unit and a control unit. The drive unit, which includes a motor and transmission, drives the luggage transport vehicle. The control unit, which includes a controller, sensor interface, and communication interface, receives optimized path information and controls the drive system, ensuring the vehicle follows the optimized path. During movement, sensors monitor environmental changes and vehicle status in real time to ensure safe operation. These four modules together form a complete luggage transport system. Through real-time data acquisition, path planning, route optimization, and precise control, they ensure efficient, safe, and reliable luggage transport.

[0138] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A baggage transport path tracking and correction method based on RFID and multi-sensor fusion is characterized by: include: By installing multiple sensors and RFID tags on each baggage transport vehicle, real-time data and the final location of each baggage during transportation are obtained; Based on the real-time data and the destination location, a path planning method is used to avoid environmental obstacles and plan a transportation path for each luggage transport vehicle to obtain a first planned path; Optimizing the first planned path by a local optimization method to obtain an optimized path; Controlling each luggage transport vehicle to move to a corresponding terminal location according to the optimized path, so that each user arrives at the corresponding terminal location to collect the luggage, wherein the terminal location corresponding to each luggage transport vehicle is different; Optimizing the first planned path by a local optimization method to obtain an optimized path includes: Set the safety distance threshold between the baggage transport vehicle and the obstacle boundary; Using the local optimization method, redundant grid nodes in the first planned path are deleted to obtain the optimized path; The step of setting a safety distance threshold between the luggage transport vehicle and the obstacle boundary includes: Calculate the shortest distance between the obstacle coordinates and the first planned path as the safety distance; The sum of the radius of the obstacle's circumscribed circle and the length of the luggage transport vehicle is used as the safety distance threshold; The method of using a local optimization method to delete redundant grid nodes in the first planned path to obtain an optimized path includes: Select three grid nodes in sequence starting from the end grid ; When the straight line and straight lines When the slopes are the same, the intermediate nodes For redundant nodes, the intermediate nodes delete; When the straight line and straight lines When the slope of the straight line is different When the safety distance between the node and the obstacle is greater than the safety distance threshold, the intermediate node delete; The screening process of redundant nodes is repeated until the middle node is the starting point of the luggage transport vehicle, and the optimized path is obtained.

2. The baggage transport path tracking and correction method based on RFID and multi-sensor fusion according to claim 1 is characterized in that: Based on the real-time data and the destination location, a path planning method is used to avoid environmental obstacles and plan a transportation path for each luggage transport vehicle to obtain a first planned path, including: The action space of the luggage transport vehicle is divided by using the grid division method to obtain multiple space grids; According to the position of the obstacle in the action space, the space grid occupied by the obstacle is used as the obstacle grid; According to the terminal position, a path planning method is used to plan the transportation path of the luggage transport vehicle within a non-obstacle grid to obtain a first planned path.

3. The baggage transport path tracking and correction method based on RFID and multi-sensor fusion according to claim 2 is characterized in that: The method of planning the transport path of the luggage transport vehicle within a non-obstacle grid using a path planning method according to the destination position to obtain a first planned path includes: By using the population optimization method, the non-obstacle grids that the luggage transport vehicle needs to pass through to reach the destination are found, and multiple intermediate grids are obtained; The intermediate grids are connected using a path connection method to form a first planning path.

4. The baggage transport path tracking and correction method based on RFID and multi-sensor fusion according to claim 3 is characterized in that: The population optimization method is used to find the non-obstacle grids that the luggage transport vehicle needs to pass through to reach the terminal location, and multiple intermediate grids are obtained, including: Initialize the population, where each individual in the population represents a set of non-obstacle grids that the luggage transport vehicle must pass through to reach the destination; Calculate the fitness value of each individual according to the preset fitness function; According to the fitness value, individuals whose fitness value is greater than a preset fitness threshold are selected as initial elite individuals; Performing a mutation operation on the initial elite individuals to generate mutant individuals; Performing a crossover operation on the mutant individual and the initial elite individual to generate a crossover individual; Select the elite individuals of the next generation according to the fitness values ​​corresponding to the crossover individuals; Until the preset number of iterations is reached, the set of non-obstacle grids that the luggage transport vehicle needs to pass through to reach the destination position, corresponding to the individual with the best fitness value among the final elite individuals, is used as the intermediate grid.

5. The baggage transport path tracking and correction method based on RFID and multi-sensor fusion according to claim 3 is characterized in that: The method of connecting the intermediate grids using a path connection method to form a first planning path includes: Starting from the current grid position of the luggage transport vehicle, searching for adjacent grids in the middle grid, wherein the adjacent grids include adjacent grids in four directions: up, down, left, and right; According to the preset evaluation function, the grid with the best evaluation result among the adjacent grids is selected as the next grid; Connect the grid center of the current grid to the grid center of the next grid; Repeat the grid selection and connection process until it is connected to the grid corresponding to the end position, and obtain the first planned path.

6. The baggage transport path tracking and correction method based on RFID and multi-sensor fusion according to claim 1 is characterized in that: The system provides multiple sensors and RFID tags on each baggage transport vehicle to obtain real-time data and the final location of each baggage during transportation, including: Perform outlier correction and filtering on the raw data collected by multiple sensors; Perform data cleaning and data compression on RFID tag data.

7. The baggage transport path tracking and correction system based on RFID and multi-sensor fusion is characterized by: The method for implementing the baggage transport path tracking and correction method based on RFID and multi-sensor fusion as described in any one of claims 1 to 6 comprises: The data acquisition module acquires the real-time data and final location of each piece of luggage during transportation by installing multiple sensors and RFID tags on each luggage transport vehicle; A baggage transport path planning module, which plans a transport path for each baggage transport vehicle based on the real-time data and the destination location using a path planning method to avoid environmental obstacles and obtain a first planned path; A baggage transport path optimization module, which optimizes the first planned path by a local optimization method to obtain an optimized path; The luggage transport module controls each luggage transport vehicle to move to a corresponding terminal position according to the optimized path, so that each user can arrive at the corresponding terminal position to collect the luggage, wherein the terminal position corresponding to each luggage transport vehicle is different.

Images