Path Planning Method and System Based on Beidou Satellite Positioning

Abstract

The present invention discloses a path planning method and system based on Beidou satellite positioning, which relates to the technical field of Beidou satellite positioning. It includes using a multi-source sensor fusion method to perform high-precision positioning and error correction on Beidou satellite signals to obtain position information; using an electronic map matching method to match electronic map data with the position information to obtain the electronic map data corresponding to the current position; constructing a traffic flow prediction model based on the position information and machine learning algorithms, and inputting the position information into the traffic flow prediction model to obtain a traffic condition prediction result; based on the traffic condition prediction result, using a path search algorithm to plan the path between the current position and the destination to obtain a preliminary path; performing personalized adjustment on the preliminary path according to user preference settings to obtain a recommended path; using a real-time monitoring and feedback mechanism to monitor the final recommended path, evaluate the position changes and traffic conditions in the path, and obtain a final path planning strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of Beidou satellite positioning, in particular to a path planning method and system based on Beidou satellite positioning. Background Art

[0002] The Beidou satellite navigation system (BDS) is a global satellite navigation system independently developed by China, providing high-precision position and time information. It can provide users with all-weather, all-time, and high-precision positioning, navigation, and timing services globally. The Beidou system consists of three parts: a space segment, a ground segment, and a user segment. The space segment includes multiple geostationary orbit satellites, inclined geosynchronous orbit satellites, and medium Earth orbit satellites.

[0003] In the field of Beidou satellite positioning, existing electronic map matching algorithms sometimes cannot accurately map the actual position of a vehicle to a digital map, resulting in incorrect path planning. Moreover, in complex urban environments, such as urban canyons with high-rise buildings or tunnels, traditional satellite positioning signals are easily interfered with, leading to a decrease in positioning accuracy. At the same time, traditional traffic flow prediction models are difficult to accurately predict future traffic conditions, seriously affecting the safety of the method during use. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a path planning method based on Beidou satellite positioning to solve the problem that existing electronic map matching algorithms sometimes cannot accurately map the actual position of a vehicle to a digital map, resulting in incorrect path planning, and in complex urban environments, such as urban canyons with high-rise buildings or tunnels, traditional satellite positioning signals are easily interfered with, leading to a decrease in positioning accuracy.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a path planning method based on Beidou satellite positioning, which includes:

[0008] Using a multi-source sensor fusion method to perform high-precision positioning and error correction on Beidou satellite signals to obtain position information;

[0009] Using an electronic map matching method to match electronic map data with the position information to obtain the electronic map data corresponding to the current position;

[0010] Based on the position information and a machine learning algorithm, constructing a traffic flow prediction model, and inputting the position information into the traffic flow prediction model to obtain a traffic condition prediction result;

[0011] Based on the traffic condition prediction results, a path search algorithm is used to plan the path between the current location and the destination, and a preliminary path is obtained;

[0012] According to the user preference settings, the preliminary path is personalized adjusted to obtain a recommended path;

[0013] A real-time monitoring and feedback mechanism is used to monitor the final recommended path, evaluate the location changes and traffic conditions in the path, and obtain the final path planning strategy.

[0014] As a preferred solution of the path planning method based on Beidou satellite positioning described in the present invention, wherein: the multi-source sensor fusion method is used to perform high-precision positioning and error correction on the Beidou satellite signal to obtain location information, and the specific steps are as follows:

[0015] Receive the current location information from the Beidou satellite, and synchronously obtain the acceleration and angular velocity data provided by the inertial navigation system IMU;

[0016] Use the inertial navigation system IMU data to predict the state at the next moment;

[0017] The state includes position, speed and attitude;

[0018] Use the position provided by the Beidou satellite to correct the predicted state;

[0019] Separate the position component from the updated state vector through an extraction matrix to obtain the location information .

[0020] As a preferred solution of the path planning method based on Beidou satellite positioning described in the present invention, wherein: the electronic map matching method is used to match the electronic map data with the location information to obtain the electronic map data corresponding to the current location, and the specific steps are as follows:

[0021] Load the electronic map data covering the current location;

[0022] The electronic map data contains the geographical information of the road network, intersections and buildings;

[0023] Define a point in the electronic map;

[0024] Calculate the distance between the current location and each candidate point on the electronic map, and the expression is:

[0025] ;

[0026] Wherein, represents the current location coordinates, represents the point coordinates on the electronic map, , , They are respectively the coordinates of the current position on , , axis, , , They are respectively the coordinates of the candidate points on the electronic map on , , axis;

[0027] Select the point with the minimum distance as the best matching point of the current position ;

[0028] Use the dynamic window technique DWA to predict the driving trajectory within a certain period in the future, and compare it with the road information on the electronic map;

[0029] Define the predicted driving trajectory as , and calculate its similarity with each road segment on the electronic map , and the expression is:

[0030] ;

[0031] Among them, represents the predicted driving trajectory, represents the road segment on the electronic map, the integration interval is the prediction time period, represents at time , the specific position or state of the predicted trajectory , represents at time , the specific position or state of the road segment ;

[0032] Select the road segment with the highest similarity as the best matching road segment of the current position;

[0033] Match the position information obtained by multi-source sensor fusion with the electronic map data to determine the accurate position and road information of the current position on the electronic map.

[0034] As a preferred solution of the path planning method based on Beidou satellite positioning according to the present invention, wherein: a traffic flow prediction model is constructed based on the position information and machine learning algorithm, and the position information is input into the traffic flow prediction model to obtain a traffic condition prediction result. The specific steps are as follows:

[0035] Use the long short-term memory network LSTM as the basis of the machine learning algorithm;

[0036] Combine the accurate position information obtained from the multi-source sensor fusion method and the road segments determined by the electronic map matching method to construct a traffic flow prediction model;

[0037] Input the collected historical traffic data into the traffic flow prediction model The training is performed in , and the expression is:

[0038] ;

[0039] in, is the sample size, , , are the actual vehicle speed, vehicle density and congestion probability respectively, , , are the predicted vehicle speed, vehicle density and congestion probability respectively;

[0040] Use the trained traffic flow prediction model to predict the current location and the road section where it is located Predict future traffic conditions and obtain specific traffic condition prediction results , the expression is:

[0041] ;

[0042] in, represents the future traffic conditions predicted by the traffic flow prediction model, is the current vehicle speed, is the vehicle density, is the current congestion probability, It is the current time information.

[0043] As a preferred solution of the Beidou satellite positioning-based path planning method of the present invention, wherein: based on the traffic condition prediction result, a path search algorithm is used to plan the path between the current location and the destination to obtain a preliminary path, and the specific steps are as follows:

[0044] Prediction results based on traffic conditions , calculate the dynamic weight of each road segment , reflecting the current road traffic efficiency, the expression is:

[0045] ;

[0046] in, represents the predicted vehicle speed, represents the predicted congestion probability, is a tuning parameter, is the dynamic weight of each road segment;

[0047] Load electronic map data covering the range from the current location to the destination;

[0048] The electronic map data within the range from the current location to the destination includes geographical information of road networks, intersections, and obstacles, and defines the nodes in the electronic map as ;

[0049] Adopt the A-star algorithm as the path search algorithm, combined with dynamic weights to plan the path between the current location and the destination. The expression is:

[0050] ;

[0051] ;

[0052] where represents the actual cost from the starting point to the current node, represents the estimated cost from the current node to the target node considering the dynamic weights, represents the original heuristic function, is the cost function;

[0053] Initialize the data structure of the A-star algorithm;

[0054] The data structure includes an open list and a closed list;

[0055] Start the iterative search process, select the node with the lowest cost from the open list , and check whether this node is the target node;

[0056] If not, move it from the open list to the closed list and expand all its neighbor nodes;

[0057] If the neighbor node is not in the open list, add it to the open list and set its parent node as the current node ;

[0058] If the neighbor node is already in the open list and the new cost is lower, update its cost and parent node;

[0059] Repeat the above process until the target node is found or the open list is empty;

[0060] By backtracking the parent node link of the target node, obtain the optimal path from the current location to the destination , the expression is:

[0061] ;

[0062] ;

[0063] Among them, is the optimal path, is the target node, is the node 's parent node, is the starting node, is the operation of reversing the path sequence, is the backtracking operation function.

[0064] As a preferred solution of the path planning method based on Beidou satellite positioning according to the present invention, wherein: the preliminary path is personalized adjusted according to the user preference setting to obtain a recommended path, and the specific steps are as follows:

[0065] Define the user preference setting vector and calculate the characteristic score vector of each path segment;

[0066] The characteristic score vector includes highway usage, landscape score, and the number of traffic lights;

[0067] Define the cost function of personalized adjustment to evaluate the cost value of each road segment after considering the user preference;

[0068] Initialize the adjusted path set and initially set it as the preliminary path;

[0069] Start the iterative adjustment process. For a road segment in the optimal path , calculate its cost after personalized adjustment and compare it with adjacent alternative road segments, and update the path set , the expression is:

[0070] ;

[0071] Repeat the above process until all road segments are traversed or no better alternative road segment can be found, is a road segment in the optimal path , is the new road segment used to replace after adjustment;

[0072] Backtrack the adjusted path set to obtain a recommended path that meets the user preference.

[0073] The final recommended path is monitored by adopting a real-time monitoring and feedback mechanism, the position change and traffic condition in the path are evaluated, and the final path planning strategy is obtained. The specific steps are as follows:

[0074] Receive the current position information from the Beidou satellite system , and compare it with the expected position on the recommended path, and calculate the deviation. The expression is:

[0075] ;

[0076] Among them, represents the expected position coordinates on the recommended path at the current time point, is the current position information, is the real-time position deviation;

[0077] Utilize the short message function of the Beidou system to collect traffic condition update data along the way;

[0078] According to the real-time position deviation and the traffic condition update data, evaluate whether it is necessary to re-plan the path;

[0079] When there is a significant deviation or a new traffic problem is encountered, trigger the path re-planning process;

[0080] Define a threshold judgment function , to determine whether it is necessary to re-plan the path, and the expression is:

[0081] ;

[0082] Among them, is the maximum allowable position deviation threshold, is the traffic condition update data;

[0083] Feed back the updated path information to the user, and continue to perform real-time monitoring until the destination is reached.

[0084] In the second aspect, the present invention provides a path planning system based on Beidou satellite positioning, including:

[0085] A positioning module, an electronic map matching module, a traffic flow prediction module, a path search module, a personalized adjustment module, and a monitoring module;

[0086] The positioning module is used to perform high-precision positioning and error correction on the Beidou satellite signal by using a multi-source sensor fusion method to obtain position information;

[0087] The electronic map matching module is used to match the electronic map data with the position information by using an electronic map matching method to obtain the electronic map data corresponding to the current position;

[0088] The traffic flow prediction module is used to construct a traffic flow prediction model based on the position information and a machine learning algorithm, and input the position information into the traffic flow prediction model to obtain a traffic condition prediction result;

[0089] The path search module is used to plan the path between the current location and the destination based on the traffic condition prediction result by using a path search algorithm to obtain a preliminary path;

[0090] The personalized adjustment module is used to perform personalized adjustment on the preliminary path according to the user preference settings to obtain a recommended path;

[0091] The monitoring module is used to monitor the final recommended path by using a real-time monitoring and feedback mechanism, evaluate the location changes and traffic conditions in the path, and obtain a final path planning strategy.

[0092] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the path planning method based on Beidou satellite positioning as described in the first aspect of the present invention is implemented.

[0093] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the path planning method based on Beidou satellite positioning as described in the first aspect of the present invention is implemented.

[0094] The beneficial effects of the present invention are as follows: By adopting a multi-source sensor fusion method to perform high-precision positioning and error correction on the Beidou satellite signal, accurate position information acquisition is realized, which not only improves the accuracy of position data, but also enhances the robustness and reliability of the system, making the subsequent path planning more reliable and efficient. By adopting an electronic map matching method to match the electronic map data with the position information, accurate positioning of the current position on the electronic map is realized. Through accurate map matching, the accuracy of the starting point and the ending point of the path planning is improved, and the route error caused by map errors is reduced. A traffic flow prediction model is constructed based on the position information and machine learning algorithms, and the position information is input into the traffic flow prediction model to realize the prediction of future traffic conditions. The prediction ability enhances the adaptability and flexibility of the method and can quickly respond to the impacts brought by emergencies such as traffic accidents or road construction. Description of the Drawings

[0095] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for description in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0096] Figure 1 It is a flowchart of the path planning method based on Beidou satellite positioning in Embodiment 1.

[0097] Figure 2 It is a schematic diagram of the path planning system based on Beidou satellite positioning in Embodiment 1. Specific implementation manners

[0098] To make the above objects, features, and advantages of the present invention more obvious and understandable, the specific implementation manners of the present invention will be described in detail below with reference to the accompanying drawings of the specification.

[0099] In the following description, many specific details are set forth to facilitate a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0100] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other with other embodiments.

[0101] Embodiment 1, referring to Figure 1 and Figure 2 , is the first embodiment of the present invention. This embodiment provides a path planning method based on Beidou satellite positioning, including the following steps:

[0102] S1. Use the multi-source sensor fusion method to perform high-precision positioning and error correction on the Beidou satellite signal to obtain position information;

[0103] Furthermore, receive the current position information from the Beidou satellite, and synchronously obtain the acceleration and angular velocity data provided by the inertial navigation system IMU;

[0104] Use the inertial navigation system IMU data to predict the state at the next moment;

[0105] The state includes position, velocity, and attitude;

[0106] Use the position provided by the Beidou satellite to correct the predicted state;

[0107] Separate the position component from the updated state vector through an extraction matrix to obtain position information ;

[0108] It should be noted that by combining the Beidou satellite signal and IMU data, not only the positioning accuracy is improved, but also the robustness of the system is enhanced. In cases where satellite signals are unstable or missing, such as in urban canyons and tunnels, the IMU data can provide continuous position updates to ensure that the navigation system can maintain high precision and reliability in various complex environments.

[0109] S2. Use the electronic map matching method to match the electronic map data with the location information to obtain the electronic map data corresponding to the current location;

[0110] Furthermore, load the electronic map data covering the current location;

[0111] The electronic map data includes the geographical information of road networks, intersections, and buildings;

[0112] Define a point in the electronic map;

[0113] Calculate the distance between the current location and each candidate point on the electronic map. The expression is:

[0114] ;

[0115] Where, represents the current location coordinates, represents the coordinates of the point on the electronic map, , , are respectively the coordinates of the current location on , , axis, , , are respectively the coordinates of the candidate point on the electronic map on , , axis;

[0116] Select the point with the minimum distance as the best matching point of the current location ;

[0117] Use the dynamic window approach (DWA) to predict the driving trajectory in the next period of time and compare it with the road information on the electronic map;

[0118] Define the predicted driving trajectory as and calculate its similarity with each road segment on the electronic map . The expression is:

[0119] ;

[0120] Where, represents the predicted driving trajectory, represents the road segment on the electronic map, and the integration interval is the prediction time period, represents at time , the specific position or state of the predicted trajectory , Indicates at time the specific location or status of road segment ;

[0121] Select the road segment with the highest similarity as the best matching road segment for the current location;

[0122] Match the location information obtained by multi-source sensor fusion with the electronic map data to determine the accurate location and road information of the current location on the electronic map;

[0123] It should be noted that the electronic map matching step not only solves the mapping problem from the physical location to the digital map, but also predicts the future driving trajectory through the Dynamic Window Approach (DWA), improving the forward-looking and accuracy of path planning. The method can effectively reduce route errors caused by map errors and provide more accurate navigation suggestions for users.

[0124] S3. Construct a traffic flow prediction model based on the location information and machine learning algorithm, and input the location information into the traffic flow prediction model to obtain the traffic condition prediction result;

[0125] Furthermore, use the Long Short-Term Memory (LSTM) network as the basis of the machine learning algorithm;

[0126] Combine the accurate location information obtained from the multi-source sensor fusion method and the road segments determined by the electronic map matching method to construct a traffic flow prediction model;

[0127] Input the collected historical traffic data into the traffic flow prediction model for training, and the expression is:

[0128] ;

[0129] where is the number of samples, , , are the actual vehicle speed, vehicle density, and congestion probability respectively, , , are the predicted vehicle speed, vehicle density, and congestion probability respectively;

[0130] Use the trained traffic flow prediction model to predict the future traffic conditions of the current location and the road segment where it is located to obtain the specific traffic condition prediction result , and the expression is:

[0131] ;

[0132] where represents the future traffic conditions predicted by the traffic flow prediction model, is the current vehicle speed, is the vehicle density, is the current congestion probability, is the current time information;

[0133] It should be noted that using the Long Short-Term Memory network (LSTM) for traffic flow prediction can not only handle the long-term dependencies in historical data but also adjust the prediction model according to real-time location information, enabling the method to more accurately predict future traffic flow, speed, and congestion conditions, helping users avoid peak hours or sections, thereby reducing travel time and improving travel efficiency.

[0134] S4. Based on the traffic condition prediction results, use a path search algorithm to plan the path between the current location and the destination to obtain a preliminary path;

[0135] Furthermore, according to the traffic condition prediction results , calculate the dynamic weight of each road section , which reflects the traffic efficiency of the current road, and the expression is:

[0136] ;

[0137] Among them, represents the predicted vehicle speed, represents the predicted congestion probability, is a tuning parameter, is the dynamic weight of each road section;

[0138] Load the electronic map data covering the range from the current location to the destination;

[0139] The electronic map data from the current location to the destination includes the geographical information of the road network, intersections, and obstacles, and defines the nodes in the electronic map as ;

[0140] Use the A-star algorithm as the path search algorithm, combined with the dynamic weight to plan the path between the current location and the destination, and the expression is:

[0141] ;

[0142] ;

[0143] Among them, represents the actual cost from the starting point to the current node, represents the estimated cost from the current node to the target node considering the dynamic weight, Represents the original heuristic function, which is the cost function;

[0144] Initialize the data structure of the A-star algorithm;

[0145] The data structure includes an open list and a closed list;

[0146] Start the iterative search process, select the node with the lowest cost from the open list and check whether this node is the target node; If not, move it from the open list to the closed list and expand all its neighbor nodes;

[0147] If a neighbor node is not in the open list, add it to the open list and set its parent node as the current node

[0148] ; ;

[0149] If the neighbor node is already in the open list and the new cost is lower, update its cost and parent node;

[0150] Repeat the above process until the target node is found or the open list is empty;

[0151] By backtracking the parent node link of the target node, obtain the optimal path from the current location to the destination , and the expression is:

[0152] ;

[0153] ;

[0154] where, is the optimal path, is the target node, is the parent node of node , is the starting node, is the operation of reversing the path sequence, is the backtracking operation function;

[0155] It should be noted that by calculating the dynamic weights of each road section and combining with the A-star algorithm for path planning, the system can flexibly respond to real-time changing traffic conditions. The dynamic weight mechanism not only considers the current road traffic efficiency but also continuously adjusts the optimal path according to the latest traffic information to ensure that users always move along the most suitable route.

[0156] S5. Make personalized adjustments to the preliminary path according to the user preference settings to obtain the recommended path;

[0157] Furthermore, define the user's preference setting vector and calculate the characteristic score vector for each path segment;

[0158] The characteristic score vector includes highway usage, landscape score, and the number of traffic lights;

[0159] Define a cost function for personalized adjustment to evaluate the cost value of each road segment considering the user's preferences;

[0160] Initialize the adjusted path set and initially set it to the preliminary path;

[0161] Start the iterative adjustment process. For a segment in the optimal path , calculate its cost after personalized adjustment and compare it with adjacent alternative segments, and update the path set , the expression is:

[0162] ;

[0163] Repeat the above process until all segments are traversed or no better alternative segment can be found. is a segment in the optimal path is the new segment used to replace after adjustment;

[0164] By backtracking the adjusted path set , obtain the recommended path that meets the user's preferences;

[0165] It should be noted that the personalized adjustment module realizes highly customized path recommendation by defining the user's preference setting vector and combining the characteristic score vector to evaluate the cost value of each road segment. The method can not only meet the special needs of different users, but also improve the user experience and satisfaction, making each trip more in line with personal preferences.

[0166] S6. Adopt a real-time monitoring and feedback mechanism to monitor the final recommended path, evaluate the position changes and traffic conditions in the path, and obtain the final path planning strategy;

[0167] Furthermore, receive the current position information from the Beidou satellite system , and compare it with the expected position on the recommended path to calculate the deviation. The expression is:

[0168] ;

[0169] Among them, represents the expected position coordinates on the recommended path at the current time point, is the current position information, is the real-time position deviation;

[0170] Use the short message function of the Beidou system to collect traffic condition update data along the way;

[0171] Based on the real-time position deviation and the traffic condition update data, evaluate whether a new path needs to be planned;

[0172] When there is a significant deviation or a new traffic problem is encountered, trigger the path replanning process;

[0173] Define a threshold judgment function , and decide whether a new path needs to be planned. The expression is:

[0174] ;

[0175] where is the maximum allowable position deviation threshold, is the traffic condition update data;

[0176] Feed back the updated path information to the user and continue to perform real-time monitoring until the destination is reached;

[0177] It should be noted that the real-time monitoring and feedback mechanism ensures the timeliness and accuracy of path planning by continuously comparing the current position with the expected position and dynamically adjusting according to the latest traffic condition update data. The mechanism can quickly respond to emergencies and replan the path when necessary, ensuring that the user is always on the optimal path, greatly improving the reliability of the method and the user experience.

[0178] This embodiment also provides a path planning system based on Beidou satellite positioning, including:

[0179] A positioning module, an electronic map matching module, a traffic flow prediction module, a path search module, a personalized adjustment module, and a monitoring module;

[0180] The positioning module is used to perform high-precision positioning and error correction on the Beidou satellite signal by using a multi-source sensor fusion method to obtain position information;

[0181] The electronic map matching module is used to match the electronic map data with the position information by using an electronic map matching method to obtain the electronic map data corresponding to the current position;

[0182] The traffic flow prediction module is used to construct a traffic flow prediction model based on the position information and a machine learning algorithm, and input the position information into the traffic flow prediction model to obtain a traffic condition prediction result;

[0183] A path search module, configured to plan a path between the current location and the destination by using a path search algorithm based on the traffic condition prediction result, so as to obtain a preliminary path;

[0184] A personalized adjustment module, configured to perform personalized adjustment on the preliminary path according to user preference settings, so as to obtain a recommended path;

[0185] A monitoring module, configured to monitor the final recommended path by using a real-time monitoring and feedback mechanism, evaluate the location changes and traffic conditions in the path, and obtain a final path planning strategy.

[0186] This embodiment further provides a computer device, which is applicable to the case of the path planning method based on Beidou satellite positioning, and includes: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the path planning method based on Beidou satellite positioning as proposed in the above embodiment.

[0187] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through Wi-Fi, a carrier network, NFC (Near Field Communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a button, a trackball or a touchpad provided on the outer shell of the computer device, or an external keyboard, a touchpad or a mouse, etc.

[0188] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the path planning method based on Beidou satellite positioning as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, abbreviated as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, abbreviated as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, abbreviated as EPROM), programmable read-only memory (Programmable Red-Only Memory, abbreviated as PROM), read-only memory (Read-Only Memory, abbreviated as ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0189] In summary, the present invention uses a multi-source sensor fusion method to perform high-precision positioning and error correction on Beidou satellite signals, achieving accurate acquisition of position information. It not only improves the accuracy of position data but also enhances the robustness and reliability of the system, making subsequent path planning more reliable and efficient. By using an electronic map matching method to match electronic map data with position information, precise positioning of the current position on the electronic map is achieved. Through precise map matching, the accuracy of the starting and ending points of path planning is improved, and route errors caused by map errors are reduced. A traffic flow prediction model is constructed based on position information and machine learning algorithms, and position information is input into the traffic flow prediction model to achieve prediction of future traffic conditions. The prediction ability enhances the adaptability and flexibility of the method and can quickly respond to the impacts brought by emergencies such as traffic accidents or road construction.

[0190] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A path planning method based on Beidou satellite positioning, characterized in that: Including: Using a multi-source sensor fusion method to perform high-precision positioning and error correction on Beidou satellite signals to obtain position information; Using an electronic map matching method to match electronic map data with the position information to obtain the electronic map data corresponding to the current position; Constructing a traffic flow prediction model based on the position information and machine learning algorithm, and inputting the position information into the traffic flow prediction model to obtain a traffic condition prediction result; Based on the traffic condition prediction result, using a path search algorithm to plan the path between the current position and the destination to obtain a preliminary path; Performing personalized adjustment on the preliminary path according to the user preference settings to obtain a recommended path; Using a real-time monitoring and feedback mechanism to monitor the final recommended path, evaluating the position deviation and traffic condition changes in the path, and obtaining a final path planning strategy; Among them, the step of using the electronic map matching method to match the electronic map data with the position information to obtain the electronic map data corresponding to the current position is as follows: Loading the electronic map data covering the current position; The electronic map data includes geographical information of road networks, intersections, and buildings; Defining a point in the electronic map; Calculating the distance between the current position and each candidate point on the electronic map, and the expression is: ; Among them, represents the current position coordinates, represents the point coordinates on the electronic map, , , are respectively the coordinates of the current position on , , axis coordinates, , , are respectively the coordinates of the candidate points on the electronic map on , , axis coordinates; Select the point with the minimum distance as the best matching point for the current position ; Using the Dynamic Window Approach (DWA) to predict the driving trajectory in the next period of time and comparing it with the road information on the electronic map; Define the predicted driving trajectory as , and calculate the similarity between it and each road segment on the electronic map . The expression is: ； Among them, represents the predicted driving trajectory, represents the road segment on the electronic map, and the integration interval is the prediction time period, represents at time the specific position or state of the predicted trajectory ; represents at time the specific position or state of the road segment ; Selecting the section with the highest similarity as the best matching section of the current position; Matching the position information obtained by multi-source sensor fusion with the electronic map data to determine the accurate position and road information of the current position on the electronic map; The step of constructing a traffic flow prediction model based on the position information and machine learning algorithm, and inputting the position information into the traffic flow prediction model to obtain a traffic condition prediction result is as follows: Using the Long Short-Term Memory (LSTM) network as the basis of the machine learning algorithm; Combining the accurate position information obtained from the multi-source sensor fusion method and the sections determined by the electronic map matching method to construct a traffic flow prediction model; Input the collected historical traffic data into the traffic flow prediction model for training, and the expression is: ; Among them, is the number of samples, , , are the actual vehicle speed, vehicle density, and congestion probability respectively, , , are the predicted vehicle speed, vehicle density, and congestion probability respectively; Use the trained traffic flow prediction model to predict the future traffic conditions at the current location and the road segment where it is located to obtain specific traffic condition prediction results , and the expression is: ； Among them, represents the future traffic conditions predicted by the traffic flow prediction model, is the current vehicle speed, is the vehicle density, is the current congestion probability, is the current time information.

2. The path planning method based on Beidou satellite positioning according to claim 1, wherein: The step of using a multi-source sensor fusion method to perform high-precision positioning and error correction on Beidou satellite signals to obtain position information is as follows: Receiving the current position information from Beidou satellites and synchronously obtaining the acceleration and angular velocity data provided by the Inertial Measurement Unit (IMU); Using the IMU data to predict the state at the next moment; The state includes position, speed, and attitude; Using the position provided by Beidou satellites to correct the predicted state; The position component is separated from the updated state vector by an extraction matrix to obtain position information .

3. The path planning method based on Beidou satellite positioning according to claim 1, characterized in that: The step of, based on the traffic condition prediction result, using a path search algorithm to plan the path between the current position and the destination to obtain a preliminary path is as follows: According to the traffic condition prediction results , calculate the dynamic weight of each road section , which reflects the current traffic efficiency of the road, and the expression is: ; Among them, represents the predicted vehicle speed, represents the predicted congestion probability, is a tuning parameter, which is the dynamic weight for each road segment; Loading the electronic map data covering the range from the current position to the destination; The electronic map data within the range from the current position to the destination includes the geographical information of road networks, intersections, and obstacles, and defines the nodes in the electronic map as ; The A-star algorithm is adopted as the path search algorithm, combined with dynamic weights Plan the path between the current position and the destination. The expression is as follows: ； ； Among them, represents the actual cost from the starting point to the current node, represents the estimated cost from the current node to the target node considering the dynamic weight, represents the original heuristic function, is the cost function; Initializing the data structure of the A-star algorithm; The data structure includes an open list and a closed list; Start the iterative search process and select the node with the lowest cost from the open list and check whether this node is the target node; ​ If not, move it from the open list to the closed list and expand all neighbor nodes of this node; If the neighbor node is not in the open list, add it to the open list and set its parent node as the current node ; If the neighbor node is already in the open list and the new cost is lower, update its cost and parent node; Repeat the above process until the target node is found or the open list is empty; By backtracking the parent node link of the target node, the optimal path from the current position to the destination is obtained , and the expression is: ； ； Among them, is the optimal path, is the target node, is the node 's parent node, is the starting node, is the operation of reversing the path sequence, is the backtracking operation function.

4. The path planning method based on Beidou satellite positioning according to claim 3, wherein: The preliminary path is personalized according to the user preference settings to obtain a recommended path. The specific steps are as follows: Define the preference setting vector of the user and calculate the characteristic score vector of each section of the path; The characteristic score vector includes highway usage, landscape score, and the number of traffic lights; Define a cost function for personalized adjustment to evaluate the cost value of each section considering the user preferences; Initialize the set of adjusted paths and initially set it as the preliminary path; Start the iterative adjustment process for the optimal path for a section in it, calculate its cost after personalized adjustment, compare it with adjacent alternative sections, and update the path set , and the expression is: ； Repeat the above process until all road segments are traversed or no better alternative road segment can be found. is the optimal path and is one of the road segments which is adjusted and used to replace as the new road segment; The set of paths adjusted by backtracking , to obtain a recommended path that meets the user's preferences.

5. The path planning method based on Beidou satellite positioning according to claim 4, characterized in that: The real-time monitoring and feedback mechanism is adopted to monitor the final recommended path, evaluate the position deviation and traffic condition changes in the path, and obtain the final path planning strategy. The specific steps are as follows: Receive the current position information from the Beidou satellite system , and compare it with the expected position on the recommended path to calculate the deviation. The expression is as follows: ； Among them, represents the expected position coordinates on the recommended path at the current time point, is the current position information, is the real-time position deviation; Use the short message function of the Beidou system to collect updated traffic condition data along the way; Based on the real-time position deviation and traffic conditions to update the data, and evaluate whether a re-planning of the route is required; When there is a significant deviation or a new traffic problem is encountered, trigger the path replanning process; Define the threshold judgment function , to determine whether a new path needs to be planned. The expression is as follows: ； Among them, is the maximum allowable position deviation threshold, is the traffic condition update data; Feed back the updated path information to the user and continue to perform real-time monitoring until the destination is reached.

6. A path planning system based on Beidou satellite positioning is used to implement the path planning method based on Beidou satellite positioning according to any one of claims 1 to 5, and is characterized in that: Including: A positioning module, an electronic map matching module, a traffic flow prediction module, a path search module, a personalized adjustment module, and a monitoring module; The positioning module is used to perform high-precision positioning and error correction on the Beidou satellite signal by using a multi-source sensor fusion method to obtain position information; The electronic map matching module is used to match the electronic map data with the position information by using an electronic map matching method to obtain the electronic map data corresponding to the current position; The traffic flow prediction module is used to construct a traffic flow prediction model based on the position information and a machine learning algorithm, and input the position information into the traffic flow prediction model to obtain a traffic condition prediction result; The path search module is used to plan the path between the current position and the destination by using a path search algorithm based on the traffic condition prediction result to obtain a preliminary path; The personalized adjustment module is used to personalize the preliminary path according to the user preference settings to obtain a recommended path; The monitoring module is used to monitor the final recommended path by using a real-time monitoring and feedback mechanism, evaluate the position deviation and traffic condition changes in the path, and obtain the final path planning strategy.

7. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the path planning method based on Beidou satellite positioning according to any one of claims 1 to ⑤.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the path planning method based on Beidou satellite positioning according to any one of claims 1 to ⑤.

Images