Road network matching method and device for underground three-dimensional roadway motion trail and computer equipment

Abstract

The invention discloses a road network matching method and device for an underground three-dimensional roadway movement track and computer equipment. The method comprises the following steps: acquiring historical position data of an underground movement target; preprocessing the historical position data and then fitting a historical track; establishing a hidden Markov model suitable for the underground environment by taking the historical track points as an observation sequence and the grid units of the topological model of the center line of the underground three-dimensional roadway as a state space; obtaining a candidate road section set by using a hidden Markov model and calculating a state transition probability; using an improved Viterbi algorithm to solve a state transition probability matrix and an observation probability matrix corresponding to the candidate road section between adjacent track points, and matching an optimal path; and displaying the motion trail of the moving target on a three-dimensional roadway map according to the optimal path. According to the invention, rapid data processing and feedback can be realized, so that a positioning and navigation target can obtain a real-time motion state and environment information, and a more real-time response capability is achieved.

Description

Technical Field

[0001] The present invention relates to the field of underground positioning technology, and in particular to a road network matching method, device and computer equipment for underground three-dimensional tunnel motion trajectory. Background Art

[0002] Efficient road network matching is an important research direction for underground positioning and navigation in coal mines. Underground operations are usually carried out in closed, complex and dynamic tunnel environments, which require extremely high accuracy and reliability of positioning and navigation. Traditional GPS positioning is not available in underground environments and requires other positioning technologies such as inertial navigation and UWB positioning. Such technologies also rely on various sensors (such as accelerometers, gyroscopes, magnetometers, etc.) to collect the motion data of objects in real time, and obtain real-time motion trajectory data through UWB positioning fusion algorithms. However, due to factors such as sensor positioning errors and external interference, these trajectory data are often affected by noise and have errors, and cannot be correctly matched to the underground road network map. Summary of the invention

[0003] In order to address the deficiencies in the prior art, the present invention provides a road network matching method, device, and computer equipment for underground three-dimensional tunnel motion trajectories, which can improve the accurate identification and effective matching of motion trajectories in complex underground environments, and are conducive to enhancing the safety and efficiency of underground operations.

[0004] The technical solution adopted by the present invention to solve the technical problem is: a road network matching method for underground three-dimensional tunnel motion trajectory, comprising:

[0005] S1. Obtain historical position data of underground moving targets;

[0006] S2, preprocessing the historical location data to fit a historical trajectory;

[0007] S3, taking the historical trajectory points as the observation sequence and the grid units of the topological model of the centerline of the underground three-dimensional tunnel as the state space, a hidden Markov model suitable for the underground environment is established;

[0008] S4. Obtaining a set of candidate road sections using the hidden Markov model

[0009] S5. In the hidden Markov model, the entire historical trajectory is divided into different increments based on reliable points, and each increment is used as a window to calculate the observation probability of the trajectory point to the candidate section; and then the state transition probability between adjacent trajectory points corresponding to the candidate section is calculated;

[0010] S6. Using the improved Viterbi algorithm, the state transition probability matrix and the observation probability matrix corresponding to the trajectory points and the candidate sections are solved to match the optimal path;

[0011] S7. Displaying the moving trajectory of the moving target on the three-dimensional lane map according to the optimal path.

[0012] Furthermore, the matching results are evaluated, and the parameters of the hidden Markov model are optimized according to the evaluation results.

[0013] Furthermore, the solution process of the improved Viterbi algorithm includes:

[0014] At each time step, for each state, the dynamic programming table is updated according to the heuristic function and the information of the previous time step, and the path with the highest heuristic value and probability is selected as the optimal path for the current state, and the recursive update of all time steps is completed; backtracking starts from the last time step of the dynamic programming table, finds the optimal hidden state sequence, and selects the optimal path in the set of candidate sections.

[0015] Furthermore, the observation probability of the observation probability matrix is ​​represented by the Euclidean distance d, and the smaller the d value is, the greater the observation probability is.

[0016] Further, the parameters of the hidden Markov model are optimized according to the evaluation results, including:

[0017] The sampling frequency of the trajectory points is adjusted, and steps S3-S5 are repeated to match the optimal path. The matching result is verified each time to adjust the parameters of the hidden Markov model, so that the accuracy of the matching result is improved.

[0018] The present invention also provides a road network matching device for underground three-dimensional tunnel motion trajectory, comprising:

[0019] The data acquisition and processing module is used to obtain the historical position data of the moving target in the well; and fit the historical trajectory after preprocessing the historical position data;

[0020] A matching module is used to establish a hidden Markov model suitable for the underground environment by taking historical trajectory points as observation sequences and the grid units of the topological model of the center line of the underground three-dimensional tunnel as the state space; using the hidden Markov model to obtain a set of candidate sections; in the hidden Markov model, the entire historical trajectory is divided into different increments based on reliable points, and each of the increments is used as a window to calculate the observation probability of the trajectory point to the candidate section; then the state transition probability corresponding to the candidate section between adjacent trajectory points is calculated; and the state transition probability matrix and the observation probability matrix corresponding to the trajectory point and the candidate section are solved by using an improved Viterbi algorithm to match the optimal path.

[0021] The present invention also provides a computer device, comprising:

[0022] processor;

[0023] A memory for storing executable instructions;

[0024] Wherein, the processor is used to read the executable instructions from the memory and execute the executable instructions to implement the road network matching method of the underground three-dimensional tunnel motion trajectory as described.

[0025] The beneficial effects of the present invention are:

[0026] The hidden Markov model can adapt to the complex underground tunnel environment by modeling the probabilities of state transitions and observation sequences, and can also improve matching efficiency and matching accuracy.

[0027] The underground motion trajectory data is fully utilized to achieve an accurate description of the underground motion trajectory. The multi-sensor data fusion mode allows the system to maintain high accuracy and robustness when some sensors fail or the data is inaccurate, providing support for path planning and navigation, and providing a strong guarantee for the safety and efficiency of underground operations.

[0028] The present invention can realize fast data processing and feedback, so that the positioning and navigation targets can obtain real-time motion status and environmental information, and have more real-time response capabilities. The training and updating mechanism of the hidden Markov model can easily adapt to new environmental changes and requirements, and can use a large amount of historical data for self-learning and optimization, and is easy to adapt and expand, so as to adapt to new underground environments or different types of tunnel map matching applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0030] Figure 1 It is a flow chart of the road network matching method of underground three-dimensional tunnel motion trajectory of the present invention.

[0031] Figure 2 It is a schematic diagram of the optimal path matching process of the present invention. DETAILED DESCRIPTION

[0032] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0033] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0034] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0035] The process of matching the trajectory of underground moving targets with the digital map network of underground tunnels through geographic coordinate sampling sequences is essentially a pattern matching problem of plane line segment sequences. General path matching methods include nearest path matching, shortest path matching, Euclidean distance matching, and dynamic time warp matching, all of which have large errors when processing low sampling rate data, resulting in inaccurate matching results and easy trajectory jumps. In the map matching problem, the motion trajectory data is visible and is regarded as an observation sequence. The actual road passed is invisible and is regarded as invisible.

[0036] like Figure 1As shown, the road network matching method of the underground three-dimensional tunnel motion trajectory of the present invention includes: S1, obtaining the historical position data of the underground moving target. S2, fitting the historical trajectory after preprocessing the historical position data. S3, taking the historical trajectory points as the observation sequence and the grid units of the topological model of the center line of the underground three-dimensional tunnel as the state space, a hidden Markov model suitable for the underground environment is established. S4, using the hidden Markov model to obtain a set of candidate sections. S5, in the hidden Markov model, the entire historical trajectory is divided into different increments based on reliable points, and each increment is used as a window to calculate the observation probability of the trajectory point to the candidate section; then the state transition probability between adjacent trajectory points corresponding to the candidate section is calculated. S6, using the improved Viterbi algorithm to solve the state transition probability matrix and observation probability matrix corresponding to the trajectory point and the candidate section, and match the optimal path. S7, displaying the motion trajectory of the moving target on the three-dimensional tunnel map according to the optimal path.

[0037] The road network matching method of the present invention aims to solve the following key problems: (1) Improving positioning accuracy: In a complex underground environment, it is very important to accurately locate the motion trajectory. The hidden Markov model can infer the most likely trajectory based on different state transition probabilities and observation probabilities, thereby improving the accuracy and reliability of positioning. (2) Noise and uncertainty processing: There are often various noises and interferences in the underground environment, such as signal attenuation, sensor errors, etc. The hidden Markov model can effectively filter these noises through its probability model to improve the matching accuracy. (3) Real-time matching in a dynamic environment: The underground environment may change, such as the formation of tunnels, landslides, etc. The method can update and adjust the matching of the motion trajectory and the road network in real time to adapt to dynamic changes. (4) Data association and state estimation: For the effective association of multi-source data (such as sensor data, map information, etc.), the hidden Markov model can provide an effective framework for state estimation and path inference, thereby improving the overall matching effect. (5) Optimizing path planning: By obtaining the matching results of the effective motion trajectory and the road network, basic data can be provided for subsequent path planning and navigation, optimizing the efficiency of operations and transportation.

[0038] Specifically, the matching results are evaluated, and the parameters of the hidden Markov model are optimized according to the evaluation results, including: adjusting the sampling frequency of the trajectory points (e.g., 5s, 10s, 15s), repeating steps S3-S5 to match the optimal path, and verifying each matching result to adjust the parameters of the hidden Markov model to improve the accuracy of the matching results.

[0039] Unlike conventional hidden Markov models, the present invention divides the entire historical trajectory into different increments based on reliable points in the hidden Markov model, and matches each increment as a window. Matching each increment as a window can reduce the amount of calculation of the state transition probability and the output delay of the matching result, which is beneficial to improving the overall matching efficiency. When obtaining a set of candidate sections, the observation probability of the observation probability matrix is ​​embodied by the Euclidean distance d. The smaller the d value, the greater the observation probability, and the greater the possibility of matching. The solution process of the improved Viterbi algorithm includes: at each time step, for each state, according to the heuristic function and the information of the previous time step, the dynamic programming table is updated, the path with the highest heuristic value and probability is selected as the optimal path for the current state, and the recursive update of all time steps is completed; backtracking from the last time step of the dynamic programming table, the optimal hidden state sequence is found, and the optimal path in the candidate section set is selected.

[0040] like Figure 2 As shown in the figure, the trajectory points obtained within a sampling time (for example, 5s) are taken as an observation sequence, and the grid units in the underground three-dimensional tunnel centerline topological road network model are taken as the state space of the hidden Markov model. When the trajectory points change from the current moment to the next moment, multiple candidate sections may appear, and an optimal section can be matched from the multiple candidate sections.

[0041] The present invention also provides a road network matching device for underground three-dimensional tunnel motion trajectory, including: a data acquisition and processing module, used to obtain the historical position data of the underground moving target; pre-process the historical position data and fit the historical trajectory. A matching module is used to use the historical trajectory points as the observation sequence and the grid units of the topological model of the center line of the underground three-dimensional tunnel as the state space to establish a hidden Markov model suitable for the underground environment; use the hidden Markov model to obtain a set of candidate sections; in the hidden Markov model, the entire historical trajectory is divided into different increments based on reliable points, and each increment is used as a window to calculate the observation probability of the trajectory point to the candidate section; then calculate the state transition probability between adjacent trajectory points corresponding to the candidate section; use the improved Viterbi algorithm to solve the state transition probability matrix and observation probability matrix corresponding to the trajectory point and the candidate section, and match the optimal path.

[0042] The present invention also provides a computer device, comprising: a processor; a memory for storing executable instructions; wherein the processor is used to read the executable instructions from the memory and execute the executable instructions to implement a road network matching method for underground three-dimensional tunnel motion trajectories.

[0043] In summary, the road network matching method, device, and computer equipment of the present invention for underground three-dimensional tunnel motion trajectory have the following advantages:

[0044] The hidden Markov model can adapt to the complex underground tunnel environment by modeling the probability of state transitions and observation sequences. The matching efficiency and accuracy of the motion trajectory will be significantly improved and more in line with the actual motion situation. The present invention adds dynamic adjustment capabilities to adapt to changes in the underground environment. It can achieve fast data processing and feedback, so that the positioning and navigation targets can obtain real-time motion status and environmental information, and have more real-time response capabilities. An update adjustment mechanism is set up to adapt to new environmental changes and requirements, and can use a large amount of historical data for self-learning and optimization. It is easy to adapt and expand, so as to adapt to new underground environments or different types of tunnel map matching applications.

[0045] The present invention significantly improves the matching accuracy and real-time performance of the underground three-dimensional tunnel motion trajectory, enhances the robustness and adaptability of the system, and reduces the path matching cost. These technical advantages make the solution widely used in underground positioning and navigation, which helps to improve the safety and work efficiency of coal mine workers and has great support significance for emergency rescue.

[0046] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, but must be determined according to the scope of the claims.

Claims

1. A road network matching method for underground three-dimensional tunnel motion trajectory, characterized in that: include: S1. Obtain historical position data of underground moving targets; S2, preprocessing the historical location data to fit a historical trajectory; S3, taking the historical trajectory points as the observation sequence and the grid units of the topological model of the centerline of the underground three-dimensional tunnel as the state space, a hidden Markov model suitable for the underground environment is established; S4, using the hidden Markov model to obtain a set of candidate road sections, S5. In the hidden Markov model, the entire historical trajectory is divided into different increments based on reliable points, and each increment is used as a window to calculate the observation probability of the trajectory point to the candidate section; and then the state transition probability between adjacent trajectory points corresponding to the candidate section is calculated; S6. Using the improved Viterbi algorithm, the state transition probability matrix and the observation probability matrix corresponding to the trajectory points and the candidate sections are solved to match the optimal path; S7. Displaying the moving trajectory of the moving target on the three-dimensional lane map according to the optimal path.

2. The road network matching method for underground three-dimensional tunnel motion trajectory according to claim 1, characterized in that: The matching results are evaluated, and the parameters of the hidden Markov model are optimized according to the evaluation results.

3. The road network matching method for underground three-dimensional tunnel motion trajectory according to claim 1, characterized in that: The solution process of the improved Viterbi algorithm includes: At each time step, for each state, the dynamic programming table is updated according to the heuristic function and the information of the previous time step, and the path with the highest heuristic value and probability is selected as the optimal path for the current state, and the recursive update of all time steps is completed; backtracking starts from the last time step of the dynamic programming table, finds the optimal hidden state sequence, and selects the optimal path in the candidate segment set.

4. The method for matching the road network of underground three-dimensional tunnel motion trajectory according to claim 1, characterized in that: The observation probability of the observation probability matrix is ​​represented by the Euclidean distance d. The smaller the d value is, the greater the observation probability is.

5. The road network matching method for underground three-dimensional tunnel motion trajectory according to claim 2, characterized in that: Optimizing the parameters of the hidden Markov model according to the evaluation results includes: The sampling frequency of the trajectory points is adjusted, and steps S3-S5 are repeated to match the optimal path. The matching result is verified each time to adjust the parameters of the hidden Markov model, so that the accuracy of the matching result is improved.

6. A road network matching device for underground three-dimensional tunnel motion trajectory, characterized in that: include: Data acquisition and processing module, used to obtain historical position data of moving targets underground; Preprocessing the historical location data to fit a historical trajectory; A matching module is used to establish a hidden Markov model suitable for the underground environment by taking the historical trajectory points as the observation sequence and the grid units of the topological model of the center line of the underground three-dimensional tunnel as the state space; and to obtain a set of candidate sections by using the hidden Markov model; In the hidden Markov model, the entire historical trajectory is divided into different increments based on reliable points, and each increment is used as a window to calculate the observation probability of the trajectory point to the candidate section; and then the state transition probability between adjacent trajectory points corresponding to the candidate section is calculated; The improved Viterbi algorithm is used to solve the state transition probability matrix and observation probability matrix corresponding to the trajectory points and candidate sections to match the optimal path.

7. A computer device, characterized in that: include: processor; A memory for storing executable instructions; Wherein, the processor is used to read the executable instructions from the memory and execute the executable instructions to implement the road network matching method of underground three-dimensional tunnel motion trajectory as described in any one of claims 1 to 5.

Images