Standard maintaining method and system based on unified space-time

Abstract

The invention relates to the technical field of satellite navigation and surveying and mapping, in particular to a standard maintenance method and system based on unified space-time, and the method comprises the steps: obtaining real-time positioning signals of a first satellite navigation system and a second satellite navigation system at a designated position, generating unified space-time standard data after the real-time positioning signals pass through a CORS network and are aligned, and transmitting the unified space-time standard data to a server; sending to a distributed reference node in the tunnel, and generating a consistent distributed space-time reference covering the tunnel range; after the vehicle terminal receives the data, the time reference and the coordinate reference are used for carrying out synchronous correction on the sampling time and the pose calculation of the local sensor, and a vehicle pose reference is generated; if the positioning precision continuously deviates from the preset threshold value, an error correction request is sent to the adjacent distributed reference nodes; and adjacent nodes generate an update reference in combination with historical cache data and a cooperative compensation mechanism, and perform fusion calculation in combination with data acquired by a local sensor to obtain accurate positioning and three-dimensional surveying and mapping of the vehicle. And the positioning precision and the navigation performance in the tunnel can be improved.

Description

Technical Field

[0001] The present invention relates to the field of satellite navigation and surveying and mapping technology, and in particular to a reference maintenance method and system based on unified time and space. Background Art

[0002] In modern urban environments, high-precision positioning, navigation and timing services have become indispensable supporting technologies in the fields of intelligent transportation, emergency rescue and precision mapping. As an important part of the global satellite navigation system, the Beidou satellite navigation system has been widely used in urban scenarios with its technical advantages of high precision, global coverage and multi-frequency signals. However, the urban environment is complex and changeable, and the factors that affect the performance of the Beidou system are also prominent.

[0003] In urban environments, when vehicles are driving in complex scenarios (such as tunnels, viaducts, and underground parking lots), the stability and reliability of Beidou satellite signals are often difficult to guarantee. In particular, in tunnel environments, due to terrain obstruction and space closure, Beidou satellite signals may be completely blocked, and the receiving device cannot obtain direct path signals, resulting in interruption of positioning information. In addition, signal propagation in tunnels is also susceptible to the multipath effect of the vehicle's metal structure and the tunnel wall. The path received by the signal after reflection may be longer, further exacerbating positioning errors.

[0004] In order to deal with these problems, the Beidou system usually combines ground-based augmentation technology to establish a CORS station (Continuously Operating Reference Station) network to provide users with high-precision positioning and timing services. The CORS station receives satellite signals and generates differential correction data in combination with ground reference equipment, providing correction information to users in real time, significantly improving positioning accuracy. At the same time, the CORS station can also monitor the quality of satellite signals and provide users with a reliable time reference. However, in tunnel scenarios, the satellite signal source that the CORS station network relies on is difficult to obtain stably due to occlusion problems, resulting in the inability to continuously provide users with a unified space-time reference. In addition, the special environment in the tunnel makes it difficult for existing ground-based augmentation technology to effectively solve the problems of signal attenuation and multipath errors, affecting the continuous positioning and navigation performance of vehicles in tunnels.

[0005] Therefore, a benchmark maintenance method and system based on unified space-time are proposed. Summary of the invention

[0006] The purpose of the present invention is to provide a benchmark maintenance method and system based on unified time and space, which is suitable for high-precision positioning and navigation in complex tunnel environments, including: obtaining real-time positioning signals of the first satellite navigation system and the second satellite navigation system at a specified location, generating differential correction data through the CORS network, and aligning according to the national geodetic coordinate system to generate unified time and space benchmark data; sending the benchmark data to the distributed benchmark nodes in the tunnel to form a consistent distributed time and space benchmark covering the tunnel range; after the vehicle terminal receives the benchmark, the local sensor data is synchronized and corrected using the time benchmark and the coordinate benchmark to generate a vehicle posture benchmark; if the positioning accuracy deviates from the preset threshold, an error correction request is sent to the adjacent node through the feedback mechanism, and the adjacent node combines the historical cache data and the collaborative compensation mechanism to generate an updated benchmark, and fuses the calculation with the sensor data to obtain high-precision vehicle positioning and three-dimensional mapping results. The present invention also optimizes the benchmark node scoring through a dynamic weight learning mechanism, which improves the benchmark synchronization stability and navigation performance in complex scenarios.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A benchmark maintenance method based on unified space-time, comprising:

[0009] Acquire real-time positioning signals from the first satellite navigation system and the second satellite navigation system at a specified location, and obtain differential correction data through the CORS network deployed on the ground;

[0010] Aligning the differential correction data according to the national geodetic coordinate system to obtain unified spatiotemporal reference data;

[0011] The unified spatiotemporal reference data is sent to the distributed reference nodes in the designated tunnel, and a consistent distributed spatiotemporal reference covering the entire range of the designated tunnel is generated with the reference point at the designated position as the starting point, so as to obtain a consistent distributed spatiotemporal reference in the tunnel; the consistent distributed spatiotemporal reference in the tunnel includes a time reference and a coordinate reference;

[0012] After the vehicle terminal receives the consistent distributed time-space reference in the tunnel, the sampling time and posture solution of the local sensor are synchronously corrected using the time reference and the coordinate reference to obtain the vehicle posture reference; if it is detected that the positioning accuracy of the vehicle posture reference deviates from the preset threshold in N consecutive sampling cycles, an error correction request is sent to the adjacent distributed reference node through a feedback mechanism; the local sensor includes at least one of an inertial measurement unit, a visual module, a laser radar and an odometer;

[0013] Receive the updated distributed spatiotemporal reference generated by the adjacent distributed reference node, and perform fusion calculation in combination with the real-time data collected by the local sensor to obtain precise vehicle positioning and three-dimensional mapping of the vehicle; the updated distributed spatiotemporal reference is generated by the adjacent distributed reference node after receiving the error correction request, in combination with historical cache data and a collaborative compensation mechanism.

[0014] Furthermore, the designated location is the entrance of the designated tunnel.

[0015] Furthermore, the first satellite navigation system is specifically a Beidou satellite navigation system.

[0016] Furthermore, the second satellite navigation system is at least one of a GPS satellite navigation system, a GLONASS satellite navigation system and a Galileo satellite navigation system.

[0017] Furthermore, the distributed reference node includes a plurality of movable reference nodes arranged in the designated tunnel, and the specific composition of each movable reference node includes:

[0018] A high-precision local clock module is used to maintain a time reference when there is no external signal input, and to monitor the clock deviation online in combination with historical drift data to obtain a stable time reference in the absence of external signals; when receiving high-precision timing information from the GNSS receiving module, the stable time reference is updated to obtain an updated time reference; and the updated time reference is provided as a node time reference to the communication and signal forwarding module and the adaptive clock drift compensation module;

[0019] The GNSS receiving module is used to periodically receive satellite signals at the entrance of the designated tunnel to obtain periodic satellite signals; calculate correction parameter information according to the periodic satellite signals, wherein the correction parameter information includes satellite orbit correction parameters and clock correction parameters; calibrate the high-precision local clock module according to the periodic satellite signals and the correction parameter information to obtain the high-precision time information aligned with the high-precision local clock;

[0020] The communication and signal forwarding module is used to receive the unified spatiotemporal reference data of the adjacent movable reference nodes, the unified spatiotemporal reference data including time information, coordinate information and signal quality data, and receive the motion state information of the vehicle terminal; according to the preset synchronization strategy, dynamically weighted fusion is performed on the clock deviation and signal delay between the movable reference nodes, and the coordinate reference is optimized in combination with the extended Kalman filter algorithm to obtain a distributed spatiotemporal reference; according to the signal quality data, the node quality score is calculated:

[0021] ;

[0022] in, represents the node quality score, Indicates signal strength. Indicates communication delay, Indicates link stability. is the first weight parameter, is the second weight parameter, is the third weight parameter;

[0023] The movable reference node with the highest node quality score is selected as a priority target node, a synchronization instruction is sent to the priority target node, and correction data returned by the priority target node is received; the distributed space-time reference is updated according to the correction data to generate a preliminary correction result; when the communication link is not interrupted and the priority target node is not faulty, the preliminary correction result is used as a consistent distributed space-time reference in the tunnel; and the distributed space-time reference is sent to the vehicle terminal;

[0024] The adaptive clock drift compensation module is used to dynamically correct the local clock drift model according to the mutual comparison results between the movable reference nodes and environmental changes. The updating process includes calculating the real-time drift rate according to the multi-node time deviation and optimizing the time reference of each node in combination with the credibility weight mechanism.

[0025] An environment perception module is used to detect the multipath effect distribution, shielding area range, interference source location, dynamic environment state and physical parameter change results in the designated tunnel, and obtain the detection result; and feed the detection result back to the adaptive clock drift compensation module;

[0026] A redundant data cache and fault takeover module is used to re-evaluate the node quality scores of the remaining nodes when the communication link is interrupted or the priority target node fails, select the movable reference node with the second highest node quality score as the update priority target node, and dynamically correct the preliminary correction result in combination with the historical cache data and the collaborative compensation mechanism of the adjacent nodes to generate an updated correction result; use the updated correction result to recalculate and generate a distributed space-time benchmark, the distributed space-time benchmark including a corrected time benchmark, a corrected coordinate benchmark and synchronization status information; and send the distributed space-time benchmark to the vehicle terminal and the adjacent movable reference node.

[0027] Furthermore, the first weight parameter , the second weight parameter and the third weight parameter Adjustments are made based on the dynamic weight learning mechanism, including:

[0028] constructing a state vector according to the signal strength, the communication delay, the link stability, the historical performance and the environmental interference strength of each of the movable reference nodes;

[0029] Inputting the state vector of each movable reference node into a deep reinforcement learning model in combination with historical data and real-time environmental parameters, wherein the deep reinforcement learning model adopts an Actor-Critic architecture, including an Actor network and a Critic network;

[0030] The Actor network is used to input the state vector and output a weight increment, wherein the weight increment includes a first weight increment , the second weight increment and the third weight increment ;

[0031] The Critic network is used to evaluate the performance of the current weight allocation scheme, and optimize the update of the first weight parameter, the second weight parameter, and the third weight parameter through a reward function;

[0032] The current weight distribution scheme is:

[0033] ;

[0034] The reward function is defined by the following formula:

[0035] ;

[0036] in, is the reward function; is the updated positioning error reduction value; is the improvement of the updated benchmark synchronization accuracy; To improve the adaptability to the updated environment; is the first reward weight coefficient; is the second reward weight coefficient; is the third reward weight coefficient.

[0037] A reference maintenance system based on unified space-time, comprising:

[0038] A signal acquisition module is used to acquire real-time positioning signals from the first satellite navigation system and the second satellite navigation system at a specified location, and obtain differential correction data through the CORS network deployed on the ground; a reference alignment module is used to align the differential correction data according to the national geodetic coordinate system to obtain unified spatiotemporal reference data;

[0039] A reference distribution module, used to send the unified spatiotemporal reference data to the distributed reference nodes in the specified tunnel, and generate a consistent distributed spatiotemporal reference covering the entire range of the specified tunnel with the reference point at the specified position as the starting point, so as to obtain a consistent distributed spatiotemporal reference in the tunnel;

[0040] A terminal correction module is used to synchronously correct the sampling time and posture solution of the local sensor by using the consistent distributed time and space reference in the tunnel after the vehicle terminal receives the consistent distributed time and space reference in the tunnel to obtain the vehicle posture reference;

[0041] A feedback mechanism module, configured to send an error correction request to an adjacent distributed reference node through a feedback mechanism if it is detected that the positioning accuracy of the vehicle posture reference deviates from a preset threshold value for N consecutive sampling periods;

[0042] An updated reference fusion module is used to receive an updated distributed spatiotemporal reference generated by an adjacent distributed reference node, and perform fusion calculations in combination with the real-time data collected by the local sensor to obtain precise vehicle positioning and three-dimensional vehicle mapping; the updated distributed spatiotemporal reference is generated by the adjacent distributed reference node after receiving the error correction request, in combination with historical cache data and a collaborative compensation mechanism.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. The present invention constructs a consistent distributed space-time benchmark covering the entire range of the tunnel by deploying distributed reference nodes in the tunnel, and combining the differential correction data generated by the CORS network with the unified alignment of the national geodetic coordinate system, effectively solving the problem of reduced positioning accuracy caused by satellite signal obstruction in tunnel scenarios. After the vehicle terminal receives the space-time benchmark, it corrects the local sensor data in combination with the time benchmark and the coordinate benchmark, thereby improving positioning accuracy and data synchronization; when the positioning accuracy is abnormal, it interacts with adjacent nodes through a feedback mechanism, dynamically generates an updated benchmark, and combines multi-sensor data for fusion calculation, thereby ensuring the vehicle's continuous high-precision positioning and three-dimensional mapping capabilities in complex environments. The present invention significantly improves the navigation performance and reliability of the space-time benchmark in special environments such as tunnels, providing strong support for high-precision positioning and mapping technologies.

[0045] 2. The present invention achieves high-precision maintenance of consistent distributed space-time references in tunnels by deploying multiple movable distributed reference nodes in the tunnel, combined with high-precision local clock modules, GNSS receiving modules and adaptive clock drift compensation modules. The priority target nodes are dynamically selected through the node quality scoring mechanism, and the generation and update of distributed space-time references are optimized in combination with historical cache data and collaborative compensation mechanisms. When the communication link is interrupted or the node fails, the method can quickly restore system functions through redundant data caching and fault takeover modules. The environmental perception module further enhances the system's adaptability to complex environments, significantly improves the positioning accuracy, space-time reference synchronization stability and navigation performance in complex shielding environments such as tunnels, and provides reliable technical support for high-precision navigation and three-dimensional surveying and mapping.

[0046] 3. The present invention realizes the adaptive optimization of the quality score of the movable reference node by introducing a dynamic weight learning mechanism. By constructing the state vector of the node, and combining historical data and real-time environmental parameters, the deep reinforcement learning model is used to dynamically adjust the first weight parameter, the second weight parameter and the third weight parameter, so that the node quality score is more accurate and adapts to the dynamic changes of the complex environment. The Actor-Critic architecture ensures the rationality of the weight increment and the efficiency of the reward optimization, and dynamically balances the improvement of positioning accuracy, reference synchronization stability and environmental adaptability through the reward function. This method significantly enhances the reliability of distributed reference nodes and the stability of spatiotemporal references in complex scenarios such as tunnels, helps to improve the positioning continuity and navigation performance of vehicle terminals, reduces the accuracy loss caused by signal interference or environmental changes, and provides a solid technical guarantee for high-precision navigation and surveying. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A flow chart of a benchmark maintenance method based on unified time and space provided by an embodiment of the present invention;

[0048] Figure 2 A system structure diagram of a movable reference node provided by an embodiment of the present invention;

[0049] Figure 3 A structural diagram of a reference maintenance system based on unified time and space provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figures 1 to 3 The present invention provides a benchmark maintenance method and system based on unified time and space, and the technical solution is as follows:

[0052] Embodiment 1

[0053] A special mapping vehicle is equipped with high-precision sensors such as laser radar, camera, inertial measurement unit and odometer. Its task is to collect structural data in a designated tunnel and generate a complete 3D model of the tunnel. The special mapping vehicle starts from the entrance position (designated position) of the designated tunnel and drives at a constant speed along the tunnel track until the tunnel exit, performing the 3D mapping task of the entire tunnel.

[0054] A benchmark maintenance method based on unified space and time, such as Figure 1 As shown, the specific process is as follows:

[0055] See also Figure 1 In S10, after the vehicle is started, when the vehicle travels to the designated location, the real-time positioning signals from the first satellite navigation system and the second satellite navigation system are received through the vehicle terminal device, and the differential correction data is obtained through the CORS network deployed on the ground; further, the designated location is the entrance of the designated tunnel. Setting the designated location as the entrance of the tunnel can ensure the efficient generation and accurate distribution of the unified time and space reference. By obtaining the real-time positioning signals of the first satellite navigation system and the second satellite navigation system at the entrance, and generating differential correction data in combination with the CORS network, a high-precision time reference and coordinate reference can be established before entering the tunnel as the reference reference point within the entire tunnel. It not only simplifies the deployment and management of the system, but also effectively avoids the influence of signal shielding in the tunnel on the generation of the reference, thereby ensuring that the time and space reference of the entire tunnel is continuous, consistent and high-precision. In addition, the design can also provide a reliable starting point for the subsequent distributed reference nodes to generate consistent distributed time and space references, improve the efficiency and accuracy of reference transmission, and lay a solid foundation for the positioning and navigation of vehicles in the tunnel.

[0056] Furthermore, the first satellite navigation system is specifically the Beidou satellite navigation system, and the second satellite navigation system is at least one of the GPS satellite navigation system, the GLONASS satellite navigation system and the Galileo satellite navigation system. Furthermore, by using the Beidou satellite navigation system as the first satellite navigation system and combining at least one of the GPS, GLONASS or Galileo satellite navigation systems as the second satellite navigation system, the global coverage characteristics and high-precision positioning capabilities of the multi-satellite system can be fully utilized to improve the positioning stability and anti-interference capabilities of the system. The Beidou system has the advantages of high precision and high reliability in the Asia-Pacific region, while the GPS, GLONASS and Galileo systems provide global supplementary and redundant support. Through the combined design of multiple satellite systems, more abundant satellite signals can be obtained at the entrance of the tunnel, the anti-blocking capability can be enhanced, and the risk of reduced positioning accuracy caused by signal blockage or error of a single system can be effectively reduced. In addition, the fusion of multiple systems can improve the accuracy and reliability of benchmark generation through differential correction algorithms, provide a more stable spatiotemporal benchmark for subsequent distributed benchmark nodes, and meet the needs of high-precision positioning and navigation in complex environments in tunnels. This design achieves the unity of high precision, continuity and global adaptability, and is particularly suitable for positioning applications in complex obstructed environments such as tunnels.

[0057] The reference point of the first position is specifically a fixed reference station that integrates a high-precision GNSS receiving module, a high-precision local clock module, a data processing module, a communication module and an environmental perception module. It receives satellite signals in real time, generates unified space-time reference data, and reliably transmits it to the distributed reference nodes in the tunnel, providing unified space-time reference support for the entire tunnel.

[0058] At the reference point at the specified location, the satellite positioning signal is received through the GNSS receiving module, and high-precision differential correction data is generated in combination with the CORS network to form a unified spatiotemporal reference data. The unified spatiotemporal reference data is distributed to the distributed reference nodes in the tunnel through the communication and signal forwarding module using a low-latency, high-reliability communication protocol. After receiving the reference data, each reference node optimizes the coordinate reference through the extended Kalman filter algorithm in combination with the signal quality, time reference and spatial position information received by itself, and uses the dynamic synchronization strategy to adjust the time deviation and signal delay between adjacent nodes to generate a distributed spatiotemporal reference. In order to achieve full tunnel coverage, each reference node establishes a collaborative network based on the node quality score, optimizes the reference transmission process through a dynamic weighted fusion mechanism, and gradually propagates the reference data to the depth of the tunnel. During the process, the redundant data cache and fault takeover module monitors the node status in real time. When a node fails or the communication is interrupted, it quickly switches to the node with the second highest quality score to ensure that the reference transmission is not interrupted. Finally, the reference nodes work together to generate a well-consistent distributed spatiotemporal reference for the entire tunnel, and send it to the vehicle terminal in the tunnel to achieve high-precision spatiotemporal synchronization and navigation positioning.

[0059] See also Figure 1 In S20, aligning the differential correction data according to the national geodetic coordinate system to obtain unified spatiotemporal reference data;

[0060] See also Figure 1 S30 in which the unified spatiotemporal reference data is sent to the distributed reference nodes in the designated tunnel, and a consistent distributed spatiotemporal reference covering the entire range of the designated tunnel is generated with the reference point at the designated position as the starting point, so as to obtain a consistent distributed spatiotemporal reference in the tunnel;

[0061] Furthermore, the distributed reference nodes include a plurality of movable reference nodes arranged in the designated tunnel, such as Figure 2 As shown, the specific composition of each movable reference node includes:

[0062] A high-precision local clock module is used to maintain a time reference when there is no external signal input, and to monitor the clock deviation online in combination with historical drift data to obtain a stable time reference in the absence of external signals; when receiving high-precision timing information from the GNSS receiving module, the stable time reference is updated to obtain an updated time reference; and the updated time reference is provided as a node time reference to the communication and signal forwarding module and the adaptive clock drift compensation module;

[0063] The GNSS receiving module is used to periodically receive satellite signals at the entrance of the designated tunnel to obtain periodic satellite signals; calculate correction parameter information according to the periodic satellite signals, wherein the correction parameter information includes satellite orbit correction parameters and clock correction parameters; calibrate the high-precision local clock module according to the periodic satellite signals and the correction parameter information to obtain the high-precision time information aligned with the high-precision local clock;

[0064] The communication and signal forwarding module is used to receive the unified spatiotemporal reference data of the adjacent movable reference nodes, the unified spatiotemporal reference data including time information, coordinate information and signal quality data, and receive the motion state information of the vehicle terminal; according to the preset synchronization strategy, dynamically weighted fusion is performed on the clock deviation and signal delay between the movable reference nodes, and the coordinate reference is optimized in combination with the extended Kalman filter algorithm to obtain a distributed spatiotemporal reference; according to the signal quality data, the node quality score is calculated:

[0065] ;

[0066] in, represents the node quality score, Indicates signal strength. Indicates communication delay, Indicates link stability. is the first weight parameter, is the second weight parameter, is the third weight parameter;

[0067] The movable reference node with the highest node quality score is selected as a priority target node, a synchronization instruction is sent to the priority target node, and correction data returned by the priority target node is received; the distributed space-time reference is updated according to the correction data to generate a preliminary correction result; when the communication link is not interrupted and the priority target node is not faulty, the preliminary correction result is used as a consistent distributed space-time reference in the tunnel; and the distributed space-time reference is sent to the vehicle terminal;

[0068] The adaptive clock drift compensation module is used to receive the updated time reference, and dynamically correct the local clock drift model according to the mutual comparison results between the movable reference nodes and the environmental changes. The updating process includes calculating the real-time drift rate according to the multi-node time deviation, and optimizing the time reference of each node in combination with the credibility weight mechanism.

[0069] An environment perception module is used to detect the multipath effect distribution, shielding area range, interference source location, dynamic environment state and physical parameter change results in the designated tunnel, and obtain the detection result; and feed the detection result back to the adaptive clock drift compensation module;

[0070] A redundant data cache and fault takeover module is used to re-evaluate the node quality scores of the remaining nodes when the communication link is interrupted or the priority target node fails, select the movable reference node with the second highest node quality score as the update priority target node, and dynamically correct the preliminary correction result in combination with the historical cache data and the collaborative compensation mechanism of the adjacent nodes to generate an updated correction result; use the updated correction result to recalculate and generate a distributed space-time benchmark, the distributed space-time benchmark including a corrected time benchmark, a corrected coordinate benchmark and synchronization status information; and send the distributed space-time benchmark to the vehicle terminal and the adjacent movable reference node.

[0071] By deploying multiple movable reference nodes in a designated tunnel and building a distributed reference system, it is possible to effectively deal with problems such as satellite signal obstruction, multipath effects and dynamic environmental changes in the tunnel environment. The movable reference node maintains the stability of the time reference through a high-precision local clock module when the signal is missing, and updates it in real time in combination with GNSS timing information to ensure the high accuracy and reliability of the reference. At the same time, the communication and signal forwarding module optimizes the coordinate reference based on the dynamic weighted fusion and extended Kalman filter algorithm through the collaborative work of adjacent nodes, effectively improving the accuracy and consistency of the distributed reference. In addition, the adaptive clock drift compensation module dynamically corrects the clock drift according to the time deviation between nodes and environmental changes, and the environmental perception module detects complex interference factors in the tunnel to provide real-time reference for the adaptive adjustment of the reference node. Through the node quality scoring mechanism, the optimal node is preferentially selected for reference update and distribution, further improving the robustness and efficiency of the system. Even in the case of communication link interruption or node failure, the redundant data cache and fault takeover module can still ensure the continuity and accuracy of the reference, thereby providing reliable technical support for high-precision positioning and navigation of vehicles in the tunnel, and realizing the efficiency and stability of the reference maintenance system in complex environments.

[0072] Furthermore, the moving mode of the movable reference node is specifically as follows: adopting the joint path planning technology of the fusion reinforcement learning algorithm and the multi-objective genetic algorithm, periodically calculating the node overall efficiency value according to the multi-path effect distribution, the shielding area range, the interference source position, the dynamic environment state, the physical parameter change result and the node quality score in the designated tunnel; when the node overall efficiency value is lower than the preset threshold, multiple rounds of simulation evaluation are performed on the candidate target position through online reinforcement learning; in the process of node movement, the mobile path is globally and locally optimized through the multi-objective genetic algorithm, and the environmental state and the node quality score are exchanged with the adjacent movable reference node through the real-time communication and signal forwarding module to adaptively fine-tune the mobile path; when the movable reference node reaches the target position, it rebroadcasts its own position and provides the adaptive clock drift compensation module with new spatiotemporal reference and environmental change information. By adopting the joint path planning technology of the fusion reinforcement learning algorithm and the multi-objective genetic algorithm, the movable reference node can realize intelligent and dynamic deployment in a complex tunnel environment, significantly improving the flexibility and robustness of the system. By periodically calculating the overall efficiency value of the node, the operating status of the benchmark node in complex environments such as multipath effect distribution, shielding area range, and interference source location can be evaluated in real time. When the efficiency value is lower than the preset threshold, the system performs multiple rounds of simulation evaluation on the candidate target location through online reinforcement learning to ensure the optimality of the target location. During the movement process, the multi-objective genetic algorithm combines global path planning and local path optimization capabilities to provide nodes with efficient and accurate movement paths. At the same time, through real-time communication and quality score exchange with adjacent nodes, adaptive fine-tuning of the path can be achieved to avoid interference areas and optimize node distribution. When the node reaches the target location, it can rebroadcast its own location information and update the spatiotemporal benchmark to effectively cover the new working area. This design not only improves the dynamic adaptability of the benchmark node, but also optimizes the overall performance of the benchmark system, especially in the complex environment of the tunnel, it ensures the efficiency, stability and continuous coverage of the distributed benchmark, thereby providing reliable guarantee for the precise positioning and navigation of the vehicle.

[0073] Furthermore, the first weight parameter , the second weight parameter and the third weight parameter Adjustments are made based on the dynamic weight learning mechanism, including:

[0074] constructing a state vector according to the signal strength, the communication delay, the link stability, the historical performance and the environmental interference strength of each of the movable reference nodes;

[0075] The state vector of each movable reference node is combined with historical data and real-time environmental parameters to input into the deep reinforcement learning model; specifically, in this embodiment, the historical data includes the operation record and performance of each movable reference node, such as the node's historical signal strength, communication delay distribution, link stability change trend, task execution success rate, correction accuracy and fault record. These data can reflect the comprehensive performance of the node in different environments and task scenarios, and provide long-term experience support for the reinforcement learning model. Real-time environmental data covers the dynamic state of the environment in which the current node is located, such as real-time signal strength, communication delay, stability of the current link, intensity of environmental interference (such as electromagnetic interference and multipath effect), motion state of neighboring vehicles, changes in physical conditions in the tunnel (such as temperature, humidity) and benchmark synchronization state. These data can dynamically reflect the current operating environment of the node and provide a reliable basis for the model's immediate decision-making.

[0076] The deep reinforcement learning model adopts an Actor-Critic architecture, including an Actor network and a Critic network;

[0077] The Actor network is used to input the state vector and output a weight increment, wherein the weight increment includes a first weight increment , the second weight increment and the third weight increment ;

[0078] The Critic network is used to evaluate the performance of the current weight allocation scheme, and optimize the update of the first weight parameter, the second weight parameter, and the third weight parameter through a reward function;

[0079] The current weight distribution scheme is:

[0080] ;

[0081] The reward function is defined by the following formula:

[0082] ;

[0083] in, is the reward function; is the updated positioning error reduction value; is the improvement of the updated benchmark synchronization accuracy; To improve the adaptability to the updated environment; is the first reward weight coefficient; is the second reward weight coefficient; is the third reward weight coefficient.

[0084] Specifically, , and All have been normalized.

[0085] As an implementation method of this embodiment, The calculation formula is as follows (it can be quantified in other ways):

[0086] ;

[0087] in, Signal strength consistency (by calculating the standard deviation of the signal strength of the node in different time periods in a dynamic environment, indicating the degree of improvement in the stability of the signal strength); is the error compensation efficiency (the comprehensive ratio of the reduction in positioning accuracy recovery time to the reduction in positioning error); The node response capability (by comparing the difference in the time interval before and after the node completes the adjustment after receiving the real-time data change, indicating the improvement in response speed); for The weight coefficient of for The weight coefficient of for The weight coefficient of .

[0088] By introducing a dynamic weight learning mechanism to adjust the weight parameters, the system can dynamically optimize the quality score according to the multi-dimensional characteristics of the movable benchmark node, such as signal strength, communication delay, link stability, historical performance, and environmental interference intensity. Through the Actor-Critic architecture in the deep reinforcement learning model, the system can not only evaluate the node operation status in real time, but also optimize the update strategy of the weight parameters according to the reward function, thereby improving the adaptability and robustness of the system in complex environments. The reward function comprehensively considers the reduction value of the positioning error, the improvement of the benchmark synchronization accuracy, and the improvement of the environmental adaptability, and achieves a fair evaluation of each indicator through a weighted formula, effectively avoiding the excessive influence of a single indicator on the scoring result. At the same time, by normalizing the weight parameters, the stability and calculation accuracy of the system in different environments and conditions are further guaranteed. This design significantly improves the evaluation efficiency and accuracy of distributed benchmark nodes, and provides strong technical support for high-precision benchmark generation and vehicle positioning and navigation in complex tunnel environments.

[0089] See also Figure 1In S40, after the vehicle terminal receives the consistent distributed spatiotemporal reference in the tunnel, the sampling time and posture solution of the local sensor are synchronously corrected by using the consistent distributed spatiotemporal reference in the tunnel to obtain the vehicle posture reference; if it is detected that the positioning accuracy of the vehicle posture reference deviates from the preset threshold value within N consecutive (N is a positive integer) sampling periods, an error correction request is sent to the adjacent distributed reference node through a feedback mechanism; the local sensor includes at least one of an inertial measurement unit, a visual module, a laser radar and an odometer;

[0090] Specifically, in this embodiment, the preset position error threshold is 10 cm, the sampling frequency is 10 Hz, and N (N=5) consecutive cycles (0.5 seconds) are used as the judgment condition. If the system detects that the vehicle position error exceeds 10 cm in the last five samplings, an error correction request is triggered.

[0091] See also Figure 1 S50 in which an updated distributed spatiotemporal reference generated by the adjacent distributed reference node is received and fused with the real-time data collected by the local sensor to obtain precise vehicle positioning and three-dimensional mapping of the vehicle; the updated distributed spatiotemporal reference is generated by the adjacent distributed reference node after receiving the error correction request, in combination with historical cache data and a collaborative compensation mechanism.

[0092] In order to verify the performance of the benchmark maintenance method based on unified space-time, experiments were conducted in an actual tunnel environment. Three tunnels with lengths of 500 meters, 1 kilometer and 2 kilometers were selected for the experiment. There are complex environmental factors such as multipath effects, signal shielding and interference sources in the tunnel. The vehicle is equipped with high-precision sensors such as inertial measurement unit, vision module, lidar and odometer, and drives along the tunnel at a fixed speed and records the actual path. The experiment compares the traditional CORS benchmark method, static weight allocation method and dynamic weight learning method, and tests the positioning accuracy, benchmark synchronization accuracy and environmental adaptability respectively. In the test, the vehicle's location information, benchmark node synchronization status and fault recovery time are collected in real time, and the positioning error is analyzed by comparison with the actual path. The experimental results are presented in tabular form, including key indicators such as the mean positioning error, synchronization accuracy and recovery time of different methods under tunnel length, environmental interference level and node failure conditions.

[0093] Table 1 Experimental results data table

[0094]

[0095] Among them, the experimental group 1 applied a benchmark maintenance method based on unified time and space proposed by the present invention, such as Figure 1As shown in Figure 1, the control group applied a traditional CORS benchmark system: a traditional CORS benchmark maintenance method using a single static benchmark node and fixed weight parameters. Control group 2 adopted an improved method based on static weight allocation: multiple benchmark nodes were also deployed in the tunnel, but the difference from the experimental group was that static weight allocation was adopted, and the first weight parameter , the second weight parameter and the third weight parameter No adjustments are made based on the dynamic weight learning mechanism.

[0096] Refer to Table 1, where the fault recovery time is the total time from when the system detects the problem to when the vehicle terminal regains an accurate and synchronized time-space reference. The experiment shows that the experimental group has significant performance advantages in complex tunnel environments, can better adapt to multipath effects and interference conditions, and has significantly better positioning accuracy and reference synchronization accuracy than other methods, and the fault recovery time is greatly shortened, proving its superiority in tunnel navigation scenarios.

[0097] Traditional positioning methods often fail in tunnels due to the blocking of satellite signals. This method uses distributed reference nodes to extend the unified spatiotemporal reference data to the entire tunnel, achieving comprehensive coverage of the positioning blind spots in the tunnel and ensuring the continuous positioning capability of the vehicle in the tunnel. The differential correction data and reference alignment mechanism of the CORS network are used to provide a high-precision spatiotemporal reference. Combined with the multi-sensor data on the vehicle side (such as inertial measurement unit, lidar and vision module, etc.), the positioning accuracy is further improved through fusion calculation to meet the needs of tunnel mapping and high-precision navigation. When the vehicle positioning accuracy continuously deviates from the preset threshold, the system sends an error correction request to the adjacent reference node through the feedback mechanism to update the distributed spatiotemporal reference in real time. Combined with historical cache data and collaborative compensation mechanism, the accuracy of the reference data is dynamically adjusted to ensure the robustness and stability of the system in complex environments. The sensor data is synchronously corrected through a consistent distributed spatiotemporal reference, which solves the problems of inconsistent sampling time of different sensors and pose solution errors, ensures the uniformity and reliability of multi-sensor data, and provides a solid foundation for precise vehicle positioning and three-dimensional mapping. The present invention has a flexible design and can be widely used in scenarios such as tunnel mapping, traffic navigation, and vehicle dispatching, providing technical support for tunnel structure monitoring, intelligent transportation, and high-precision navigation.

[0098] Embodiment 2

[0099] An automatic guided vehicle is used for precise positioning and navigation in complex tunnel environments. Its task is to complete high-precision path tracking through the tunnel and record the vehicle's driving path for traffic optimization and tunnel safety management.

[0100] The vehicle applies a reference maintenance system based on unified space and time, such as Figure 3 As shown, including:

[0101] A signal acquisition module is used to acquire real-time positioning signals from the first satellite navigation system and the second satellite navigation system at a specified location, and obtain differential correction data through the CORS network deployed on the ground; a reference alignment module is used to align the differential correction data according to the national geodetic coordinate system to obtain unified spatiotemporal reference data;

[0102] A reference distribution module, used to send the unified spatiotemporal reference data to the distributed reference nodes in the specified tunnel, and generate a consistent distributed spatiotemporal reference covering the entire range of the specified tunnel with the reference point at the specified position as the starting point, so as to obtain a consistent distributed spatiotemporal reference in the tunnel;

[0103] A terminal correction module is used to synchronously correct the sampling time and posture solution of the local sensor by using the consistent distributed time and space reference in the tunnel after the vehicle terminal receives the consistent distributed time and space reference in the tunnel to obtain the vehicle posture reference;

[0104] A feedback mechanism module, configured to send an error correction request to an adjacent distributed reference node through a feedback mechanism if it is detected that the positioning accuracy of the vehicle posture reference deviates from a preset threshold value for N consecutive sampling periods;

[0105] An updated reference fusion module is used to receive an updated distributed spatiotemporal reference generated by an adjacent distributed reference node, and perform fusion calculations in combination with the real-time data collected by the local sensor to obtain precise vehicle positioning and three-dimensional vehicle mapping; the updated distributed spatiotemporal reference is generated by the adjacent distributed reference node after receiving the error correction request, in combination with historical cache data and a collaborative compensation mechanism.

[0106] When running, the system can realize all the same functions as the method described in the first embodiment.

[0107] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A benchmark maintenance method based on unified space-time, characterized in that: include: Acquire real-time positioning signals from the first satellite navigation system and the second satellite navigation system at a specified location, and obtain differential correction data through the CORS network deployed on the ground; Aligning the differential correction data according to the national geodetic coordinate system to obtain unified spatiotemporal reference data; The unified spatiotemporal reference data is sent to the distributed reference nodes in the designated tunnel, and a consistent distributed spatiotemporal reference covering the entire range of the designated tunnel is generated with the reference point at the designated location as the starting point, so as to obtain a consistent distributed spatiotemporal reference in the tunnel; After the vehicle terminal receives the consistent distributed spatiotemporal reference in the tunnel, the sampling time and posture solution of the local sensor are synchronously corrected using the consistent distributed spatiotemporal reference in the tunnel to obtain the vehicle posture reference; if it is detected that the positioning accuracy of the vehicle posture reference deviates from the preset threshold in N consecutive sampling cycles, an error correction request is sent to the adjacent distributed reference node through a feedback mechanism; the local sensor includes at least one of an inertial measurement unit, a visual module, a laser radar and an odometer; Receiving the updated distributed spatiotemporal reference generated by the adjacent distributed reference nodes, and performing fusion calculation in combination with the real-time data collected by the local sensors to obtain accurate vehicle positioning and three-dimensional vehicle mapping; The updated distributed spatiotemporal reference is generated by the adjacent distributed reference node after receiving the error correction request, combining historical cache data and a collaborative compensation mechanism.

2. The method for maintaining a unified space-time benchmark according to claim 1, characterized in that: The designated location is the entrance of the designated tunnel.

3. The method for maintaining a unified space-time benchmark according to claim 1, characterized in that: The first satellite navigation system is specifically the Beidou satellite navigation system.

4. The method for maintaining a unified space-time benchmark according to claim 1, characterized in that: The second satellite navigation system is at least one of a GPS satellite navigation system, a GLONASS satellite navigation system and a Galileo satellite navigation system.

5. The method for maintaining a unified space-time benchmark according to claim 1, characterized in that: The distributed reference node includes a plurality of movable reference nodes arranged in the designated tunnel, and the specific composition of each movable reference node includes: A high-precision local clock module is used to maintain a time reference when there is no external signal input, and to monitor the clock deviation online in combination with historical drift data to obtain a stable time reference in the absence of external signals; when receiving high-precision timing information from the GNSS receiving module, the stable time reference is updated to obtain an updated time reference; and the updated time reference is provided as a node time reference to the communication and signal forwarding module and the adaptive clock drift compensation module; The GNSS receiving module is used to periodically receive satellite signals at the entrance of the designated tunnel to obtain periodic satellite signals; calculate correction parameter information according to the periodic satellite signals, wherein the correction parameter information includes satellite orbit correction parameters and clock correction parameters; calibrate the high-precision local clock module according to the periodic satellite signals and the correction parameter information to obtain the high-precision time information aligned with the high-precision local clock; The communication and signal forwarding module is used to receive the unified spatiotemporal reference data of the adjacent movable reference nodes, the unified spatiotemporal reference data including time information, coordinate information and signal quality data, and receive the motion state information of the vehicle terminal; according to the preset synchronization strategy, dynamically weighted fusion is performed on the clock deviation and signal delay between the movable reference nodes, and the coordinate reference is optimized in combination with the extended Kalman filter algorithm to obtain a distributed spatiotemporal reference; according to the signal quality data, the node quality score is calculated: ； in, represents the node quality score, Indicates signal strength. Indicates communication delay, Indicates link stability. is the first weight parameter, is the second weight parameter, is the third weight parameter; The movable reference node with the highest node quality score is selected as a priority target node, a synchronization instruction is sent to the priority target node, and correction data returned by the priority target node is received; the distributed space-time reference is updated according to the correction data to generate a preliminary correction result; when the communication link is not interrupted and the priority target node is not faulty, the preliminary correction result is used as a consistent distributed space-time reference in the tunnel; and the distributed space-time reference is sent to the vehicle terminal; The adaptive clock drift compensation module is used to dynamically correct the local clock drift model according to the mutual comparison results between the movable reference nodes and environmental changes. The updating process includes calculating the real-time drift rate according to the multi-node time deviation and optimizing the time reference of each node in combination with the credibility weight mechanism. An environment perception module is used to detect the multipath effect distribution, shielding area range, interference source location, dynamic environment state and physical parameter change results in the designated tunnel, and obtain the detection result; and feed the detection result back to the adaptive clock drift compensation module; A redundant data cache and fault takeover module is used to re-evaluate the node quality scores of the remaining nodes when the communication link is interrupted or the priority target node fails, select the movable reference node with the second highest node quality score as the update priority target node, and dynamically correct the preliminary correction result in combination with the historical cache data and the collaborative compensation mechanism of the adjacent nodes to generate an updated correction result; use the updated correction result to recalculate and generate a distributed space-time benchmark, the distributed space-time benchmark including a corrected time benchmark, a corrected coordinate benchmark and synchronization status information; and send the distributed space-time benchmark to the vehicle terminal and the adjacent movable reference node.

6. A method for maintaining a unified space-time benchmark according to claim 5, characterized in that: The first weight parameter , the second weight parameter and the third weight parameter Adjustments are made based on the dynamic weight learning mechanism, including: constructing a state vector according to the signal strength, the communication delay, the link stability, the historical performance and the environmental interference strength of each of the movable reference nodes; Inputting the state vector of each movable reference node into a deep reinforcement learning model in combination with historical data and real-time environmental parameters, wherein the deep reinforcement learning model adopts an Actor-Critic architecture, including an Actor network and a Critic network; The Actor network is used to input the state vector and output a weight increment, wherein the weight increment includes a first weight increment , the second weight increment and the third weight increment ; The Critic network is used to evaluate the performance of the current weight allocation scheme, and optimize the update of the first weight parameter, the second weight parameter, and the third weight parameter through a reward function; The current weight distribution scheme is: ； The reward function is defined by the following formula: ； in, is the reward function; is the updated positioning error reduction value; is the improvement of the updated benchmark synchronization accuracy; To improve the adaptability to the updated environment; is the first reward weight coefficient; is the second reward weight coefficient; is the third reward weight coefficient.

7. A reference maintenance system based on unified space-time, characterized in that: include: A signal acquisition module, used to acquire real-time positioning signals from the first satellite navigation system and the second satellite navigation system at a specified location, and obtain differential correction data through a CORS network deployed on the ground; A reference alignment module, used to align the differential correction data according to the national geodetic coordinate system to obtain unified spatiotemporal reference data; A reference distribution module, used to send the unified spatiotemporal reference data to the distributed reference nodes in the specified tunnel, and generate a consistent distributed spatiotemporal reference covering the entire range of the specified tunnel with the reference point at the specified position as the starting point, so as to obtain a consistent distributed spatiotemporal reference in the tunnel; A terminal correction module is used to synchronously correct the sampling time and posture solution of the local sensor using the time reference and the coordinate reference after the vehicle terminal receives the consistent distributed time and space reference in the tunnel, so as to obtain the vehicle posture reference; A feedback mechanism module, configured to send an error correction request to an adjacent distributed reference node through a feedback mechanism if it is detected that the positioning accuracy of the vehicle posture reference deviates from a preset threshold value for N consecutive sampling periods; An updated reference fusion module is used to receive the updated distributed spatiotemporal reference generated by the adjacent distributed reference nodes, and perform fusion calculations in combination with the real-time data collected by the local sensor to obtain accurate vehicle positioning and three-dimensional vehicle mapping; The updated distributed spatiotemporal reference is generated by combining historical cache data and a collaborative compensation mechanism after the adjacent distributed reference node receives the error correction request.

Images