Intelligent vehicle system based on single-Beidou multi-source data acquisition

By using a multi-source data acquisition intelligent vehicle system based on a single Beidou system, time synchronization and spatial alignment of multi-source data are achieved, and weights are dynamically adjusted for adaptive fusion. This solves the problem of unstable fusion of multi-source sensors in intelligent vehicle systems, improves positioning accuracy and the continuity of environmental perception, and ensures the autonomy and safety of the system.

CN121832552APending Publication Date: 2026-04-10ANHUI UNIV OF SCI & TECH
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202610313377.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-16
Publication Date
2026-04-10

AI Technical Summary

Technical Problem

Existing intelligent vehicle systems suffer from problems such as inconsistent time references and asynchronous data in multi-source sensor fusion, leading to unstable perception results. In particular, it is difficult to achieve efficient coordination of multi-source perception and control in complex environments, and the hardware cost is high. Multi-source data fusion methods are difficult to balance perception accuracy and stability.

Method used

The system adopts a single Beidou multi-source data acquisition intelligent vehicle system. Through a multi-source data acquisition module, a spatiotemporal alignment module, a multi-source fusion module, a scene adaptive perception and path generation module, and a motion control and execution module, it uses single Beidou GNSS timing data to achieve time synchronization and spatial alignment of multi-source data, and dynamically adjusts the weights for adaptive fusion. Combined with an emergency obstacle avoidance and safety control module, it forms a closed-loop control.

Benefits of technology

It achieves stability and reliability of multi-source sensing results in complex environments, improves positioning accuracy and continuity of environmental perception, ensures the autonomy and security of the system, and reduces hardware costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121832552A_ABST
    Figure CN121832552A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent vehicle system based on single Beidou multi-source data acquisition, which belongs to the technical field of non-electrical variable control or adjustment systems and comprises six series modules, namely a multi-source data acquisition module, a space-time alignment module, a multi-source fusion module, a scene adaptive sensing and path generation module, a motion control and execution module and an emergency obstacle avoidance and safety control module. According to the system, multi-source data space-time alignment is realized by taking single Beidou GNSS time service data as a unified reference, credibility evaluation is performed on a single Beidou positioning state, a fusion weight is dynamically adjusted, an adaptive driving path is generated in combination with positioning credibility, closed-loop feedback is formed by motion control, and an emergency obstacle avoidance module can cover a control instruction at the highest priority. By the adoption of the system, self-adaptive fusion of multi-source sensing information is achieved only depending on a single Beidou positioning signal, the sensing control continuity of the system is guaranteed, Beidou positioning participates in operation decision, and the operation stability and safety of an intelligent vehicle in a complex environment are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of control or regulation systems for non-electrical variables, and in particular to an intelligent vehicle system based on single BeiDou multi-source data acquisition. Background Technology

[0002] With the development of intelligent transportation, mobile robots, and unmanned systems, higher demands are being placed on positioning accuracy, environmental perception capabilities, and safety control capabilities in complex environments. Intelligent vehicles typically rely on multiple onboard sensors to acquire environmental information and combine this with satellite navigation systems to achieve vehicle positioning and motion control. Therefore, multi-source sensor fusion has become an important means to improve environmental perception and positioning accuracy.

[0003] Currently, intelligent vehicle systems typically integrate cameras, radar, infrared sensors, inertial measurement units (IMUs), and multi-constellation satellite navigation systems or rely on external high-precision positioning base stations. They are heavily dependent on GNSS systems, primarily relying on multi-constellation, multi-frequency, or RTK differential positioning and precise single-point positioning. This results in high hardware costs and signal discontinuity issues in environments with obstructions or urban canyons. Furthermore, there is a lack of uniformity in multi-source data fusion: existing fusion methods are mostly based on fixed weights or single scenarios, making it difficult to balance perception accuracy and stability in dynamic environments. In particular, visual and radar perception results often fail to form a closed-loop feedback with the global positioning status, leading to a disconnect between perception and control systems and resulting in deviations in path planning and control execution. On embedded platforms such as STM32 and Raspberry Pi, existing solutions struggle to achieve efficient coordination of multi-source perception, fusion, and control. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent vehicle system based on single Beidou multi-source data acquisition to solve the problem of inconsistent time references and serious data asynchrony among multiple source sensors, which leads to unstable perception results and realizes intelligent navigation in complex scenarios.

[0005] To achieve the above objectives, the present invention provides an intelligent vehicle system based on single Beidou multi-source data acquisition, including a multi-source data acquisition module, a spatiotemporal alignment module connected to the multi-source data acquisition module, a multi-source fusion module connected to the spatiotemporal alignment module, a scene adaptive perception and path generation module connected to the scene adaptive perception and path generation module, a motion control and execution module connected to the motion control and execution module, and an emergency obstacle avoidance and safety control module. The multi-source data acquisition module is used to acquire multi-source data, preprocess the acquired multi-source data, and output single BeiDou GNSS timing data.

[0006] The spatiotemporal alignment module achieves time synchronization of multi-source data based on single BeiDou GNSS timing data, and maps various types of sensing data to a unified coordinate system to achieve spatial alignment. The multi-source fusion module performs a reliability assessment on the single BeiDou positioning status and dynamically adjusts the weights based on the assessment results to achieve adaptive fusion of multi-source data. The scene adaptive perception and path generation module constructs an intelligent vehicle operation status model based on the multi-source fusion results, and generates an adapted driving path by combining the single Beidou positioning reliability level. The motion control and execution module realizes the motion control of the intelligent vehicle according to the planned driving path, and feeds back the execution status to the multi-source fusion module to form closed-loop control; The emergency obstacle avoidance and safety control module detects obstacles around the intelligent vehicle. When an emergency obstacle is detected, it executes the obstacle avoidance operation with the highest priority, overriding the motion control commands of the motion control and execution module.

[0007] Preferably, the multi-source data collected by the multi-source data acquisition module includes the intelligent vehicle's global position information, speed information, heading information, time reference information, visual images, attitude angles, and short-term motion state information; The collected multi-source data is preprocessed, including normalization, outlier removal and noise suppression, and then single BeiDou GNSS timing data is obtained.

[0008] Preferably, the spatiotemporal alignment module completes time synchronization based on single BeiDou GNSS timing information, and maps various types of sensing data to a unified intelligent vehicle body coordinate system. It achieves time synchronization of multi-source data through timestamp alignment and achieves spatial alignment of multi-source data using coordinate transformation formulas. Vehicle coordinate system The coordinate system is established with the center of gravity of the intelligent vehicle as the origin, using a right-handed Cartesian coordinate system, with the positive directions of the X, Y, and Z axes being the front, left, and top of the vehicle body. Let the coordinate system of the multi-source sensor be... Multi-source sensor coordinate system To the vehicle coordinate system The coordinate transformation formula is: ; in, For the vehicle body coordinate system The coordinates below, To obtain coordinates from multi-source sensor system To the vehicle coordinate system The rotation matrix, Multi-source sensor coordinate system The coordinates below, This is the translation vector representing the sensor's installation position in the vehicle coordinate system.

[0009] Preferably, the multi-source fusion module is based on the number of available satellites. Average signal-to-noise ratio Stability of positioning results and time synchronization integrity Four indicators are used to assess the reliability of a single BeiDou positioning status, and a single BeiDou reliability scoring function is defined. The formula is: ; in, , , The normalized indicator, , , and The number of available satellites Average signal-to-noise ratio Stability of positioning results and time synchronization integrity The weighting coefficients, ,and , , Assess the reliability of single BeiDou positioning status, and .

[0010] Preferably, the multi-source fusion module incorporates a weighting factor based on the BeiDou reliability dependency. This is used to adjust the participation of BeiDou data in the fusion process, and sets the minimum value of the preset credibility threshold. and the highest value ; Based on credibility rating The lowest value of the credibility threshold and the highest value The BeiDou weight factor was obtained by performing a three-stage weight adjustment. The formula is adjusted as follows: when At this time, the BeiDou weight is reduced to a minimum, mainly relying on local sensing, as shown in the formula: ; in, To adjust the coefficient, This represents the minimum threshold for BeiDou weighting. when At that time, the weight of Beidou was Non-linear growth within the interval, the formula is: ; in, This represents the maximum threshold for BeiDou weighting. when At that time, the BeiDou weight is close to its maximum value, and the formula is: ; In the process of multi-source data fusion, the final fusion result is obtained by weighting and summing the BeiDou data and local sensing data, as shown in the formula: ; in, For the final fusion positioning results, For single BeiDou positioning data, This is local sensing data.

[0011] Preferably, the scene adaptive perception and path generation module constructs an intelligent vehicle operation status model that includes location information, motion state information and environmental perception information based on the fused multi-source perception results.

[0012] Preferably, the scene adaptive perception and path generation module calculates the scene density index (SDI) in real time, analyzes obstacle distribution characteristics, and combines the single BeiDou reliability level. It then employs a hybrid strategy to smoothly transition at scene boundaries, selecting the optimal path planning algorithm from the algorithm strategy library. Each algorithm is weighted according to its reliability level. The parameters are adaptively adjusted to generate suitable path planning results and output them to the motion control and execution module.

[0013] Preferably, the motion control and execution module receives the path planning results output by the scene adaptive perception and path generation module, sends them to the STM32 controller via the UART interface, and uses a PID control strategy to realize path tracking of the intelligent vehicle.

[0014] Preferably, the emergency obstacle avoidance and safety control module uses an infrared obstacle avoidance sensor as the highest priority safety control module. When an emergency obstacle is detected, it immediately overrides the current control command of the motion control and execution module. After the obstacle avoidance action is completed, it determines whether the obstacle has been cleared. If it has been cleared, the original navigation state is restored. If it has not been cleared, the obstacle avoidance strategy continues to be executed.

[0015] Preferably, the multi-source data acquisition module includes a GNSS receiver module, an IMU module, a radar module, an OV5640 camera module, and an E18 infrared obstacle avoidance sensor.

[0016] Therefore, the present invention employs the above-mentioned intelligent vehicle system based on single BeiDou multi-source data acquisition, which has the following beneficial effects: (1) Relying solely on a single BeiDou positioning signal, the fusion participation mode of multi-source sensor information can be dynamically adjusted according to the differences in the number of satellites, signal quality, and positioning stability, thereby achieving adaptive fusion under different positioning reliability conditions and significantly improving the stability and reliability of positioning and environmental perception results.

[0017] (2) Using single BeiDou timing information as a unified time reference for multi-source data, BeiDou positioning information is used simultaneously for global position calculation, time synchronization of multi-source sensing data, system status assessment and fusion constraints, so as to ensure the continuity of the overall perception and control process of the system under single BeiDou positioning conditions.

[0018] (3) Based on the single Beidou positioning status change constraint perception fusion strategy and path planning behavior, Beidou positioning information participates in the upper-level operation decision-making without directly interfering with the lower-level motion control, thereby improving the stability and safety of the intelligent vehicle in complex environments while maintaining the system's autonomy.

[0019] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0020] Figure 1 This is a module connection diagram of an intelligent vehicle system based on single Beidou multi-source data acquisition according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a multi-source data acquisition intelligent vehicle based on a single Beidou constraint according to an embodiment of the present invention; Figure 3 This is a front view of a multi-source data acquisition intelligent vehicle based on a single Beidou constraint according to an embodiment of the present invention; Figure 4 This is a left view of a multi-source data acquisition intelligent vehicle based on a single Beidou constraint according to an embodiment of the present invention. Figure 5 This is a top view of a multi-source data acquisition intelligent vehicle based on a single BeiDou constraint according to an embodiment of the present invention; Figure Labels 1. Vehicle body; 2. Tires; 3. Main control board; 4. E18 infrared obstacle avoidance sensor; 5. OV5640 camera module; 6. Antenna; 7. GNSS receiver module; 8. IMU module; 9. Radar module; 10. Lithium battery; 11. ULM3-PDOA base station. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. In the description of the present invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product is in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the present invention.

[0022] Example This invention discloses an intelligent vehicle system based on single BeiDou multi-source data acquisition, such as... Figure 1 As shown, it includes a multi-source data acquisition module, which is connected to a spatiotemporal alignment module. The spatiotemporal alignment module is connected to a multi-source fusion module. The multi-source fusion module is connected to a scene adaptive perception and path generation module. The scene adaptive perception and path generation module is connected to a motion control and execution module. The motion control and execution module is connected to an emergency obstacle avoidance and safety control module.

[0023] The multi-source data acquisition module includes a GNSS receiver module 7, an IMU module 8, a radar module 9, an OV5640 camera module 5, and an E18 infrared obstacle avoidance sensor 4.

[0024] like Figures 2-5 As shown, the vehicle body 1 consists of four 75mm outer diameter tires 2 and a main control board 3. The main control board 3 integrates the core hardware required for each module, including an STM32F103RCT6 and... Embedded within the main control board 3, it provides the control core for all functional modules. The front of the main control board 3 houses an E18 infrared obstacle avoidance sensor 4 and an OV5640 camera module 5; the middle section contains an antenna 6, a GNSS receiver module 7, an IMU module 8, and a radar module 9; and the rear section contains a lithium battery 10 and a ULM3-PDOA base station 11. The lithium battery 10 powers all hardware and modules of the entire system. The GNSS receiver module 7 operates in single BeiDou mode, receiving and processing only BeiDou satellite signals. The ULM3-PDOA base station 11 can provide local relative positioning information when the GNSS receiver module 7 signal is weak or malfunctioning, serving as emergency hardware integrated into the multi-source fusion module. The E18 infrared obstacle avoidance sensor 4, OV5640 camera module 5, antenna 6, GNSS receiver module 7, IMU module 8, and radar module 9 together form the multi-source data acquisition module, with antenna 6 and GNSS receiver module 7 serving as the core hardware of the spatiotemporal alignment module. The specifications of the multi-source data acquisition module are shown in Table 1.

[0025] Table 1. Indicators of Multi-Source Data Acquisition Module

[0026] The multi-source data acquisition module is used to collect multi-source data, including the intelligent vehicle's global position information, speed information, heading information, time reference information, visual images, attitude angles, and short-term motion state information; and to preprocess the collected multi-source data, including normalization, outlier removal, and noise suppression, to obtain single BeiDou GNSS timing data.

[0027] Output the single BeiDou GNSS timing data to the spatiotemporal alignment module.

[0028] The spatiotemporal alignment module achieves time synchronization of multi-source data based on single BeiDou GNSS timing data. At the same time, it maps various types of sensing data to a unified intelligent vehicle body coordinate system, achieves time synchronization of multi-source data through timestamp alignment, and achieves spatial alignment of multi-source data using coordinate transformation formulas.

[0029] Vehicle coordinate system The coordinate system is established with the center of gravity of the intelligent vehicle as the origin and a right-handed Cartesian coordinate system is adopted. The positive directions of the X, Y, and Z axes are the front, left, and top of the vehicle body 1. Let the coordinate system of the multi-source sensor be... Multi-source sensor coordinate system To the vehicle coordinate system The coordinate transformation formula is: ; in, For the vehicle body coordinate system The coordinates below, To obtain coordinates from multi-source sensor system To the vehicle coordinate system The rotation matrix, Multi-source sensor coordinate system The coordinates below, To represent the translation vector of the sensor's installation position in the vehicle coordinate system; ; in, Yaw angle The pitch angle, This is the roll angle. To bypass The rotation matrix of the axis. To bypass The rotation matrix of the axis. To bypass The rotation matrix of the axis; ; ; ; The metrics for the spatiotemporal alignment module are shown in Table 2.

[0030] Table 2 Spatiotemporal Alignment Module Indicators

[0031] The multi-source fusion module assesses the reliability of a single BeiDou positioning status and dynamically adjusts the weights based on the assessment results to achieve adaptive fusion of multi-source data.

[0032] Specifically: The multi-source fusion module is based on the number of available satellites. Average signal-to-noise ratio Stability of positioning results and time synchronization integrity Four indicators are used to assess the reliability of a single BeiDou positioning status, and a single BeiDou reliability scoring function is defined. The formula is: ; in, , , The normalized indicator, , , and The number of available satellites Average signal-to-noise ratio Stability of positioning results and time synchronization integrity The weighting coefficients, ,and , , Assess the reliability of single BeiDou positioning status, and .

[0033] The multi-source fusion module introduces a weighting factor for BeiDou reliability dependence. This is used to adjust the participation of BeiDou data in the fusion process, and sets the minimum value of the preset credibility threshold. and the highest value .

[0034] Based on credibility rating The lowest value of the credibility threshold and the highest value The BeiDou weight factor was obtained by performing a three-stage weight adjustment. The formula is adjusted as follows: when At this time, the BeiDou weight is reduced to a minimum, mainly relying on local sensing, as shown in the formula: ; in, To adjust the coefficient, This represents the minimum threshold for BeiDou weighting. when At that time, the weight of Beidou was Non-linear growth within the interval, the formula is: ; in, This represents the maximum threshold for BeiDou weighting. when At that time, the BeiDou weight is close to its maximum value, and the formula is: ; In the process of multi-source data fusion, the final fusion result is obtained by weighting and summing the BeiDou data and local sensing data, as shown in the formula: ; in, For the final fusion positioning results, For single BeiDou positioning data, As local sensing data, the local relative positioning information output by the ULM3-PDOA base station 11 can be used as... Emergency supplementary data.

[0035] Based on this dynamic weight adjustment mechanism, it can be ensured that when the BeiDou signal quality deteriorates, the system can enhance its reliance on local sensing information and maintain the continuity and stability of environmental perception. The multi-source fusion module indicators are shown in Table 3.

[0036] Table 3 Indicators of Multi-Source Fusion Module

[0037] The scene adaptive perception and path generation module constructs an intelligent vehicle operation status model based on the multi-source fusion results, providing a basis for the generation of driving paths, including the intelligent vehicle's location information, motion status information, and environmental perception information; and generates an adapted driving path by combining the single Beidou positioning reliability level.

[0038] Specifically, the scene adaptive perception and path generation module calculates the scene density index (SDI) in real time, analyzes obstacle distribution characteristics, and combines the single BeiDou reliability level. It then employs a hybrid strategy for smooth transitions at scene boundaries, selecting the optimal path planning algorithm from the algorithm strategy library. The algorithm selection rules are as follows: In low-density scenarios and when BeiDou has high reliability, i.e. and Using A based on global coordinates The algorithm aims to guarantee optimality; in medium-density scenarios, when and When SDI ≥ 1, the dynamic window DWA algorithm is used. Furthermore, when the obstacle distribution is linear / channel-shaped, a spatiotemporal constraint RRT is applied. Algorithm; in high-density scenarios or when BeiDou reliability is low, i.e. or Artificial potential field method is used to ensure safe obstacle avoidance.

[0039] Each algorithm is based on a confidence weight. The parameters are adaptively adjusted to generate suitable path planning results and output them to the motion control and execution module.

[0040] Spatiotemporal constraints are introduced to ensure the continuity, feasibility, and safety of the path, including continuity constraints, kinematic feasibility constraints, and safety constraints. The generated path must satisfy... Continuity means that the position, tangential direction, and curvature are continuous, and the path generation must satisfy temporal consistency. The formula is: ; in, To achieve the minimum time resolution, prevent the control frequency from being too high due to excessively small time steps; Based on the vehicle model, constrain the front wheel steering angle. ,speed acceleration This ensures that vehicles along the route can be tracked. Among other things, Wheelbase This is the minimum turning radius.

[0041] For static obstacles, the path points must satisfy the following conditions: ,in, For the first in the path sequence One point, For the first A static obstacle, path point To the One obstacle The minimum Euclidean distance For intelligent vehicles at path points instantaneous velocity at that point This is the maximum permissible speed for intelligent vehicles.

[0042] For dynamic obstacles, the following requirements must be met in the time dimension: ;in, For smart cars The expected location at that moment For the first A dynamic obstacle Predicted location at time for The Euclidean distance between the vehicle and the obstacle at any given time. For the first The velocity vectors of each dynamic obstacle. The metrics for the scene adaptive perception and path generation module are shown in Table 4.

[0043] Table 4. Metrics of the Scene Adaptive Perception and Path Generation Module

[0044] The motion control and execution module receives the path planning results output by the scene adaptive perception and path generation module, and sends them to the STM32 controller in the main control board 3 via the UART interface. A PID control strategy is used to achieve path tracking for the intelligent vehicle, and the execution status is fed back to the multi-source fusion module to form closed-loop optimization control. The performance indicators of the motion control and execution module are shown in Table 5.

[0045] Table 5 Indicators of Motion Control and Execution Module

[0046] The emergency obstacle avoidance and safety control module uses the E18 infrared obstacle avoidance sensor 4 as the highest priority safety control module. When an emergency obstacle is detected, it immediately overrides the current control command of the motion control and execution module. After completing the obstacle avoidance action, it determines whether the obstacle has been cleared. If cleared, the original navigation state is restored; if not cleared, the obstacle avoidance strategy continues to be executed. The indicators of the emergency obstacle avoidance and safety control module are shown in Table 6.

[0047] Table 6 Indicators for Emergency Obstacle Avoidance and Safety Control Module

[0048] Therefore, the present invention adopts the above-mentioned intelligent vehicle system based on single Beidou multi-source data acquisition. By continuously sensing and evaluating the environmental state and single Beidou positioning state of the intelligent vehicle, it solves the problem of how to dynamically adjust the participation mode of multi-source sensor information in the fusion process according to the changes in the number of satellites, signal quality bands, and positioning stability when relying solely on a single Beidou positioning signal. This enables adaptive fusion of multi-source sensing information under different positioning reliability conditions, thereby improving the stability and reliability of positioning and environmental sensing results.

[0049] It further solves the problem of how to use single BeiDou timing information as a unified time reference for multi-source data and introduce it into the synchronization and fusion process of multi-source sensing data. This enables BeiDou positioning information to not only provide global location information, but also participate in the time synchronization, state evaluation and fusion constraints of multi-source sensing data, thereby ensuring the continuity of the overall sensing and control process of the system under single BeiDou positioning conditions.

[0050] While ensuring the stability of the intelligent vehicle's positioning and perception, this paper solves the problem of how to constrain and control the perception fusion strategy and path planning behavior based on changes in the single BeiDou positioning status. This allows the single BeiDou positioning information to participate in the intelligent vehicle's operation decision-making without directly interfering with the underlying motion control process, thereby improving the operational stability and safety of the intelligent vehicle in complex environments while maintaining the system's autonomy.

[0051] Finally, 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 preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A smart vehicle system based on single BeiDou multi-source data acquisition, characterized in that: It includes a multi-source data acquisition module, which is connected to a spatiotemporal alignment module. The spatiotemporal alignment module is connected to a multi-source fusion module. The multi-source fusion module is connected to a scene adaptive perception and path generation module. The scene adaptive perception and path generation module is connected to a motion control and execution module. The motion control and execution module is connected to an emergency obstacle avoidance and safety control module. The multi-source data acquisition module is used to acquire multi-source data, preprocess the acquired multi-source data, and output single BeiDou GNSS timing data. The spatiotemporal alignment module achieves time synchronization of multi-source data based on single BeiDou GNSS timing data, and maps various types of sensing data to a unified coordinate system to achieve spatial alignment. The multi-source fusion module performs a reliability assessment on the single BeiDou positioning status and dynamically adjusts the weights based on the assessment results to achieve adaptive fusion of multi-source data. The scene adaptive perception and path generation module constructs an intelligent vehicle operation status model based on the multi-source fusion results, and generates an adapted driving path by combining the single Beidou positioning reliability level. The motion control and execution module realizes the motion control of the intelligent vehicle according to the planned driving path, and feeds back the execution status to the multi-source fusion module to form closed-loop control; The emergency obstacle avoidance and safety control module detects obstacles around the intelligent vehicle. When an emergency obstacle is detected, it executes the obstacle avoidance operation with the highest priority, overriding the motion control commands of the motion control and execution module.

2. The intelligent vehicle system based on single Beidou multi-source data acquisition according to claim 1, characterized in that: The multi-source data acquisition module collects multi-source data including the intelligent vehicle's global position information, speed information, heading information, time reference information, visual images, attitude angles, and short-term motion state information; The collected multi-source data is preprocessed, including normalization, outlier removal and noise suppression, and then single BeiDou GNSS timing data is obtained.

3. The intelligent vehicle system based on single Beidou multi-source data acquisition according to claim 1, characterized in that: The spatiotemporal alignment module completes time synchronization based on single BeiDou GNSS timing information, and maps various types of sensing data to a unified intelligent vehicle body coordinate system. It achieves time synchronization of multi-source data through timestamp alignment and spatial alignment of multi-source data using coordinate transformation formulas. Vehicle coordinate system The coordinate system is established with the center of gravity of the intelligent vehicle as the origin, using a right-handed Cartesian coordinate system, with the positive directions of the X, Y, and Z axes being the front, left, and top of the vehicle body. Let the coordinate system of the multi-source sensor be... Multi-source sensor coordinate system To the vehicle coordinate system The coordinate transformation formula is: ; in, For the vehicle body coordinate system The coordinates below, To obtain coordinates from multi-source sensor system To the vehicle coordinate system The rotation matrix, Multi-source sensor coordinate system The coordinates below, This is the translation vector representing the sensor's installation position in the vehicle coordinate system.

4. The intelligent vehicle system based on single Beidou multi-source data acquisition according to claim 1, characterized in that: The multi-source fusion module is based on the number of available satellites. Average signal-to-noise ratio Stability of positioning results and time synchronization integrity Four indicators are used to assess the reliability of a single BeiDou positioning status, and a single BeiDou reliability scoring function is defined. The formula is: ; in, , , The normalized indicator, , , and Number of available satellites Average signal-to-noise ratio Stability of positioning results and time synchronization integrity The weighting coefficients, ,and , , Assess the reliability of single BeiDou positioning status, and .

5. The intelligent vehicle system based on single Beidou multi-source data acquisition according to claim 4, characterized in that: The multi-source fusion module introduces a weighting factor for BeiDou reliability dependence. This is used to adjust the participation of BeiDou data in the fusion process, and sets the minimum value of the preset credibility threshold. and the highest value ; Based on credibility rating The lowest value of the credibility threshold and the highest value The BeiDou weight factor was obtained by performing a three-stage weight adjustment. The formula is adjusted as follows: when At this time, the BeiDou weight is reduced to a minimum, mainly relying on local sensing, as shown in the formula: ; in, To adjust the coefficient, This represents the minimum threshold for BeiDou weighting. when At that time, the weight of Beidou was Non-linear growth within the interval, the formula is: ; in, This represents the maximum threshold for BeiDou weighting. when At that time, the BeiDou weight is close to its maximum value, and the formula is: ; In the process of multi-source data fusion, the final fusion result is obtained by weighting and summing the BeiDou data and local sensing data, as shown in the formula: ; in, For the final fusion positioning results, For single BeiDou positioning data, This is local sensing data.

6. The intelligent vehicle system based on single BeiDou multi-source data acquisition according to claim 1, characterized in that: The scene adaptive perception and path generation module constructs an intelligent vehicle operation status model that includes location information, motion state information and environmental perception information based on the fused multi-source perception results.

7. The intelligent vehicle system based on single Beidou multi-source data acquisition according to claim 1, characterized in that: The scene adaptive perception and path generation module calculates the scene density index (SDI) in real time, analyzes obstacle distribution characteristics, and combines the single BeiDou reliability level. It employs a hybrid strategy for smooth transitions at scene boundaries, selecting the optimal path planning algorithm from an algorithm strategy library. Each algorithm is weighted according to its reliability level. The parameters are adaptively adjusted to generate suitable path planning results and output them to the motion control and execution module.

8. The intelligent vehicle system based on single Beidou multi-source data acquisition according to claim 1, characterized in that: The motion control and execution module receives the path planning results output by the scene adaptive perception and path generation module, and sends them to the STM32 controller via the UART interface. The PID control strategy is used to realize the path tracking of the intelligent vehicle.

9. The intelligent vehicle system based on single Beidou multi-source data acquisition according to claim 1, characterized in that: The emergency obstacle avoidance and safety control module uses an infrared obstacle avoidance sensor as the highest priority safety control module. When an emergency obstacle is detected, it immediately overrides the current control command of the motion control and execution module. After completing the obstacle avoidance action, it determines whether the obstacle has been cleared. If it has been cleared, the original navigation state is restored. If it has not been cleared, the obstacle avoidance strategy continues to be executed.

10. The intelligent vehicle system based on single BeiDou multi-source data acquisition according to claim 1, characterized in that: The multi-source data acquisition module includes a GNSS receiver module, an IMU module, a radar module, an OV5640 camera module, and an E18 infrared obstacle avoidance sensor.

Citation Information

Patent Citations

  • Power distribution network distributed measurement synchronization method and device based on Beidou satellite time service

    CN120729459A

  • Unmanned system autonomous navigation method based on Beidou and multi-source information adaptive fusion

    CN120927019A

  • Inspection robot navigation method, system and equipment based on Beidou and binocular vision fusion and storage medium

    CN120928813A

  • Beidou RTK transformer substation operation positioning method based on AI auxiliary dynamic fusion

    CN121348387A

  • Multi-source data fusion monitoring device, system and method for Beidou time service synchronization

    CN121430544A