A navigation control method and system for port tractor transportation section

Abstract

This invention relates to the field of vehicle navigation control technology, and in particular to a navigation control method and system for segmented container truck transportation at a port. The method includes the following steps: dynamically dividing the container truck transportation trajectory based on port digital map information and container truck transportation traffic information to obtain segmented container truck transportation trajectories; obtaining the control complexity index of the segmented container truck transportation trajectory, and determining the segmented transportation trajectory type based on the control complexity index; constructing a segmented container truck navigation control strategy for the segmented container truck transportation trajectory based on the segmented transportation trajectory type; establishing a smooth transition function to perform inter-segment transition connection of the control parameters of the segmented container truck navigation control strategy to obtain the container truck navigation control strategy; and executing the container truck navigation control strategy to realize navigation control of the segmented container truck transportation at the port. This invention achieves navigation control of segmented container truck transportation at a port through dynamic trajectory division, classification control, smooth inter-segment transition, and replanning mechanisms.

Description

Technical Field

[0001] This invention relates to the field of vehicle navigation and control technology, and in particular to a navigation and control method and system for segmented container truck transportation at a dock. Background Technology

[0002] In automated terminals and intelligent logistics, automatic navigation control of container trucks is a core technology for improving operational efficiency and safety. Existing technologies mainly employ the following methods: First, navigation based on global path planning, which generates a global trajectory from start to finish using a digital map of the terminal and uses a single control method for full-process tracking. Its control parameters are typically fixed values ​​or switched according to simple rules. Second, rule-based segmentation methods, which roughly divide the path into finite categories such as straight lines and curves based on prior knowledge and preset corresponding control strategies for each type of path. Third, introducing perception technology for local obstacle avoidance or speed adjustment.

[0003] However, existing technologies have limitations: First, rule-based segmentation cannot adapt to the dynamic and complex operating environment of a terminal. When traffic flow changes or temporary obstacles occur, the preset segmentation points and control strategies may fail, lacking dynamic adjustment capabilities. Second, a single global control strategy struggles to balance different needs such as the stability of straight-line driving, the accuracy of curve tracking, and the low-speed precision control near loading and unloading areas. Furthermore, the lack of smooth transitions between different path segments causes trucks to brake suddenly, jerk, or experience trajectory oscillations at the segment switching points, affecting driving stability and transportation safety. Finally, when significant path tracking errors occur, only local corrections or complete stops are possible, lacking a mechanism to trigger a comprehensive replanning of the trajectory and control strategy.

[0004] Therefore, there is an urgent need for a segmented navigation control method for trucks that can achieve dynamic and precise path segmentation, adaptive control, and ensure smooth transitions between segments. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a navigation control method and system for segmented container truck transportation at a wharf.

[0006] To achieve the above objectives, in a first aspect, the present invention provides a navigation control method for segmented container truck transportation at a terminal. The method includes the following steps: dynamically dividing the container truck transportation trajectory based on terminal digital map information and container truck transportation traffic information to obtain segmented container truck transportation trajectories; obtaining a control complexity index for the segmented container truck transportation trajectory, and determining the segmented transportation trajectory type based on the control complexity index; constructing a segmented container truck navigation control strategy for the segmented container truck transportation trajectory based on the segmented transportation trajectory type; establishing a smooth transition function to perform inter-segment transition connections between the control parameters of the segmented container truck navigation control strategy to obtain the container truck navigation control strategy; and executing the container truck navigation control strategy to achieve navigation control of the segmented container truck transportation at the terminal. The present invention combines digital maps and traffic information for dynamic trajectory division, adapting to the complex environment of the terminal. The segmented strategy improves the targeting of control, and the smooth transition avoids parameter abrupt changes, thereby improving the efficiency and navigation safety of container truck transportation and achieving refined control of container truck navigation.

[0007] Optionally, the step of dynamically dividing the truck transport trajectory into segmented transport trajectories based on terminal digital map information and truck transport traffic information includes: extracting a set of path points for the truck transport trajectory based on the terminal digital map information and obtaining feature parameters for each path point; constructing a segmentation point decision function based on the feature parameters and obtaining a segmentation index for the path points based on the segmentation point decision function; determining a segmentation point threshold and comparing the segmentation index with the segmentation point threshold to select candidate segmentation points; dynamically adjusting the candidate segmentation points according to the truck transport traffic information to determine the final segmentation points; and dividing the truck transport trajectory into the segmented transport trajectories using the final segmentation points. This invention achieves accuracy and adaptability in trajectory division through feature parameter extraction and dynamic adjustment of candidate segmentation points. It constructs a decision function based on path point features and optimizes segmentation points using real-time traffic information, avoiding over-segmentation or under-segmentation, providing a reasonable segmentation basis for subsequent differentiated control, and improving the effectiveness of overall navigation control.

[0008] Optionally, constructing the segmentation point decision function based on the feature parameters includes: evaluating the feature importance of the feature parameters to select segmentation decision parameters; obtaining dynamic weight coefficients based on historical data, and linearly weighting the segmentation decision parameters to construct the segmentation point decision function. This invention filters key parameters through feature importance evaluation and combines them with dynamic weighting based on historical data, making the segmentation point decision function more closely aligned with actual transportation scenarios, reducing redundant parameter interference, improving the reliability of segmentation index calculation, making trajectory segmentation more scientific, reducing the influence of subjective factors, and providing a decision-making basis for dynamic trajectory division.

[0009] Optionally, obtaining the control complexity index of the segmented transportation trajectory of the container truck and determining the segmented transportation trajectory type based on the control complexity index includes: extracting features from the segmented transportation trajectory of the container truck to obtain segmented trajectory features; constructing a control complexity evaluation model based on the segmented trajectory features to obtain the control complexity index; obtaining a type classification threshold, and determining the segmented transportation trajectory type of the container truck segmented transportation trajectory in combination with the control complexity index, including straight segments, turning segments, and loading / unloading segments. This invention classifies trajectory types through control complexity indices, achieving differentiation and accuracy in segmented control. It extracts trajectory features to construct an evaluation model, accurately distinguishing between straight, turning, and loading / unloading segments, matching adaptation strategies for different scenarios, avoiding the limitations of uniform control, improving the targeting and effectiveness of navigation control for each segment, and ensuring the smoothness of container truck transportation.

[0010] Optionally, constructing a control complexity evaluation model based on the segmented trajectory features includes: obtaining trajectory change features based on the segmented trajectory features, including the rate of change of curvature, the rate of change of velocity, and the rate of change of direction angle; obtaining a balance adjustment coefficient; and fusing the trajectory change features to construct the control complexity evaluation model. This invention integrates multi-dimensional trajectory change features and balance adjustment coefficients, resulting in a more comprehensive and accurate evaluation model. It comprehensively evaluates complexity using indicators such as curvature, velocity, and rate of change of direction angle, avoiding the one-sidedness of a single indicator. The balance adjustment coefficients adapt to different path scenarios, making the complexity indicators more aligned with actual control needs and improving the adaptability of strategy formulation.

[0011] Optionally, constructing a segmented navigation control strategy for the segmented transport trajectory based on the segmented transport trajectory type includes: determining a navigation control algorithm for different types of segmented transport trajectories based on the segmented transport trajectory type, and obtaining the desired control parameters for the segmented transport trajectories; generating the segmented navigation control strategy based on the navigation control algorithm and the desired control parameters. This invention determines the algorithm and parameters based on the trajectory type, making the segmented navigation control strategy more adaptable. It selects the optimal control algorithm for different trajectory types and generates a control strategy by combining the desired parameters, ensuring a high degree of matching between the strategy and segmented characteristics, avoiding the inefficiency of general strategies, improving the accuracy and response speed of navigation in each segment, and optimizing the transport process.

[0012] Optionally, establishing a smooth transition function to obtain the truck navigation control strategy by transitioning the control parameters of the segmented navigation control strategy between segments includes: constructing the smooth transition function based on a normalized time variable by combining the inter-segment parameter differences and truck dynamic constraints; determining the transition spatiotemporal region according to the segmented navigation control strategy, including time length and spatial range; generating an inter-segment parameter transition sequence within the transition spatiotemporal region using the smooth transition function; and for adjacent segmented navigation control strategies, transitioning the control parameters according to the inter-segment parameter transition sequence to obtain the truck navigation control strategy. This invention, by constructing a smooth transition function combining parameter differences and dynamic constraints, achieves seamless connection of inter-segment parameters, improves the continuity and stability of navigation control, determines a reasonable transition spatiotemporal region, and generates a smooth parameter sequence, avoiding truck bumps or trajectory deviations caused by abrupt changes in inter-segment parameters, and ensuring a stable and reliable transportation process.

[0013] Optionally, the step of constructing the smooth transition function based on a normalized time variable, combining the inter-segment parameter differences and truck dynamics constraints, includes: determining the key control parameters to be smoothed based on the inter-segment parameter differences; obtaining the maximum allowable rate of change of the key control parameters according to the truck dynamics constraints during the parameter transition; constructing a parameter smooth transition curve that satisfies the maximum allowable rate of change; and mapping the parameter smooth transition curve to the normalized time domain to construct the smooth transition function. This invention focuses on key control parameters, determines the maximum rate of change based on dynamic constraints, constructs a transition curve that meets safe operation limits, and improves applicability through normalized time domain mapping, ensuring smooth parameter transition and guaranteeing the safety and control stability of truck operation.

[0014] Optionally, executing the truck navigation control strategy to achieve navigation control of the segmented truck transportation at the terminal includes: acquiring truck operating status data to determine path tracking error during the execution of the truck navigation control strategy; triggering a replanning mechanism when the path tracking error exceeds a control safety threshold to generate the segmented truck transportation trajectory and the replanning result of the segmented truck navigation control strategy; updating the truck navigation control strategy based on the replanning result, and converting the truck navigation control strategy into real-time control commands to achieve navigation control of the segmented truck transportation at the terminal. This invention calculates tracking error using operating status data, triggers replanning when the error exceeds a threshold, dynamically updates the trajectory and strategy, avoids accidents caused by error accumulation, ensures that trucks always operate along the optimal path, and improves transportation safety and efficiency.

[0015] Secondly, this invention provides a navigation control system for segmented container truck transportation at a port. The system executes the navigation control method for segmented container truck transportation provided by this invention. The system includes input devices, output devices, a processor, and a memory, which are interconnected. The memory stores a computer program, which includes program instructions. The processor is configured to call the program instructions. This invention achieves efficient implementation of the method through high-performance hardware collaboration, ensuring automated and precise navigation control processes, improving the intelligence level of container truck transportation at ports, reducing manual intervention costs, and guaranteeing stable and efficient transportation. Attached Figure Description

[0016] Figure 1 This is a flowchart of a navigation control method for segmented container truck transportation at a dock, according to an embodiment of the present invention. Figure 2 This is a framework diagram of a navigation control system for a segmented container truck transportation system at a dock, according to an embodiment of the present invention. Detailed Implementation

[0017] Specific embodiments of the present invention will now be described in detail. It should be noted that the embodiments described herein are for illustrative purposes only and are not intended to limit the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be apparent to those skilled in the art that these specific details are not necessary to practice the invention. In other instances, well-known circuits, software, or methods have not been specifically described to avoid obscuring the invention.

[0018] Throughout this specification, references to "an embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment of the invention. Therefore, the phrases "in an embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, or characteristics can be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. Moreover, those skilled in the art will understand that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.

[0019] Please see Figure 1 One embodiment of the present invention provides a navigation control method for segmented container truck transportation at a dock, the method comprising the following steps: S1. Based on the digital map information of the port and the transportation information of the container trucks, the container truck transportation trajectory is dynamically divided to obtain the segmented transportation trajectory of the container trucks.

[0020] Specifically, S1 includes the following steps: S11. Extract the path point set of the container truck transportation trajectory based on the digital map information of the wharf, and obtain the feature parameters of each path point.

[0021] In this embodiment, the terminal digital map information serves as the basic data source for trajectory division; the acquisition steps include the following: First, static geographic information of the terminal is acquired through methods such as laser scanning, including but not limited to the geographic coordinates of road centerlines, lane lines, intersection boundaries, container yard areas, quay crane locations, and parking / loading points; subsequently, the static geographic information is digitally modeled to form a multi-layered terminal digital map, which includes at least a path network layer (describing the topological connections of passable paths), a facility layer (marking the location and attributes of key facilities), and a traffic rule layer (such as speed limits, one-way streets, etc.). The terminal digital map information is stored in vector data format on a central server.

[0022] Furthermore, based on the digital map information of the terminal, a set of path points for the truck transportation trajectory is extracted, including: performing global path planning on the path network layer according to the starting and ending points of the transportation task to generate a preliminary truck transportation trajectory. Each path point contains at least its coordinates in the terminal's global coordinate system. This preliminary transportation trajectory is then sampled with equal arc lengths or interpolated with equal time intervals to form a set of path points with uniform density.

[0023] After obtaining the path point set, the feature parameters of each path point are acquired one by one. This aims to describe the geometric and contextual characteristics of the point in the global trajectory from different dimensions, including but not limited to: Geometric feature parameters: Curvature is estimated by calculating the reciprocal of the radius of the inscribed circle formed by a path point and its adjacent path points, reflecting the degree of curvature of the trajectory at that point; the angle between the forward direction vector of a path point and the forward direction vector of the previous path point is calculated as the change in direction angle, reflecting the abrupt change in path direction.

[0024] Topological feature parameters: Based on the path network layer of the terminal digital map information, determine whether the path point is the intersection of multiple paths (such as crossroads, T-junctions) to obtain the adjacency relationship; calculate the Euclidean distance from the path point to the nearest critical facility (such as quay crane, loading and unloading point, intersection center) defined in the facility layer as the distance to the critical facility.

[0025] Environment-rule feature parameters: The maximum permissible speed at the location of a path point is read from the traffic rule layer as the speed limit value; the width information of the lane where a path point is located is obtained from the path network layer as the path width.

[0026] S12. Construct a segmentation point decision function based on the feature parameters, and obtain the segmentation index of the path point based on the segmentation point decision function.

[0027] In this embodiment, feature importance is evaluated to select the most critical segmentation decision parameters. A labeled dataset containing a large number of historical transportation tasks is constructed, in which the path points of each trajectory have been labeled with ideal segmentation point locations. Using this labeled dataset, a machine learning model (e.g., gradient boosting decision tree) capable of outputting feature importance scores is trained. This model calculates and outputs the importance score of each feature by analyzing the correlation between each feature parameter and the labeled segmentation points. Simultaneously, domain knowledge of terminal operations (e.g., recognizing that proximity to loading / unloading points is a key control switching node) is incorporated to validate and fine-tune the results of the model's automatic evaluation. Finally, by combining the machine learning model and domain knowledge, the most representative parameters are selected as the core inputs for constructing the decision function, i.e., the segmentation decision parameters.

[0028] Furthermore, dynamic weight coefficients are assigned to the selected segmentation decision parameters. A set of typical transportation scenarios is predefined, such as "high-speed transportation on main roads" and "precise positioning within the storage area." For each scenario, a corresponding subset of trajectory data is extracted from the historical database. For each data subset of a scenario, a statistical regression method is used, with the selected segmentation decision parameters as input and the ideal segmentation tendency as output, to perform a fitting process. The core purpose of the fitting process is to determine the relative contribution of each decision parameter to the judgment segmentation point under that specific scenario, i.e., the dynamic weight coefficients.

[0029] In this embodiment, a segmentation point decision function is constructed by combining segmented decision parameters and dynamic weighting coefficients to calculate the segmentation index of the path points. First, due to the significant differences in the numerical units and ranges of different decision parameters, normalization preprocessing is required to convert them to the same numerical scale, ensuring comparability during weighted summation. Then, the segmentation point decision function is constructed; this function is essentially a linear weighter, multiplying each normalized decision parameter by its corresponding dynamic weighting coefficient, and then summing all the products to obtain a total, which is the segmentation index of the path point. This process is repeated for each path point on the trajectory to obtain a sequence of segmentation indices for the path point set. The segmentation index quantifies the probability that each point is a segment point; the higher the value, the greater the probability.

[0030] The above piecewise decision function satisfies the following relationship: in, For segmented exponents, For the index variable of the path point, For dynamic weighting coefficients, path point curvature at that point path point curvature at that point path point The speed limit value at that location, path point The speed limit value at that location, path point Distance from key facilities.

[0031] S13. Determine the segmentation point threshold, and compare the segmentation index with the segmentation point threshold to filter out candidate segmentation points.

[0032] In this embodiment, after obtaining the segmentation indices of all path points, a mechanism combining dynamic thresholding and local competition is used to filter candidate segmentation points. First, the global statistical characteristics (such as average value and fluctuation range) of the entire trajectory segmentation index sequence are calculated, and a global threshold is set based on the global statistical characteristics. This threshold can adapt to the overall complexity of the trajectory. Next, a sliding window is used to traverse the entire trajectory. Within each window, points whose segmentation indices are local peaks (i.e., higher than their immediate and adjacent path points) and whose values ​​are also significantly higher than the local average level within the window are found. Finally, the global threshold and the local peak condition are used as segmentation point thresholds, and path points that simultaneously satisfy both conditions are marked as candidate segmentation points.

[0033] S14. Based on the truck transportation information, dynamically adjust the candidate segmentation points to determine the final segmentation points.

[0034] In this embodiment, real-time truck transportation traffic information is used to dynamically optimize candidate segment points generated based on terminal digital map information to determine the final segment points. Truck transportation traffic information from the vehicle network, roadside units, and central dispatch system is continuously received, including but not limited to real-time traffic events (such as obstacles and congestion), traffic flow status, and dispatch instructions from other trucks. The adjustment process for candidate segment points follows this logic: First, adding segment points: when dynamic obstacles or congestion are detected in areas not covered by preceding candidate points, new segment points are inserted at the start and end positions of that area to address unforeseen circumstances; Second, deleting or merging segment points: if the area where a candidate point is located is confirmed to be unobstructed in real-time and has no special control requirements, the point is deleted from the list; if two adjacent candidate points are too close and there are no dynamic events between them, they are merged into one; Third, adjusting the position and attributes of segment points: the precise position of existing candidate points is fine-tuned based on dynamic information. For example, candidate points at curves are appropriately moved forward based on information about vehicles merging ahead to initiate deceleration earlier. Through the above operations, the candidate segmentation points are optimized into final segmentation points that can simultaneously reflect static path characteristics and dynamic environmental changes.

[0035] S15. The truck transportation trajectory is divided into truck segmented transportation trajectories through the final segmentation point.

[0036] In this embodiment, after obtaining the final segmentation point, the start and end points of the entire transportation trajectory are included in the final segmentation point as the beginning and end of the entire sequence; strictly following the order of the final segmentation point in the original path sequence, the final segmentation point is used as the cutting point in sequence, thereby dividing the truck transportation trajectory to obtain the truck segmented transportation trajectory.

[0037] Specifically, starting from the first segment point (track start point) and ending at the second segment point, all path points between these two points are divided into the first track segment. Then, all path points between the second and third segment points are divided into the second track segment, and so on, until the second-to-last segment point to the last segment point (track end point) is divided into the final track segment. Each segmented truck transport track includes its path point coordinate sequence, segment number, and start and end point information. Based on these steps, the continuous track is converted into an ordered list of segments, providing precise input for subsequent customized navigation control strategies for each segment.

[0038] S2. Obtain the control complexity index of the segmented transportation trajectory of the container truck, and determine the segmented transportation trajectory type based on the control complexity index.

[0039] Specifically, S2 includes the following steps: S21. Extract features from the segmented transport trajectory of the container truck to obtain segmented trajectory features.

[0040] In this embodiment, feature extraction is performed on the segmented transport trajectory of the container truck, transforming it into a set of segmented trajectory features that can quantify its control difficulty. First, geometric feature extraction is performed, calculating the overall curvature characteristics of the segmented trajectory, including average curvature and maximum curvature, to measure the degree of path curvature. Simultaneously, the direction angles of the segment's starting and ending points are calculated, and their difference is obtained as the total directional change to capture the turning amplitude. Second, kinematic feature extraction is performed. Based on road speed limits, safety constraints, and segment lengths in the terminal's digital map, the theoretical expected speed curve of the segmented trajectory is obtained, and features such as average expected speed, maximum expected speed, and speed change amplitude are extracted. Furthermore, the theoretical shortest travel time required to complete the segment is estimated. Finally, contextual semantic feature extraction is performed. Combining the facility layer of the digital map, the functional area where the segmented trajectory is located is determined, for example, whether it is entirely within the yard, whether it crosses an intersection, or whether its endpoint directly points to the loading / unloading position. Simultaneously, the average path width of the segment (if the lane width is variable) and its average distance to obstacles (such as static facility boundaries) are extracted. The above characteristic parameters together constitute the segmented trajectory characteristics of the segmented transportation trajectory of this container truck.

[0041] S22. Construct a control complexity evaluation model based on the segmented trajectory features to obtain the control complexity index.

[0042] Based on the segmented trajectory characteristics, dynamic change indicators that directly reflect the frequency and difficulty of control are further obtained, namely trajectory change characteristics, mainly including curvature change rate, velocity change rate, and heading angle change rate. The curvature change rate is obtained as follows: First, the curvature sequence of the segmented trajectory is smoothed and filtered to eliminate noise. Then, the absolute value of the difference in curvature between adjacent path points is calculated. Finally, the average value of the curvature difference sequence for the entire segment is taken, quantifying the intensity of fluctuations in the trajectory curvature shape. The velocity change rate is obtained as follows: Based on the expected velocity curve of the segment, the absolute value of the difference in expected velocity between adjacent path points is calculated. Similarly, the average value of the velocity difference sequence for the entire segment is taken, reflecting the frequency of acceleration or deceleration operations required to maintain the movement of this segment. The heading angle change rate is obtained as follows: Within a unit of time, the instantaneous change in heading angle at each path point within the segment is calculated, which is the heading angle change rate. The average value of the instantaneous heading angle change rates for all path points is taken. This indicator captures the fine-tuning frequency of heading control. The above rate-of-change characteristics provide direct input for assessing control complexity from three dimensions: path tracking, speed control, and heading stability.

[0043] In this embodiment, since the curvature change rate, velocity change rate, and azimuth angle change rate have different impacts on the overall control complexity, and their importance varies with the characteristics of container truck operations at the terminal, a balance adjustment coefficient is introduced. Obtaining the balance adjustment coefficient is a process based on domain knowledge and historical data optimization. First, initial settings are made using expert experience. For example, in a terminal environment, the accuracy of path tracking is often crucial, so the curvature change rate is given a high initial weight; while near the loading and unloading area, smooth speed control is more critical. Then, the initial coefficients are optimized and calibrated using historical data: a large amount of historical segmented trajectory data on the three change rates mentioned above, as well as quantifiable indicators of control difficulty during actual control (such as the mean of actual lateral error, the variance of actual speed fluctuation, and the standard deviation of controller output energy), are collected. Through multivariate regression analysis or optimization algorithms (such as gradient descent), an optimal set of balance adjustment coefficients is found, such that the estimated complexity index calculated by weighting these three change rates has the highest correlation with the actual control difficulty. The data-optimized coefficients are then used as the final balance adjustment coefficients.

[0044] Furthermore, the aforementioned three trajectory change characteristics are integrated with the balance adjustment coefficient to construct a control complexity evaluation model, including: first, normalizing the rate of change of curvature, rate of change of velocity, and rate of change of orientation angle to eliminate the deviation caused by their different dimensions and orders of magnitude; then, multiplying each normalized rate of change characteristic by its corresponding balance adjustment coefficient; finally, adding the three weighted results to obtain a comprehensive scalar value, which is the control complexity index of the segmented trajectory.

[0045] The above control complexity evaluation model satisfies the following relationship: in, To control complexity metrics, To balance the adjustment coefficient, For normalization function, The rate of change of curvature, For the rate of change of velocity, This represents the rate of change of the direction angle.

[0046] It should be noted that the higher the control complexity index, the more difficult it is to control the segmented transportation trajectory of the truck. The control complexity assessment model integrates the scattered and different dimensions of change characteristics into a unified and comparable quantitative assessment value, providing a strong basis for subsequent segment type determination.

[0047] S23. Obtain the type classification threshold, and determine the segmented transportation trajectory type of the truck segmented transportation trajectory in combination with the control complexity index, including straight segment, turning segment and loading and unloading segment.

[0048] In this embodiment, a strategy combining hierarchical threshold determination and rule verification is adopted to determine the segmented transportation trajectory type of the truck segmented transportation trajectory. Two core type classification thresholds are preset: a lower "straight segment threshold" and a higher "turning segment threshold". The above thresholds are not fixed values, but are adaptively determined by cluster analysis of the complexity index of historical segmented trajectories, thereby reflecting the overall distribution of control difficulty under the specific operating environment of the terminal.

[0049] Specifically, the classification logic is as follows: If the control complexity index of a segment is lower than the "straight line segment threshold," it is initially classified as a straight line segment because low complexity usually corresponds to a straight path and constant speed. If the control complexity index of a segment is higher than the "turning line segment threshold," it is initially classified as a turning line segment because high complexity often stems from significant changes in curvature and direction angle.

[0050] Furthermore, rule validation is performed on segments with control complexity indices between two thresholds, as well as all initially classified segments; the semantic features of the segment context obtained during the feature extraction stage are queried. Rule validation plays a decisive role, particularly in determining loading / unloading segments: even if a segment has a low control complexity index (e.g., a short straight section near a loading / unloading point), if its contextual features clearly indicate that the segment's endpoint is a loading / unloading position and its average expected speed is extremely low, its final type is classified as "loading / unloading segment." Conversely, a segment with high complexity, even if close to the loading / unloading area, is still classified as a "turning segment" if its semantic features indicate that it is merely passing through rather than performing loading / unloading. Through this decision-making mechanism, which primarily uses quantitative indicators and secondarily uses semantic rules, the automatic identification of segmented transportation trajectory types is achieved.

[0051] S3. Based on the segmented transportation trajectory type, construct the segmented navigation control strategy for the segmented transportation trajectory of the truck.

[0052] In this embodiment, a predefined algorithm-type mapping rule base is used to match the most suitable navigation control algorithm for different types of segmented trajectories. The core idea of ​​this rule base is to call dedicated control algorithms that have been proven in practice for the core control requirements of various segments.

[0053] For straight sections: the core control objective is to maintain stable heading and constant speed, requiring high real-time computational efficiency; therefore, a navigation control algorithm based on proportional-integral-derivative (PID) control is chosen. Lateral control employs a PID controller based on heading and lateral deviations to precisely adjust the front wheel angle to eliminate deviations from the preset straight line; longitudinal control uses a PID controller based on speed deviations to stably maintain the preset cruise speed.

[0054] For cornering sections: the core control principle is to anticipate curvature changes, smoothly coordinate steering and speed, and satisfy the truck's own dynamic constraints. Therefore, Model Predictive Control (MPC) is adopted. MPC introduces the truck's dynamic model and predicts the vehicle's state changes over a future time period within each control cycle. By solving a constrained optimization problem, it generates a series of optimal control commands (steering, throttle, braking). These commands not only minimize deviation from the desired trajectory but also consider safety constraints such as corner curvature, tire adhesion limits, and maximum lateral acceleration, thus achieving smooth, safe, and precise cornering.

[0055] It should be noted that the dynamic model of the truck is a two-degree-of-freedom single-vehicle model. The state variables include lateral velocity, yaw rate, longitudinal position, lateral position and heading angle. The control variables are the front wheel steering angle and longitudinal acceleration. The constraints include the front wheel steering angle range, acceleration range and tire friction circle constraint.

[0056] For the loading and unloading section: the core control objective is to achieve centimeter-level high-precision parking positioning and agile obstacle avoidance at low speeds near complex and dynamic loading and unloading points. This is achieved by employing a fusion of fuzzy logic control and a real-time feedback algorithm. The fuzzy logic controller can handle ambiguous language information such as "slightly faster" and "very close," making it particularly suitable for scenarios like loading and unloading points where precise quantification of rules is difficult. Based on inputs such as distance and angle deviation from the target point, flexible speed and steering commands are derived. Simultaneously, this algorithm tightly couples real-time feedback from the high-precision positioning unit and proximity sensing sensors, forming a closed loop to ensure the accuracy of final parking and immediate response to sudden obstacles.

[0057] In this embodiment, the desired control parameters are calculated for each specific segment of the transportation trajectory, and specific behavioral goals and performance boundaries are set for the control algorithm. These are derived from the trajectory characteristics of the segment, the dock rules, and the global task requirements.

[0058] The desired control parameters for straight sections include, but are not limited to: the desired cruising speed calculated through speed planning based on the length of the section, the traffic flow density of the section, and the global scheduling timeliness requirements; the tolerance thresholds include the maximum permissible lateral deviation and the maximum permissible heading deviation, which are preset according to lane width and safety requirements. When the deviation exceeds this threshold, the controller will increase the correction force.

[0059] The desired cruising speeds described above satisfy the following relationship: in, For the desired cruising speed, This indicates taking the minimum value. The maximum permissible speed based on traffic flow density. Traffic flow density, To achieve the speed required by global scheduling, The maximum speed is limited by the performance of the truck. For blocking density, The segment length of the segmented transportation trajectory of the container truck. The time allocation for segmented trajectories. For global scheduling time, This represents the total length of the truck's transport trajectory.

[0060] The above tolerance thresholds satisfy the following relationship: in, For the maximum permissible lateral deviation, For safety reasons, Lane width, For the maximum permissible heading deviation, This is the preset heading deviation angle.

[0061] It should be noted that the range of values ​​for the safety factor is [insert range here]. For example, a value of 0.3 means that the allowable lateral deviation is 30% of the lane width.

[0062] The desired control parameters for the turning segment include, but are not limited to: the desired speed profile is a sequence that changes over time or position, dynamically calculated using the curve radius of curvature, road surface adhesion coefficient, and comfort standards (such as maximum normal acceleration), to ensure a smooth process of the truck decelerating before entering the curve, maintaining a constant speed at the apex of the curve, and accelerating upon exiting the curve; the reference trajectory point sequence is path points extracted from the original segmented trajectory points and possibly smoothed and optimized, quantized into a two-dimensional coordinate set, serving as the direct tracking target for the model predictive control solver.

[0063] The above desired velocity profile satisfies the following relationship: in, For the desired velocity profile, The location of the path point. For the desired cruising speed, This is the starting position for braking. The acceleration due to braking. This is the starting point of the curve. The maximum permissible speed for the curve. This is the end point of the curve. The acceleration that begins to accelerate, This is the position where acceleration begins.

[0064] The desired control parameters for the loading and unloading section include, but are not limited to: final docking posture, the target position and heading precisely obtained from the facility layer of the digital map; safe approach speed, which is an extremely low value (e.g., 5 km / h) that is dynamically adjusted according to the congestion level of the loading and unloading point; and a virtual safety boundary, which defines a rectangular protection zone around the docking point, where any obstacle entering this zone will trigger obstacle avoidance or emergency braking, with the size of the boundary determined according to the dimensions of the truck and container.

[0065] The final docking position described above satisfies the following relationship: in, For the final docking position, Let x be the x-coordinate of the target docking location. Let be the ordinate of the target docking location. The target heading angle.

[0066] The above-mentioned safe approach speeds satisfy the following relationship: in, For safe approach speed, Based on the approach speed, The degree of congestion at the loading and unloading points.

[0067] The above virtual security boundary satisfies the following relationship: in, The length of the virtual security boundary, For truck length, For a safe buffer distance, The width of the virtual security boundary, This refers to the width of the truck.

[0068] In this embodiment, a segmented navigation control strategy for the truck is generated based on the navigation control algorithm and desired control parameters. An independent, complete, and executable strategy instance is constructed for each segmented transport trajectory through strategy integration. First, a unique identifier is created for each strategy instance and associated with its corresponding segment number and type to ensure precise correspondence between the strategy and the trajectory segment. Then, the corresponding core algorithm instance is initialized according to the segment type: for straight segments, a PID controller is instantiated and its proportional, integral, and derivative parameters for the lateral and longitudinal control loops are configured. These parameters are obtained through pre-calibration based on the truck's dynamic characteristics and straight-line tracking performance requirements. For turning segments, an MPC controller instance is constructed, and the truck's dynamic model is loaded. Optimization time domain, control time domain, state weight matrix, control weight matrix, and dynamic constraints including maximum front wheel steering angle, maximum yaw rate, and friction circle limit are set. For loading and unloading segments, a pre-set fuzzy logic control rule base is loaded, and the membership degrees of its input / output variables are initialized. The function is then used; next, all the desired control parameters calculated for this segment are encapsulated into a parameter set and bound to the corresponding algorithm instance; then, the trigger and termination conditions are explicitly defined for each strategy instance: the trigger condition is that the truck's centroid enters a circular area with a specific radius centered on the segment's starting point; the termination condition is that the segment's endpoint is reached and the state is stable (e.g., the speed and pose errors of straight and turning segments are less than the set values, and the loading and unloading segments meet the final docking pose accuracy requirements and remain stable for more than a specific time); finally, all of the above generate strategy instances for each segment, containing algorithm instances, parameter sets, and execution conditions, and are combined into an ordered strategy list according to the spatial order of their corresponding segments in the global trajectory, thus forming a global, serializable, or directly deployable truck segment navigation control strategy.

[0069] S4. Establish a smooth transition function to connect the control parameters of the segmented navigation control strategy of the truck to obtain the truck navigation control strategy.

[0070] Specifically, S4 includes the following steps: S41. Combining the inter-segment parameter differences and truck dynamics constraints, construct the smooth transition function based on the normalized time variable.

[0071] First, the end control parameters of the current segment are extracted and compared with the starting control parameters of the next segment. These parameters mainly cover two dimensions: lateral control and longitudinal control. Lateral control parameters include the target front wheel angle and its corresponding desired path curvature; longitudinal control parameters include the target speed, target acceleration, and specific parameters of the control algorithm itself, such as the proportional gain of the PID controller or the prediction time domain of the MPC. The calculation of the inter-segment parameter difference involves calculating the absolute difference of each parameter, setting a difference threshold, and marking a parameter as a critical control parameter to be smoothed when its difference exceeds the corresponding threshold.

[0072] For example, when transitioning from a high-speed straight section (high target speed, near-zero curvature) to a low-speed sharp curve section (low target speed, high curvature), the difference between the target speed and the desired path curvature will significantly exceed the threshold, and therefore it is identified as a key control parameter that requires smoothing.

[0073] Secondly, based on truck dynamics constraints, an upper limit, i.e., the maximum permissible rate of change, is set for the rate of change of each parameter to ensure that the transition process conforms to the physical characteristics of the truck and guarantees the smoothness and safety of driving. Based on the predefined truck dynamics constraints, for longitudinal control parameters, the maximum permissible acceleration and maximum permissible deceleration (i.e., the boundary of the target speed change rate) are jointly determined by the truck's engine power, braking system performance, and load mass. For lateral control parameters, the maximum front wheel steering angle change rate (i.e., the maximum speed of the steering actuator) and the maximum curvature change rate are constrained by the mechanical structure of the steering system, hydraulic response speed, and tire-ground adhesion limits. The dynamic constraint values ​​are obtained and stored through vehicle parameter calibration during the design phase. During the transition, the maximum permissible rate of change is invoked for the transition process of specific parameters, serving as a hard boundary condition for constructing a smooth transition curve.

[0074] Finally, the fifth-order polynomial can simultaneously specify the position, velocity (first derivative), and acceleration (second derivative) of the start and end points, thus ensuring that not only are the function values ​​continuous at the transition start and end points, but also their first and second derivatives are continuous, corresponding to the smooth transition of control parameter values ​​and their rates of change; therefore, the fifth-order polynomial curve is used as the basic form of the parameter smooth transition curve.

[0075] The construction process of the parametric smooth transition curve is as follows: Taking a single key control parameter (e.g., target velocity) as an example, its value and rate of change at the transition start point (the initial value of the rate of change is usually set to 0), and its value and rate of change at the transition end point are used as boundary conditions; simultaneously, the maximum allowable rate of change (e.g., maximum deceleration) is used as an optimization constraint; a constrained optimization problem is solved, and a set of coefficients of a fifth-degree polynomial is found using a sequential quadratic programming algorithm, ensuring that the curve's transition process is natural while satisfying all boundary conditions and rate of change constraints; subsequently, to improve generality, this smooth transition curve based on actual time is mapped to the normalized time domain. Normalized time variable The domain is ,in This represents the start of the transition. Representing the end time of the transition, a smooth transition function based on the normalized time variable is obtained through mapping, satisfying the following relationship: in, For smooth transition function, For normalized time variables, The coefficients are undetermined for a fifth-degree polynomial.

[0076] S42. Determine the transition time-space region based on the segmented navigation control strategy of the truck, including the time length and spatial range.

[0077] In this embodiment, a specific transition spatiotemporal region is determined for each pair of adjacent segment navigation control strategies based on the segmented navigation control strategy of the container truck. This region clearly defines the specific time span and spatial range for the smooth transition. The determination of the time length mainly considers the following factors: First, the degree of difference in parameters between segments; the greater the difference, the longer the transition time is usually required to ensure smoothness. Second, strictly adhering to the maximum allowable rate of change of key control parameters obtained from the container truck dynamics constraints, ensuring that the parameter changes do not exceed physical limits within a given time length. Third, taking into account the timeliness requirements of navigation, avoiding excessively long transition times that affect overall efficiency. The determination of the spatial range is strongly correlated with the time length, and is the path distance that the container truck can cover within the total time when traveling according to the planned speed transition curve at the current transition starting speed; thus, the spatial range where the transition occurs is accurately defined in the path coordinate system. This provides a precise spatiotemporal framework for the subsequent generation of parameter transition sequences.

[0078] S43. Within the transition time-space region, an inter-segment parameter transition sequence is generated using the smooth transition function.

[0079] In this embodiment, firstly, based on the total transition time and the fixed execution cycle of the control system (e.g., 0.01 seconds or 0.02 seconds), the entire transition time domain is discretized into N uniformly distributed time points. For each physical time point, its corresponding normalized time is calculated, thus mapping all discrete time points to a normalized time domain of [0,1]. Next, for each key control parameter (e.g., target speed), its smoothing transition function is evaluated at these discrete time points, resulting in a set of intermediate transition values. This ordered set is the inter-segment parameter transition sequence for the target speed parameter. The same operation is performed in parallel on all other key control parameters marked as to be smoothed (e.g., desired curvature, front wheel angle, etc.), generating its own inter-segment parameter transition sequence for each parameter. All these time-aligned inter-segment parameter transition sequences together constitute a complete, synchronized set of inter-segment parameter transition sequences. This set accurately describes the complete evolution of all key control parameters over time from the end state of the previous segmented strategy to the beginning state of the next segmented strategy.

[0080] S44. For adjacent segmented navigation control strategies for container trucks, the control parameters are transitioned and connected according to the inter-segment parameter transition sequence to obtain the container truck navigation control strategy.

[0081] In this embodiment, as the truck approaches the starting point of the transition spatiotemporal region, the generated inter-segment parameter transition sequence is tracked and executed. In each control cycle, the controller reads the parameter values ​​(such as target velocity and desired curvature) corresponding to the current moment in the transition sequence and uses these values ​​as the desired input for the current control cycle. For example, the lateral controller receives the desired curvature value from the transition sequence, rather than the curvature at the end of the current segment or the curvature at the beginning of the next segment; the longitudinal controller similarly receives the target velocity value from the transition sequence. The controller's setpoint is then smoothly and continuously guided from the end state of the current segment to the initial state of the next segment. After the transition phase ends, the system fully switches to and executes the original navigation control strategy for the next segment.

[0082] By using the above transition and connection method, all adjacent strategy pairs are connected, and the segmented navigation control strategies are integrated into a globally smooth, continuous and dynamically feasible truck navigation control strategy.

[0083] S5. Execute the truck navigation control strategy to achieve navigation control of the truck transportation segments at the dock.

[0084] In this embodiment, during the execution of the truck navigation control strategy, multi-source sensors continuously acquire truck operating status data, including but not limited to: the truck's absolute position and heading angle in the global coordinate system, vehicle travel distance, three-axis acceleration, angular velocity, and the vehicle's relative position to the lane lines. This sensor data is fused using a Kalman filter to ultimately output an optimal, frequently updated real-time truck status estimate, including its position, velocity, acceleration, and heading.

[0085] Furthermore, based on the truck's real-time status and the reference path defined by the currently executed navigation strategy, three core error quantities are calculated as path tracking errors: lateral error, which is the normal distance from the vehicle's rear axle center point to the nearest point on the reference path; heading error, which is the angle between the vehicle's current heading and the tangent direction of the reference path at the nearest point; and longitudinal error, which is the difference between the vehicle's actual travel arc length and the expected arc length of the reference path. These error values ​​are calculated and updated in real time during each control cycle, providing accurate input for evaluating tracking performance and triggering replanning.

[0086] In this embodiment, dynamic control safety thresholds are preset based on actual transportation task requirements and are adaptively adjusted according to the current segment type, truck speed, and road width. For example, the allowable lateral error threshold is wider on high-speed straight sections, while it is very strict on low-speed loading and unloading sections. The real-time calculated path tracking error is continuously compared with these dynamic thresholds. When any of the above errors (lateral, heading, or longitudinal) exceeds its corresponding control safety threshold, it is determined that the current tracking performance does not meet safety and accuracy requirements, and a replanning mechanism is immediately triggered.

[0087] The replanning mechanism includes: First, root cause analysis is performed using real-time sensing data. If the path tracking error continues to increase and the sensing system detects obstacles ahead, it is determined to be dynamic obstacle interference; if the error originates from abrupt curvature changes or unreasonable speed planning, it is determined to be a path planning problem; if the error persists even in obstacle-free conditions, it is determined to be a control deviation. Next, using the truck's current position and state as a new starting point, and keeping the original task endpoint unchanged, the segmented transport trajectory of the truck is regenerated. The replanning process fully considers the latest digital map information of the terminal and real-time truck transport traffic information (such as the positions of other moving vehicles and temporary closed areas) to generate a completely new, collision-free, and dynamically consistent basic trajectory. Subsequently, a complete process of segmenting, complexity assessment, type determination, and strategy construction is performed on the basic trajectory to quickly generate a new segmented transport trajectory and segmented navigation control strategy that matches the current environmental state, together constituting the replanning result.

[0088] In this embodiment, the replanning results are verified for safety and feasibility to ensure that the new strategy can be executed immediately at the current location and is compatible with the truck's dynamic state. After the verification is passed, a calculation cycle boundary or a preset logical synchronization point (such as the end point of the current execution segment) is selected, and the old strategy in operation is replaced with the new replanning results in an atomic operation to update the truck navigation control strategy.

[0089] Furthermore, after the strategy update is completed, the truck navigation control strategy is transformed into real-time control commands. Based on the truck's real-time positioning information, the current segment it occupies in the new trajectory is determined, and the navigation control algorithm instance (such as a PID controller or MPC solver) bound to that segment is invoked. This algorithm instance takes the desired control parameters of this segment and the truck's real-time status from the sensors as inputs, and outputs low-level, quantified physical control quantities after calculation. For example, the longitudinal control loop outputs a specific throttle opening percentage or braking pressure value, and the lateral control loop outputs the target front wheel steering angle in radians. After actuator characteristic compensation and output limiting, the physical control quantities are encapsulated into standardized control messages and sent to the drive controller, brake controller, and steering actuator at a fixed high frequency through the vehicle control local area network, thereby realizing continuous, accurate, and adaptive closed-loop navigation control of the terminal truck transportation segment.

[0090] Please see Figure 2 In an optional embodiment, the present invention provides a navigation control system for a segmented container truck transportation system at a port. The system includes an input device, an output device, a processor, and a memory, all interconnected. The memory stores a computer program comprising program instructions, and the processor is configured to invoke the program instructions to execute specific steps as described in the relevant embodiments of the navigation control method for segmented container truck transportation at a port provided by the present invention. The navigation control system for segmented container truck transportation at a port provided by the present invention has a complete and stable structure, enhancing the overall applicability and practical application capabilities of the present invention.

[0091] In summary, this invention provides a navigation control method and system for segmented container truck transportation at a terminal. First, based on digital maps and real-time traffic information, the transportation trajectory is dynamically divided by evaluating path point characteristic parameters. Then, the control complexity index of each segment trajectory is calculated, classifying them into different types such as straight segments, turning segments, or loading / unloading segments. Next, for different types, an optimal segmented navigation control strategy is adaptively constructed. Then, to achieve smooth switching between segments, a smooth transition function is introduced, and the control parameters are smoothly connected under the premise of considering the container truck dynamics constraints, generating a globally coherent navigation control strategy. Finally, a replanning mechanism based on path tracking error is introduced during execution to ensure robustness in dynamic environments. This invention is easy to understand, computationally simple, requires minimal workload, and is convenient for engineering applications, providing a theoretical foundation and technical support for the further development of vehicle navigation control technology.

[0092] 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 the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A navigation control method for segmented container truck transportation at a wharf, characterized in that, Includes the following steps: Based on the digital map information of the port and the transportation information of container trucks, the transportation trajectory of container trucks is dynamically divided to obtain the segmented transportation trajectory of container trucks. Obtain the control complexity index of the segmented transportation trajectory of the container truck, and determine the segmented transportation trajectory type based on the control complexity index; Based on the segmented transportation trajectory type, a segmented navigation control strategy for the segmented transportation trajectory of the container trucks is constructed; A smooth transition function is established to perform inter-segment transition connection of the control parameters of the segmented navigation control strategy for trucks to obtain the truck navigation control strategy. The aforementioned truck navigation control strategy is executed to achieve navigation control of the truck transportation segments at the dock.

2. The method of navigation control for a port yard truck transport segment according to claim 1, wherein, The method of dynamically dividing the truck transportation trajectory based on the port digital map information and truck transportation traffic information to obtain segmented truck transportation trajectories includes: Based on the digital map information of the wharf, the path point set of the truck transportation trajectory is extracted, and the feature parameters of each path point are obtained. Based on the feature parameters, a segmentation point decision function is constructed, and the segmentation index of the path point is obtained based on the segmentation point decision function; Determine the segmentation point threshold, and compare the segmentation index with the segmentation point threshold to filter out candidate segmentation points; The candidate segmentation points are dynamically adjusted based on the truck transportation traffic information to determine the final segmentation points; The truck transport trajectory is divided into segmented truck transport trajectories by the final segmentation point.

3. The method of navigation control for a port yard truck transport segment according to claim 2, wherein, The step of constructing the segmentation point decision function based on the feature parameters includes: The feature parameters are evaluated for feature importance to select segmented decision parameters; Dynamic weighting coefficients are obtained based on historical data, and the segmented decision parameters are linearly weighted to construct the segmented point decision function.

4. The method of navigation control for a port yard truck transport segment of claim 1, wherein, The process of obtaining the control complexity index of the segmented transportation trajectory of the container truck, and determining the segmented transportation trajectory type based on the control complexity index, includes: Feature extraction is performed on the segmented transportation trajectory of the container truck to obtain segmented trajectory features; A control complexity evaluation model is constructed based on the segmented trajectory features to obtain the control complexity index; Obtain the type classification threshold, and combine it with the control complexity index to determine the segmented transportation trajectory type of the truck segmented transportation trajectory, including straight segments, turning segments and loading and unloading segments.

5. The method of navigation control for a port yard truck transport segment according to claim 4, wherein, The construction of the control complexity evaluation model based on the segmented trajectory features includes: Based on the segmented trajectory features, trajectory change features are obtained, including the rate of change of curvature, the rate of change of velocity, and the rate of change of orientation angle; Obtain the balance adjustment coefficient and fuse the trajectory change features to construct the control complexity evaluation model.

6. The navigation control method for segmented container truck transportation at a wharf according to claim 1, characterized in that, The method for constructing a segmented navigation control strategy for the segmented transport trajectory based on the segmented transport trajectory type includes: Based on the segmented transportation trajectory type, a navigation control algorithm is determined for the different types of segmented transportation trajectories of the container trucks, and the desired control parameters of the segmented transportation trajectories of the container trucks are obtained; The segmented navigation control strategy for the truck is generated based on the navigation control algorithm and the desired control parameters.

7. The navigation control method for segmented container truck transportation at a wharf according to claim 1, characterized in that, The establishment of a smooth transition function, which connects the control parameters of the segmented navigation control strategy of the truck to obtain the truck navigation control strategy through inter-segment transition, includes: By combining the inter-segment parameter differences and truck dynamics constraints, a smooth transition function based on normalized time variables is constructed. The transition time-space region, including time length and spatial range, is determined based on the segmented navigation control strategy for container trucks. Within the transition spatiotemporal region, an inter-segment parameter transition sequence is generated using the smooth transition function; For adjacent segmented navigation control strategies for container trucks, the control parameters are transitioned and connected according to the inter-segment parameter transition sequence to obtain the container truck navigation control strategy.

8. The navigation control method for segmented container truck transportation at a wharf according to claim 7, characterized in that, The smooth transition function, based on normalized time variables, is constructed by combining the inter-segment parameter differences and truck dynamic constraints, including: The key control parameters to be smoothed are determined based on the inter-segment parameter differences. During the parameter transition period, the maximum allowable rate of change of the key control parameters is obtained based on the truck dynamics constraints; Construct a parameter smooth transition curve that satisfies the maximum allowable rate of change, and map the parameter smooth transition curve to the normalized time domain to construct the smooth transition function.

9. The navigation control method for segmented container truck transportation at a wharf according to claim 1, characterized in that, The execution of the truck navigation control strategy to achieve navigation control of the segmented truck transportation at the terminal includes: During the execution of the truck navigation control strategy, truck operating status data is acquired to determine path tracking error; When the path tracking error exceeds the control safety threshold, a replanning mechanism is triggered to generate the replanning results of the truck segment transportation trajectory and the truck segment navigation control strategy. The truck navigation control strategy is updated based on the replanning results, and the truck navigation control strategy is converted into real-time control commands to realize navigation control of the truck transportation segments at the terminal.

10. A navigation and control system for segmented container truck transportation at a dock, characterized in that, The system includes an input device, an output device, a processor, and a memory, which are interconnected. The memory stores a computer program, which includes program instructions. The processor is configured to invoke the program instructions to execute the navigation control method for a terminal truck transportation segment as described in any one of claims 1-9.

Images