Cooperative control method and system based on port automatic driving mixed driving scene

Abstract

The invention provides a cooperative control method and system based on a port automatic driving mixed driving scene, and relates to the technical field of port traffic management, and the method comprises the steps: firstly obtaining a dynamic interaction data set containing information of multiple aspects such as an automatic driving vehicle and manual driving equipment in a port operation region; and then carrying out association feature extraction on the dynamic interaction data set, generating dynamic association representation data containing traffic participant association relationships and other features, executing collaborative decision analysis based on the dynamic association representation data, and determining a right-of-way priority sequence and a collaborative path planning scheme. And a cooperative control instruction set including speed cooperative parameters and the like is generated according to a cooperative decision analysis result, and finally the cooperative control instruction set is distributed to a corresponding control system, so that dynamic cooperative driving control in a port mixed driving scene is realized, and the port operation efficiency and safety are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of port traffic management, and in particular to a collaborative control method and system based on a mixed traffic scenario of autonomous driving in a port. Background Art

[0002] In port operations, the continuous advancement of automation technology has led to the gradual introduction of autonomous vehicles, creating a complex situation where autonomous vehicles and manually driven vehicles coexist. However, existing port traffic management models, designed primarily for traditional manually driven vehicles, struggle to adapt to the demands of this mixed traffic scenario.

[0003] Currently, the management of traffic participants within ports mostly relies on manual command or simple signal control systems, lacking comprehensive access to and accurate analysis of dynamic information about various traffic participants. When autonomous vehicles and manually driven equipment operate together, the inability to obtain real-time operational data from autonomous vehicles, operational status data from manually driven equipment, and behavioral intention data from traffic participants makes it difficult to accurately judge the relationships and collaborative needs between traffic participants, leading to irrationalities in task scheduling and right-of-way allocation. At the same time, the lack of effective assessment and early warning mechanisms for potential conflict risks can easily lead to traffic accidents, impacting port operational efficiency and safety. Furthermore, existing control methods are unable to provide accurate collaborative path planning and conflict avoidance operating rules for each traffic participant, making it difficult to achieve efficient, safe, and collaborative driving control in mixed traffic scenarios at ports. Summary of the Invention

[0004] In view of the above-mentioned problems, in combination with the first aspect of the present invention, an embodiment of the present invention provides a collaborative control method based on a mixed traffic scenario of autonomous driving in a port, the method comprising: Acquire a dynamic interactive data set within the port operation area, the dynamic interactive data set including real-time operation data of autonomous vehicles, operation status data of manually driven equipment, port operation task scheduling information, and behavioral intention data of traffic participants; Performing correlation feature extraction processing on the dynamic interaction data set to generate dynamic correlation representation data of the port mixed traffic scene, wherein the dynamic correlation representation data includes traffic participant correlation relationship characteristics, task collaboration requirement parameters, and conflict risk assessment indicators; Performing collaborative decision-making analysis based on the dynamic association representation data to determine a right-of-way priority sequence and a collaborative path planning scheme for each traffic participant in the port operation area, wherein the right-of-way priority sequence is generated by sorting the node importance indexes, and the collaborative path planning scheme includes a recommended driving route, an estimated transit time, and conditions for allowing route changes; generate a set of cooperative control instructions according to the priority sequence of the right-of-way and the cooperative path planning scheme, the set of cooperative control instructions including a speed coordination parameter, a path adjustment sequence, and a conflict avoidance operation rule; distribute the set of cooperative control instructions to corresponding traffic participant control systems to perform dynamic cooperative driving control in a port mixed driving scenario.

[0005] In still another aspect, the embodiments of the present application also provide a cooperative control system based on a port automatic driving mixed driving scenario, which comprises a processor and a machine readable storage medium, the machine readable storage medium is connected with the processor, the machine readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the machine readable storage medium to realize the above-mentioned method.

[0006] Based on the above aspects, the embodiments of the present application obtain a set of dynamic interaction data in a port operation area, which covers information such as automatic driving vehicles, manually driven devices, operation task scheduling, and behavior intention of traffic participants, then performs correlation feature extraction processing on the set of dynamic interaction data, the generated dynamic correlation representation data can accurately depict the correlation between traffic participants, task coordination demand and conflict risk, the cooperative decision analysis based on the dynamic correlation representation data can reasonably determine the priority sequence of the right-of-way and the cooperative path planning scheme of each traffic participant, the priority sequence of the right-of-way is generated by sorting the node importance index, which ensures the fairness and rationality of the right-of-way allocation; the cooperative path planning scheme includes a recommended driving path, an estimated passing time and a path change permission condition, thereby providing clear driving guidance. The set of cooperative control instructions generated according to the priority sequence of the right-of-way and the cooperative path planning scheme includes a speed coordination parameter, a path adjustment sequence and a conflict avoidance operation rule, which can effectively guide the traffic participants to perform dynamic cooperative driving control. Finally, the set of cooperative control instructions is distributed to the corresponding traffic participant control systems to realize efficient, safe and orderly dynamic cooperative driving in the port mixed driving scenario, and significantly improve the operation efficiency and safety of the port. BRIEF DESCRIPTION OF DRAWINGS

[0007] Figure 1 is an execution flow diagram of the cooperative control method based on the port automatic driving mixed driving scenario provided by the embodiments of the present application; Figure 2 is a schematic diagram of exemplary hardware and software components of the cooperative control system based on the port automatic driving mixed driving scenario provided by the embodiments of the present application. DETAILED DESCRIPTION

[0008] The present application will be described in detail below with reference to the accompanying drawings, Figure 1is a flowchart of a collaborative control method based on a mixed driving scene of port automatic driving provided by an embodiment of the present application. The following will introduce the collaborative control method based on the mixed driving scene of port automatic driving in detail.

[0009] Step S110: Obtain a dynamic interaction data set in the port operation area, wherein the dynamic interaction data set comprises real-time running data of an automatic driving vehicle, operation state data of a manually driven device, port operation task scheduling information, and behavior intention data of a traffic participant.

[0010] In this embodiment, the port operation area comprises a plurality of container stacking areas, cargo loading and unloading areas, transportation channels, and a plurality of operation berths. There are various traffic participants in the port operation area, including an automatic driving container transport vehicle, an automatic driving tractor trailer, a manually driven forklift, a manually driven truck, a shore-based container crane, a yard crane, and the like.

[0011] The real-time running data of the automatic driving vehicle can be collected through a plurality of sensors installed on the automatic driving vehicle. The plurality of sensors can include a laser radar, a millimeter wave radar, a high-definition camera, a global positioning system receiver, an inertial measurement unit, and the like. The laser radar is used to obtain three-dimensional point cloud data of the environment around the vehicle, which can accurately perceive the position, shape, and distance of the surrounding objects. The millimeter wave radar can work in various weather conditions and continuously monitor the dynamic targets in front of and around the vehicle, providing the relative speed and distance information of the targets. The high-definition camera is used to collect image information of the surrounding environment, which assists in identifying traffic signs, lane lines, and other appearance characteristics of traffic participants. The global positioning system receiver, in combination with the positioning base station deployed in the port, obtains the accurate position coordinates of the vehicle in the port coordinate system. The inertial measurement unit is used to collect motion state data such as acceleration and angular velocity of the vehicle. The real-time running data can specifically include the current position coordinates of the vehicle (based on the three-dimensional coordinate system set in the port operation area), the instantaneous driving speed, the driving direction (represented by the heading angle), the acceleration, the current lane position, the size parameters (length, width, and height) of the vehicle itself, the remaining power reserve (electricity or fuel), the vehicle identification number, and the like. The collected data is transmitted to the port central data processing center through the wireless communication module built-in the vehicle according to the set transmission period.

[0012] Furthermore, the operational status data of manually operated equipment can be acquired through data acquisition devices installed on the manually operated equipment. For example, an operational status sensor can be installed on a manually operated forklift to collect data such as the driver's steering wheel operation, accelerator pedal depression depth, brake pedal pressure, and the lift height and tilt angle of the forklift's forks. Corresponding sensors can be installed on manually operated trucks to collect information such as the vehicle's speed, steering angle, braking status, and gear position. Simultaneously, the real-time location information of the manually operated equipment can be acquired through an on-board positioning device, and the equipment's operating status, such as engine speed and equipment fault information, can be acquired through the equipment's status monitoring module. This operational status data can also be transmitted in real time to a central data processing center via wireless communication.

[0013] Furthermore, port operation task scheduling information can be provided by the port operation management system. This port operation task scheduling information includes the basic content of each operation task, such as the task number, task type (container loading and unloading, cargo transshipment, site preparation, etc.), the starting and destination locations involved in the task, the required completion time range, the traffic participants involved in the task (autonomous driving vehicles or manually driven equipment responsible for performing the task), and the cargo information associated with the task (such as container number, cargo type, weight, size, etc.). In addition, it can also include task priority settings and dependencies between tasks (for example, a transshipment task must be completed before another loading and unloading task can begin). This information is synchronized in real time through the interface between the port operation management system and the central data processing center.

[0014] Traffic participant behavioral intention data can be obtained by analyzing and processing collected real-time operational data and operational status data. For example, for autonomous vehicles, behavioral intentions can be extracted from the vehicle's navigation planning information and real-time control instructions, such as the vehicle's preset driving route, upcoming steering operations, and planned stops. For manually driven equipment, behavioral intentions are inferred by analyzing the driver's operating behavior patterns and the equipment's movement trends. For example, continuously monitored steering operations and speed changes can be used to determine whether a manually driven truck is preparing to turn, change lanes, or dock. Furthermore, combined with port operation task scheduling information, it can assist in determining the behavioral intentions of traffic participants. For example, based on the task target location, the approximate driving direction and destination of the traffic participant can be inferred.

[0015] It is worth noting that during the data acquisition process, sensitive data, such as driver identification information and detailed device operation logs, is desensitized. Sensitive fields are encrypted to remove identifiable information about individuals or specific devices. Encrypted transmission protocols are also used to ensure data security during transmission and prevent data leaks. All collected data is aggregated into a dynamic interactive data set, which is stored in the database of the central data processing center.

[0016] Step S120: performing correlation feature extraction processing on the dynamic interaction data set to generate dynamic correlation representation data of the port mixed traffic scene, wherein the dynamic correlation representation data includes traffic participant correlation relationship characteristics, task collaboration requirement parameters and conflict risk assessment indicators.

[0017] Step S121: parsing the port operation task scheduling information in the dynamic interaction data set, extracting the task attribute parameters of each traffic participant, wherein the task attribute parameters include task urgency, cargo type characteristics, and operation area relevance.

[0018] In this embodiment, when parsing the port operation task scheduling information in the dynamic interaction data set, the task items associated with each traffic participant are first filtered out from the task scheduling information. Each traffic participant may correspond to one or more operation tasks, which need to be parsed one by one.

[0019] To extract task urgency, we analyze the required completion time range and the current time in the task scheduling information. If the gap between the required completion time and the current time is short, the task needs to be executed as soon as possible and has a high urgency; if the gap is long, the urgency is relatively low. Furthermore, considering the task priority setting, tasks with higher priority have a correspondingly higher urgency. Through this analysis, a corresponding task urgency description is determined for each traffic participant's task.

[0020] Cargo type features are extracted based on the cargo information associated with the task scheduling information. Cargo type features include the cargo's physical and categorical properties. For example, for containerized cargo, features include the container's material, whether it is hazardous material (if so, the category of hazardous material must also be specified), and the cargo's intended use (e.g., general cargo, refrigerated cargo, specialty cargo, etc.). For bulk cargo, features include particle size, density, and dust generation. These features are then organized to form cargo type features for each transport participant's task.

[0021] The correlation between work areas is extracted by analyzing the relationship between the task's starting and target locations and the traffic participant's current work area. If the traffic participant's current area is the same as or adjacent to the task's starting or target location, the work area correlation is strong; if the distance is greater, the correlation is weaker. Furthermore, the connection between the different areas of the work processes involved in the task is considered. For example, if the target location of one task is the starting location of another task, and the two tasks are performed by different traffic participants, the correlation between the work areas of the two traffic participants is strengthened due to the connection between the task processes. Through this analysis, the work area correlation parameters of each traffic participant are determined.

[0022] Step S122: constructing a task association matrix based on the task attribute parameters, wherein the task urgency level is positively correlated with the urgency weight value, and the operation area association value is positively correlated with the association value between traffic participants.

[0023] Step S1221: Divide the task urgency in the task attribute parameters into different levels, assign a corresponding urgency weight value to each level, and the urgency weight values ​​corresponding to the task urgency levels increase in order of the levels.

[0024] In this embodiment, when classifying the task urgency, the required completion time interval and the task priority are comprehensively considered. The task urgency is divided into multiple different levels, for example, four levels from low to high.

[0025] For each level, an urgency weight is assigned based on its urgency. The lowest-level task has the smallest urgency weight. As the level increases, the urgency weight increases, with the highest-level task having the largest weight. This ensures that the urgency levels and urgency weights increase in order of rank, allowing tasks with higher urgency to have a greater impact in the correlation calculation when constructing the correlation matrix.

[0026] For example, level 1 (lowest urgency) corresponds to a smaller urgency weight value, level 2 corresponds to a slightly larger weight value than level 1, level 3 has a larger weight value than level 2, and level 4 (highest urgency) has the largest weight value. Through the above level division and weight value allocation, the attribute parameter of task urgency is quantified. Step S1222: Classify the cargo type characteristics in the task attribute parameters and determine the cargo type weight coefficient.

[0027] In this embodiment, cargo classification is based on the handling standards and priority requirements for different cargoes in port operations. First, cargo is divided into broad categories, such as containerized cargo, bulk cargo, and general cargo. Each broad category is then further subdivided. For example, containerized cargo can be subdivided into ordinary containers, refrigerated containers, and dangerous goods containers. Dangerous goods containers can be further subdivided based on the hazard level of the dangerous goods, such as explosives, flammable liquids, and corrosive substances.

[0028] For each subdivided cargo type, a corresponding cargo type weight coefficient is determined based on factors such as the difficulty of handling in port operations, safety requirements, and transportation priority. For example, dangerous goods containers have a relatively large corresponding cargo type weight coefficient due to the higher safety and professionalism required for their transportation and handling; ordinary containers have a relatively small weight coefficient; and refrigerated containers, due to their need to maintain a specific temperature, have a weight coefficient between dangerous goods containers and ordinary containers. Through this classification and weight coefficient determination, the characteristics of cargo types are quantified, so that the impact of different cargo types on the degree of association can be reflected in the construction of the task association matrix.

[0029] Step S1223: Calculate the operation area relevance in the task attribute parameters. The operation area relevance is determined by the normalized distance value between the current operation area of ​​the traffic participant and the target operation area and the operation process dependency.

[0030] In this embodiment, when calculating the relevance of operating areas, the current operating area of ​​the traffic participant and the target operating area for their task are first determined. Using a digitized map of the port's operating area, the coordinate ranges of these two areas are obtained, and the straight-line distance between the centers of the two areas is calculated. The closer the distance, the stronger the spatial relevance.

[0031] At the same time, the dependency relationship of the operation process is analyzed. If, after the task currently performed by a traffic participant is completed, the output of its operation area is the input of another task (performed by other traffic participants), and the operation area of ​​the other task is the target operation area of ​​the current task, then the operation areas of these two traffic participants have a strong dependency relationship due to the connection of the operation process, and the correlation of the operation areas is correspondingly high.

[0032] Taking into account both distance and process dependencies, each is assigned a specific weight. The correlation values ​​corresponding to distance and process dependencies are weighted together to arrive at the final work area correlation value. For example, closer distances are associated with greater distance correlation values; stronger process dependencies are associated with greater correlation values. This weighted calculation yields a comprehensive work area correlation.

[0033] Step S1224: Constructing a task attribute comprehensive weight based on the urgency weight value, cargo type weight coefficient and operation area relevance score. The task attribute comprehensive weight is a weighted sum of the urgency weight value, cargo type weight coefficient and operation area relevance score.

[0034] In this embodiment, when constructing the comprehensive weight of task attributes, a weight coefficient is first assigned to each of the urgency weight value, cargo type weight coefficient, and work area relevance. The weight coefficients are determined based on the importance of these three parameters in the task association. For example, if task urgency is more important in the task association, a larger weight coefficient is assigned to it; if the work area relevance is less important, a smaller weight coefficient is assigned to it.

[0035] Then, multiply the urgency weight value by its corresponding weight coefficient to obtain the contribution value of the urgency in the comprehensive weight; similarly, multiply the cargo type weight coefficient by its corresponding weight coefficient to obtain the contribution value of the cargo type in the comprehensive weight; multiply the operation area relevance by its corresponding weight coefficient to obtain the contribution value of the operation area relevance in the comprehensive weight.

[0036] Finally, the three contribution values ​​are summed up to obtain the task attribute comprehensive weight. Through the above weighted summation method, the three different task attribute parameters are integrated into a comprehensive weight value for use in the subsequent construction of the task association matrix.

[0037] Step S1225: Using the traffic participants in the port operation area as matrix rows and matrix columns, and the product of the comprehensive weights of the task attributes of any two traffic participants as the matrix element value, an initial task association matrix is ​​constructed.

[0038] In this embodiment, when constructing the initial task association matrix, all traffic participants within the port's operating area are listed and each participant is assigned a unique identification number. These identification numbers serve as the row and column indices of the initial task association matrix, meaning each row and column of the matrix corresponds to a traffic participant.

[0039] For each element in the initial task association matrix, the row corresponding to traffic participant A and the column corresponding to traffic participant B are calculated by multiplying the combined weight of traffic participant A's task attributes by the combined weight of traffic participant B's task attributes. Following this method, the products of all the traffic participants corresponding to the rows and columns are calculated and filled into the corresponding positions in the matrix, thus constructing the initial task association matrix.

[0040] For example, if the comprehensive weight of the task attributes of traffic participant 1 is W1, and the comprehensive weight of the task attributes of traffic participant 2 is W2, then the element value in the first row and second column of the matrix is ​​W1 multiplied by W2, and the element value in the second row and first column is W2 multiplied by W1, and so on, to complete the construction of the entire initial task association matrix.

[0041] Step S1226: Normalize the initial task association matrix, and adjust the normalized task association matrix according to the port operation rules and historical collaborative data, increase the association value between traffic participants with direct operation process association, and reduce the association value between traffic participants without operation association, to obtain the final task association matrix.

[0042] In this embodiment, when normalizing the initial task association matrix, the maximum and minimum values ​​of all elements in the initial task association matrix are first found. Then, each element in the matrix is ​​processed according to a normalization formula, converting the element value to a set numerical range (e.g., between 0 and 1). The purpose of normalization is to eliminate the influence of different magnitudes and make the element values ​​in the initial task association matrix comparable.

[0043] After normalization, the matrix is ​​adjusted based on port operation rules. For example, port operation rules may require fixed operational connections between certain transport participants, such as when a quayside container crane lifts a container onto an autonomous container transporter. Therefore, the corresponding element value in the initial task association matrix needs to be increased to reflect this stronger connection.

[0044] At the same time, referring to historical collaborative data, the matrix element values ​​of traffic participant pairs that often work together and have close connections in historical operations are appropriately increased; while for those traffic participant pairs that have no connection in the operation process and have rarely had collaborative interactions in history, their matrix element values ​​are reduced.

[0045] Therefore, through the above adjustments, the task correlation matrix can more accurately reflect the actual correlation between traffic participants, and the final task correlation matrix is ​​obtained.

[0046] Step S123: extracting the traffic participant behavior intention data from the dynamic interaction data set, and identifying the driving intention category of each traffic participant, wherein the driving intention category includes straight-through, turning operation, parking operation and emergency avoidance.

[0047] In this embodiment, after extracting the traffic participant behavior intention data, the traffic participant behavior intention data is analyzed to identify the driving intention category. For an autonomous vehicle, its behavior intention data is contained in the preset navigation path and real-time control instructions. By analyzing the above behavior intention data, if the vehicle is straight driving according to the current path and there is no steering instruction, it is identified as straight driving. If the vehicle is detected to have a steering control signal and the navigation path shows that the direction will be changed soon, it is identified as a steering operation. If the vehicle receives an instruction to stop at a specific location and is gradually slowing down to approach the location, it is identified as a parking operation. If the vehicle detects an emergency obstacle and has control actions such as sudden deceleration and sharp steering, it is identified as emergency avoidance.

[0048] For a manually driven device, by analyzing its operation state data and motion trajectory, if the device maintains a straight driving state and the steering operation amount is zero or very small, it is identified as straight driving. If a large steering operation amount is detected and the driving direction of the device is changing, it is identified as a steering operation. If the device is gradually decelerating and finally stops at a specified work point (such as a loading and unloading area or a parking space), and combined with the parking requirements of the device in the task scheduling information, it is identified as a parking operation. If the device suddenly decelerates greatly and frequently changes direction during driving, and there are sudden obstacles around it (such as other devices suddenly entering or falling goods), it is identified as emergency avoidance.

[0049] In the identification process, for a manually driven device, it also needs to be combined with its historical driving behavior pattern for auxiliary judgment. For example, a certain manually driven forklift usually slows down before turning to park when approaching a specific loading and unloading area in past operations. When similar speed and steering changes are detected again, it can be more accurately identified as a parking operation. Through the above method, the driving intention categories of all traffic participants are identified, and the identification results are stored as structured data and associated with the identification information of the traffic participants.

[0050] Step S124: determining the potential interaction relationship between the traffic participants according to the driving intention category, the potential interaction relationship including cross driving, converging driving, following driving and parallel driving.

[0051] Step S1241: constructing a driving intention interaction rule library, the driving intention interaction rule library including potential interaction relationship judgment rules corresponding to different driving intention category combinations.

[0052] In this embodiment, when constructing the driving intention interaction rule base, all possible driving intention category combinations are first shared. Since driving intention categories include straight-through, turning, stopping, and emergency avoidance, possible combinations include straight-through and straight-through, straight-through and turning, straight-through and stopping, straight-through and emergency avoidance, turning and turning, turning and stopping, turning and emergency avoidance, stopping and stopping, stopping and emergency avoidance, and emergency avoidance and emergency avoidance.

[0053] For each combination of driving intention categories, corresponding potential interaction relationship judgment rules can be constructed based on the driving characteristics and interaction patterns of traffic participants in port operation scenarios. For example, for the combination of "straight through" and "straight through," if the driving routes of the two traffic participants intersect and are likely to reach the intersection within a preset time, a potential interaction relationship of crossing driving is determined to exist; if the driving routes are parallel, in the same direction, and at similar speeds, a potential interaction relationship of parallel driving is determined to exist; if the driving routes are in the same direction and follow each other, a potential interaction relationship of car-following driving is determined to exist.

[0054] For the combination of straight-through and turning operations, if the turning route of the traffic participant performing the turning operation intersects with the driving route of the traffic participant passing through straight, it is judged that there is a potential interactive relationship of intersecting driving; if the driving routes of the two tend to be consistent after the turning operation and there is a converging point, it is judged that there is a potential interactive relationship of merging driving.

[0055] For a combination of steering operations, if the steering directions of the two cause the driving routes to intersect, it is determined that there is a potential interactive relationship of cross-driving; if the driving routes are in the same direction after turning and form a front-to-back following, it is determined that there is a potential interactive relationship of following driving.

[0056] For other combinations, such as stopping and going straight, if the driving route of the traffic participant going straight passes near the stopping area where the traffic participant is stopping, there may be potential interference interaction, which needs to be further judged based on the specific distance and speed.

[0057] These rules are systematically organized to clarify the judgment conditions for different potential interaction relationships under each combination (such as route intersection, distance range, speed relationship, etc.), forming a structured driving intention interaction rule library, which is stored in the rule database of the central data processing center for subsequent reference when judging potential interaction relationships.

[0058] Step S1242: For any two traffic participants in the port operation area, obtain their driving intention category combination.

[0059] In this embodiment, when obtaining the driving intention category combination of any two traffic participants, all traffic participants in the port operation area are first traversed to form a list of traffic participant pairs to ensure that each pair of traffic participants is covered without duplication.

[0060] For each pair of traffic participants in the traffic participant pair list (e.g., traffic participants E and F), extract the driving intention categories of E and F from the identified driving intention category data. For example, if E's driving intention category is "straight through" and F's driving intention category is "turning maneuver," then the combination of the two is "straight through" and "turning maneuver."

[0061] The extracted driving intention category combinations are associated with the identification information of the traffic participant pairs (such as the identification numbers of E and F) and stored to form a dataset containing all traffic participant pairs and their corresponding driving intention category combinations.

[0062] Step S1243: Match the driving intention category combination with the driving intention interaction rules in the driving intention interaction rule library to determine a preliminary judgment result of the corresponding potential interaction relationship.

[0063] In this embodiment, when performing a matching operation, for each pair of traffic participant driving intention category combinations, the corresponding judgment rule is retrieved from the driving intention interaction rule library. For example, for the combination of a straight-through and a turn operation, the corresponding rule retrieved is: "If the turning route of the turning traffic participant intersects the driving route of the straight-through traffic participant, a potential interaction relationship of crossing driving is determined; if the routes merge after the turn, a potential interaction relationship of merging driving is determined."

[0064] Then, based on the judgment conditions in the rule and the real-time driving route information of the traffic participants (extracted from the dynamic interaction data set), the conditions are verified. If the turning route of traffic participant F (turning operation) intersects with the driving route of traffic participant E (going straight), a potential interaction relationship of crossing driving is preliminarily determined. If the route after F turns and the route of E merge at a certain point, a potential interaction relationship of merging driving is preliminarily determined.

[0065] The potential interaction relationship type obtained by matching is recorded as the preliminary judgment result, and the rule items and verification condition information based on the matching process are recorded at the same time for reference in the subsequent verification of the authenticity of the potential interaction relationship.

[0066] Step S1244: extracting the real-time location data and movement direction data of the traffic participants from the dynamic interaction data set, and combining the preliminary judgment result of the potential interaction relationship to verify the authenticity of the potential interaction relationship.

[0067] In this embodiment, after extracting the real-time position data (such as coordinate values in the port coordinate system) and the motion direction data (such as the heading angle) of the traffic participants, the authenticity of the potential interaction relationship is verified for each pair of traffic participants with the preliminary judgment result.

[0068] For example, for traffic participants E and F preliminarily judged to have a cross-driving potential interaction relationship, the current position coordinates of the two are calculated through the real-time position data, and the driving trajectories of the two in a future period of time are simulated in combination with the motion direction data. If the simulated trajectories show that the two will indeed meet at the intersection, and the meeting time is within a reasonable range (such as the time difference between the arrival of the two at the intersection being within a preset time threshold), it is indicated that the cross-driving potential interaction relationship preliminarily judged has high authenticity; if the simulated trajectories show that the two will not arrive at the same intersection, or the time difference is too large, it is indicated that the preliminary judgment result may be inaccurate and needs to be further verified.

[0069] For traffic participants preliminarily judged to have a merging potential interaction relationship, it is verified whether the driving trajectories of the two will converge at a preset merging point, and whether the speed and distance at the time of merging conform to the characteristics of merging; for a preliminary judgment of following driving, it is verified whether the two maintain the same direction of driving, and whether the distance between the following vehicle and the leading vehicle is within the following distance range; for a preliminary judgment of parallel driving, it is verified whether the driving routes of the two are parallel, the directions are consistent, and the speeds are similar.

[0070] Through the above verification process, the preliminary judgment results that do not conform to the actual driving situation are eliminated, and the preliminary judgment results of the real and effective potential interaction relationship are retained.

[0071] Step S1245: If the real-time position data and the motion direction data of the two traffic participants indicate that they will be in the same area within a preset time, it is confirmed that the potential interaction relationship is established.

[0072] In this embodiment, when judging whether the two traffic participants will be in the same area within a preset time, the driving trajectory ranges of the two within the preset time are first predicted according to their real-time position data and motion direction data. The preset time is set according to the general driving speed of the traffic participants in the port operation area and the size of the area, and the principle is to effectively judge whether there is an interaction possibility.

[0073] Then, it is calculated whether the predicted trajectory ranges of the two traffic participants have an overlapping area, i.e., the same area. If there is an overlapping area, and the time when the two arrive at the area is within the preset time, it is confirmed that the preliminary judgment of the potential interaction relationship is established. For example, the predicted trajectories of traffic participants G and H both cover a certain specific area (such as the range of a certain intersection) within the preset time, and it is confirmed that the potential interaction relationship between them is established.

[0074] If there is no overlap in the predicted trajectory range, or the time it takes for one party to reach the overlapping area exceeds the preset time, the potential interaction relationship is not confirmed. Through the above judgment, the actual potential interaction relationship is further screened.

[0075] Step S1246: The interaction strength of the confirmed potential interaction relationship is evaluated by the ratio of the distance between the traffic participants to the relative speed to obtain an interaction strength value.

[0076] In this embodiment, when performing interaction intensity assessment, the real-time distance data (extracted from the dynamic interaction data set, which is the straight-line distance between the current positions of the two) and relative speed data (calculated based on the movement direction and driving speed of the two, that is, the size of the speed vector difference between the two) of the two traffic participants involved in the confirmed potential interaction relationship are first obtained.

[0077] Then, the ratio of the distance between the two participants to their relative speed is calculated. This ratio reflects the approximate time it takes for the two participants to reach each other's current locations. A smaller ratio indicates a closer interaction and a higher interaction intensity; a larger ratio indicates a longer interaction and a lower interaction intensity. This ratio is used as the interaction intensity value, with a smaller value indicating a higher interaction intensity.

[0078] For example, if the distance between traffic participants I and J is D and their relative speed is V (V is not zero), the interaction intensity value is D divided by V. If D is small and V is large, the interaction intensity value is small, indicating that the interaction intensity between the two is high.

[0079] Step S1247: Mark the potential interaction relationship with an interaction strength value greater than a preset threshold as a primary potential interaction relationship, and mark the potential interaction relationship with an interaction strength value less than or equal to the preset threshold as a secondary potential interaction relationship.

[0080] In this embodiment, the preset threshold is determined based on the average speed of traffic participants within the port operation area, distance characteristics of typical interaction scenarios, and safety requirements. By analyzing historical interaction data for interactions that lead to conflicts or require focused coordination, a reasonable threshold range is determined, ensuring that potential interactions with interaction strength values ​​less than or equal to the preset threshold are generally prioritized and addressed.

[0081] For example, after analysis, the preset threshold is determined to be T. For potential interaction relationships with an interaction intensity value of S, if S is less than or equal to T, it is marked as a primary potential interaction relationship, indicating that the interaction relationship is more urgent and needs to be considered in subsequent collaborative decision-making; if S is greater than T, it is marked as a secondary potential interaction relationship, indicating that the interaction relationship is relatively mild and can be considered as a secondary factor in collaborative decision-making.

[0082] After the marking is completed, the marking results of each potential interaction relationship are recorded and stored in association with information such as traffic participant pairs and interaction types.

[0083] Step S1248: Record the primary potential interaction relationships and secondary potential interaction relationships between all traffic participants in the port operation area, and establish a potential interaction relationship list.

[0084] In this embodiment, when creating a potential interaction relationship list, all marked primary and secondary potential interaction relationships are summarized. Each entry in the potential interaction relationship list includes information such as the identifier of the traffic participant pair (e.g., the identification numbers of the two traffic participants), the potential interaction relationship type (e.g., crossing, merging, etc.), the interaction strength value, the marking type (primary or secondary), and the basis for confirmation (e.g., verification results of real-time location and movement direction data).

[0085] The list is structured and organized, either by interaction intensity, from highest to lowest or vice versa, or by interaction type, allowing for quick query and use of relevant information when extracting relationship features for traffic participants. Furthermore, an indexing mechanism for the list of potential interactions is established, allowing for quick retrieval of all potential interactions involving a traffic participant using their identification number, improving data query efficiency.

[0086] Step S125: generating a traffic participant association relationship feature by combining the task association matrix and the potential interaction relationship, wherein the traffic participant association relationship feature is used to describe the degree of interaction between different traffic participants during the task execution process.

[0087] In this embodiment, when generating traffic participant association features by combining the task association matrix and potential interaction relationships, the association value of each pair of traffic participants (i.e., the corresponding element value in the matrix) is first extracted from the task association matrix. The association value reflects the degree of association between the two in terms of task attributes.

[0088] Then, the potential interaction relationship information of the pair of traffic participants is extracted from the potential interaction relationship list, including the interaction type, interaction strength value, and mark type (primary or secondary). For primary potential interaction relationships, a higher interaction influence weight is assigned, while for secondary potential interaction relationships, a lower interaction influence weight is assigned.

[0089] The correlation value of the task correlation matrix is ​​weighted and fused with the interaction influence weight of the potential interaction relationship (for example, multiplying the correlation value by the corresponding interaction influence weight) to obtain a comprehensive correlation value. At the same time, the interaction strength value is taken into account. The smaller the interaction strength value (the more urgent the interaction), the larger the correction coefficient for the comprehensive correlation value, which further improves the comprehensive correlation value; conversely, the correction coefficient is smaller.

[0090] Furthermore, the comprehensive correlation value can be further adjusted based on the historical interaction frequency and interaction quality between traffic participants (such as whether conflicts have occurred and the efficiency of coordination). For traffic participant pairs with high historical interaction frequency and good coordination, their comprehensive correlation value will be appropriately increased; otherwise, it will be appropriately decreased.

[0091] The final comprehensive correlation value and its corresponding information such as interaction type and marking type together constitute the traffic participant correlation feature, which comprehensively reflects the degree of interaction between different traffic participants during the task execution process, including two factors: task attribute correlation and actual driving interaction.

[0092] Step S126: Analyze the real-time operation data of the autonomous driving vehicle and the operation status data of the manual driving equipment in the dynamic interaction data set, and extract the task collaboration requirement parameters, which include task completion time requirements, path overlap and resource sharing requirements.

[0093] In this embodiment, when analyzing the relevant data in the dynamic interaction data set to extract the task collaboration requirement parameters, first, based on the task completion time requirement, the required completion time of the task performed by each traffic participant is obtained from the port operation task scheduling information. Combined with the current time, the remaining task completion time is calculated, and the remaining time is used as the parameter value of the task completion time requirement. The smaller the parameter value, the more urgent the task and the higher the collaboration requirement.

[0094] For path overlap, the planned driving paths of each traffic participant are extracted (derived from navigation information for autonomous vehicles, and inferred by manual driving equipment based on the mission's starting point, destination, and historical driving routes). Each path is then broken down into multiple continuous segments (for example, using landmark locations within a port operating area as nodes). The ratio of the length of the overlapping segments in the paths of any two traffic participants to the total length of their respective paths is then calculated. The smaller or average of the two ratios is used as the path overlap parameter for the two traffic participants. A larger value indicates a greater degree of overlap in the driving paths of the two participants, and a greater need for collaborative path planning.

[0095] Resource sharing requirements are analyzed by analyzing the cargo information associated with the tasks and the resource capabilities of the transport participants. For example, if two transport participants perform tasks involving different aspects of the same cargo shipment (e.g., one responsible for transportation, the other for loading and unloading), and the use of loading and unloading equipment must be coordinated with the arrival of the transport vehicle, then there is a need for equipment resource sharing. If multiple transport participants need to use the same operating area (e.g., the same loading and unloading bay), then there is a need for site resource sharing. Based on the necessity and closeness of resource sharing, the resource sharing requirement is quantified, for example, using a resource sharing coefficient. A larger resource sharing coefficient indicates a higher demand for resource sharing.

[0096] The three parameters of task completion time requirement, path overlap and resource sharing requirement are integrated to form the task collaboration requirement parameters. Each parameter is associated with the corresponding traffic participant or traffic participant pair for subsequent use in collaborative decision-making analysis.

[0097] Step S127: Construct a conflict risk assessment model based on the relationship characteristics of the traffic participants and the task collaboration requirement parameters, and calculate the conflict risk assessment index between each traffic participant through the conflict risk assessment model. The conflict risk assessment index is used to characterize the possibility and severity of conflict between traffic participants during driving.

[0098] In this embodiment, when constructing a conflict risk assessment model, the model's input variables are first determined to be the relationship characteristics of traffic participants (e.g., comprehensive relationship values, interaction types, etc.) and task coordination requirement parameters (e.g., task completion time requirements, path overlap, etc.). Next, an appropriate model structure is selected, perhaps employing a machine learning model trained on historical data (e.g., a neural network model). This machine learning model establishes a mapping relationship between the input variables and conflict risk by studying historical case data of conflicts between traffic participants.

[0099] The conflict risk assessment model's training data is derived from historical conflict records within the port's operational area, along with corresponding traffic participant relationship characteristics and task coordination requirement parameters. During training, the model uses the likelihood of a conflict (e.g., whether it will occur) and severity (e.g., the magnitude of damage caused by the conflict and the scope of its impact) as labels. By adjusting the model's parameters, the model accurately predicts conflict risk.

[0100] In the conflict risk assessment model, the correlation feature and the task coordination demand parameter of the traffic participants to be evaluated are input into the trained conflict risk assessment model, and the conflict risk assessment model outputs the corresponding conflict risk assessment index. The conflict risk assessment index can include two parts, one part is the probability value of the conflict, and the other part is the severity level or quantitative value after the conflict, and the two parts comprehensively represent the conflict risk between the traffic participants.

[0101] For example, for traffic participants K and L, their comprehensive correlation value, path coincidence degree, task completion time requirement, etc. are input into the conflict risk assessment model, the conflict risk assessment model outputs the probability of conflict P and the severity S, and the conflict risk assessment index between K and L is (P, S). Through the two values, the risk condition of the conflict between the two in the driving process can be judged.

[0102] Step S128: Fusion of the traffic participant correlation feature, the task coordination demand parameter and the conflict risk assessment index to generate dynamic correlation representation data.

[0103] In this embodiment, when the dynamic correlation representation data is generated by fusing the above three parts of data, the structure and feature dimension of each part of data are first determined. The traffic participant correlation feature exists in the form of a matrix and a list, the matrix represents the correlation degree between all traffic participants, and the list clearly shows the main and secondary potential interaction relationship; the task coordination demand parameter includes multiple sub-parameters, each sub-parameter has its corresponding description and quantitative value; the conflict risk assessment index also consists of multiple evaluation items, each evaluation item corresponds to the risk situation of different traffic participant combinations.

[0104] Then, the feature alignment processing is performed on the above three parts of data. Taking the unique identifier of the traffic participant as the benchmark, the correlation degree value and the potential interaction relationship information related to each traffic participant in the traffic participant correlation feature are matched with the task coordination demand parameter and the conflict risk assessment index corresponding to the traffic participant, so that the related data of the same traffic participant can be accurately corresponded.

[0105] Then, the fusion is performed in the feature splicing manner. The matrix data in the traffic participant correlation feature is converted into a vector form, each traffic participant corresponds to a correlation relationship vector, and the elements in the vector include the correlation degree value and the interaction relationship type identifier of the traffic participant and all other traffic participants; each sub-parameter in the task coordination demand parameter is arranged in a predetermined order to form a task coordination demand vector; similarly, each evaluation item in the conflict risk assessment index is arranged in order to form a conflict risk vector.

[0106] After that, the association relationship vector, the task coordination demand vector and the conflict risk vector of each traffic participant are spliced to form the comprehensive feature vector of the traffic participant. For example, for traffic participant A, the association relationship vector is V1, the task coordination demand vector is V2, and the conflict risk vector is V3. After splicing, the comprehensive feature vector formed is [all elements of V1, all elements of V2, and all elements of V3].

[0107] In the splicing process, it is necessary to ensure that the dimensions of the vectors can be correctly connected and there is no dimension conflict. At the same time, in order to facilitate the subsequent processing of the data by the collaborative decision analysis, the comprehensive feature vector after splicing can be standardized in format, and the storage format and coding method of the data can be unified.

[0108] Finally, the comprehensive feature vectors of all traffic participants are summarized to form a set containing the dynamic association information of all traffic participants in the entire port operation area, i.e. the dynamic association representation data. The dynamic association representation data completely retains the association relationship, coordination demand and conflict risk information between the traffic participants, and the information is interrelated, which can fully reflect the dynamic characteristics of the port mixed running scene.

[0109] Step S130: performing collaborative decision analysis based on the dynamic association representation data to determine the priority sequence of the traffic right of each traffic participant in the port operation area and the collaborative path planning scheme, the priority sequence of the traffic right being generated by sorting the node importance index, and the collaborative path planning scheme including the recommended driving path, the expected passing time and the path change permission condition.

[0110] Step S131: analyzing the traffic participant association relationship characteristics in the dynamic association representation data to determine the association influence range of each traffic participant, the association influence range including other traffic participants having main potential interaction relationship with the traffic participant.

[0111] In this embodiment, when analyzing the traffic participant association relationship characteristics in the dynamic association representation data, the main potential interaction relationship list and the association degree value are focused on. For each traffic participant, all other traffic participants having main potential interaction relationship with the traffic participant are selected from the main potential interaction relationship list.

[0112] Then, taking the real-time position distribution of the other traffic participants as a reference, and in combination with the geographical layout of the port operation area, the associated influence range of the traffic participant is determined. The associated influence range not only includes the area where the other traffic participants are currently located, but also includes the area that they can reach within a preset time period. For example, if traffic participant B has a main potential interaction relationship with traffic participant A, and traffic participant B is driving in a certain direction at a certain speed, the associated influence range of traffic participant A will cover the current position of traffic participant B and the area that traffic participant B can travel to in the future.

[0113] Meanwhile, the size of the associated influence range is also related to the correlation value. The higher the correlation value of the other traffic participant, the greater the weight of the other traffic participant in the associated influence range, and the greater the proportion of the corresponding area in the associated influence range. Through the above-mentioned manner, the associated influence range of each traffic participant is accurately determined, and the other traffic participants that need to be considered in the collaborative decision-making are clearly determined.

[0114] Step S132: Construct a traffic participant collaborative network based on the associated influence range, wherein the nodes in the traffic participant collaborative network are traffic participants, the edges between the nodes represent the correlation relationships between the traffic participants, and the weights of the edges are correlation values.

[0115] Step S1321: Take each traffic participant in the port operation area as an independent node, assign a unique identifier to each node, and implement the identifier to contain traffic participant type information and task number information.

[0116] In this embodiment, when assigning a unique identifier to each traffic participant, a hierarchical coding structure is adopted. The first two characters of the identifier represent the type of the traffic participant, such as “AV” representing an autonomous vehicle, “MV” representing a manually driven device, “QC” representing a shore-based container crane, and “YG” representing a yard bridge; the middle four digits represent the device number of the traffic participant, which is used to distinguish different devices under the same type; and the last six digits represent the task number of the current execution, which is consistent with the task number in the port operation task scheduling information. For example, the identifier “AV0001T202305” indicates that the autonomous vehicle numbered 0001 is executing the operation task numbered T202305. Through this coding method, the core attribute information of the traffic participant can be intuitively obtained from the identifier, which is convenient for subsequent management and analysis of the collaborative network.

[0117] Step S1322: For each traffic participant node, find other traffic participant nodes that have a main potential interaction relationship within the associated influence range of the traffic participant node.

[0118] In this embodiment, when searching for the main potential interaction relationship nodes, the potential interaction relationship list established in step S1248 is first called, and the identifier of the current traffic participant node is used as the index to filter out the entries marked as "main potential interaction relationship". Then, in combination with the geographical boundary of the associated influence range determined in step S131, the filtered entries are spatially verified to eliminate traffic participant nodes that are marked as main potential interaction relationships but whose actual locations are beyond the associated influence range. For example, the associated influence range of traffic participant A is a circular area with a radius of 50 meters and its current position as the center. By comparing the position coordinates, the traffic participant nodes outside the area in the potential interaction relationship list are excluded, and only the nodes within the area are retained as associated nodes.

[0119] Step S1323: establishing a connection edge between the traffic participant node and other traffic participant nodes within its associated influence range, where the direction of the connection edge represents the direction of the interactive influence.

[0120] In this embodiment, when establishing connecting edges, directed edges are used to represent the direction of interaction. If the driving trajectory of traffic participant B affects the driving decision of traffic participant A (e.g., B is located in front of A), a directed edge is established from B to A. If there is a mutual influence between the two (e.g., a two-way meeting at an intersection), a bidirectional directed edge is established. The establishment of connecting edges is based on real-time motion state analysis, and the direction of influence is determined by calculating the relative position vector and motion trend prediction. For example, when A is approaching B's parking area, B's parking state will affect A's passing decision, so a directed edge is established from B to A. When A and B are traveling in the same lane and in the same direction at a close distance, there is a mutual influence between the two, and a bidirectional directed edge is established.

[0121] Step S1324: Determine the weight value of the connecting edge according to the association value between the traffic participants.

[0122] In this embodiment, the weight value of the connecting edge directly adopts the comprehensive correlation value in the traffic participant association relationship feature generated in step S125. This value has integrated the correlation value of the task association matrix and the interaction intensity of the potential interaction relationship, and the value range is between 0 and 1 after normalization. The larger the comprehensive correlation value, the higher the weight value of the connecting edge, indicating that the degree of association between the two is closer. For example, if the comprehensive correlation value of traffic participants C and D is 0.85, the weight value of the connecting edge between the two is set to 0.85; if the comprehensive correlation value of traffic participants E and F is 0.32, the weight value of the connecting edge is 0.32. The weight value is accurate to two decimal places to ensure that the quantitative accuracy meets the requirements of collaborative decision-making.

[0123] Step S1325: adding attribute labels to the connection edges in the traffic participant collaborative network, wherein the attribute labels include interaction relationship type, interaction intensity, and interaction duration.

[0124] In this embodiment, attribute labels are added based on a list of potential interaction relationships and real-time monitoring data. The interaction relationship type label directly uses the type determined in step S124, such as "crossing," "merging," "following," and "parallel." The interaction intensity label uses the interaction intensity value calculated in step S1246, retaining the original calculation result to reflect the actual urgency of the interaction. The interaction duration label is determined by predicting the time difference between traffic participants entering and leaving the interaction area. For example, if the time interval between A and B entering the interaction influence area and leaving is predicted to be 3 minutes, the interaction duration label is "180 seconds." All attribute labels are stored as key-value pairs in the attribute field of the connecting edge, facilitating the rapid extraction of key information by the network analysis algorithm.

[0125] Step S1326: Perform a topological structure analysis on the traffic participant collaborative network to identify key nodes and key paths. The key nodes are traffic participant nodes that have connecting edges with multiple other nodes, and the key paths are connecting edge sequences connecting multiple key nodes.

[0126] In this embodiment, the topology analysis adopts a complex network analysis algorithm. The identification of key nodes is achieved by calculating the degree centrality of the node. The degree centrality is the number of connected edges owned by the node. The nodes ranked in the top 20% of the degree centrality are marked as key nodes. For example, if there are 50 nodes in the network, the 10 nodes with the highest degree centrality are selected as key nodes. These nodes are usually core equipment or hub traffic participants in busy operation areas. The identification of critical paths adopts the shortest path algorithm. The weight value of the connection edge is used as the path cost. The path sequence with the largest number of key nodes is searched. The more key nodes contained in the path and the larger the total weight value, the more critical the path. For example, if the path sequence connecting the shore crane, the main transport channel, and the yard bridge contains 3 key nodes and has the highest total weight value, it is identified as a critical path.

[0127] Step S1327: After performing spatial constraint processing on the traffic participant collaborative network according to the physical layout of the port operation area, the constructed traffic participant collaborative network is visualized to generate the traffic participant collaborative network.

[0128] In this embodiment, spatial constraint processing maps the abstract location of network nodes to the actual geographic coordinates of the port. Through the coordinate conversion of the port electronic map, the identifier of each traffic participant node is associated with its real-time GPS coordinates to ensure that the relative position of the node in the network is consistent with the physical layout of the actual operation area. For example, the traffic participant node located in Area A of the container yard is positioned within the coordinate range of Area A of the map, and the nodes located in the transport channel are distributed along the axis of the channel. The visualization processing adopts layered rendering technology, with the port electronic map as the base map. Key nodes are highlighted in red, ordinary nodes are displayed in blue, the line width of the connecting edge becomes thicker as the weight value increases, and the direction of the directed edge is indicated by an arrow. At the same time, the detailed attribute labels of any node or connecting edge can be viewed through the interactive control, and the generated visual network can be refreshed in real time, supporting managers to intuitively grasp the coordinated status of port traffic.

[0129] Step S133: Analyze the task collaboration requirement parameters in the dynamic association representation data, extract the task completion time requirement and path overlap, and determine the traffic participant combination whose task completion time requirement value is less than a first set value and whose path overlap value is greater than a second set value as the key object of collaborative decision-making.

[0130] In this embodiment, when analyzing the task coordination requirement parameters in the dynamic association representation data, the two sub-parameters, task completion time requirement and path overlap, are first extracted from the parameter set. The task completion time requirement reflects the urgency of task completion, while path overlap reflects the degree of overlap between the travel paths of different traffic participants.

[0131] For each participant combination (composed of two or more associated participants), the task completion time requirement and the degree of path overlap between each participant in the combination are obtained. The task completion time requirement is then compared with a first set value, while the path overlap is compared with a second set value.

[0132] If a particular traffic participant combination's task completion time requirement is less than the first set value, it indicates a tight deadline for completion. If its path overlap is greater than the second set value, it indicates significant overlap and potential conflicts. Traffic participant combinations meeting these two conditions warrant special attention and processing in collaborative decision-making, and are therefore designated as key targets for collaborative decision-making.

[0133] Through the above screening, limited decision-making resources can be concentrated on the combination of traffic participants that most needs collaborative processing, thereby improving the efficiency and pertinence of collaborative decision-making.

[0134] Step S134: performing importance evaluation on the nodes in the traffic participant collaborative network, preliminarily determining the right-of-way priority ranking of the traffic participants based on the node importance evaluation results, and obtaining a first right-of-way priority ranking result.

[0135] In this embodiment, a combination of multiple evaluation indicators is used to evaluate the importance of nodes in the collaborative network of traffic participants. First, the degree centrality of a node is considered, that is, the number of connections between the node and other nodes. The more connections there are, the more extensive the connections between the traffic participant and other traffic participants, and the higher the degree centrality.

[0136] Secondly, consider betweenness centrality. Betweenness centrality reflects the degree to which the node acts as a path intermediary between other nodes in the entire network. Nodes with high betweenness centrality play a key intermediary role in network information transmission and interaction.

[0137] Consider closeness centrality again. Closeness centrality measures the average distance between the node and all other nodes in the network. The shorter the average distance, the higher the closeness centrality, indicating that the traffic participant can quickly interact with other traffic participants.

[0138] In addition, the comprehensive weight of the task attributes of the traffic participants corresponding to the nodes is also considered. The nodes with large comprehensive weight of task attributes are relatively more important.

[0139] These evaluation indicators are assigned specific weights, and a weighted calculation is performed to obtain the comprehensive importance index of each node. All traffic participants are then ranked from high to low according to their comprehensive importance index to obtain the first right-of-way priority ranking result.

[0140] For example, if the comprehensive importance index of node A obtained by weighted calculation of its degree centrality, betweenness centrality, closeness centrality and the comprehensive weight of task attributes is the highest, then in the first right-of-way priority sorting result, traffic participant A is ranked first, and so on.

[0141] Step S135: adjusting the first right-of-way priority ranking result in combination with the conflict risk assessment index in the dynamic association representation data to obtain a second right-of-way priority ranking result.

[0142] In this embodiment, when adjusting the first right-of-way priority ranking result in combination with the conflict risk assessment index in the dynamic association representation data, the conflict risk assessment index between each traffic participant is first extracted, including the possibility of conflict occurrence, the severity of the conflict, etc.

[0143] For adjacent traffic participants in the first right-of-way priority ranking results, analyze their conflict risk assessment indicators. If traffic participant C is ranked ahead of traffic participant D in the first ranking results, but the conflict risk assessment indicators show that the conflict risk between traffic participant C and other high-priority traffic participants is much higher than that between traffic participant D and other high-priority traffic participants, to reduce the overall conflict risk, traffic participant D can be repositioned ahead of traffic participant C.

[0144] At the same time, for a combination of traffic participants with a high conflict risk, if the priority of one of the traffic participants is too high, which may make the conflict difficult to avoid, its priority should be appropriately lowered; while for traffic participants with a low conflict risk and urgent tasks, their priority should be appropriately increased.

[0145] Through the above adjustments, the right-of-way priority ranking results are made more reasonable, taking into account both the importance of nodes and the conflict risk, and the second right-of-way priority ranking result is obtained.

[0146] Step S136: Constructing a collaborative path planning scheme based on the second right-of-way priority ranking result and the task collaboration requirement parameters. The collaborative path planning scheme includes the recommended driving path, estimated passing time and path change permission conditions of each traffic participant.

[0147] In this embodiment, when constructing a collaborative routing plan based on the second right-of-way priority ranking results and the task collaboration requirement parameters, a recommended route is first planned for each participant based on their priority and the task destination. Participants with higher priorities have more options in route selection, allowing them to prioritize better and smoother routes while avoiding excessive overlap with the routes of other high-priority participants.

[0148] When planning recommended routes, the path overlap in the task collaboration requirement parameters is fully considered. For combinations of traffic participants with high path overlap, their travel order and travel time intervals are rationally arranged to reduce path conflicts. For example, high-priority traffic participants can be allowed to pass through a certain overlapping section first, and low-priority traffic participants can enter the section after a period of time.

[0149] The estimated transit time is calculated based on the total length of the recommended route, the average speed of traffic participants, and the expected waiting time along the route. For sections where waiting for other traffic participants is required, a reasonable estimate of the waiting time is factored into the estimated transit time based on the expected passing times and spacing requirements of other traffic participants.

[0150] The setting of route change permission conditions is based on real-time conflict risk assessment and traffic flow changes. It clarifies which alternative routes traffic participants can choose from when the conflict risk of a certain road section exceeds the set threshold, as well as the process and requirements for reporting route changes to the central control system.

[0151] Therefore, the above contents are integrated to form a complete collaborative path planning solution to ensure that all traffic participants can travel in an orderly manner according to the plan and improve port operation efficiency.

[0152] Step S140: Generate a collaborative control instruction set according to the right-of-way priority sequence and the collaborative path planning scheme, wherein the collaborative control instruction set includes speed coordination parameters, path adjustment sequence and conflict avoidance operation rules.

[0153] Step S141: parsing the right-of-way priority sequence to determine the position index of each traffic participant in the sequence.

[0154] In this embodiment, when parsing the right-of-way priority sequence, each traffic participant is assigned a position index based on the order in which they are listed. Position indices start at 1 and increase in descending order of priority. That is, the highest-priority traffic participant has a position index of 1, the next-highest has a position index of 2, and so on.

[0155] The position index intuitively reflects each traffic participant's relative position in the right-of-way priority sequence. A smaller position index indicates a higher priority. The position index serves as an important reference when generating control commands such as speed coordination parameters. For example, traffic participants with a smaller position index receive more favorable parameter settings when adjusting speed.

[0156] Step S142: Based on the recommended driving path in the collaborative path planning scheme, a specific driving trajectory is planned for each traffic participant.

[0157] Step S1421: extract the recommended driving route in the collaborative route planning scheme, and determine the path segments and corresponding usage time windows that can be used by each traffic participant.

[0158] In this embodiment, when extracting the recommended driving path in the collaborative path planning solution, matching is performed according to the unique identifiers of the traffic participants to obtain the recommended driving path corresponding to each traffic participant.

[0159] The recommended route is then divided into multiple consecutive segments, each bounded by two adjacent landmarks (such as intersections, yard entrances, or specific coordinate points). For each segment, the time window within which each participant can use the segment is determined based on the estimated transit time in the collaborative routing plan and the usage of the segment by other participants. This window, in other words, determines the earliest time a participant can enter and the latest time a participant can leave the segment.

[0160] For example, for path segment P1, the usage time window of traffic participant A is from T1 to T2, and the usage time window of traffic participant B is from T3 to T4, and T2 is smaller than T3 to avoid both of them appearing on the path segment at the same time.

[0161] Step S1422: Taking the current position of the traffic participant as the starting point and the target operation area as the end point, an initial path candidate set is constructed by combining the available path segments and the available time window.

[0162] In this embodiment, when constructing an initial path candidate set with the current position of the traffic participant as the starting point and the target operation area as the end point, multiple complete paths from the starting point to the end point are generated through different combinations based on the available path segments.

[0163] When combining path segments, ensure that the path segments can be smoothly connected and that the usage time windows of the path segments contained in each complete path can be connected to each other, that is, the latest departure time of the previous path segment is no later than the earliest entry time of the next path segment.

[0164] All complete paths that meet the conditions are collected to form an initial path candidate set. Each candidate path contains the path segment sequence and the corresponding time window information.

[0165] Step S1423: Calculate the length of each path in the initial path candidate set, and select paths with length values ​​within a preset range as path alternatives.

[0166] In this embodiment, when calculating the length of each path in the initial path candidate set, the lengths of the path segments included in the path are added together to obtain the total length of each path.

[0167] Next, a preset range of path lengths is set, based on the straight-line distance from the start point to the end point and the road layout of the port's operating area. Paths with total lengths within this range are selected as alternative routes, eliminating unreasonable routes that are too long or too short.

[0168] For example, if the straight-line distance from the start point to the end point is L, the preset range may be 1.2L to 1.8L, and paths with a total length within this range are retained as path alternatives.

[0169] Step S1424: Analyzing the conflict situation between the path candidate and the path candidates of other traffic participants, calculating the path conflict times and the conflict duration.

[0170] In this embodiment, when analyzing the conflict situation between the path candidate and the path candidates of other traffic participants, firstly, each path candidate of the current traffic participant is compared with each path candidate of all other traffic participants in the port operation area one by one. The comparison content includes the path segment involved in the path candidate, the use time window of each path segment, and the spatial position distribution of the path.

[0171] For two path candidates, if there is a common path segment and the use time windows of the two path candidates corresponding to the traffic participants on the common path segment overlap, it is determined that the two path candidates have a conflict on the path segment. The path segment involved in each conflict and the time period of the time window overlap are recorded.

[0172] The calculation method of the path conflict times is to count the total number of conflicts between the current path candidate and the path candidates of all other traffic participants. For example, the path candidate A of the current path candidate has 2 conflicts with the path candidate B1 of the traffic participant B and 1 conflict with the path candidate C1 of the traffic participant C, and the path conflict times of the path candidate A is 3.

[0173] The calculation of the conflict duration is to add up the time lengths of the time window overlap periods of each conflict. For each common path segment with time window overlap, the time length of the overlap period is the end time minus the start time of the overlapping part of the two time windows. Adding up all the time lengths, the total conflict duration of the path candidate is obtained.

[0174] By calculating the path conflict times and the conflict duration, the conflict situation between each path candidate and other path candidates can be effectively known.

[0175] Step S1425: Determining the path candidate with the path conflict times less than the set number threshold and the conflict duration less than the set time threshold as the high-quality path candidate.

[0176] In this embodiment, when determining the high-quality path candidate, firstly, the set number threshold of the path conflict times and the set time threshold of the conflict duration are set according to the traffic flow, the path complexity, and the requirement on the operation efficiency of the port operation area.

[0177] The number of path conflicts for each alternative route is then compared to a set number threshold, and the duration of the conflict is compared to a set time threshold. If a path alternative has fewer than the set number threshold and a conflict duration less than the set time threshold, it indicates that the path alternative performs well in coordinating with other traffic participants, with a relatively low probability of conflict and a relatively low impact. Therefore, it is identified as a high-quality path alternative.

[0178] For example, if the number threshold is set to 3 times and the time threshold is set to 10 time units, the number of conflicts of a certain path alternative is 2 times and the conflict duration is 8 time units, then the path alternative is determined to be a high-quality path alternative.

[0179] Step S1426: Estimating the travel time of the high-quality path alternatives, and selecting the high-quality path alternatives whose travel time is less than the set travel time and meets the usage time window requirements as the recommended driving path to generate a specific driving trajectory.

[0180] In this embodiment, travel time estimation for high-quality alternative routes is performed by first calculating the travel time for each segment based on the length of each segment and the expected travel speed of the traffic participant along each segment. Travel time is calculated by dividing the segment length by the expected travel speed.

[0181] Next, consider the potential wait time on each route segment. This includes wait times caused by other participants on the same route segment and their sequential use of time windows, as well as wait times due to factors such as traffic control at route segment entrances. These wait times are added to the travel time for the corresponding route segment.

[0182] Add up the travel time and waiting time of all path segments to get the total travel time of the high-quality path alternative.

[0183] Next, the total travel time is compared with the set travel time, which is determined based on the required completion time of the task and the overall scheduling of port operations. At the same time, the time windows of each path segment of the high-quality alternative route are checked to ensure that they fully meet the time requirements of the collaborative path planning solution, ensuring that there are no conflicts with the time windows of other traffic participants.

[0184] A high-quality alternative route with a total travel time less than the set travel time and meeting the time window requirement is selected as the recommended driving route for the traffic participant. A specific driving trajectory is then generated based on the recommended driving route using the method described in step S142.

[0185] Step S143: Calculate the expected driving speed of the traffic participant based on the driving trajectory and the task completion time requirement in the task collaboration requirement parameter, where the expected driving speed is the ratio of the driving trajectory length to the task completion time requirement.

[0186] In this embodiment, when calculating the expected driving speed of a traffic participant, the total length of the specific driving trajectory of the traffic participant is first obtained. The total length of the driving trajectory is the sum of the lengths of all path segments contained in the trajectory and the lengths of transition curves, and is obtained by parsing and accumulating the driving trajectory data.

[0187] Then, the task completion time requirement in the task collaboration requirement parameters is extracted. The time requirement is the time interval from the current moment to the deadline when the task must be completed.

[0188] The expected driving speed is calculated by dividing the total length of the driving trajectory by the task completion time requirement. The expected driving speed calculated in this way can ensure that traffic participants reach the target work area according to the planned driving trajectory within the task completion time requirement.

[0189] For example, if the total length of the driving trajectory is S and the task completion time requirement is T, then the expected driving speed V is equal to S divided by T.

[0190] During the calculation process, it is necessary to ensure that the units of the driving trajectory length match the units of the task completion time requirements to ensure that the dimensions of the expected driving speed are correct.

[0191] Step S144: The expected driving speed is adjusted in combination with the position index in the right-of-way priority sequence, and the adjusted expected driving speed is determined as the speed coordination parameter. The expected driving speed adjustment coefficient of the traffic participant with a forward position index is greater than that of the traffic participant with a backward position index.

[0192] In this embodiment, when adjusting the desired speed based on the position index in the right-of-way priority sequence, a corresponding desired speed adjustment coefficient is first set for each position index. Position indexes closer to the front of the road correspond to larger adjustment coefficients, while position indexes closer to the back of the road correspond to smaller adjustment coefficients. The size of the adjustment coefficient is determined based on a combination of factors, including traffic volume within the port operating area, route conditions, and the urgency of each participant's task.

[0193] Then, multiply each traffic participant's expected speed by its corresponding adjustment coefficient to obtain the adjusted expected speed. For example, the adjustment coefficient for the traffic participant with position index 1 is K1, and the adjustment coefficient for the traffic participant with position index 2 is K2, with K1 being greater than K2. Traffic participant A has position index 1 and an expected speed of V1, so the adjusted expected speed is V1 multiplied by K1. Traffic participant B has position index 2 and an expected speed of V2, so the adjusted expected speed is V2 multiplied by K2.

[0194] The adjusted expected speed takes into account the right-of-way priorities of traffic participants, allowing high-priority participants to travel at relatively higher speeds, improving their task completion efficiency while avoiding unnecessary speed conflicts with other traffic participants. The adjusted expected speed is determined as the speed coordination parameter for the traffic participant.

[0195] Step S145: Analyze the estimated passing time and path change permission conditions in the collaborative path planning solution, and construct a path adjustment sequence, which includes path change timing, lane selection suggestions, and confluence point passing order.

[0196] In this embodiment, when analyzing the Estimated Passing Time and Route Change Permit Conditions in the collaborative routing plan to construct a route adjustment sequence, the estimated passing time is first used to determine the time at which each traffic participant will arrive at key nodes on the route (such as intersections, confluence points, and route segment start and end points). These time points serve as an important reference for determining when to change the route.

[0197] The determination of the timing of route change needs to be combined with the route change permission conditions. When traffic participants reach a key node and it is judged based on real-time traffic conditions that a route change is needed to avoid conflict or improve driving efficiency, and at the same time meet the change requirements specified in the route change permission conditions (such as the warning time before the change, the distance requirements to surrounding traffic participants, etc.), the time point corresponding to the key node is set as the route change timing.

[0198] Lane selection recommendations are constructed based on the lane distribution and traffic flow along the route. For routes with multiple lanes, the system recommends a suitable lane for the current driver based on the lane selection and speed of other drivers. For example, if a lane has light traffic and high speed, and it matches the driver's direction of travel, that lane will be recommended.

[0199] The order of passage at a confluence point is determined based on the participants' right-of-way priorities and their estimated arrival times. Participants with higher priorities are given priority. If multiple participants have similar estimated arrival times, the order of passage is determined based on their priorities. This ensures orderly traffic flow at the confluence point and reduces congestion and conflicts.

[0200] The timing of path changes, lane selection suggestions, and the order of passing through the confluence points are arranged in chronological order and in the order of path nodes to form a complete path adjustment sequence.

[0201] Step S146: Based on the conflict risk assessment indicators in the dynamic association characterization data, conflict avoidance operation rules are constructed. The conflict avoidance operation rules include deceleration avoidance operation parameters, parking waiting time threshold, path detour offset and sound and light warning activation conditions.

[0202] Step S1461: parsing the conflict risk assessment index in the dynamic association representation data to determine the conflict risk level, wherein the conflict risk level is divided into different levels according to the numerical range of the conflict risk assessment index.

[0203] In this embodiment, when analyzing the conflict risk assessment indicators in the dynamic correlation representation data to determine the conflict risk level, the first step is to extract the quantitative values ​​reflecting the likelihood and severity of the conflict from the conflict risk assessment indicators. These values ​​are typically obtained through a comprehensive analysis of multiple factors such as the location, speed, driving direction, and path overlap of traffic participants.

[0204] Then, based on port safety standards and historical conflict data, multiple numerical ranges for conflict risk assessment indicators are preset, with each numerical range corresponding to a conflict risk level. For example, the numerical ranges for conflict risk assessment indicators can be divided into four levels, with the smallest numerical range corresponding to the lowest conflict risk level and the largest numerical range corresponding to the highest conflict risk level.

[0205] The quantified value of the conflict risk assessment indicator obtained by analysis is compared with a preset numerical range. The conflict risk level for that traffic participant combination is determined to be the level corresponding to that range. By determining the conflict risk level, the severity of the conflict can be more intuitively judged.

[0206] Step S1462: Construct corresponding basic conflict avoidance operation rules for different conflict risk levels.

[0207] In this embodiment, when constructing corresponding basic conflict avoidance operation rules for different conflict risk levels, a basic avoidance operation framework is set for each conflict risk level.

[0208] For the lowest conflict risk level, the basic conflict avoidance operation rules mainly focus on maintaining the current driving status and strengthening observation, such as appropriately increasing vigilance and paying close attention to the movement status of the conflicting object. There is no need to take active deceleration or steering operations.

[0209] For lower conflict risk levels, basic conflict avoidance operating rules include slight deceleration, lane adjustment to maintain a safe distance, etc. The deceleration is small and the range of lane adjustment is limited, so as not to affect the overall driving efficiency.

[0210] For higher conflict risk levels, the basic conflict avoidance operation rules require obvious deceleration operations, and small-scale detours can be made when necessary. The deceleration amplitude and detour offset must ensure that the conflict risk can be effectively reduced. At the same time, the early warning device is activated to alert surrounding traffic participants.

[0211] For the highest conflict risk level, basic conflict avoidance operation rules include emergency deceleration, immediate parking and waiting, or large-scale detours to ensure that the conflict can be completely avoided. At the same time, strong sound and light warning signals are issued to alert all relevant traffic participants.

[0212] Step S1463: Extract the real-time running data and operating status data of the traffic participants, and obtain the current driving speed, acceleration and braking performance parameters of the vehicle.

[0213] In this embodiment, when extracting the real-time running data and operating status data of traffic participants, for autonomous driving vehicles, the real-time driving speed, acceleration (including longitudinal acceleration and lateral acceleration), braking system response time, maximum braking deceleration and other braking performance parameters are obtained through their on-board sensors and control systems; for manually driven equipment, the real-time driving speed, acceleration generated by the driver's operation, brake pedal travel and maximum braking force of the braking system and other parameters are obtained through the data acquisition device installed on the equipment.

[0214] Step S1464: Calculate the operation margin required for conflict avoidance by combining the current driving state parameters of the vehicle and the basic conflict avoidance operation rules. The operation margin includes a time margin and a space margin.

[0215] In this embodiment, when calculating the maneuver margin based on the vehicle's current driving state parameters and the basic conflict avoidance rules, the time margin is calculated as follows: based on the traffic participant's current driving speed, distance from the conflicting party, and the deceleration or stopping requirements specified in the basic conflict avoidance rules, the minimum time from the current moment to the time the conflict can be avoided after the evasive maneuver is taken is calculated, and then the estimated time required to take the evasive maneuver is subtracted to obtain the time margin. For example, if the calculated minimum time to avoid the conflict is T1 and the estimated time required to take the evasive maneuver is T2, the time margin is calculated as T1 minus T2.

[0216] The space margin is calculated by calculating the minimum safe distance between the traffic participant and the conflicting object after the avoidance maneuver is taken, based on the traffic participant's speed, steering performance, and the routing requirements specified in the basic conflict avoidance rules. The space margin is then subtracted from the actual distance between the two to obtain the space margin. If the calculated minimum safe distance is S1 and the actual distance is S2, the space margin is S1 minus S2.

[0217] The time margin and space margin together constitute the operational margin required for conflict avoidance. The larger the operational margin, the larger the buffer space for taking avoidance actions and the higher the possibility of successful avoidance.

[0218] Step S1465: According to the comparison result between the operation margin and the preset threshold, the specific parameters of the basic conflict avoidance operation rule are adjusted, wherein the deceleration avoidance operation rule is adopted when the time margin is greater than the preset threshold, and the stop and wait operation rule is adopted when the time margin is less than or equal to the preset threshold.

[0219] In this embodiment, when adjusting the specific parameters of the basic conflict avoidance rules based on the comparison between the operational margin and the preset thresholds, the preset thresholds for the time margin and the space margin are first set. These thresholds are determined based on the type of traffic participant, driving speed, and the environmental characteristics of the port operation area.

[0220] When the time margin exceeds the preset threshold, there is sufficient time to decelerate and avoid the conflict. In this case, the deceleration and avoidance rules are implemented. Adjustments to the deceleration and avoidance parameters, such as increasing the absolute value of the deceleration acceleration, allow traffic participants to reduce speed over a shorter distance and maintain a safe distance from the conflicting party. Lane selection is also adjusted appropriately based on the available space. If the available space is large, a small lane deviation can be used to assist in deceleration and avoidance.

[0221] When the time margin is less than or equal to the preset threshold, it is indicated that the conflict cannot be effectively avoided only by the deceleration operation, and the parking and waiting operation rule is adopted at this time. A parking and waiting time threshold is set, and the parking and waiting time threshold is determined according to the time required for the conflict object to pass through the conflict region, to ensure that the parking and waiting time is sufficient for the conflict object to pass safely. At the same time, the specific position of parking is determined according to the space margin, and it is necessary to ensure that the parking position does not affect the normal driving of other road users, and there is enough space to restart driving later.

[0222] For the comparison result of the space margin, if the space margin is less than the preset threshold, it is indicated that the current path may not meet the detour requirement in the basic conflict avoidance operation rule, and the path detour offset needs to be further increased, or whether the parking and waiting operation needs to be adopted is re-evaluated.

[0223] Through the above adjustment, the conflict avoidance operation rule is more in line with the actual conflict situation, and the effectiveness of the avoidance operation is improved.

[0224] Step S1466: Analyzing the traffic right priority sequence of the traffic participants involved in the conflict, assigning a set number of traffic participants in the rear position in the traffic right priority sequence to the main conflict avoidance responsibility, and obtaining the conflict avoidance operation rule.

[0225] In this embodiment, when analyzing the traffic right priority sequence of the traffic participants involved in the conflict to assign the main conflict avoidance responsibility, first, all the traffic participants involved in the conflict are determined, and their position indexes in the traffic right priority sequence are checked.

[0226] According to the rule of the traffic right priority sequence, the traffic participants in the rear position have lower priority. A number, such as 2 or 3, is set, and the traffic participants in the rear position in the traffic right priority sequence are determined as the objects that need to bear the main conflict avoidance responsibility.

[0227] For these traffic participants bearing the main conflict avoidance responsibility, more stringent avoidance requirements are specified in their conflict avoidance operation rules, such as earlier start of avoidance operation, larger deceleration amplitude, longer parking and waiting time, or larger path detour offset. The traffic participants in the front position bear the secondary conflict avoidance responsibility, and their avoidance operation rules are relatively relaxed, mainly to maintain the driving state and cooperate with the operation of the main avoidance responsibility party.

[0228] For example, in a conflict involving 3 traffic participants, their position indexes are 2, 5, and 7 respectively, and the set number is 2, then the traffic participants with position indexes 5 and 7 bear the main conflict avoidance responsibility, and more stringent parameters are set in their conflict avoidance operation rules.

[0229] Through the above-mentioned allocation of responsibilities, conflict avoidance operations are more targeted, with full consideration given to the priority of right of way, ensuring the orderliness and efficiency of the overall traffic.

[0230] Step S147: The speed coordination parameters, the path adjustment sequence, and the conflict avoidance operation rules are integrated to generate a local coordination control instruction, and the local coordination control instructions of all traffic participants are aggregated to generate a coordination control instruction set.

[0231] In this embodiment, when generating local collaborative control instructions by integrating speed coordination parameters, path adjustment sequences, and conflict avoidance rules, these three components are first organized into a unified format. Speed ​​coordination parameters are represented by clear speed values ​​and speed change intervals; path adjustment sequences are arranged in chronological order and by path nodes; and conflict avoidance rules are categorized by different conflict scenarios and corresponding operation steps.

[0232] Next, a correlation mapping is established, mapping the speed coordination parameters to key nodes in the route adjustment sequence. For example, at a node in the route adjustment sequence requiring a turn, the corresponding speed coordination parameter sets a speed suitable for the turn, ensuring that traffic participants maintain a reasonable speed when turning and ensuring driving safety. Furthermore, conflict avoidance rules are associated with high-risk areas along the route. When a traffic participant is about to enter a high-risk area, the corresponding conflict avoidance rule is activated first, providing clear operational guidance.

[0233] Then, these three parts are logically integrated to form a coherent local collaborative control instruction. The instruction first clarifies the speed coordination parameters of traffic participants at the current stage, then explains when to make path adjustments and the specific methods of adjustment according to the time sequence and node requirements of the path adjustment sequence, and finally attaches the conflict avoidance operation rules that should be followed in different scenarios. For example, the local collaborative control instruction will first stipulate that traffic participants maintain a certain speed for the next 10 minutes, and then explain that a turning operation should be performed when reaching a certain coordinate point. The speed must be reduced to a certain range when turning. At the same time, it points out which conflict avoidance rules should be followed if other traffic participants are encountered during the turning process.

[0234] During the integration process, it is necessary to ensure that there are no logical contradictions between the various parts. For example, the turning operation time points required in the path adjustment sequence must match the speed change time points set in the speed coordination parameters. The operation requirements in the conflict avoidance operation rules cannot conflict with the provisions in the speed coordination parameters and the path adjustment sequence.

[0235] After the local cooperative control instruction generation of a single traffic participant is completed, the local cooperative control instructions of all traffic participants are aggregated. During aggregation, the local cooperative control instructions of each traffic participant are classified and arranged according to the unique identifier of the traffic participant, and each local cooperative control instruction of the traffic participant is taken as an independent entry, which contains the identifier information of the traffic participant and the corresponding instruction content. At the same time, consistency check is performed on the aggregated instruction set to ensure that the instructions of different traffic participants do not conflict with each other, for example, the instructions of two traffic participants in the same time period and in the same area do not contradict each other.

[0236] Finally, all the local cooperative control instructions that have passed the consistency check are integrated into a unified cooperative control instruction set, which is stored and transmitted in a standardized data format so that the control systems of various traffic participants can accurately parse and execute the relevant instructions.

[0237] Step S150: Distribute the cooperative control instruction set to the corresponding traffic participant control system to perform dynamic cooperative driving control in the port mixed driving scenario.

[0238] In this embodiment, when the cooperative control instruction set is distributed to the corresponding traffic participant control system, the connection with each traffic participant control system is first established through the communication network inside the port. The communication network uses high-reliability wireless communication technology to ensure the real-time and stability of instruction transmission.

[0239] Then, according to the traffic participant identifier corresponding to each local cooperative control instruction in the cooperative control instruction set, the instruction is accurately routed to the corresponding traffic participant control system. During transmission, the instruction is encrypted to prevent tampering or leakage of the instruction and to ensure the security of the instruction.

[0240] After receiving the local cooperative control instruction, the traffic participant control system parses the instruction, extracts key information such as speed coordination parameters, path adjustment sequence, and conflict avoidance operation rules, and converts these information into control signals executable by itself. For example, the control system of an autonomous vehicle will convert the speed coordination parameters into control signals for the accelerator and brake, convert the path adjustment sequence into control signals for the steering system, and perform the corresponding operations according to the instruction requirements.

[0241] During execution, the traffic participant control system monitors its own operating status and changes in the surrounding environment in real time, transmitting execution status and feedback information back to the port's central data processing center via the communication network. The central data processing center analyzes this feedback. If it finds that a traffic participant has not followed instructions or has encountered an abnormality, it regenerates collaborative control instructions based on the real-time dynamic interaction data set and promptly distributes them to the traffic participant control system for dynamic adjustments. This ensures that traffic participants in mixed traffic scenarios at the port can always maintain coordinated driving, improving the efficiency and safety of port operations.

[0242] Figure 2 A schematic diagram illustrates exemplary hardware and software components of a coordinated control system 100 for a port autonomous mixed traffic scenario, provided in some embodiments of the present application, that can implement the concepts of the present application. For example, processor 120 can be used in coordinated control system 100 for a port autonomous mixed traffic scenario and perform the functions described in the present application.

[0243] For example, the collaborative control system 100 based on the port autonomous driving mixed traffic scenario may include a network port 110 connected to the network, one or more processors 120 for executing program instructions, a communication bus 130, and different forms of storage media 140, such as disks, ROM, or RAM, or any combination thereof. Exemplarily, the collaborative control system 100 based on the port autonomous driving mixed traffic scenario may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application can be implemented according to these program instructions. The collaborative control system 100 based on the port autonomous driving mixed traffic scenario also includes an I / O interface 150 between the computer and other input and output devices.

[0244] In addition, an embodiment of the present invention also provides a readable storage medium, in which computer-executable instructions are preset. When the processor executes the computer-executable instructions, the above-mentioned collaborative control method based on the mixed traffic scenario of port autonomous driving is implemented.

[0245] It should be noted that in order to simplify the description of the present invention and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present invention, multiple features are sometimes combined into one embodiment, figure or description thereof.

Claims

1. A collaborative control method based on a mixed traffic scenario of autonomous driving in a port, characterized in that: The method comprises: Acquire a dynamic interactive data set within the port operation area, the dynamic interactive data set including real-time operation data of autonomous vehicles, operation status data of manually driven equipment, port operation task scheduling information, and behavioral intention data of traffic participants; Performing correlation feature extraction processing on the dynamic interaction data set to generate dynamic correlation representation data of the port mixed traffic scene; Performing collaborative decision-making analysis based on the dynamic association representation data to determine a right-of-way priority sequence and a collaborative path planning scheme for each traffic participant in the port operation area, wherein the right-of-way priority sequence is generated by sorting the node importance indexes, and the collaborative path planning scheme includes a recommended driving route, an estimated transit time, and conditions for allowing route changes; generating a collaborative control instruction set according to the right-of-way priority sequence and the collaborative path planning scheme; The collaborative control instruction set is distributed to the corresponding traffic participant control systems to execute dynamic collaborative driving control in the mixed traffic scenario of the port.

2. The collaborative control method based on the mixed traffic scenario of port autonomous driving according to claim 1 is characterized in that: The performing of correlation feature extraction processing on the dynamic interaction data set to generate dynamic correlation representation data of the port mixed traffic scene includes: parsing the port operation task scheduling information in the dynamic interaction data set, and extracting task attribute parameters of each traffic participant, wherein the task attribute parameters include task urgency, cargo type characteristics, and operation area relevance; A task correlation matrix is ​​constructed based on the task attribute parameters, wherein the task urgency level is positively correlated with the urgency weight value, and the operation area correlation value is positively correlated with the correlation value between traffic participants; Extracting traffic participant behavior intention data from the dynamic interaction data set and identifying a driving intention category of each traffic participant, wherein the driving intention category includes straight-through, turning, stopping, and emergency avoidance; determining potential interaction relationships between traffic participants based on the driving intention categories, wherein the potential interaction relationships include crossing driving, merging driving, following driving, and parallel driving; generating a traffic participant association feature by combining the task association matrix and the potential interaction relationship, wherein the traffic participant association feature is used to describe the degree of interaction between different traffic participants during the task execution process; Analyze the real-time operation data of the autonomous driving vehicle and the operation status data of the manually driven equipment in the dynamic interaction data set to extract task collaboration requirement parameters, wherein the task collaboration requirement parameters include task completion time requirements, path overlap, and resource sharing requirements; A conflict risk assessment model is constructed based on the traffic participant association characteristics and task collaboration requirement parameters, and a conflict risk assessment index between each traffic participant is calculated using the conflict risk assessment model. The conflict risk assessment index is used to characterize the possibility and severity of a conflict between traffic participants during driving; The traffic participant association relationship characteristics, task collaboration requirement parameters and conflict risk assessment indicators are integrated to generate dynamic association representation data.

3. The collaborative control method based on the mixed traffic scenario of port autonomous driving according to claim 2 is characterized in that: The step of constructing a task association matrix based on the task attribute parameters includes: Dividing the task urgency in the task attribute parameters into different levels, assigning a corresponding urgency weight value to each level, and the urgency weight values ​​corresponding to the task urgency levels increase in order of the levels; Classifying the cargo type characteristics in the task attribute parameters and determining a cargo type weight coefficient; Calculating the operation area relevance in the task attribute parameters, where the operation area relevance is determined by a normalized distance value between a current operation area of ​​a traffic participant and a target operation area and an operation process dependency relationship; Constructing a task attribute comprehensive weight based on the urgency weight value, cargo type weight coefficient, and operation area relevance, where the task attribute comprehensive weight is a weighted sum of the urgency weight value, cargo type weight coefficient, and operation area relevance; The initial task association matrix is ​​constructed by taking the traffic participants in the port operation area as matrix rows and matrix columns, and taking the product of the comprehensive weights of the task attributes of any two traffic participants as the matrix element value; The initial task association matrix is ​​normalized, and the normalized task association matrix is ​​adjusted according to port operation rules and historical collaborative data, increasing the association value between traffic participants with direct operation process association and reducing the association value between traffic participants without operation association, to obtain the final task association matrix.

4. The collaborative control method based on the mixed traffic scenario of port autonomous driving according to claim 2 is characterized in that: The determining of potential interaction relationships between traffic participants according to the driving intention category includes: Constructing a driving intention interaction rule library, wherein the driving intention interaction rule library includes potential interaction relationship judgment rules corresponding to different driving intention category combinations; For any two traffic participants in the port operation area, obtain their driving intention category combination; Matching the driving intention category combination with the driving intention interaction rules in the driving intention interaction rule library to determine a preliminary judgment result of the corresponding potential interaction relationship; Extracting the real-time location data and movement direction data of the traffic participants from the dynamic interaction data set, and combining the preliminary judgment result of the potential interaction relationship to verify the authenticity of the potential interaction relationship; If the real-time location data and movement direction data of two traffic participants indicate that they will appear in the same area within the preset time, the potential interaction relationship is confirmed to be established; The interaction strength of the confirmed potential interaction relationship is evaluated by the ratio of the distance and relative speed between traffic participants to obtain the interaction strength value; The potential interaction relationships with interaction strength values ​​greater than a preset threshold are marked as primary potential interaction relationships, and those with interaction strength values ​​less than or equal to the preset threshold are marked as secondary potential interaction relationships; Record the primary and secondary potential interaction relationships among all traffic participants in the port operation area and establish a potential interaction relationship list.

5. The collaborative control method based on the mixed traffic scenario of port autonomous driving according to claim 1 is characterized in that: The collaborative decision analysis is performed based on the dynamic association representation data to determine the right-of-way priority sequence and collaborative path planning scheme for each traffic participant in the port operation area, including: parsing the traffic participant association relationship characteristics in the dynamic association representation data to determine the association influence range of each traffic participant, wherein the association influence range includes other traffic participants that have a primary potential interaction relationship with the traffic participant; Building a traffic participant collaborative network based on the associated influence range, wherein the nodes in the traffic participant collaborative network are traffic participants, the edges between the nodes represent the association relationships between the traffic participants, and the weights of the edges are association values; Analyzing the task collaboration requirement parameters in the dynamic association representation data, extracting the task completion time requirement and the path overlap, and determining a traffic participant combination whose task completion time requirement value is less than a first set value and whose path overlap value is greater than a second set value as a collaborative decision-making focus object; Performing an importance evaluation on nodes in the traffic participant collaborative network, and preliminarily determining a right-of-way priority ranking of the traffic participants based on the node importance evaluation results, thereby obtaining a first right-of-way priority ranking result; Adjusting the first right-of-way priority ranking result based on the conflict risk assessment index in the dynamic association representation data to obtain a second right-of-way priority ranking result; A collaborative path planning scheme is constructed based on the second right-of-way priority ranking result and the task collaboration requirement parameters. The collaborative path planning scheme includes the recommended driving path, estimated passing time and path change permission conditions of each traffic participant.

6. The collaborative control method based on the mixed traffic scenario of port autonomous driving according to claim 5 is characterized in that: The step of constructing a collaborative network of traffic participants based on the associated influence range includes: Each traffic participant in the port operation area is treated as an independent node, and a unique identifier is assigned to each node. The implementation identifier includes traffic participant type information and task number information; For each traffic participant node, find other traffic participant nodes with major potential interaction relationships within its associated influence range; Establishing a connection edge between the traffic participant node and other traffic participant nodes within its associated influence range, wherein the direction of the connection edge represents the direction of the interaction influence; Determining the weight value of the connecting edge according to the association value between the traffic participants; Adding attribute labels to the connection edges in the traffic participant collaborative network, wherein the attribute labels include interaction relationship type, interaction intensity, and interaction duration; Performing a topological structure analysis on the collaborative network of traffic participants to identify key nodes and key paths. The key nodes are nodes of traffic participants that have edges connecting to multiple other nodes, and the key paths are sequences of edges connecting multiple key nodes. After spatial constraint processing is performed on the traffic participant collaborative network according to the physical layout of the port operation area, visualization processing is performed on the constructed traffic participant collaborative network to generate the traffic participant collaborative network.

7. The collaborative control method based on the mixed traffic scenario of port autonomous driving according to claim 1 is characterized in that: Generating a collaborative control instruction set according to the right-of-way priority sequence and the collaborative path planning scheme includes: parsing the right-of-way priority sequence to determine the position index of each traffic participant in the sequence; Planning a specific driving trajectory for each traffic participant based on the recommended driving path in the collaborative path planning solution; Calculating the expected driving speed of the traffic participant based on the driving trajectory and the task completion time requirement in the task collaboration requirement parameter, wherein the expected driving speed is the ratio of the driving trajectory length to the task completion time requirement; The expected driving speed is adjusted based on the position index in the right-of-way priority sequence, and the adjusted expected driving speed is determined as a speed coordination parameter, wherein the expected driving speed adjustment coefficient of the traffic participant with an earlier position index is greater than that of the traffic participant with a later position index; Analyzing the estimated passing time and path change permission conditions in the collaborative path planning solution to construct a path adjustment sequence, the path adjustment sequence including path change timing, lane selection suggestions, and confluence point passing order; Based on the conflict risk assessment indicators in the dynamic correlation characterization data, conflict avoidance operation rules are constructed. The conflict avoidance operation rules include deceleration avoidance operation parameters, parking waiting time threshold, path detour offset and sound and light warning activation conditions; The speed coordination parameters, the path adjustment sequence and the conflict avoidance operation rules are integrated to generate local coordination control instructions, and the local coordination control instructions of all traffic participants are aggregated to generate a coordination control instruction set.

8. The collaborative control method based on the mixed traffic scenario of port autonomous driving according to claim 7 is characterized in that: The step of planning a specific driving trajectory for each traffic participant based on the recommended driving path in the collaborative path planning solution includes: Extract the recommended driving routes from the collaborative route planning scheme and determine the available route segments and corresponding usage time windows for each traffic participant; Taking the current location of the traffic participant as the starting point and the target operation area as the end point, the initial path candidate set is constructed by combining the available path segments and the usage time window; Calculate the length of each path in the initial path candidate set and select the paths with length values ​​within the preset range as path alternatives; Analyze the conflicts between the alternative route plans and those of other traffic participants, and calculate the number of conflict times and conflict durations. The path alternatives whose number of path conflicts is less than the set resignation threshold and whose conflict duration is less than the set time threshold are determined as high-quality path alternatives; The travel time of the high-quality path alternatives is estimated, and the high-quality path alternatives whose travel time is less than the set travel time and meets the use time window requirements are selected as the recommended driving path to generate a specific driving trajectory.

9. The collaborative control method based on the mixed traffic scenario of port autonomous driving according to claim 7 is characterized in that: The conflict avoidance operation rules are constructed based on the conflict risk assessment indicators in the dynamic association representation data, including: parsing the conflict risk assessment indicator in the dynamic association representation data to determine a conflict risk level, wherein the conflict risk level is divided into different levels according to a numerical range of the conflict risk assessment indicator; Construct corresponding basic conflict avoidance operation rules for different conflict risk levels; Extract real-time running data and operating status data of traffic participants, and obtain the current driving speed, acceleration and braking performance parameters of the vehicle; Calculating the required operation margin for conflict avoidance by combining the vehicle's current driving state parameters and basic conflict avoidance operation rules, wherein the operation margin includes a time margin and a space margin; Adjusting specific parameters of the basic conflict avoidance operation rule based on a comparison result between the operation margin and a preset threshold, wherein a deceleration avoidance operation rule is adopted when the operation margin is greater than the preset threshold, and a stop and wait operation rule is adopted when the operation margin is less than or equal to the preset threshold; The right-of-way priority sequence of traffic participants involved in the conflict is analyzed, and a set number of traffic participants at the rear of the right-of-way priority sequence are assigned primary conflict avoidance responsibilities to obtain conflict avoidance operation rules.

10. A collaborative control system based on a mixed traffic scenario of autonomous driving in a port, characterized by: It includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the collaborative control method based on the port autonomous driving mixed traffic scenario as described in any one of claims 1 to 9.

Images