Collaborative operation method and system for port unmanned container trucks

Abstract

The invention provides a collaborative operation method and system for port unmanned container trucks. Belongs to the technical field of automatic driving. Based on the vehicle and road data, global path planning and local path planning of the unmanned container truck are carried out; wherein the local path planning comprises the steps of executing dynamic path planning of the unmanned container truck based on the vehicle road data, and screening a feasible path based on a collision detection result of a planned path and a traffic participant. According to the technical scheme of the invention, the method can reduce the collision risk, reduces the right of way conflict, and improves the safety of collaborative operation.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a collaborative operation method and system for unmanned container trucks in a port. Background Art

[0002] In the existing technical solution, the starting point, task end point and transit points of unmanned container trucks are abstracted as coordinate points based on the work task, and the shortest path between any two coordinate points is calculated through an artificial intelligence algorithm to obtain the optimal global path. When unmanned container trucks and manned container trucks mix, it is easy to cause vehicle right-of-way conflicts or even local deadlocks, which in turn leads to reduced transportation efficiency. Summary of the invention

[0003] In order to solve at least one technical problem in the prior art, the present disclosure provides a collaborative operation method and system for unmanned container trucks in a port.

[0004] According to a first aspect of the present disclosure, a method for collaborative operation of unmanned container trucks in a port is provided, the method comprising:

[0005] Obtain vehicle-road data;

[0006] Based on vehicle-road data, global and local path planning for unmanned container trucks is performed;

[0007] Among them, the local path planning includes: executing dynamic path planning of unmanned container trucks based on vehicle-road data, and screening feasible paths based on collision detection results between the planned path and traffic participants.

[0008] Optionally, the method further includes:

[0009] The local path planning is integrated into the global path planning and sent to the unmanned container truck.

[0010] Optionally, the global path planning of the unmanned container truck includes:

[0011] A heuristic search algorithm is used to determine the global shortest time path based on the starting point and the end point;

[0012] The heuristic function of the heuristic search algorithm is: the sum of the time from the starting point to the current node, the time from the current node to the selected node and the target time, and the target time is the quotient of the Euclidean distance from the selected node to the end point and the maximum driving speed of the roads in the entire port map.

[0013] Optionally, the global path planning of the unmanned container truck includes:

[0014] According to the driving speed information of each road contained in the vehicle-road data, a weighted average of the driving speeds of all vehicles on the same road is used as a recommended driving speed for the corresponding road;

[0015] According to the driving speed information of each road contained in the vehicle-road data, the maximum value of the driving speeds of the roads in the entire port area map is used as the maximum driving speed of the roads in the entire port area map.

[0016] Optionally, the step of executing dynamic path planning of the unmanned container truck includes:

[0017] When the unmanned container truck drives to the container area, if the unmanned container truck meets the preset conditions, the lane change decision logic is executed, otherwise, the unmanned container truck is prohibited from changing lanes; the preset conditions include that the unmanned container truck drives to the container area where the mission end point is located and there is a target operating vehicle that is closer to the destination than the corresponding unmanned container truck, and the target operating vehicle is an operating vehicle with a higher priority sequence than the unmanned container truck.

[0018] Optionally, the method of screening a feasible path based on a collision detection result between the planned path and a traffic participant includes:

[0019] Acquire first length and width information of the unmanned container truck and second length and width information of the traffic participant;

[0020] Determine the center position and radius of the circle enclosing the unmanned container truck according to the first length and width information;

[0021] Determine the center position and radius of a circle enclosing the traffic participant according to the second length and width information;

[0022] Based on the center position and radius of the circle enclosing the unmanned container truck and the center position and radius of the circle enclosing the traffic participant, the collision risk between the unmanned container truck and the traffic participant is determined.

[0023] Optionally, determining the center position and radius of a circle enclosing the unmanned container truck according to the first length and width information includes:

[0024] Taking the circumscribed circles of the longitudinal equinumerical rectangles of the unmanned container truck as the circle enclosing the unmanned container truck, determining the center position and radius of the circle enclosing the unmanned container truck;

[0025] or,

[0026] The step of determining the center position and radius of a circle enclosing the traffic participant according to the second length and width information includes:

[0027] The circumscribed circles of the longitudinal equinumerical rectangles of the traffic participants are used as the circles enclosing the traffic participants, and the center position and radius of the circle enclosing the unmanned container truck are determined.

[0028] Optionally, the range of expansion rate values ​​is matched according to the type of the traffic participant, and the number of circles that wrap the corresponding traffic participant is determined according to the range of expansion rate values, and the expansion rate is the ratio of the part of the collision detection area that exceeds the actual area of ​​the object to the actual area of ​​the object.

[0029] Optionally, judging the collision risk between the unmanned container truck and the traffic participant based on the center position and radius of the circle enclosing the unmanned container truck and the center position and radius of the circle enclosing the traffic participant includes:

[0030] According to the vehicle heading angle, the center position of the corresponding circle is converted;

[0031] If the distance between the center of the circle enclosing the unmanned container truck and the center of the circle enclosing the traffic participant is less than the sum of the radii of the two circles, it is determined that there is a risk of collision between the unmanned container truck and the traffic participant; otherwise, it is determined that there is no risk of collision between the unmanned container truck and the traffic participant.

[0032] Optionally, the screening of feasible paths based on collision detection results between the planned path and traffic participants includes:

[0033] With the goal of eliminating collision risk, feasible paths are screened based on the collision detection results between the planned path and traffic participants.

[0034] According to a second aspect of the present disclosure, a collaborative operation system for unmanned container trucks in a port is provided, the system comprising a V2X communication module, a panoramic data module and a collaborative planning module, the data module and the collaborative planning module are respectively communicatively connected to the V2X communication module; the collaborative planning module is used to execute any method described in the first aspect of the present disclosure.

[0035] One or more technical solutions provided in the embodiments of the present application can realize global path planning and local path planning, wherein dynamic path planning of unmanned container trucks is performed based on vehicle-road data, and feasible paths are screened based on collision detection results between the planned path and traffic participants, so that the dynamic path can avoid collision risks, reduce the probability of right-of-way conflicts, overcome the technical problem of reduced transportation efficiency caused by right-of-way conflicts, and improve port operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings illustrate exemplary embodiments of the present disclosure and together with the description serve to explain the principles of the present disclosure. These drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification.

[0037] Figure 1 A flow chart showing a collaborative operation method of unmanned container trucks in a port according to an exemplary embodiment of the present disclosure is shown;

[0038] Figure 2 A schematic diagram of local path planning according to an exemplary embodiment of the present disclosure is shown;

[0039] Figure 3 A schematic diagram showing a plurality of circles wrapped around rectangles according to an exemplary embodiment of the present disclosure is shown;

[0040] Figure 4 A schematic block diagram of a collaborative operation system of unmanned container trucks at a port according to an exemplary embodiment of the present disclosure is shown;

[0041] Figure 5 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0042] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0043] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0044] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions of other terms will be given in the description below. It should be noted that the concepts of "first", "second", etc. mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0045] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0046] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0047] The following are the explanations of terms related to the present disclosure:

[0048] Basic Safety Message BSM

[0049] Vehicle Intention And Request VIR

[0050] Road Side Information RSI

[0051] Road Side Message RSM

[0052] On-Board Unit OBU

[0053] Autonomous Vehicle AV

[0054] Terminal Operating System TOS

[0055] Vehicle to everything V2X

[0056] Vehicle Management System VMS

[0057] Abstract Syntax Notation One ASN.1

[0058] Aspects of the present disclosure are described below with reference to the accompanying drawings.

[0059] See also Figure 1 , a collaborative operation method of unmanned container trucks in a port, the method comprising:

[0060] S101, obtaining vehicle-road data.

[0061] In this step, the vehicle-road data includes roadside data and vehicle data. The vehicle information data is used for global path planning and local path planning. In actual application, the vehicle information data to be obtained can be determined based on the data requirements of global path planning and local path planning.

[0062] The collaborative operation method disclosed herein may be executed by a collaborative operation system, which may be a vehicle-road collaborative platform, etc.

[0063] Exemplarily, the vehicle-road cooperative platform obtains real-time port traffic information through roadside sensing equipment, generates real-time port traffic data, and forms road test data. The road test data may include roadside traffic messages RSI, roadside traffic participant messages RSM, etc.

[0064] Exemplarily, the vehicle-road collaborative platform obtains unmanned truck operation information by connecting to the vehicle management system VMS, completes information parsing, generates a job list, and calls the global path planning service through the open source RPC framework gRPC communication mechanism.

[0065] S102, based on the vehicle-road data, perform global path planning and local path planning for the unmanned container truck; wherein the local path planning includes: executing dynamic path planning for the unmanned container truck based on the vehicle-road data, and screening feasible paths based on collision detection results between the planned path and traffic participants.

[0066] In this step, the global path planning of the unmanned container truck can be planned using relevant global path planning methods.

[0067] In this step, the local path planning of the unmanned container truck is based on the vehicle-road data, and the dynamic path planning of the unmanned container truck is carried out, and the feasible path is screened based on the collision detection results with the traffic participants. This dynamic path planning is part of the local path planning, and the collision detection results of the unmanned container truck lane change path and the traffic participants are used to screen the dynamic planning path to avoid the collision risk, so that the collaborative operation method of this application can reduce the collision risk, reduce the right-of-way conflict, and improve the safety of collaborative operation.

[0068] In one embodiment, the local path planning is integrated with the global path planning and sent to the unmanned container truck.

[0069] In one embodiment, for global path planning, the global path planning can plan a recommended driving speed, plan a maximum driving speed, plan a global shortest time path, etc.

[0070] Exemplarily, based on the driving speed information of each road contained in the vehicle-road data, the weighted average of the driving speeds of all vehicles on the same road is used as the recommended driving speed for the corresponding road. Specifically, based on the vehicle driving speed information of each road on the map, the recommended driving speed for each road can be obtained. The calculation method is: obtain the driving speed of all vehicles on each road, remove the maximum and minimum values, set the speed of all vehicles on the road that exceed the road speed limit as the maximum driving speed of the road, and perform weighted average of the driving speeds of all vehicles to obtain the recommended driving speed. Exemplarily, the weighted average speed is calculated according to formula (1):

[0071]

[0072] Where V represents the weighted average speed, n represents the number of vehicles, and v i represents the speed of the i-th vehicle, α i represents the weight of the i-th vehicle. The weight can be set by the corresponding expert or according to the vehicle-related conditions, for example, according to the type of vehicle, the traffic flow of the vehicle, etc. Specifically, the corresponding weight can be set in advance according to the vehicle type or according to the traffic flow.

[0073] Exemplarily, according to the driving speed information of each road contained in the vehicle-road data, the maximum driving speed of the roads in the entire port map is used as the maximum driving speed of the roads in the entire port map. Specifically, the maximum driving speed of the roads in the entire map can be calculated by the vehicle driving speed information of each road, that is, the maximum driving speed of the roads in the entire map is the maximum driving speed of all the roads in the map.

[0074] Exemplarily, the heuristic search algorithm AStar is used to determine the global shortest time path based on the starting point and the end point. The heuristic function of the heuristic search algorithm is: the sum of the time from the starting point to the current node, the time from the current node to the selected node and the target time, and the target time is the quotient of the Euclidean distance from the selected node to the end point and the maximum driving speed of the roads on the entire map of the port area. Specifically, AStar searches are performed with the starting and end lanes as the starting points respectively. When the nodes searched by the two meet, the two routes are connected to form the global shortest time path; among them, the heuristic function of the AStar algorithm node selection is: the sum of the time from the starting point to the current node, the time from the current node to the selected node and the target time, and the target time is the quotient of the Euclidean distance from the selected node to the end point and the maximum driving speed of the roads on the entire map of the port area.

[0075] The global shortest time path information can be converted into protobuf data format (Protocol Buffers, a structured data storage format), and the global path planning can be sent to the unmanned container truck through the 5G Uu communication link.

[0076] In one embodiment, for local path planning, by sensing static and dynamic obstacles in the port, tracking the movement trajectory of dynamic obstacles and performing real-time trajectory deduction, the possibility of future collisions is analyzed to ensure the safety of unmanned container trucks traveling according to the global path planning. In a mixed traffic scenario of manned and unmanned container trucks in ports, right-of-way conflicts are prone to occur at container areas and intersections. Especially when operating in container areas, unmanned container trucks are limited by single-vehicle perception and computing power, making it difficult to perform dynamic path planning in the case of multiple vehicles. They often have to park and queue to complete the container area passage, resulting in low operating efficiency. The technical solution disclosed in the present invention can sense the information of traffic participants in the container area in real time, and provide unmanned container trucks with beyond-line-of-sight perception information and local path planning. Figure 2 , roadside equipment, unmanned container trucks AV and manned container trucks NV can use 5G base station communication to obtain the real-time location of obstacles (such as manned container trucks NV) sensed by the roadside, and provide lane change guidance for the unmanned container trucks AV to avoid obstacles NV on the road. For example, when the unmanned container truck AV needs to change lanes to the lane of a manned container truck NV, the possibility of collision when the unmanned container truck AV changes lanes is judged, and lanes are changed when there is no collision risk to ensure the safety of the unmanned container trucks and realize the mixed traffic of manned and unmanned container trucks in the port, so as to avoid unmanned container trucks waiting in line due to obstacles ahead, affecting operational efficiency.

[0077] Exemplarily, when the unmanned container truck drives to the container area, if the unmanned container truck meets the preset conditions, the lane change decision logic is executed, otherwise, the unmanned container truck is prohibited from changing lanes; the preset conditions include that the unmanned container truck drives to the container area where the task end is located and there is a target operating vehicle that is closer to the destination than the corresponding unmanned container truck, and the target operating vehicle is an operating vehicle with a higher priority sequence than the unmanned container truck. Specifically, it can be determined whether the unmanned container truck drives to the container area where the task end is located. If it does not drive to the container area where the task end is located, the lane change decision logic is executed; if the unmanned container truck drives to the container area where the task end is located, it is determined whether the unmanned container truck is the first priority sequence. If so, the lane change decision logic is executed. If not, it is determined whether the operating vehicle with a higher priority sequence than the unmanned container truck is closer to the destination than the unmanned container truck. If so, the lane change decision logic is executed. If not, the lane change is prohibited. Specifically, when the unmanned container truck drives to the container area, the gRPC local path planning interface is called, and the collaborative planning service is used to determine the lane change strategy in the container area. When the unmanned container truck meets the preset conditions, the lane change decision logic related to this field can be specifically adopted. When the unmanned container truck meets the preset conditions, the lane change decision logic can also be executed based on the collision detection results disclosed in the present invention. Specifically, when judging the unmanned container truck to change lanes, the collision detection between the main vehicle of the unmanned container truck and the traffic participants can be performed to judge whether there is a risk of collision between the unmanned container truck and the traffic participants. When there is no risk of collision, the lane change is executed. It can be known that the lane change decision logic can judge whether to change lanes in advance based on relevant information such as the vehicle path and whether to turn. For example, there are three lanes on the road, the first lane is used for right turns, the second lane is used for straight driving, and the third lane is used for left turns. When the unmanned container truck needs to turn right and the vehicle is in the second lane, it can be judged that the unmanned container truck pre-changes lanes to the first lane. At this time, the collision risk between the unmanned container truck and the traffic participants is judged, and the lane is changed when there is no collision risk.

[0078] Exemplarily, before detecting a collision between a planned path and a traffic participant, the method includes:

[0079] Obtaining first length and width information of the unmanned container truck and second length and width information of the traffic participant;

[0080] Determine the center position and radius of the circle of the unmanned container truck according to the first length and width information;

[0081] Determine the center position and radius of the circle enclosing the traffic participant according to the second length and width information;

[0082] Based on the center position and radius of the circle enclosing the unmanned container truck and the center position and radius of the circle enclosing the traffic participant, the collision risk between the unmanned container truck and the traffic participant is judged.

[0083] It can be known that the collision risk determined is the collision detection result, and the position of the unmanned container truck can be known based on the planned path of the dynamic planning path, and the center position of the circle of the unmanned container truck can be obtained based on the position of the unmanned container truck and the first length and width information.

[0084] Exemplarily, the circumscribed circles of each longitudinal equimolecular rectangle of the unmanned container truck are used as the circle enclosing the unmanned container truck, and the center position and radius of the circle enclosing the unmanned container truck are determined. Specifically, the unmanned container truck is regarded as a rectangle, and the circumscribed circles of each longitudinal equimolecular rectangle of the rectangle are used as the circle enclosing the unmanned container truck. It should be understood that each longitudinal equimolecular rectangle of the rectangle is a sub-rectangle obtained by equally dividing the rectangle in the longitudinal direction (length direction), wherein it can be known that the circle enclosing the unmanned container truck belongs to the circumscribed circles of each longitudinal equimolecular rectangle of the unmanned container truck, and the longitudinal equimolecular rectangle can be constructed, and the circle enclosing the unmanned container truck is obtained based on the constructed longitudinal equimolecular rectangle, but it is not necessary to construct the longitudinal equimolecular rectangle. Correspondingly, the circumscribed circles of each longitudinal equimolecular rectangle of the traffic participant can be used as the circle enclosing the traffic participant, and the center position and radius of the circle enclosing the unmanned container truck can be determined. Specifically, the traffic participant is regarded as a rectangle, and the circumscribed circles of each longitudinal equimolecular rectangle of the rectangle are used as the circle enclosing the traffic participant.

[0085] Exemplarily, the expansion rate value range is matched according to the type of traffic participant, and the number of circles that enclose the corresponding traffic participant is determined according to the expansion rate value range, and the expansion rate is the ratio of the portion of the collision detection area that exceeds the actual area of ​​the object to the actual area of ​​the object. The relationship between the type of traffic participant and the expansion rate value range can be preset to facilitate matching the expansion rate value range according to the type of traffic participant.

[0086] Exemplarily, according to the vehicle heading angle, the center position of the corresponding circle is converted; if the distance between the center of the circle that wraps the unmanned truck and the center of the circle that wraps the traffic participant is less than the sum of the radii of the two circles, it is determined that the unmanned truck and the traffic participant have a collision risk, otherwise it is determined that there is no collision risk between the unmanned truck and the traffic participant. It can be known that, taking the example that the circle that wraps the unmanned truck includes circle A and circle B, and the circle that wraps the traffic participant includes circle C and circle D, if the center distance between circle A and circle C is greater than the sum of the radii of circle A and circle C, or the center distance between circle A and circle D is less than the sum of the radii of circle A and circle D, or the center distance between circle B and circle C is less than the sum of the radii of circle B and circle C, or the center distance between circle B and circle D is less than the sum of the radii of circle B and circle D, then the unmanned truck and the traffic participant have a collision risk, otherwise there is no collision risk.

[0087] For example, with no collision risk as the goal, feasible paths are screened based on collision detection results between the planned path and traffic participants. Specifically, with no collision risk during lane change for unmanned container trucks as the goal, feasible paths are screened based on collision detection results.

[0088] In this embodiment, collision detection is performed on traffic participants for lane change paths, and lane change paths without collision risks are screened out. It can be known that the dynamic path planning of the embodiment of the present disclosure can use a related dynamic path planning algorithm to plan a path.

[0089] Exemplarily, the specific steps of local path planning include:

[0090] Step 1.1: Determine whether the unmanned container truck (main vehicle) is in the destination container area. If not, execute the vehicle lane change decision logic; if yes, go to step 1.2; the destination container area refers to the container area where the end point of the main vehicle's current scheduling task is located.

[0091] Step 1.2: Determine whether the unmanned container truck (main vehicle) is the first priority sequence operating vehicle. If so, execute the vehicle lane change decision logic; if not, go to step 1.3; wherein the first priority sequence vehicle refers to the vehicle that ranks first in the operating order of the operating point in the operating platform.

[0092] Step 1.3: Determine whether all operating vehicles with a higher priority sequence than the main vehicle are closer to the destination than the unmanned container truck (main vehicle). If so, execute the lane change decision logic of the unmanned container truck (main vehicle); if not, prohibit lane change in vehicle decision-making.

[0093] Step 2.1: Obtain the length and width information of all traffic participants and multiple main vehicles at the working platform, represented by l and w respectively.

[0094] Step 2.2: Based on the length and width information of the traffic participant, consider the traffic participant as a rectangle and wrap it with n circles, where 0≤n≤l / w+1, and calculate its radius r, the position of the circle center O and the expansion rate α. Figure 3 , the leftmost circle and the rightmost circle pass through the two vertices of the rectangle. The length of the rectangle is l, the width is w, the radius of the circle is R, and the distance between the leftmost circle and the left side of the rectangle is l inf , the distance between the rightmost circle and the upper side of the rectangle is W inf , W inf , l inf The larger the expansion rate, the greater the expansion rate. Two adjacent circles, the circle on the left and the circle on the right, have four intersections with the corresponding rectangles respectively. The two intersections on the right side of the circle on the left and the two intersections on the left side of the circle on the right coincide with each other. Each circle is the circumscribed circle of each longitudinal equinumerical rectangle of the corresponding rectangle. The expansion rate is the quotient of the part of the collision detection area that exceeds the actual area of ​​the object and the actual area of ​​the object.

[0095] Specifically, radius r, center O i , the expansion rate α can be calculated according to formulas (2), (3) and (4) respectively:

[0096]

[0097]

[0098]

[0099] In formulas (2), (3) and (4), r represents the radius of the circle, w represents the width of the rectangle, l represents the length of the rectangle, n represents the number of circles that wrap the rectangle, and O i represents the center of the ith circle, and α represents the expansion rate.

[0100] Step 2.3: Convert the center of the circle according to the vehicle heading angle θ. The conversion formula is: i ′=(xcosθ-ysinθ, ycosθ+xsinθ), the range of the expansion rate α is set according to the types of different traffic participants, so as to determine the number n of appropriate wrapping circles, and the center O and radius r of the multiple circles calculated by each traffic participant and the main vehicle are transmitted to the planning decision service. Exemplarily, the range of the expansion rate α of each traffic participant can be set by an expert according to the actual situation, or by an operator of the system executing the method according to the actual needs. The types of traffic participants include cars, unmanned trucks, manned trucks, etc. When setting the expansion rate of each type of traffic participant, it can be set according to the flexibility, safety requirements and other characteristics of the traffic participants. Generally, if the flexibility of the traffic participant is high, the expansion rate can be set relatively low, and if the flexibility of the traffic participant is poor, the expansion rate can be set relatively high. For example, if the flexibility of the car is high, the relative expansion rate value can be set low, and if the flexibility of the unmanned truck is poor, the relative expansion rate value can be set high. Generally, if the safety requirements of the traffic participant are lower, the expansion rate is set lower, and if the safety requirements of the traffic participant are higher, the expansion rate is set higher. The circle-wrapped-rectangle algorithm adopted in the present invention effectively solves the problem of coordinated operation of vehicles of different lengths and widths and different types of main vehicles in the scene and real-time collision avoidance.

[0101] Step 2.4: Different from collision detection from a single vehicle perspective, vehicle-road collaboration can provide planning and decision-making services with information on all traffic participants in a local area. When the planning and decision-making service supports collision-free detection of driving paths for multiple main vehicles at the same time, collision detection will be performed on each circle that wraps the main vehicle and each circle that wraps the traffic participant. When the square root of the sum of the squares of the centers of a circle that wraps the main vehicle and a circle that wraps the traffic participant is less than the sum of the radii of the two circles, a collision is determined to have occurred. Otherwise, if the square root of the sum of the squares of the centers of the circle that wraps the main vehicle and the circle that wraps the traffic participant is less than the sum of the radii of the two circles, no collision is determined to have occurred.

[0102] Step 3: Perform local path planning for the unmanned container truck to ensure that there is no collision risk during the planning process. During the path planning process, in order to consider the vehicle driving safety, the vehicle's planned path is required to have no collision with obstacles. Therefore, collision detection between the planned path and obstacles is required during the planning process.

[0103] Step 4: Convert the local path planning path information into protobuf data format, and send the global path planning to the unmanned container truck through the 5G Uu communication link.

[0104] The technical solution disclosed in the present invention introduces vehicle-road collaborative technology, and implements the lane change decision logic of unmanned container trucks in the container area based on port operation scheduling information and combined with real-time environmental conditions.

[0105] The technical solution disclosed in the present invention adopts an improved circle-wrapped-rectangle collision detection algorithm in a lane change path collision risk detection method in a scenario where manned and unmanned container trucks coexist in a port area. The algorithm is based on the vehicle length and width parameters and sets expansion rate parameters for different types of vehicles, which is different from the prior art. The collision judgment parameters required by the algorithm are obtained: the circle radius and the corresponding number of multi-circle center coordinates. The collision risk is judged between the main vehicle and the circles of each traffic participant, so that the cost incurred when colliding with different types of traffic participants is considered in the collision detection.

[0106] See also Figure 4 A collaborative operation system for unmanned container trucks in a port, the system includes a V2X communication module 401, a panoramic data module 402 and a collaborative planning module 403, the lane change decision logic 402 and the collaborative planning module 403 are respectively connected to the V2X communication module 401; the collaborative planning module 403 is used to execute the collaborative operation method for unmanned container trucks in a port according to any embodiment of the present disclosure.

[0107] Exemplary:

[0108] The V2X communication module, specifically a high-dynamic V2X communication module, requires the roadside to provide risk warning and path planning for the vehicle within a delay of 100 milliseconds, which places extremely high demands on the algorithm experiment and communication delay of the vehicle-road cooperative system. The high-dynamic V2X communication module, based on vehicle-road cooperative communication technology, can provide low-latency path planning information services for unmanned container trucks. This module adopts the gRPC communication mechanism and is developed based on the ProtoBuf (Protocol Buffers) serialization protocol. It can connect to multiple platforms, realize fast calls between microservices, and obtain instant feedback. This module builds data gateway capabilities, and based on resource requirements such as data resource sharing between multiple devices and multiple road sections, completes the rapid access and processing of vehicle-side and road-side data. By accessing the operation task data of the port vehicle management platform VMS, it obtains and parses the operation task information of the unmanned container truck and completes the operation task data processing; the protocol parser has V2X encoding and decoding capabilities, and supports converting the original V2X encoding (that is, the UPER encoding in ASN.1) into protobuf format data and memory object data for the protocol conversion module to perform protocol conversion. Due to its fast serialization and deserialization speed, protobuf can improve the vehicle-road BSM communication efficiency; real-time distribution push, and the corresponding V2X message after encoding and decoding is sent down through the 5G Uu communication link, which can serve the uplink and downlink of data at the same time.

[0109] Panoramic data module: realizes the fusion of multi-data of vehicles and roads, including roadside perception and vehicle-side data fusion, that is, based on the collection, aggregation, fusion and calculation of all traffic elements such as vehicle side, road side and environment side, panoramic data is formed to realize real-time, accurate, dynamic, seamless and reliable holographic perception of the traffic environment in the port area. The panoramic data module includes: roadside perception fusion, vehicle-road information fusion, sensor sharing and high-precision map. Roadside fusion perception: by constructing the single-site roadside sensor data and the corresponding point topology map, the filtering results of various roadside perception devices (cameras, lidar) are gathered, and the target information output by different sensors is processed through multi-source data spatiotemporal synchronization, multi-source data smoothing and noise reduction, and multi-source data fusion confidence model to form roadside panoramic data. Vehicle-road information fusion: refers to the fusion of vehicle BSM data (including vehicle positioning, speed, and heading angle) reported to the vehicle-road cooperative system with the roadside panoramic perception structured data, and finally obtains more accurate panoramic data to provide data support for the collaborative planning module. Sensor sharing: Sharing sensor data between vehicles and roadside equipment to enhance the perception of the traffic environment. For example, a vehicle's radar may detect an obstacle ahead and share this information with other vehicles or roadside systems. High-precision maps: Use accurate map data to provide more detailed road information, including lane lines, traffic signs, traffic lights, and other key infrastructure elements. This data can be used to assist navigation and enhance the accuracy of lane change decisions.

[0110] Collaborative planning module: Based on the panoramic data of port traffic, the planning and decision-making capabilities for vehicle driving paths are established, and behavioral decision-making suggestions, local paths, vehicle speed planning, and global path planning are provided for port unmanned container trucks. The driving paths and speeds of multiple vehicles can be optimized locally, and the road network and tasks can be operated efficiently, providing safety and efficiency enhancement for port traffic. The panoramic data here corresponds to the vehicle-road data.

[0111] The exemplary embodiment of the present disclosure also provides an electronic device, including: at least one processor; and a memory connected to the at least one processor. The memory stores a computer program that can be executed by the at least one processor, and the computer program is used to cause the electronic device to perform the method according to the embodiment of the present disclosure when executed by the at least one processor. The collaborative planning module can be an electronic device.

[0112] Exemplary embodiments of the present disclosure also provide a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute the method according to an embodiment of the present disclosure.

[0113] The exemplary embodiments of the present disclosure also provide a computer program product, including a computer program, wherein the computer program is used to cause the computer to perform the method according to the embodiments of the present disclosure when executed by a processor of the computer.

[0114] refer to Figure 5 , a block diagram of an electronic device 500 that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0115] like Figure 5As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0116] A plurality of components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. The input unit 506 may be any type of device capable of inputting information to the electronic device 500, and the input unit 506 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 507 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 508 may include, but is not limited to, a disk, an optical disk. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0117] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above. For example, in some embodiments, the method of the embodiment of the present disclosure may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. In some embodiments, the computing unit 501 may be configured to perform the method of the embodiment of the present disclosure in any other appropriate manner (e.g., by means of firmware).

[0118] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0119] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0120] As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0121] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0122] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0123] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

Claims

1. A collaborative operation method for unmanned container trucks in a port, characterized in that: The method comprises: Obtain vehicle-road data; Based on vehicle-road data, global and local path planning for unmanned container trucks is performed; Among them, the local path planning includes: executing dynamic path planning of unmanned container trucks based on vehicle-road data, and screening feasible paths based on collision detection results between the planned path and traffic participants.

2. The method according to claim 1, characterized in that The method further comprises: The local path planning is integrated into the global path planning and sent to the unmanned container truck.

3. The method according to claim 1, characterized in that The global path planning of the unmanned container truck includes: A heuristic search algorithm is used to determine the global shortest time path based on the starting point and the end point; The heuristic function of the heuristic search algorithm is: the sum of the time from the starting point to the current node, the time from the current node to the selected node and the target time, and the target time is the quotient of the Euclidean distance from the selected node to the end point and the maximum driving speed of the roads in the entire port map.

4. The method according to claim 1, characterized in that The global path planning of the unmanned container truck includes: According to the driving speed information of each road contained in the vehicle-road data, a weighted average of the driving speeds of all vehicles on the same road is used as a recommended driving speed for the corresponding road; According to the driving speed information of each road contained in the vehicle-road data, the maximum value of the driving speeds of the roads in the entire port area map is used as the maximum driving speed of the roads in the entire port area map.

5. The method according to claim 1, characterized in that The method of executing dynamic path planning of unmanned container trucks includes: When the unmanned container truck drives to the container area, if the unmanned container truck meets the preset conditions, the lane change decision logic is executed, otherwise, the unmanned container truck is prohibited from changing lanes; the preset conditions include that the unmanned container truck drives to the container area where the mission end point is located and there is a target operating vehicle that is closer to the destination than the corresponding unmanned container truck, and the target operating vehicle is an operating vehicle with a higher priority sequence than the unmanned container truck.

6. The method according to claim 1, characterized in that Before screening the feasible paths based on the collision detection results between the planned paths and the traffic participants, the method includes: Acquire first length and width information of the unmanned container truck and second length and width information of the traffic participant; Determine the center position and radius of the circle enclosing the unmanned container truck according to the first length and width information; Determine the center position and radius of a circle enclosing the traffic participant according to the second length and width information; Based on the center position and radius of the circle enclosing the unmanned container truck and the center position and radius of the circle enclosing the traffic participant, the collision risk between the unmanned container truck and the traffic participant is determined.

7. The method according to claim 6, characterized in that The determining, according to the first length and width information, the center position and radius of the circle enclosing the unmanned container truck comprises: Taking the circumscribed circles of the longitudinal equinumerical rectangles of the unmanned container truck as the circle enclosing the unmanned container truck, determining the center position and radius of the circle enclosing the unmanned container truck; and / or, Determining the center position and radius of a circle enclosing the traffic participant according to the second length and width information includes: The circumscribed circles of the longitudinal equinumerical rectangles of the traffic participants are used as the circles enclosing the traffic participants, and the center position and radius of the circle enclosing the unmanned container truck are determined.

8. The method according to claim 6, characterized in that The expansion rate value range is matched according to the type of the traffic participant, and the number of circles that wrap the corresponding traffic participant is determined according to the expansion rate value range. The expansion rate is the ratio of the part of the collision detection area that exceeds the actual area of ​​the object to the actual area of ​​the object.

9. The method according to claim 6, characterized in that The step of judging the collision risk between the unmanned container truck and the traffic participant based on the center position and radius of the circle enclosing the unmanned container truck and the center position and radius of the circle enclosing the traffic participant comprises: According to the vehicle heading angle, the center position of the corresponding circle is converted; If the distance between the center of the circle enclosing the unmanned container truck and the center of the circle enclosing the traffic participant is less than the sum of the radii of the two circles, it is determined that the unmanned container truck has a collision risk with the traffic participant; otherwise, it is determined that the unmanned container truck has no collision risk with the traffic participant.

10. The method according to claim 1, characterized in that The screening of feasible paths based on the collision detection results between the planned path and the traffic participants includes: With the goal of eliminating collision risk, feasible paths are screened based on the collision detection results between the planned path and traffic participants.

11. A collaborative operation system for unmanned container trucks in ports, characterized in that: The system includes a V2X communication module, a panoramic data module and a collaborative planning module, wherein the data module and the collaborative planning module are respectively connected to the V2X communication module for communication; The collaborative planning module is used to execute the method according to any one of claims 1 to 10.

Images