A path planning method and system for a heavy truck vehicle in a port in a narrow environment

Abstract

The present application relates to the technical field of automatic driving, in particular to a path planning method and system for heavy truck vehicles in narrow environment in port, the method comprising: a self-unloading heavy truck in port drives along a preset reference line, and real-time obtains port road boundary, obstacle information and vehicle own pose data; when it is detected that an obstacle exists traffic interference to the current reference line, a path fine adjustment function is triggered; based on an improved time elastic band (TEB) algorithm, the pose of the disturbed reference line waypoint is optimized and adjusted under multi-dimensional driving constraint conditions, and a to-be-verified planning trajectory is generated; collision detection and curvature detection are performed on the generated to-be-verified planning trajectory, and according to the detection result, effective trajectory output or cyclic optimization is completed, and a parking protection mechanism is triggered when optimization fails. Through the improved obstacle edge residual error calculation method of the TEB algorithm, efficient path planning of the heavy truck in the narrow straight and curved scenes in the port is realized, and the transportation efficiency is ensured.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, specifically to a path planning method and system for heavy-duty trucks used in ports in narrow environments. Background Technology

[0002] Closed and semi-closed structured road scenarios are core scenarios for the rapid deployment of autonomous driving technology. Among them, port scenarios, with their fixed operation processes and closed driving environments, have become a core application area for autonomous driving technology for heavy trucks. In the transfer transportation scenarios between port terminals and storage yards, narrow passageways often appear due to unstructured roads, temporary barriers, and temporary stacking of goods. In some sections, the passable area is only a few tens of centimeters wider than the heavy truck, and the road boundaries are irregularly distributed. At the same time, the dump trucks used for port transportation have large body size, long wheelbase, and large turning radius. When turning, the vehicle footprint covers a wide area, which places extremely high demands on the accuracy, smoothness, and safety of path planning.

[0003] Current mainstream trajectory planning algorithms for vehicles mostly employ a spatiotemporally decoupled approach, prioritizing path planning followed by velocity planning. This requires modular design and inevitably sacrifices overall solution accuracy, making it difficult to meet the high-precision planning requirements of heavy trucks in confined environments. Existing route smoothing algorithms largely fail to incorporate obstacle constraints into the overall solution framework, and even when they do, they employ a decoupled architecture, failing to achieve globally optimal solutions under multiple constraints. Commonly used obstacle avoidance planning algorithms have high requirements for feasible space, resulting in low space utilization and making them unsuitable for space-constrained scenarios such as narrow straight sections in ports and extreme turns. Furthermore, existing trajectory planning algorithms are primarily applied to passenger vehicles, with few planning schemes specifically for large heavy trucks, and dedicated path planning schemes adapted for heavy trucks operating in confined port environments are even scarcer.

[0004] In the application of the TimeElasticBand (TEB) algorithm based on graph optimization, the existing methods for calculating obstacle edge residuals have inherent flaws: when the vehicle's footprint overlaps with the obstacle's outline, the obstacle distance is determined to be 0, and the residual is a fixed value. This prevents the formation of an optimization direction for residual gradient descent through pose adjustment during g2o optimization, causing obstacle constraint edges to fail. Ultimately, this leads to path planning failures and vehicle breakdowns, affecting not only the operation of individual vehicles but also causing port road congestion and severely impacting platooning efficiency. Therefore, there is an urgent need for a dedicated path planning scheme adapted to the driving characteristics of heavy-duty trucks in ports and optimized for narrow environments to address the aforementioned shortcomings in existing technologies. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, this invention provides a method and system for path planning of heavy-duty trucks used in ports in narrow environments, thereby solving the problems of poor adaptability to narrow scenarios, easy failure of obstacle constraints, insufficient planning accuracy, and low space utilization in existing port heavy-duty truck path planning technologies.

[0006] This invention is achieved through the following technical solution: A method for path planning of heavy-duty trucks used in ports in narrow environments is provided, the method comprising the following steps: Step S10: The port dump truck travels along the preset reference line, and obtains information on the port road boundary, obstacles and the vehicle's own pose data in real time, and detects whether the obstacles interfere with the current reference line. Step S20: When an obstacle is detected to interfere with the current reference line, step S30 is triggered to perform fine path adjustment. When an obstacle is detected to not interfere with the current reference line, the vehicle follows the preset reference line. Step S30: Fine-tuning of the path. Based on the improved time elastic band TEB algorithm, the pose of the disturbed reference line waypoints is optimized and adjusted under multi-dimensional driving constraints to generate the planned trajectory to be verified. Step S40: Perform collision detection and curvature detection on the generated planned trajectory to be verified, complete the output of the effective trajectory based on the detection results, and iteratively optimize the fine-tuning function of the path based on the detection results. If the optimization fails, trigger the parking protection mechanism.

[0007] Preferably, in step S10, the rectangular frame size of the port dump truck body is 12. With a length of 2.7m, a wheelbase of 8m, and a minimum turning radius of 10m, the vehicle acquires real-time information including structured map information of closed / semi-closed roads in the port, information on temporary roadside obstacles and irregular road boundaries collected by onboard sensing equipment, as well as real-time vehicle position, heading angle, and speed data.

[0008] Preferably, in step S20, the criterion for determining whether an obstacle interferes with the current reference line is based on the vehicle's current position and the preset reference line, and predicts whether the vehicle's footprints along the reference line overlap with the obstacle outline and road boundary, or whether the safe passage space for the vehicle is insufficient.

[0009] Preferably, in step S30, the improved time elastic band (TEB) algorithm is based on the principle of graph optimization and is implemented through the g2o optimization library. The vehicle's route pose to be optimized and the time difference between adjacent poses are used as vertices of the graph, and various driving constraints are used as edges of the graph. The vertex pose is adjusted by iteratively calculating the residuals of the edges until the residuals converge to complete the trajectory optimization. The edges of the graph include binary edges of dynamic constraints, unary edges of obstacle constraints, ternary edges of velocity constraints, pentagonal edges of acceleration constraints, unary edges of time-optimal constraints, and unary edges of fixed-point constraints.

[0010] Preferably, the improved Time Elastic Band (TEB) algorithm improves the residual calculation method for unary edges constrained by obstacles. Specifically, when the vehicle's footprint and obstacle contour do not overlap at the current waypoint pose, the obstacle edge residual is calculated based on the minimum distance between the vehicle and the obstacle. When the vehicle's footprint and obstacle contour overlap at the current waypoint pose, the residual is taken as the square root of the area of ​​the overlapping region between the vehicle footprint and the obstacle. This makes the residual smaller as the vehicle adjusts away from the obstacle, thus forming an optimization direction for gradient descent.

[0011] Preferably, the multi-dimensional driving constraints in step S30 include road boundary constraints, obstacle constraints, vehicle size constraints, maximum curvature constraints, non-omnidirectional motion constraints, maximum linear velocity constraints, maximum linear acceleration constraints, maximum angular velocity constraints, and maximum angular acceleration constraints.

[0012] Preferably, step S40 specifically includes: Step S401: Perform full-journey collision detection and curvature compliance detection on the planned trajectory to be verified. If both detections pass, the planning is deemed successful, a valid trajectory is output, and the vehicle is controlled to travel along the trajectory. If the detections fail, proceed to step S402. Step S402: Determine if the current optimization loop count is less than 10. If it is less than 10, use the optimization result of the previous loop as the new reference line and return to step S30 to continue fine-tuning. If the optimization loop count reaches 10 and still fails to pass the test, the planning is determined to have failed, the parking protection mechanism is triggered, and manual intervention or the escape procedure is initiated.

[0013] Furthermore, to achieve the above objectives, the present invention also proposes a path planning system for heavy-duty trucks used in ports in confined environments, the path planning system for heavy-duty trucks used in ports in confined environments comprising: Vehicle tracking and environmental perception module: used for port dump trucks to follow a preset reference line, acquire port road boundary and obstacle information and vehicle pose data in real time, and detect whether obstacles interfere with the current reference line. Path adjustment trigger module: When an obstacle is detected that interferes with the current reference line, it triggers step S30 to perform fine path adjustment. When an obstacle is detected that does not interfere with the current reference line, it follows the preset reference line. The trajectory optimization and solution module is used for fine-tuning of the path. Based on the improved time elastic band TEB algorithm, it optimizes and adjusts the pose of disturbed reference line waypoints under multi-dimensional driving constraints to generate a planned trajectory to be verified. The trajectory verification and output module is used to perform collision detection and curvature detection on the generated planned trajectory to be verified, complete the output of the valid trajectory based on the detection results, and perform fine-tuning of the path in a loop based on the detection results. If the optimization fails, a parking protection mechanism is triggered.

[0014] Furthermore, to achieve the above objectives, the present invention also proposes a path planning device for port heavy-duty trucks in narrow environments. The device includes: a memory, a processor, and a program for path planning of port heavy-duty trucks in narrow environments stored in the memory and executable on the processor. The program for path planning of port heavy-duty trucks in narrow environments comprises the steps for implementing the path planning method for port heavy-duty trucks in narrow environments as described above.

[0015] In addition, to achieve the above objectives, the present invention also provides a computer program product, which includes programs such as path planning for port heavy-duty trucks in narrow environments. When the program such as path planning for port heavy-duty trucks in narrow environments is executed by a processor, it implements a path planning method for port heavy-duty trucks in narrow environments as described above.

[0016] The advantages and effects of this invention are: This invention proposes a path planning method and system for heavy-duty trucks used in ports in narrow environments. It applies an improved TEB graph optimization algorithm to path planning for large heavy-duty trucks in extreme scenarios such as narrow straight sections and curves in ports. This allows for the planning of safe, collision-free, smooth, and continuous driving trajectories, meeting the stability requirements of heavy-duty trucks under heavy loads and preventing structural damage due to trajectory impacts, thus ensuring stable vehicle operation. Furthermore, during path planning, this invention incorporates multi-dimensional constraints such as road boundaries, obstacles, vehicle size, curvature, non-omnidirectional motion, speed, and acceleration into a unified optimization framework. Joint optimization of pose, speed, and acceleration solves the accuracy loss problem of traditional spatiotemporal decoupling planning, significantly improving path planning accuracy in narrow scenarios. In addition, this invention makes a core improvement to the obstacle edge residual calculation method of the TEB algorithm, effectively avoiding the problem of obstacle edge constraint failure when vehicle footprints overlap with obstacle contours. This significantly improves space utilization in narrow port road scenarios, solves the problems of planning failure and vehicle breakdown in extreme narrow road scenarios, avoids port road congestion, and significantly improves the overall efficiency of heavy-duty truck platooning operations in ports. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a path planning method for heavy-duty trucks used in ports in narrow environments, according to the present invention.

[0019] Figure 2 This is a schematic diagram illustrating the graph optimization principle of the improved TEB algorithm provided in an embodiment of the present invention.

[0020] Figure 3 This is a diagram illustrating the path planning effect in a narrow, straight road scenario provided by an embodiment of the present invention.

[0021] Figure 4 This is a diagram illustrating the path planning effect in a narrow curve scenario provided by an embodiment of the present invention.

[0022] Figure 5 This is a schematic diagram of a path planning system for heavy-duty trucks used in ports in narrow environments, according to the present invention.

[0023] Figure 6 This is a schematic block diagram of an electronic device for path planning in narrow environments for heavy-duty trucks used in ports, according to the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] like Figure 1 As shown, in one embodiment of the present invention, a path planning method for heavy-duty trucks used in ports in narrow environments includes the following steps: Step S10: The port dump truck travels along the preset reference line, acquires information on the port road boundary, obstacles and the vehicle's own pose data in real time, and detects whether the obstacles interfere with the current reference line.

[0026] Specifically, this embodiment applies to dump trucks used for parallel transport and transshipment at bulk cargo ports, with a vehicle body rectangular enclosure size of 12. With a length of 2.7m, a wheelbase of 8m, and a minimum turning radius of 10m, this vehicle is suitable for use as a connecting road between enclosed and semi-enclosed port terminals and storage yards, including space-constrained scenarios such as narrow straight roads and narrow bends formed by unstructured roads, temporary barriers, and cargo stacking.

[0027] Specifically, the vehicle follows a global reference line generated by a high-precision map of the port. It collects information on temporary roadside obstacles and irregular road boundaries in real time through onboard LiDAR and high-definition vision cameras. It obtains the position, size and motion data of obstacles through onboard millimeter-wave radar. It obtains its own pose data such as real-time position, heading angle, speed, linear acceleration and angular acceleration through the vehicle's inertial navigation unit, wheel speedometer and GPS / BeiDou dual-mode positioning unit. At the same time, it also obtains information on hard road boundaries and fixed structures in the high-precision map of the port.

[0028] Step S20: When an obstacle is detected to interfere with the current reference line, step S30 is triggered to perform fine path adjustment. When an obstacle is detected to not interfere with the current reference line, the vehicle follows the preset reference line.

[0029] Specifically, in step S20, based on the vehicle's current pose, a preset reference line, and the vehicle's kinematic model, the full-travel footprint of the vehicle along the reference line is predicted. The footprint is generated according to the vehicle's real-time pose and dimensions, covering the inner wheel difference and outward swing area when the vehicle is turning. If the predicted footprint overlaps with the obstacle outline or the hard boundary of the road, it is determined that the obstacle interferes with the current reference line, and the path fine adjustment function is immediately triggered.

[0030] Step S30: Fine-tuning of the path. Based on the improved time elastic band TEB algorithm, the pose of the disturbed reference line waypoints is optimized and adjusted under multi-dimensional driving constraints to generate the planned trajectory to be verified.

[0031] Specifically, in step S30, the improved time-elastic band TEB algorithm is based on graph optimization principles and implemented using the g2o optimization library, such as... Figure 2 As shown in the diagram, the improved TEB algorithm provided in this embodiment of the invention uses the vehicle's route pose to be optimized and the time difference between adjacent poses as vertices of the graph, and various driving constraints as edges of the graph. In each iteration, the residuals of each edge are calculated, and the vertex poses are continuously adjusted by calculating the direction of residual descent until the residuals converge to a preset threshold range, thus completing trajectory optimization.

[0032] The graph vertices include two types: the Pose vertex of the route pose to be optimized, which corresponds to the discrete waypoint position and heading angle of the vehicle on the planned trajectory; and the time difference vertex timediff between adjacent poses, which corresponds to the time dt required for the vehicle to travel between two adjacent waypoints. The edges of the graph include six types: kinematic constraint binary edges (h), used to constrain the non-omnidirectional motion characteristics of vehicles and prevent lateral movement and slippage; obstacle constraint unary edges (ρ), used to constrain the safe distance between vehicles and obstacles and road boundaries; velocity constraint ternary edges (v), used to constrain the linear velocity and angular velocity of vehicles to not exceed the maximum limits; acceleration constraint pentagonal edges (a), used to constrain the linear acceleration and angular acceleration of vehicles to not exceed the maximum limits; time-optimal constraint unary edges (t), used to optimize the overall travel time of the trajectory and ensure transportation efficiency; and fixed-point constraint unary edges, used to fix the start and end points of the trajectory and ensure the connectivity of the trajectory with the global reference line.

[0033] Specifically, the core improvement of the improved Time Elastic Band (TEB) algorithm lies in optimizing the residual calculation method for unary edges constrained by obstacles. The specific improvement strategy is as follows: when the vehicle's footprint at the current waypoint pose does not overlap with the obstacle contour, the obstacle edge residual is calculated based on the minimum distance between the vehicle and the obstacle. The calculation formula is: when the distance between the vehicle and the obstacle, dist, is greater than the minimum safe distance, min_obstacle_dist + ... When the residual error is 0, the residual error is 0; when dist ≤ min_obstacle_dist + At that time, the residual error = (min_obstacle_dist + -dist; where min_obstacle_dist is set to 0.3m based on the port scenario. For safety redundancy, a value of 0.2m is set. When the vehicle's footprint at the current waypoint pose overlaps with the obstacle outline, the existing algorithm determines the obstacle distance as 0, and the residual is a fixed value min_obstacle_dist + Since a gradient descent direction cannot be formed, in this embodiment, the residual is taken as the square root of the area of ​​the overlapping region between the vehicle footprint and the obstacle, i.e., error = Where S is the area of ​​the overlap between the vehicle footprint and the obstacle, so that when the vehicle adjusts away from the obstacle, the smaller the overlap area, the smaller the residual, forming a continuous and effective gradient descent optimization direction. Even if the vehicle overlaps with the obstacle, obstacle avoidance can be achieved through iterative optimization, avoiding the failure of obstacle constraints.

[0034] Specifically, the multi-dimensional driving constraints for trajectory optimization in step S30 include road boundary constraints, obstacle constraints, vehicle size constraints, maximum curvature constraints, non-omnidirectional motion constraints, maximum linear velocity constraints, maximum linear acceleration constraints, maximum angular velocity constraints, and maximum angular acceleration constraints. Among these, the maximum curvature constraint is set to 0.1m based on the vehicle's minimum turning radius. -1 The maximum rate of change of curvature is set to 0.05m. -2 The maximum linear speed is set at 30 km / h according to the port operation speed limit, and the maximum linear acceleration is set at 2 m / s². 2 The maximum linear deceleration is set to 3 m / s². 2 Through multi-constraint joint optimization, the planned trajectory is ensured to meet the kinematic characteristics of heavy trucks and the safe driving requirements of narrow port scenarios.

[0035] Step S40: Perform collision detection and curvature detection on the generated planned trajectory to be verified, complete the output of the effective trajectory based on the detection results, and iteratively optimize the fine-tuning function of the path based on the detection results. If the optimization fails, trigger the parking protection mechanism.

[0036] Specifically, step S40 includes: Step S401: Perform full-journey collision detection and curvature compliance detection on the planned trajectory to be verified. Collision detection generates vehicle footprints in the corresponding pose for each waypoint on the trajectory, verifying that the vehicle footprints do not overlap with obstacles or road boundaries throughout the entire journey, meeting the minimum safe distance requirements. Curvature detection calculates the trajectory curvature and rate of change of curvature for each segment of the trajectory, verifying that they are both within the vehicle's maximum steering capability range, avoiding sharp turns that the vehicle cannot achieve. When both checks pass, the planning is considered successful, a valid trajectory is output, and the vehicle is controlled by the drive-by-wire chassis to travel along the trajectory. If either check fails, proceed to step S402. Step S402: Determine if the current optimization loop count is less than 10. If it is less than 10, use the optimization result of the previous loop as the new reference line and return to step S30 to continue fine-tuning. Gradually approach the compliance trajectory through iterative optimization. If the optimization loop count reaches 10 and still fails to pass the test, the planning is determined to be a failure. The parking protection mechanism is immediately triggered. The vehicle is controlled to brake smoothly and stop through the vehicle's brake-by-wire system. At the same time, a planning failure alarm is sent to the port dispatch center, waiting for manual takeover or the vehicle extrication procedure to be initiated.

[0037] like Figure 3 The diagram shown is a path planning effect diagram for a narrow straight road scenario in this embodiment. The green route is the original reference line before adjustment, the red arrow is the planned trajectory after optimization and adjustment, the red rectangle is the vehicle's footprint after adjustment, and the irregular red polygons on both sides are non-standard roadside obstacles. The optimized trajectory can achieve smooth, collision-free driving in a narrow straight road that is only a few tens of centimeters wider than the vehicle width, making full use of the narrow passage space.

[0038] like Figure 4 The diagram shown is a path planning effect diagram for a narrow curve scenario in this embodiment. The green route is the original reference line before adjustment, the red arrow is the planned trajectory after optimization and adjustment, the red and yellow rectangles are the vehicle body footprints after adjustment, and the irregular red polygons on both sides are non-standard roadside obstacles. The optimized trajectory can fully adapt to the turning characteristics of heavy trucks, cover the inner wheel difference and outer swing area of ​​the vehicle during turning, and achieve collision-free turning in narrow curves, solving the planning problem of extreme turning scenarios for large heavy trucks.

[0039] In addition, such as Figure 5 As shown, in one embodiment of the present invention, a path planning system for port heavy-duty trucks in narrow environments is proposed. The path planning system for port heavy-duty trucks in narrow environments includes: Vehicle tracking and environmental perception module: used for port dump trucks to follow a preset reference line, acquire port road boundary and obstacle information and vehicle pose data in real time, and detect whether obstacles interfere with the current reference line. Path adjustment trigger module: When an obstacle is detected that interferes with the current reference line, it triggers step S30 to perform fine path adjustment. When an obstacle is detected that does not interfere with the current reference line, it follows the preset reference line. The trajectory optimization and solution module is used for fine-tuning of the path. Based on the improved time elastic band TEB algorithm, it optimizes and adjusts the pose of disturbed reference line waypoints under multi-dimensional driving constraints to generate a planned trajectory to be verified. The trajectory verification and output module is used to perform collision detection and curvature detection on the generated planned trajectory to be verified, complete the output of the valid trajectory based on the detection results, and perform fine-tuning of the path in a loop based on the detection results. If the optimization fails, a parking protection mechanism is triggered.

[0040] This application provides a path planning system for port heavy-duty trucks in confined environments. Employing a path planning method for port heavy-duty trucks in confined environments as described in the above embodiments, it solves the technical problems of poor adaptability to confined spaces, easy failure of obstacle constraints, insufficient planning accuracy, and low space utilization in existing port heavy-duty truck path planning technologies. Compared with the prior art, the beneficial effects of the path planning system for port heavy-duty trucks in confined environments provided in this application are the same as those of the path planning method for port heavy-duty trucks in confined environments provided in the above embodiments. Furthermore, other technical features of the path planning system for port heavy-duty trucks in confined environments are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0041] This application provides a path planning device for heavy-duty trucks used in ports in narrow environments. The path planning device for heavy-duty trucks used in ports in narrow environments includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the path planning method for heavy-duty trucks used in ports in narrow environments as described in Embodiment 1 above.

[0042] like Figure 6As shown in the illustration, in one embodiment of the present invention, a schematic diagram of a path planning device suitable for implementing the embodiments of this application for port heavy-duty trucks in confined environments is presented. The path planning device for port heavy-duty trucks in confined environments in this application embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), etc., as well as fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The illustrated path planning device for heavy-duty trucks in narrow environments at ports is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0043] Figure 6 The illustrated path planning device for port heavy-duty trucks in confined environments may include a processor 1001 (e.g., a central processing unit, graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a machine-readable storage medium (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the path planning device for port heavy-duty trucks in confined environments. The processor 1001, the read-only memory 1002, and the machine-readable storage medium 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and a communication unit 1009. Communication unit 1009 allows a path planning device for a port heavy-duty truck in a confined environment to exchange data wirelessly or via wired communication with other devices. Although a path planning device for a port heavy-duty truck in a confined environment with various systems is shown in the figure, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0044] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication unit, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processor 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0045] This application provides a path planning device for port heavy-duty trucks in confined environments. Employing a path planning method for port heavy-duty trucks in confined environments as described in the above embodiments, it solves the technical problems of poor adaptability to confined spaces, easy failure of obstacle constraints, insufficient planning accuracy, and low space utilization in existing port heavy-duty truck path planning technologies. Compared with the prior art, the beneficial effects of the path planning device for port heavy-duty trucks in confined environments provided in this application are the same as those of the path planning method for port heavy-duty trucks in confined environments provided in the above embodiments. Furthermore, other technical features of this path planning device for port heavy-duty trucks in confined environments are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0046] The various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0047] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for path planning of heavy-duty trucks for use in ports in confined environments.

[0048] The computer program product provided in this application can solve the technical problems of poor adaptability to narrow scenarios, easy failure of obstacle constraints, insufficient planning accuracy, and low space utilization in existing port heavy truck path planning technology. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the path planning method for port heavy trucks in narrow environments provided in the above embodiments, and will not be repeated here.

[0049] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A path planning method for heavy-duty trucks used in ports in confined environments, characterized in that, The method includes the following steps: Step S10: The port dump truck travels along the preset reference line, and obtains information on the port road boundary, obstacles and the vehicle's own pose data in real time, and detects whether the obstacles interfere with the current reference line. Step S20: When an obstacle is detected to interfere with the current reference line, step S30 is triggered to perform fine path adjustment. When an obstacle is detected to not interfere with the current reference line, the vehicle follows the preset reference line. Step S30: Fine-tuning of the path. Based on the improved time elastic band TEB algorithm, the pose of the disturbed reference line waypoints is optimized and adjusted under multi-dimensional driving constraints to generate the planned trajectory to be verified. Step S40: Perform collision detection and curvature detection on the generated planned trajectory to be verified, complete the output of the effective trajectory based on the detection results, and iteratively optimize the fine-tuning function of the path based on the detection results. If the optimization fails, trigger the parking protection mechanism.

2. The method for path planning of heavy-duty trucks in narrow environments for use in ports according to claim 1, characterized in that, In step S10, the information acquired in real time includes structured map information of the port's closed / semi-closed roads, information on temporary roadside obstacles and irregular road boundaries collected by the vehicle-mounted sensing device, and real-time vehicle position, heading angle, and driving speed data.

3. The method for path planning of heavy-duty trucks in narrow environments for use in ports according to claim 1, characterized in that, In step S20, the criterion for detecting that an obstacle interferes with the current reference line is to predict whether the vehicle's footprints along the reference line overlap with the outline of the obstacle or the road boundary, or whether the safe passage space for the vehicle is insufficient, based on the vehicle's current position and the preset reference line.

4. The method for path planning of heavy-duty trucks in narrow environments for use in ports according to claim 1, characterized in that, In step S30, the improved time elastic band (TEB) algorithm is based on the principle of graph optimization and is implemented through the g2o optimization library. The vehicle's route pose to be optimized and the time difference between adjacent poses are used as vertices of the graph, and various driving constraints are used as edges of the graph. The vertex pose is adjusted by iteratively calculating the residuals of the edges until the residuals converge to complete the trajectory optimization. The edges of the graph include binary edges of dynamic constraints, unary edges of obstacle constraints, ternary edges of velocity constraints, pentagonal edges of acceleration constraints, unary edges of time-optimal constraints, and unary edges of fixed-point constraints.

5. The method for path planning of heavy-duty trucks in narrow environments for use in ports according to claim 4, characterized in that, The improved Time Elastic Band (TEB) algorithm improves the residual calculation method for unary edges constrained by obstacles. Specifically, when the vehicle's footprint and obstacle contour do not overlap at the current waypoint pose, the obstacle edge residual is calculated based on the minimum distance between the vehicle and the obstacle; when the vehicle's footprint and obstacle contour overlap at the current waypoint pose, the residual is taken as the square root of the area of ​​the overlapping region between the vehicle footprint and the obstacle.

6. The method for path planning of heavy-duty trucks in narrow environments for use in ports according to claim 1, characterized in that, The multi-dimensional driving constraints in step S30 include road boundary constraints, obstacle constraints, vehicle size constraints, maximum curvature constraints, non-omnidirectional motion constraints, maximum linear velocity constraints, maximum linear acceleration constraints, maximum angular velocity constraints, and maximum angular acceleration constraints.

7. The method for path planning of heavy-duty trucks in narrow environments for use in ports according to claim 1, characterized in that, Step S40 specifically includes: Step S401: Perform full-journey collision detection and curvature compliance detection on the planned trajectory to be verified. If both detections pass, the planning is deemed successful, a valid trajectory is output, and the vehicle is controlled to travel along the trajectory. If the detections fail, proceed to step S402. Step S402: Determine if the current number of optimization loops is less than 10. If it is less than 10, use the optimization result of the previous loop as the new reference line and return to step S30 to continue fine-tuning. If the number of optimization loops reaches 10 and still fails to pass the test, the planning is determined to have failed, the parking protection mechanism is triggered, and the vehicle waits for manual intervention or the vehicle extrication procedure is started.

8. A path planning system for heavy-duty trucks used in ports in confined environments, characterized in that, The system executes the path planning method for port heavy-duty trucks in narrow environments as described in claim 1, including: Vehicle tracking and environmental perception module: used for port dump trucks to follow a preset reference line, acquire port road boundary and obstacle information and vehicle pose data in real time, and detect whether obstacles interfere with the current reference line. Path adjustment trigger module: When an obstacle is detected that interferes with the current reference line, it triggers step S30 to perform fine path adjustment. When an obstacle is detected that does not interfere with the current reference line, it follows the preset reference line. The trajectory optimization and solution module is used for fine-tuning of the path. Based on the improved time elastic band TEB algorithm, it optimizes and adjusts the pose of disturbed reference line waypoints under multi-dimensional driving constraints to generate a planned trajectory to be verified. The trajectory verification and output module is used to perform collision detection and curvature detection on the generated planned trajectory to be verified, complete the output of the valid trajectory based on the detection results, and perform fine-tuning of the path in a loop based on the detection results. If the optimization fails, a parking protection mechanism is triggered.

9. A path planning device for heavy-duty trucks used in ports in confined spaces, characterized in that, include: The present invention includes a memory, a processor, and a path planning program for a port heavy-duty truck in a narrow environment, which is stored in the memory and can run on the processor. When the path planning program for a port heavy-duty truck in a narrow environment is executed by the processor, the path planning program for a port heavy-duty truck in a narrow environment implements a path planning method for a port heavy-duty truck in a narrow environment as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a path planning program for port heavy-duty trucks in narrow environments, which, when executed by a processor, implements a path planning method for port heavy-duty trucks in narrow environments as described in any one of claims 1 to 7.

Images