Parking path generation method and device
By applying parking optimization algorithms and dynamic planning technology in open-pit mines, target parking paths are generated, and the problems of complex path interleaving and unstable planning starting points in the existing technology are solved, transportation efficiency and safety are improved, and operation costs are reduced.
Patent Information
- Application Number
- CN202510290320.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-12
- Publication Date
- 2025-06-06
AI Technical Summary
The existing open-pit mine excavation site docking position planning technology has problems such as complex path interlacing, unstable planning starting points, cumbersome map drawing and untimely updates, resulting in low transportation efficiency and high safety risks.
The parking optimization algorithm is used in combination with dynamic planning, and the target docking path is generated based on the longitude and latitude coordinates of the target to be parked and the path information of the first main path, allowing the target vehicle to be used as the initial starting point at any position of the first main path to avoid path interleaving and instability in the planning starting point.
It improves the efficiency and safety of unloading operations during the transportation of materials in open-pit mines, reduces the workload and operation costs of professionals, and adapts to the dynamic changes in the mining environment.
Smart Images

Figure CN120096551A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of data processing, and in particular to a parking path generation method and device. Background Art
[0002] With the rapid development of science and technology, artificial intelligence technology has made significant progress, and the application of unmanned driving technology in closed scenarios has become more and more extensive. In the unmanned transportation scenario of open-pit mines, the material unloading operation is a key link in the entire transportation process. From the perspective of intelligence, safety and efficiency, reasonable planning of the driving path of unmanned vehicles entering the spoil dump is not only a necessary prerequisite for achieving efficient and safe unloading operations, but also the core of improving the working efficiency of the entire unmanned transportation system.
[0003] At present, when unmanned vehicles enter the spoil dump and plan the parking path, they mainly rely on the map module to pre-draw a main entry path and a main exit path, and the parking algorithm selects the planning starting point on these fixed main paths. However, in actual open-pit mine production operations, this method exposes many problems. On the one hand, the space of the spoil dump is usually limited. In order to improve the planning success rate, the main path length is often set shorter to expand the search space of the parking algorithm. But this practice has caused a series of serious problems: when multiple bulldozers select multiple parking spaces at the same time, the planning starting point often appears the same, resulting in the planned parking paths being intertwined and complicated, which brings great difficulties to road right control. In a narrow spoil dump environment with frequent vehicle traffic, path interlacing can easily cause vehicle collisions, congestion and other situations, seriously reducing transportation efficiency. At the same time, map drawing is cumbersome, requiring professionals to spend a lot of time and energy to operate, which increases the workload and difficulty of map drawing personnel. Moreover, the mining environment is complex and changeable, and untimely map updates will lead to deviations in path planning, further affecting the normal progress of transportation operations.
[0004] On the other hand, in a large spoil dump, the traditional method is often to manually drive the vehicle to a fixed position first, which is used as the planning starting point of the algorithm. However, this method is limited by factors such as the vehicle heading angle, and some spatial pointing operations are prone to failure, resulting in a reduced planning success rate. For example, when the terrain where the vehicle is located is complex, with slopes, obstacles, etc., the planning starting point determined by manual driving may not meet the requirements of the algorithm, causing subsequent path planning to fail. This brings a lot of inconvenience to bulldozer operators and further affects transportation efficiency. In addition, as the spoil dump boundary is constantly updated, the planning starting point of the algorithm needs to be constantly changed to meet the algorithm requirements. Frequent adjustment of the planning starting point seriously reduces work efficiency and increases operating costs.
[0005] In summary, the existing open-pit mine dump parking space planning technology has many shortcomings, and an innovative method is urgently needed to solve these problems in order to improve the efficiency and safety of unloading operations during open-pit mine material transportation. Summary of the invention
[0006] In view of this, an embodiment of the present application provides a parking path generation method and device, which can improve the unloading efficiency and safety during the material transportation process in an open-pit mine.
[0007] In a first aspect, an embodiment of the present application provides a parking path generation method, comprising:
[0008] Receiving a target waiting point for parking the target vehicle sent by the target vehicle at the initial starting point; the target waiting point is located within a preset range of the spoil dump; the initial starting point is any point on the first main path leading into the spoil dump;
[0009] Acquire first longitude and latitude coordinates, second longitude and latitude coordinates, and path information corresponding to the first main path; the first longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the initial starting point; the second longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the target to-be-stopped point; the path information includes the longitude and latitude coordinates corresponding to the first main path and path boundary information;
[0010] Based on a parking optimization algorithm, analyzing and reasoning are performed in combination with the first longitude and latitude coordinates, the second longitude and latitude coordinates and the path information of the first main path to generate a target parking path; the parking optimization algorithm is to perform dynamic planning according to the longitude and latitude coordinates corresponding to the target parking point;
[0011] The target parking path is sent to a target vehicle control system to instruct the target vehicle to park at the target to-be-parked point.
[0012] As an optional implementation of the embodiment of the present application, the parking optimization algorithm is used to analyze and reason based on the longitude and latitude coordinates and the path information of the first main path to generate a target parking path, including:
[0013] Determine a target transition point in the first main path by combining the first longitude and latitude coordinates and the second longitude and latitude coordinates through the parking optimization algorithm;
[0014] The target parking path is generated based on the first longitude and latitude coordinates, the target transition point, and the path information of the first main path.
[0015] As an optional implementation of the embodiment of the present application, determining the target transition point in the first main path by combining the first longitude and latitude coordinates and the second longitude and latitude coordinates through the parking optimization algorithm includes:
[0016] For each point in the first main path, calculate a first distance between the point and the second longitude and latitude coordinates, and a second distance between the point and the second longitude and latitude coordinates, and select points where the sum of the first distance and the second distance is within a first threshold range, so as to generate a set of candidate transition points;
[0017] For each point in the candidate transition point set, the angle between the first main path direction and the second longitude and latitude coordinates is obtained to determine the target transition point according to the angle.
[0018] As an optional implementation of the embodiment of the present application, the generating of the target parking path based on the first longitude and latitude coordinates, the target transition point and the path information of the first main path includes:
[0019] With the target transition point as the center point, the target parking path is generated by combining the first longitude and latitude coordinates, the second longitude and latitude coordinates, the target transition point and the path information of the first main path within a preset range around the target transition point.
[0020] As an optional implementation of the embodiment of the present application, the sending of the target parking path to the target vehicle control system to instruct the target vehicle to park at the target to-be-parked point includes:
[0021] A task file is generated based on the target parking path, and the task file is sent to the target vehicle control system, so that the target vehicle control system controls the target vehicle to park until the target parking point according to the task file in combination with a tracking method.
[0022] As an optional implementation of the embodiment of the present application, after sending the target parking path to the target vehicle control system to instruct the target vehicle to park at the target to-be-parked point, the method further includes:
[0023] Receiving a target operation completion notification; the target operation completion notification is used to indicate that the target vehicle has completed the target operation at the target waiting point;
[0024] In response to the target operation completion notification, the target vehicle is instructed to leave the spoil dump via a target parking exit path.
[0025] As an optional implementation of the embodiment of the present application, the method further includes:
[0026] The target exit path is generated according to the second longitude and latitude coordinates and the path information corresponding to the second main path.
[0027] In a second aspect, an embodiment of the present application provides a parking path generation device, including:
[0028] A receiving unit is used to receive a target waiting point for the target vehicle to stop, which is sent by the target vehicle at the initial starting point; the target waiting point is located within a preset range of the spoil dump; the initial starting point is any point on the first main path leading into the spoil dump;
[0029] an acquisition unit, configured to acquire first longitude and latitude coordinates, second longitude and latitude coordinates, and path information corresponding to the first main path; the first longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the initial starting point; the second longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the target to-be-stopped point; the path information includes the longitude and latitude coordinates corresponding to the first main path and path boundary information;
[0030] a generating unit, configured to generate a target parking path by analyzing and reasoning based on a parking optimization algorithm in combination with the first longitude and latitude coordinates, the second longitude and latitude coordinates, and the path information of the first main path; the parking optimization algorithm is a dynamic planning based on the longitude and latitude coordinates corresponding to the target parking point;
[0031] The instruction unit is used to send the target parking path to the target vehicle control system to instruct the target vehicle to park at the target to-be-parked point.
[0032] As an optional implementation of an embodiment of the present application, the generation unit is specifically used to determine the target transition point in the first main path through the parking optimization algorithm in combination with the first longitude and latitude coordinates and the second longitude and latitude coordinates; based on the first longitude and latitude coordinates, the target transition point and the path information of the first main path, generate the target parking path.
[0033] As an optional implementation of the embodiment of the present application, the generation unit is specifically used to calculate, for each point in the first main path, the first distance between it and the second longitude and latitude coordinates, and the second distance to the second longitude and latitude coordinates, and filter out points where the sum of the first distance and the second distance is within a first threshold range to generate a set of candidate transition points; for each point in the set of candidate transition points, obtain the angle between the direction of the first main path and the second longitude and latitude coordinates to determine the target transition point based on the angle.
[0034] As an optional implementation of an embodiment of the present application, the generation unit is specifically used to generate the target parking path by taking the target transition point as the center point and combining the first longitude and latitude coordinates, the second longitude and latitude coordinates, the target transition point and the path information of the first main path within a preset range around the target transition point.
[0035] As an optional implementation of the embodiment of the present application, the control unit is specifically used to generate a task file based on the target parking path, and send the task file to the target vehicle control system, so that the target vehicle control system controls the target vehicle to park according to the task file in combination with the tracking method until the target parking point.
[0036] As an optional implementation of an embodiment of the present application, the control unit is also used to receive a target operation completion notification; the target operation completion notification is used to indicate that the target vehicle has completed the target operation at the target waiting point; in response to the target operation completion notification, the target vehicle is instructed to leave the spoil dump through a target parking path.
[0037] As an optional implementation of the embodiment of the present application, the control unit is also used to respond to the target operation completion notification and generate the target exit path according to the second longitude and latitude coordinates and the path information corresponding to the second main path; the second main path is the main path for exiting the spoil dump.
[0038] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the parking path generation method described in any one of the above embodiments when executing the computer program.
[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a computing device, the computing device implements the parking path generation method described in any one of the above embodiments.
[0040] The parking path generation method provided in the embodiment of the present application is specifically as follows: receiving a target to-be-parked point for parking the target vehicle sent by a target vehicle located at an initial starting point; the target to-be-parked point is located within a preset range of a spoil dump; the initial starting point is any point on a first main path entering the spoil dump; obtaining first longitude and latitude coordinates, second longitude and latitude coordinates, and path information corresponding to the first main path; the first longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the initial starting point; the second longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the target to-be-parked point; the path information includes longitude and latitude coordinates and path boundary information corresponding to the first main path; based on a parking optimization algorithm, analyzing and reasoning is performed in combination with the first longitude and latitude coordinates, the second longitude and latitude coordinates, and the path information of the first main path to generate a target parking path; the parking optimization algorithm is to perform dynamic planning based on the longitude and latitude coordinates corresponding to the target to-be-parked point; and the target parking path is sent to a target vehicle control system to instruct the target vehicle to park at the target to-be-parked point. The present application allows the target vehicle to use any position of the first main path as the initial starting point, and then plans the path in combination with the initial starting point, the target waiting point and the first main path to obtain the target parking path. Compared with the prior art in which the algorithm independently selects the initial starting point or fixes the initial starting point, the present application can be used more conveniently and avoid the problem of the same and conflicting target parking paths obtained by multiple vehicles at the same starting point. At the same time, since the present application abandons the traditional method of relying on the map module to pre-draw the path, the workload of professionals in drawing and updating maps is reduced, and the labor cost is reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0043] Figure 1 One of the flow charts of the steps of the parking path generation method provided in the embodiment of the present application;
[0044] Figure 2 A schematic diagram of a parking path provided in an embodiment of the present application;
[0045] Figure 3 A schematic diagram of a parking path generated by the parking path generation method provided in an embodiment of the present application;
[0046] Figure 4 A second flowchart of the method for generating a parking path provided in an embodiment of the present application;
[0047] Figure 5 A schematic diagram of the structure of a parking path generation device provided in an embodiment of the present application;
[0048] Figure 6 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0049] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.
[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.
[0051] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way. In addition, in the description of the embodiments of the present application, unless otherwise specified, the meaning of "multiple" refers to two or more.
[0052] It should be noted that, in this article, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.
[0053] The present application embodiment provides a parking path generation method, referring to Figure 1 As shown, the parking path generation method includes the following steps S101-S104:
[0054] S101, receiving a target to-be-stopped point for the target vehicle to park sent by the target vehicle at the initial starting point.
[0055] Among them, the target docking point is located within a preset range of the spoil dump; and the initial starting point is any point on the first main path leading into the spoil dump.
[0056] In the operation scenario of an open-pit mine spoil dump, a bulldozer is often required to load and unload soil. In this scenario, the target vehicle is a bulldozer. When the target vehicle travels to any point on the first main path into the spoil dump, the automatic parking path generation process of the embodiment of the present application can be entered.
[0057] Among them, the first main path can be understood as the name of the main path used to enter the spoil dump. Then, when a bulldozer is needed to load and unload soil, the bulldozer can be driven to any point on the first main path, and then any point on the first main path can be used as the starting point for subsequently generating a target parking path. Starting from this starting point, parking paths to different parking positions are generated to achieve dynamic path planning according to changes in parking positions.
[0058] Furthermore, when the bulldozer travels to any point on the first main path, the driver can use the vehicle-mounted collaborative operation terminal installed on the bulldozer to specify the target stopping point within the preset range. At the same time, the vehicle-mounted collaborative operation terminal will feed back the information of the target stopping point to the intelligent cloud control platform subsystem in real time to ensure timely transmission and updating of information. Furthermore, after receiving the target stopping point, the intelligent cloud control platform subsystem will immediately execute subsequent steps S102 to S104.
[0059] S102: Obtain first longitude and latitude coordinates, second longitude and latitude coordinates, and path information corresponding to the first main path.
[0060] Among them, the first longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the initial starting point; the second longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the target stopping point; and the path information includes the longitude and latitude coordinates corresponding to the first main path and path boundary information.
[0061] In some embodiments, the first longitude and latitude coordinates are the current location of the target vehicle, that is, any point on the first main path, which is the starting point of the path planning for the target vehicle to reach the target stop; the second longitude and latitude coordinates specify the location of the current target to-be-stopped point, which is the end point of the path planning. The longitude and latitude coordinates in the path information of the first main path are used to fully describe the trajectory corresponding to the main path, while the path boundary information defines the range boundary that the target vehicle can use during driving to prevent the vehicle from deviating from the main path or driving out of the safe area.
[0062] Specifically, the first longitude and latitude coordinates and the second longitude and latitude coordinates can be obtained with the help of a high-precision global positioning system (GPS) or other positioning technologies; the path information can be collected in advance by staff and stored in the intelligent cloud control platform subsystem, and called when needed.
[0063] It should be noted that the first longitude and latitude coordinates may correspond to the coordinates of the center point of the rectangular box corresponding to the current target vehicle position, and the second longitude and latitude coordinates may correspond to the coordinates of the center point of the rectangular box corresponding to the parking space of the target parking point.
[0064] S103: Based on a parking optimization algorithm, analyze and infer the first longitude and latitude coordinates, the second longitude and latitude coordinates, and the path information of the first main path to generate a target parking path.
[0065] The parking optimization algorithm is dynamically planned according to the longitude and latitude coordinates corresponding to the target parking point.
[0066] In an embodiment of the present application, the parking optimization algorithm will be installed in the intelligent cloud control platform subsystem, and after obtaining the first longitude and latitude coordinates, the second longitude and latitude coordinates, and the path information corresponding to the first main path, the intelligent cloud control platform subsystem will immediately call the parking optimization algorithm for analysis and reasoning.
[0067] Specifically, the first longitude and latitude coordinates (the starting point coordinates of the target vehicle), the second longitude and latitude coordinates (the coordinates of the target parking point) and the path information of the first main path can be used as algorithm inputs, and further analyzed and reasoned through the parking optimization algorithm. In the reasoning process, the terrain of the spoil dump, the obstacle distribution and the vehicle's own dynamic characteristics (such as the minimum turning radius, the maximum driving speed, etc.) can also be comprehensively considered. Then, through calculation and reasoning, while meeting various conditions, an optimal target parking path can be selected to ensure that the vehicle can safely and efficiently drive from the starting point of the main path to the target parking point.
[0068] Exemplarily, the parking optimization algorithm can be an algorithm based on machine learning, for example, a reinforcement learning algorithm in deep learning, such as a deep Q network (DQN). In this method, the algorithm takes the environmental state of the spoil dump (including main path information, stop point location, terrain, obstacle distribution, etc.) as input, and obtains the optimal actions under different states (such as selecting a planning starting point, adjusting the driving direction, etc.) through continuous trial and error learning by the intelligent agent in the environment. After a lot of training, the intelligent agent can learn to autonomously select a suitable planning starting point and plan an efficient parking path based on the stop point location specified by the bulldozer in different spoil dump scenarios, and can dynamically adjust the path according to the real-time changing environment.
[0069] It should be noted that the parking optimization algorithm adopts a dynamic planning strategy and performs calculations based on the longitude and latitude coordinates of the target parking point, thereby realizing real-time planning of the optimal path according to the dynamic transformation of the target parking point.
[0070] S104: Send the target parking path to a target vehicle control system to instruct the target vehicle to park at the target to-be-parked point.
[0071] After obtaining the target parking path in step S103, the intelligent cloud control platform subsystem sends the generated target parking path to the control system of the target vehicle, and the target parking path can be transmitted to the target vehicle through wireless communication technology or other data transmission methods. Then, when the vehicle control system receives the target parking path, it will convert it into specific control instructions, such as controlling the steering, acceleration, deceleration and other operations of the vehicle, to guide the vehicle to accurately drive along the planned path.
[0072] During the process, the vehicle will use a specific tracking method (such as pure tracking method) to ensure that the deviation between the actual driving path and the planned path is controlled within the preset error range to achieve accurate docking. This not only ensures that the vehicle can accurately dock at the target docking point, improves the efficiency of unloading operations, but also reduces the safety risks and material spillage caused by inaccurate docking.
[0073] Taking a mining area as an example, the parking route planning map generated by the existing technology is referenced Figure 2 shown; can be seen in Figure 2 In the example, the starting points of the generated paths are all concentrated together, resulting in a very cramped path, which affects the entry and exit of vehicles in the spoil dump.
[0074] The path planning generated by the method of the embodiment of the present application is as follows Figure 3 As shown, the planning starting point is automatically adjusted according to the longitude and latitude of the stop position to avoid complex and intertwined generated paths.
[0075] The parking path generation method provided in the embodiment of the present application is specifically as follows: receiving a target to-be-parked point for parking the target vehicle sent by a target vehicle located at an initial starting point; the target to-be-parked point is located within a preset range of a spoil dump; the initial starting point is any point on a first main path entering the spoil dump; obtaining first longitude and latitude coordinates, second longitude and latitude coordinates, and path information corresponding to the first main path; the first longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the initial starting point; the second longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the target to-be-parked point; the path information includes longitude and latitude coordinates and path boundary information corresponding to the first main path; based on a parking optimization algorithm, analyzing and reasoning is performed in combination with the first longitude and latitude coordinates, the second longitude and latitude coordinates, and the path information of the first main path to generate a target parking path; the parking optimization algorithm is to perform dynamic planning based on the longitude and latitude coordinates corresponding to the target to-be-parked point; and the target parking path is sent to a target vehicle control system to instruct the target vehicle to park at the target to-be-parked point. This application allows the target vehicle to use any position of the first main path as the initial starting point, and then plans the path in combination with the initial starting point, the target waiting point and the first main path to obtain the target parking path. Compared with the prior art in which the algorithm independently selects the initial starting point or fixes the initial starting point, this application can be used more conveniently and avoid the problem of the same or conflicting target parking paths obtained by multiple vehicles at the same starting point. At the same time, since this application abandons the traditional method of relying on the map module to pre-draw the path, it reduces the workload of professionals in drawing and updating maps and reduces labor costs. As an extension and refinement of the above embodiment, refer to Figure 4 As shown, the embodiment of the present application also provides another parking path generation method, and the specific steps include the following:
[0076] S401, receiving a target to-be-stopped point for the target vehicle to park sent by the target vehicle at the initial starting point.
[0077] Among them, the target docking point is located within a preset range of the spoil dump; and the initial starting point is any point on the first main path leading into the spoil dump.
[0078] It should be noted that the description of this step can refer to the description of the above step S101, which will not be repeated here.
[0079] S402: Obtain first longitude and latitude coordinates, second longitude and latitude coordinates, and path information corresponding to the first main path.
[0080] Among them, the first longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the initial starting point, and the second longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the target stopping point; the path information includes the longitude and latitude coordinates corresponding to the first main path and path boundary information.
[0081] It should be noted that the description of this step can refer to the description of the above step S102, which will not be repeated here.
[0082] S403: Determine a target transition point in the first main path by using the parking optimization algorithm and combining the first longitude and latitude coordinates with the second longitude and latitude coordinates.
[0083] In an embodiment of the present application, when planning a path from an initial starting point corresponding to a first longitude and latitude coordinate to an end point corresponding to a second longitude and latitude coordinate, since the first longitude and latitude coordinates of multiple bulldozers are different and their target stopping points may also be different, it is necessary to screen and match the optimal path in real time according to the positions of different initial starting points and target stopping points; in this process, determination of the target transition point is particularly important.
[0084] Specifically, the target transition point is a point on the first main path that has the highest matching degree with the initial starting point and the target to-be-stopped point; the matching degree of each point on the first main path with the initial starting point and the target to-be-stopped point can be comprehensively evaluated, and then the best point can be selected as the target transition point. For example, a point that is short in distance from both the initial starting point and the target to-be-stopped point and has a relatively reasonable change in steering angle when the vehicle is driving toward the stop point will be preferentially selected, thereby reducing the energy loss and path complexity of the vehicle during driving, making driving smoother and more efficient.
[0085] Since the initial starting point and the target stopping point will be adjusted dynamically in real time according to the actual situation of the spoil dump, the target transition point will also change. When the bulldozer updates the initial starting point or specifies a new target stopping point, the intelligent cloud control platform subsystem will re-call the parking optimization algorithm for calculation to determine the new target transition point on the first main path, and then generate a new parking path to ensure that the path planning can adapt to the needs of different stopping points and effectively avoid the complex and intertwined parking paths.
[0086] It should be noted that the number of target transition points may vary according to the environmental conditions of the spoil dump, and the embodiments of the present application do not impose any limitation thereto.
[0087] Specifically, in the embodiment of the present application, the specific implementation method of determining the target transition point in the first main path by combining the first longitude and latitude coordinates and the second longitude and latitude coordinates through the parking optimization algorithm can be refined into the following S4031 and S4032:
[0088] S4031. For each point in the first main path, calculate the first distance between the point and the second longitude and latitude coordinates, and the second distance between the point and the second longitude and latitude coordinates, and filter out the points whose sum of the first distance and the second distance is within a first threshold range to generate a set of candidate transition points.
[0089] Specifically, the parking optimization algorithm can first calculate the first distance between the point corresponding to the first longitude and latitude coordinates and each point on the first main path, and then calculate the second distance between the second longitude and latitude coordinates and each point on the first main path; then for each point on the first main path, the first distance and the second distance are added to preliminarily screen out points whose sum of distances is within the first threshold range; it should be noted that the setting of the first threshold range needs to comprehensively consider factors such as the turning performance of the vehicle and the space limitation of the spoil dump. For example, if the turning radius of the vehicle is large, the threshold should be set larger accordingly to ensure that there is enough turning space.
[0090] Then, the candidate transition point set is generated based on these points, so as to further determine the target transition point in the candidate transition point set.
[0091] S4032. For each point in the candidate transition point set, obtain the angle between the first main path direction and the second longitude and latitude coordinates, so as to determine the target transition point according to the angle.
[0092] Specifically, for each point in the candidate transition point set, since each point in the candidate transition point set is on the first main path, it is only necessary to calculate the angle between each point and the second longitude and latitude coordinates, and then determine the target transition point in the middle according to the size of the angle; the target transition point can be determined as a point with a larger angle, so that when the vehicle drives from the initial starting point to the target stop point, the steering operation is smoother, which can effectively reduce the energy loss and path complexity during driving.
[0093] It should be noted that after the target transition point is determined, verification work can also be performed. For example, check whether the target transition point is within the feasible area for entering the main path, whether it will cause the target vehicle to collide with other objects or other vehicles during the turning process, etc. If problems are found, it is necessary to readjust the screening conditions or algorithm parameters, and calculate and select again until a suitable target transition point is determined.
[0094] S404: Generate the target parking path based on the first longitude and latitude coordinates, the target transition point, and the path information of the first main path.
[0095] It should be noted that, in the above step S404, the specific implementation method of generating the target parking path based on the first longitude and latitude coordinates, the target transition point and the path information of the first main path can be refined into the following steps:
[0096] With the target transition point as the center point, the target parking path is generated by combining the first longitude and latitude coordinates, the second longitude and latitude coordinates, the target transition point and the path information of the first main path within a preset range around the target transition point.
[0097] Specifically, the target transition point represents a reasonable transition position from the first main path to the target to-be-stopped point, and subsequent path planning is then performed with it as the center, which can ensure that the planned path is effectively connected with the main path and can efficiently guide the vehicle to the target to-be-stopped point, avoiding confusing or unreasonable path planning.
[0098] Then, the path planning is performed within the preset range of the target transition point, wherein the size of the preset range needs to comprehensively consider the driving characteristics of the vehicle, such as the minimum turning radius of the vehicle, acceleration and deceleration performance, etc. If the range is too small, it may limit the flexibility of path planning, resulting in the inability to plan a path that meets the driving requirements of the vehicle; if the range is too large, it will increase unnecessary calculations and reduce the efficiency of path planning. On the other hand, it is also necessary to combine the actual environmental factors of the spoil dump, such as terrain undulations, obstacle distribution, etc. A reasonable preset range can ensure the quality of path planning while making full use of the available space in the spoil dump, allowing vehicles to travel safely and efficiently.
[0099] Finally, the target parking path is generated by combining the first longitude and latitude coordinates with the path information of the first main path; the first longitude and latitude coordinates specify the starting position of the main path, provide a starting reference point for path planning, and ensure that the generated path can start smoothly from the main path. The path information of the first main path covers the detailed direction and boundaries of the main path into the spoil dump. During the planning process, the algorithm will strictly follow the limited range of the main path based on this information, while avoiding dangerous areas outside the path boundary, such as the edge of the spoil dump, obstacles, etc. By integrating this information, the algorithm can select the optimal or suboptimal target parking path from many possible paths within the preset range to meet the safety and efficient driving needs of vehicles in the spoil dump environment.
[0100] S405: Generate a task file based on the target parking path, and send the task file to the target vehicle control system, so that the target vehicle control system controls the target vehicle to park until the target parking point according to the task file and a tracking method.
[0101] Specifically, the task file generated based on the target parking path is to integrate this path information and related control instructions to form a file format that can be recognized and executed by the target vehicle control system. The task file not only contains a series of coordinate point information on the target parking path, accurately indicating the driving position of the vehicle at each stage, but may also include the vehicle's driving speed requirements, steering angle restrictions, acceleration and deceleration instructions, etc. on different sections of the road. For example, when approaching the target parking point, the task file will instruct the vehicle to reduce the driving speed to ensure safe and accurate parking; in the curved part of the path, the appropriate steering angle will be clearly specified to enable the vehicle to turn smoothly. Through these detailed instruction information, the task file provides comprehensive and accurate guidance for the vehicle's driving.
[0102] Then, after sending the task file to the control system of the target vehicle, the target vehicle is controlled to perform parking operations in combination with a specific tracking method.
[0103] It should be noted that the tracking method is a technology used to control the vehicle to travel along a preset path, and the most common one is the pure tracking method. This method continuously calculates the deviation between the current position of the vehicle and the target point on the preset path, and adjusts the vehicle's steering, speed and other control parameters in real time to ensure that the vehicle always travels towards the target waiting point. During the driving process, the vehicle control system will continuously read the path information and control instructions in the task file, and dynamically adjust the control strategy according to the real-time status and position of the vehicle. For example, when the vehicle deviates from the preset path, the control system will adjust the steering angle in time according to the calculation results of the tracking method to guide the vehicle back to the correct path; at the same time, according to the speed requirements in the task file, control the acceleration and deceleration of the vehicle to ensure that the vehicle travels at an appropriate speed and finally stops accurately at the target waiting point.
[0104] As an extension and refinement of the above embodiment, after completing steps S104 and S405 in the above embodiment, the embodiment of the present application further needs to perform the following steps 1 and 2:
[0105] Step 1: Receive target job completion notification.
[0106] The target operation completion notification is used to indicate that the target vehicle has completed the target operation at the target waiting point.
[0107] Specifically, when the target vehicle arrives at the target waiting point, it will perform the target operation; wherein, the target operation may be unloading soil. When the target operation is completed, the vehicle will send a target operation completion notification to the intelligent cloud control platform subsystem, and then the intelligent cloud control platform subsystem will receive a notification that the target vehicle's mission at the target waiting point has ended and that the next path planning is required for the target vehicle. By receiving the target operation completion notification, the system can know the vehicle status in a timely manner, and then start the subsequent process of leaving the soil dump, ensuring the continuity and efficiency of the soil dump operation.
[0108] Step 2: In response to the target operation completion notification, instruct the target vehicle to leave the spoil dump through a target exit path.
[0109] Specifically, the target exit path is used to indicate the path for the target vehicle to leave the spoil dump from the target waiting point; after receiving the target operation completion notification, the system will immediately call the target exit path information and send it to the control system of the target vehicle.
[0110] It should be noted that the planning of the target parking path will also be planned by comprehensively considering factors such as the terrain of the spoil dump, the distribution of obstacles, and the driving status of other vehicles. However, when the spoil dump environment is relatively stable, since the location of the parking point is fixed for a period of time, the target parking path can be a pre-set fixed route. After receiving the target operation completion notification, the matching target exit path can be obtained based on the second longitude and latitude coordinates of the target vehicle; when there are dynamic changing factors in the spoil dump, such as changes in the geographical environment, the intelligent cloud control platform subsystem will call the parking optimization algorithm again for path planning according to the actual situation.
[0111] Further refinement of step 2 above yields:
[0112] The target exit path is generated according to the second longitude and latitude coordinates and the path information corresponding to the second main path.
[0113] The second main path is a main path for exiting the spoil dump.
[0114] It should be noted that, corresponding to the first main path, the second main path can be understood as the name of the main path used to exit the spoil dump.
[0115] Specifically, when the target vehicle leaves the spoil dump, the generation of the target exit path for indicating the target vehicle can be specifically divided into two cases.
[0116] The first situation is when the current environment of the spoil dump is stable, that is, after the target vehicle completes the operation at the target waiting point, there are no other vehicles or obstacles blocking it, and the main path is unobstructed. The fixed target parking path generated in advance by the second longitude and latitude coordinates and the path information corresponding to the second main path can be directly called, and the target parking path is sent to the vehicle control system to instruct the target vehicle to leave the spoil dump, thereby improving the work efficiency of the target vehicle.
[0117] It should be noted that when generating the target exit path corresponding to each stop point in advance, the distance from the target stop point to each point on the second main path can be calculated based on the second longitude and latitude coordinates and the location information of multiple main paths, and the point with the closest distance is selected as the turning point, and then the second longitude and latitude coordinates are used as the starting point, and the turning point is used as the transition point to the second main path to form the target exit path. At the same time, when generating the target exit path, the driving characteristics of the vehicle, such as the minimum turning radius, etc., need to be considered to ensure that the path is within the drivable range of the vehicle.
[0118] The second situation is that when the environment in the current spoil dump is unstable, after the target vehicle completes the operation at the target waiting point, there are other vehicles around, or the environment changes, or part of the main path is congested. Therefore, it is necessary to combine the second longitude and latitude coordinates, as well as the real-time obstacle location information and the remaining passable sections of the main path, and use the path planning algorithm to generate a target parking path that bypasses obstacles and congested sections.
[0119] It should be noted that the obstacle positions around the target vehicle and the congestion of the main path can be obtained in real time through the monitoring system of the spoil dump, the vehicle's sensors and other equipment, and then the vehicle's passable area can be determined based on the obstacle positions and the remaining passable sections of the main path. Based on the positional relationship between the passable area and the target parking point and the second main path, the parking optimization algorithm is used to generate a target parking path that bypasses obstacles and congested sections with the second longitude and latitude coordinates as the starting point.
[0120] Based on the same inventive concept, as an implementation of the above method, an embodiment of the present application further provides a parking path generation device, which corresponds to the above method embodiment. For ease of reading, this embodiment will no longer repeat the details of the above method embodiment one by one, but it should be clear that a parking path generation device in this embodiment can correspond to and implement all the contents in the above method embodiment.
[0121] The present application embodiment provides a parking path generation device, Figure 5 is a structural schematic diagram of the parking path generating device, such as Figure 5 As shown, the parking path generating device 500 includes:
[0122] The receiving unit 501 is used to receive a target waiting point for the target vehicle to stop, which is sent by the target vehicle at the initial starting point; the target waiting point is located within a preset range of the spoil dump; the initial starting point is any point on the first main path entering the spoil dump;
[0123] The acquisition unit 502 is used to acquire the first longitude and latitude coordinates, the second longitude and latitude coordinates, and the path information corresponding to the first main path; the first longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the initial starting point; the second longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the target to-be-stopped point; the path information includes the longitude and latitude coordinates corresponding to the first main path and the path boundary information;
[0124] A generating unit 503 is configured to generate a target parking path based on a parking optimization algorithm by analyzing and reasoning the first longitude and latitude coordinates, the second longitude and latitude coordinates, and the path information of the first main path; the parking optimization algorithm is a dynamic planning based on the longitude and latitude coordinates corresponding to the target parking point;
[0125] The instructing unit 504 is configured to send the target parking path to a target vehicle control system to instruct the target vehicle to park at the target to-be-parked point.
[0126] As an optional implementation of an embodiment of the present application, the generation unit 502 is specifically used to determine the target transition point in the first main path through the parking optimization algorithm in combination with the first longitude and latitude coordinates and the second longitude and latitude coordinates; based on the first longitude and latitude coordinates, the target transition point and the path information of the first main path, generate the target parking path.
[0127] As an optional implementation of an embodiment of the present application, the generation unit 502 is specifically used to calculate, for each point in the first main path, the first distance between it and the second longitude and latitude coordinates, and the second distance to the second longitude and latitude coordinates, and filter out points where the sum of the first distance and the second distance is within a first threshold range to generate a set of candidate transition points; for each point in the set of candidate transition points, obtain the angle between the direction of the first main path and the second longitude and latitude coordinates to determine the target transition point based on the angle.
[0128] As an optional implementation of an embodiment of the present application, the generation unit 502 is specifically used to generate the target parking path by taking the target transition point as the center point and combining the first longitude and latitude coordinates, the second longitude and latitude coordinates, the target transition point and the path information of the first main path within a preset range around the target transition point.
[0129] As an optional implementation of the embodiment of the present application, the control unit is specifically used to generate a task file based on the target parking path, and send the task file to the target vehicle control system, so that the target vehicle control system controls the target vehicle to park according to the task file in combination with the tracking method until the target parking point.
[0130] As an optional implementation of an embodiment of the present application, the control unit is also used to receive a target operation completion notification; the target operation completion notification is used to indicate that the target vehicle has completed the target operation at the target waiting point; in response to the target operation completion notification, the target vehicle is instructed to leave the spoil dump through a target parking path.
[0131] As an optional implementation of the embodiment of the present application, the control unit is also used to respond to the target operation completion notification and generate the target exit path according to the second longitude and latitude coordinates and the path information corresponding to the second main path; the second main path is the main path for exiting the spoil dump.
[0132] Based on the same inventive concept, an embodiment of the present disclosure also provides an electronic device. Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure, such as Figure 6 As shown, the electronic device provided in this embodiment includes: a memory 601 and a processor 602, wherein the memory 601 is used to store a computer program; and the processor 602 is used to execute the parking path generation method provided in the above embodiment when executing the computer program.
[0133] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the computing device implements the parking path generation method provided in the above embodiment.
[0134] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media that include computer-usable program code.
[0135] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0136] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0137] Computer readable media include permanent and non-permanent, removable and non-removable storage media. Storage media can be implemented by any method or technology to store information, and the information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.
Claims
1. A parking path generation method, characterized in that: include: Receiving a target waiting point for parking the target vehicle sent by the target vehicle at the initial starting point; The target waiting point is located within the preset range of the spoil dump; The initial starting point is any point on the first main path leading into the spoil dump; Acquire first longitude and latitude coordinates, second longitude and latitude coordinates, and path information corresponding to the first main path; the first longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the initial starting point; the second longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the target to-be-stopped point; the path information includes the longitude and latitude coordinates corresponding to the first main path and path boundary information; Based on a parking optimization algorithm, analyzing and reasoning the first longitude and latitude coordinates, the second longitude and latitude coordinates, and the path information of the first main path to generate a target parking path; The parking optimization algorithm is to perform dynamic planning based on the longitude and latitude coordinates corresponding to the target parking point; The target parking path is sent to a target vehicle control system to instruct the target vehicle to park at the target to-be-parked point.
2. The method according to claim 1, characterized in that The method of analyzing and reasoning based on the parking optimization algorithm in combination with the latitude and longitude coordinates and the path information of the first main path to generate a target parking path includes: Determine a target transition point in the first main path by combining the first longitude and latitude coordinates and the second longitude and latitude coordinates through the parking optimization algorithm; The target parking path is generated based on the first longitude and latitude coordinates, the target transition point, and the path information of the first main path.
3. The method according to claim 2, characterized in that Determining a target transition point in the first main path by combining the first longitude and latitude coordinates and the second longitude and latitude coordinates through the parking optimization algorithm includes: For each point in the first main path, calculate a first distance between the point and the second longitude and latitude coordinates, and a second distance between the point and the second longitude and latitude coordinates, and select points where the sum of the first distance and the second distance is within a first threshold range, so as to generate a set of candidate transition points; For each point in the candidate transition point set, the angle between the first main path direction and the second longitude and latitude coordinates is obtained to determine the target transition point according to the angle.
4. The method according to claim 2, characterized in that: The step of generating the target parking path based on the first latitude and longitude coordinates, the target transition point, and the path information of the first main path includes: With the target transition point as the center point, the target parking path is generated by combining the first longitude and latitude coordinates, the second longitude and latitude coordinates, the target transition point and the path information of the first main path within a preset range around the target transition point.
5. The method according to claim 1, characterized in that The step of sending the target parking path to a target vehicle control system to instruct the target vehicle to park at the target parking point includes: A task file is generated based on the target parking path, and the task file is sent to the target vehicle control system, so that the target vehicle control system controls the target vehicle to park until the target parking point according to the task file in combination with a tracking method.
6. The method according to claim 1, characterized in that After sending the target parking path to the target vehicle control system to instruct the target vehicle to park at the target to-be-parked point, the method further includes: Receiving a target operation completion notification; the target operation completion notification is used to indicate that the target vehicle has completed the target operation at the target waiting point; In response to the target operation completion notification, the target vehicle is instructed to leave the spoil dump via a target parking exit path.
7. The method according to claim 6, characterized in that The method further comprises: The target exit path is generated according to the second longitude and latitude coordinates and the path information corresponding to the second main path; the second main path is the main path for exiting the spoil dump.
8. A parking path generation device, characterized in that: include: A receiving unit, used for receiving a target to-be-stopped point for the target vehicle to stop sent by the target vehicle at the initial starting point; The target waiting point is located within the preset range of the spoil dump; The initial starting point is any point on the first main path leading into the spoil dump; an acquisition unit, configured to acquire first longitude and latitude coordinates, second longitude and latitude coordinates, and path information corresponding to the first main path; the first longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the initial starting point; the second longitude and latitude coordinates are the longitude and latitude coordinates corresponding to the target to-be-stopped point; the path information includes the longitude and latitude coordinates corresponding to the first main path and path boundary information; a generating unit, configured to generate a target parking path by analyzing and reasoning based on a parking optimization algorithm and combining the first longitude and latitude coordinates, the second longitude and latitude coordinates, and the path information of the first main path; The parking optimization algorithm is to perform dynamic planning based on the longitude and latitude coordinates corresponding to the target parking point; The instruction unit is used to send the target parking path to the target vehicle control system to instruct the target vehicle to park at the target to-be-parked point.
9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store a computer program; and the processor is used to enable the electronic device to implement the parking path generation method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a computing device, the computing device implements the parking path generation method according to any one of claims 1 to 7.
Citation Information
Patent Citations
Parking path planning method and device, vehicle-mounted equipment and storage medium
CN112477850A
Parking method for unmanned mining vehicle in long and narrow area
CN115071686A
Unmanned mine truck path planning method for loading and unloading area of strip mine
CN115774443A
Vehicle parking control method, computer readable storage medium and vehicle
CN117601849A
Method, device and equipment for backing-up and parking of automatic driving mine car based on dynamic planning
CN118746298A