Path planning method, electronic equipment and storage medium

Abstract

The invention discloses a path planning method, electronic equipment and a storage medium, and the path planning method comprises the steps: obtaining an initial path of a target object, the initial path comprising a connection relationship among a plurality of nodes and action information of the target object on each node; on the basis of the related information of the target object, interpolation is carried out on areas between nodes in the initial path, an advanced path is obtained, a target node group containing multiple nodes and multiple non-nodes exists in the advanced path, and the related information of the target object comprises the size, the operation precision and / or the preset car following distance of the target object; and based on a conflict relationship between the advanced path and the driving tracks of other target objects, adjusting the advanced path to obtain a to-be-driven path of the target object. According to the scheme, the probability that the target object collides with other equipment in the driving process can be reduced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a path planning method, an electronic device, and a storage medium. Background Art

[0002] Automated Guided Vehicle (AGV) is an important means of transportation in smart factories and is widely used in all walks of life. As a means of transportation in smart unmanned factories, AGV carries the task of transferring workpieces and connects the orderly and efficient operation of various production unit modules in smart factories. In order to improve work efficiency, multiple AGVs need to work together in the operation site at the same time.

[0003] With the improvement of industrial level, the number of AGVs and the average daily workload in automated industrial scenes have increased significantly, and AGV path conflicts have become more serious. Whether AGV equipment can be transported efficiently has become a key factor in determining the efficiency of system operation. Therefore, a method that can reduce the probability of collision during the driving of each AGV equipment is urgently needed. Summary of the invention

[0004] The present application at least provides a path planning method, an electronic device and a storage medium.

[0005] The present application provides a path planning method, including: obtaining an initial path of a target object, wherein the initial path includes connectivity relationships between multiple nodes and action information of the target object at each node; interpolating regions between each node in the initial path based on relevant information of the target object to obtain an advanced path, wherein the advanced path includes a target node group including multiple nodes and multiple non-nodes, and the relevant information of the target object includes the size of the target object, operating accuracy and / or a preset following distance; and adjusting the advanced path based on a conflict relationship between the advanced path and driving trajectories of other target objects to obtain a path to be driven by the target object.

[0006] The present application provides a path planning device, including: an initial path acquisition module, an interpolation module and a path updating module; the initial path acquisition module is used to acquire an initial path of a target object, wherein the initial path includes a connectivity relationship between multiple nodes and action information of the target object at each node; the interpolation module is used to interpolate the areas between the nodes in the initial path based on relevant information of the target object to obtain an advanced path, wherein the advanced path includes a target node group including multiple nodes and multiple non-nodes, and the relevant information of the target object includes the size of the target object, the running accuracy and / or the preset following distance; the path updating module is used to adjust the advanced path based on the conflict relationship between the advanced path and the driving trajectories of other target objects to obtain the to-be-driven path of the target object.

[0007] The present application provides an electronic device, including a memory and a processor, wherein the processor is used to execute program instructions stored in the memory to implement the above-mentioned path planning method.

[0008] The present application provides a computer-readable storage medium on which program instructions are stored. When the program instructions are executed by a processor, the above-mentioned path planning method is implemented.

[0009] In the above scheme, after obtaining the initial path of the target object, considering that there may be situations in the initial path where the nodes are far apart, resulting in the area between two nodes actually being available for parking, waiting or continuing to drive, this scheme interpolates the area between the nodes in the initial path based on factors such as the size of the target object, the operating accuracy or the preset following distance, thereby obtaining an advanced path with multiple nodes and non-nodes, and then adjusting the advanced path according to the conflict between the advanced path and the driving trajectory of other target objects, so that the target object can reduce the probability of collision with other target objects by driving along the advanced path.

[0010] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0012] Figure 1 It is a flowchart of an embodiment of the path planning method of the present application;

[0013] Figure 2 is a schematic diagram of an initial path provided by an embodiment of a path planning method of the present application;

[0014] Figure 3 This is a schematic diagram of the relationship between the node range and the sub-nodes provided in an embodiment of the path planning method of the present application;

[0015] Figure 4 yes Figure 1 Schematic diagram of the sub-process of step S12;

[0016] Figure 5 is a schematic diagram of a locked grid area shown in an embodiment of a path planning method of the present application;

[0017] Figure 6 This is another flowchart of an embodiment of the path planning method of the present application;

[0018] Figure 7 It is a structural schematic diagram of an embodiment of a path planning device of the present application;

[0019] Figure 8 It is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0020] Fig. 9 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0021] The scheme of the embodiment of the present application is described in detail below in conjunction with the drawings of the specification.

[0022] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0023] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated before and after are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, can mean including any one or more elements selected from the set consisting of A, B, and C.

[0024] In some application scenarios, the path planning method provided by the present application can be applied to fields such as industry or robot transportation. The execution subject for implementing the path planning method described in the present application can be a path planning device, an electronic device, etc. For example, the path planning device can be set in a terminal device or a server or other processing device, wherein the terminal device can be an audio device, an electronic device, a device (User Equipment, UE), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the path planning method can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0025] See also Figure 1 , Figure 1 It is a flowchart of an embodiment of the path planning method of the present application.

[0026] like Figure 1 As shown, the path planning method provided by the embodiment of the present disclosure may include the following steps:

[0027] Step S11: Obtain the initial path of the target object.

[0028] The execution subject of path planning can be the target object itself, or it can be a device or platform that performs path planning for each target object in a unified manner. This solution takes the execution subject as a device or platform that performs path planning for each target object in a unified manner as an example. Target objects include but are not limited to robots, automatic guided transport vehicles, and express transfer vehicles at express stations. The initial path includes the connectivity relationship between multiple nodes and the action information of the target object at each node. The connectivity relationship between each node may include the driving order between each node, for example, the target object goes from node A to node B to node C in sequence. The action information may be going straight, stopping and waiting, rotating, or performing specific processing on the shelf, etc.

[0029] Exemplarily, an environmental map network can be pre-established, and the location of each node, the attributes of each node, and the connectivity information between each node can be marked on the map network, for example, whether the node belongs to a workbench, a shelf area, or an operation area. In other embodiments, the map network can also mark the real-time status of each target object, such as the real-time task, current location, and path, etc. For example, the path issued to each target object and the target object is traveling or about to travel can be displayed. Among them, the specific way to obtain the initial path of the target object can be to plan an optimal global path from the starting position (starting node) to the end position (terminating node) for the target object based on the map network using the shortest path planning algorithm such as A*.

[0030] Then, the initial path containing action information can be generated based on the node direction and node connectivity information contained in the optimal global path. For example, the initial path can be as follows: Figure 2 As shown, ① go straight from node 0 to node 1, ② turn left 90 degrees at node 1, ③ follow the Bezier curve from node 1 to node 2, ④ turn right 180 degrees at node 2, ⑤ retreat from node 2 to node 3.

[0031] Step S12: interpolating the regions between the nodes in the initial path based on the relevant information of the target object to obtain an advanced path.

[0032] Among them, there is a target node group including multiple nodes and multiple non-nodes in the advanced path, and the relevant information of the target object includes the size of the target object, the running accuracy and / or the preset following distance. Exemplarily, interpolation can be performed according to the size of the target object or according to the preset following distance, or interpolation can be performed in combination with the running accuracy and the preset following distance, or interpolation can be performed according to the size of the target object, the running accuracy and the preset following distance. By adding multiple non-nodes, the number of positions where the target object can follow the vehicle and stop and wait can be increased. When the latter node is occupied by other target objects and the current node is far away from the latter node, if the current node is waiting for the release of the latter node, it will actually cause a low following efficiency. This solution increases the number of non-nodes by interpolation, so that the target object can continue to travel to a non-node position where it can stop and wait, thereby improving the following efficiency.

[0033] Step S13: Based on the conflict relationship between the advanced path and the driving trajectories of other target objects, the advanced path is adjusted to obtain the to-be-driven path of the target object.

[0034] The existence of a conflict may specifically be that the target object and other target objects travel to the same position at the same time, or even if they are not in the same position, there is a possibility of collision between the two. For example, when the target object is a car, two car fronts collide, two car rears collide, or the front and rear of a car collide.

[0035] In the above scheme, after obtaining the initial path of the target object, considering that there may be situations in the initial path where the nodes are far apart, resulting in the area between two nodes actually being available for parking, waiting or continuing to drive, this scheme interpolates the area between the nodes in the initial path based on factors such as the size of the target object, the operating accuracy or the preset following distance, thereby obtaining an advanced path with multiple nodes and non-nodes, and then adjusting the advanced path according to the conflict between the advanced path and the driving trajectory of other target objects, so that the target object can reduce the probability of collision with other target objects by driving along the advanced path.

[0036] In some embodiments, the advanced path is a global path, and the path planning method may further include the following steps:

[0037] The pre-issued segment path is determined from the advanced path based on the preset longest path length and the shortest path length. Among them, the preset longest path length is the longest distance allowed for the target object to move, and the shortest path length is the shortest distance allowed for the target object to move. A length can be selected from the longest path length and the shortest path length as the length of the pre-issued segment path, and then the current position of the device or the end node of the current driving path is used as the starting node of the pre-issued segment path, and a path of this length is selected from the advanced path to obtain the pre-issued segment path. That is, after obtaining the advanced path, because the advanced path is a global path, the advanced path may be longer. If the entire advanced path is directly locked and issued to the target object, the longer distance cannot be used by other devices, resulting in low scheduling efficiency. Therefore, each time a segment of the path is issued to the target object, the movement of the target object is safer, more flexible and efficient.

[0038] Then, in response to the fact that the action information of the node or non-node in the pre-issued segment path is a rotation action, the terminal node in the pre-issued segment path is adjusted to the node or non-node corresponding to the rotation action. That is, if the node is a rotation action point and the vehicle needs to decelerate and stop here and then rotate in place, it will be truncated.

[0039] Or, in response to the attribute of the terminal node in the pre-delivered segment path being that parking and waiting is prohibited, the terminal node in the pre-delivered segment path is moved forward or backward by at least one node or non-node. For example, if the node is at an important traffic node such as an intersection, where parking is not allowed, the terminal node can be moved forward or backward to a point where parking and waiting are allowed, thereby avoiding parking at the node.

[0040] On this basis, the above step S13 may include the following steps: based on the conflict relationship between the pre-issued segment path and the driving trajectory of other target objects, the pre-issued segment path is adjusted to obtain the to-be-driven path of the target object.

[0041] Optionally, the non-nodes obtained by interpolation between the nodes in the above step S12 can be used as child nodes of the corresponding node. For example, if there are 3 non-nodes between node A and node B, node A and the 3 non-nodes can be used as child nodes under the range of node A, that is, there was originally only one parking area under the range of node A, which is node A. After interpolation, 3 parking areas are added, making there are 4 parking areas under the range of node A. In this way, each node and non-node can be regarded as a node set. The pre-sent segment path includes the starting node range, the starting child node, the ending node range and the ending child node, such as Figure 3As shown in the figure, ① when the device sends down the segment path for the first time, its starting node range (startIdx) and starting subnode (startIPIdx) are both 0. Assuming that the device pre-sends three nodes 0, 1, and 2, its ending node range (endIdx) is 2 and its ending subnode (endIPIdx) is 5. ② If the device does not send down the segment path for the first time, its starting node range startIdx and starting subnode startIPIdx are determined by moving the ending node range endIdx and ending subnode endIPIdx of the previous segment path back one subnode.

[0042] Optionally, the path planning method may further include the following steps: in response to the distance between the current position of the target object and the terminal node of the to-be-traveled path being less than or equal to a preset distance, determining a new to-be-traveled path from the advanced path.

[0043] That is, if the target object has not yet reached the end node in the initial path or the advanced path, and the target object is about to reach the end node of the segment path, the next segment path can be determined for the target object. If the end node of the segment path is the same as the end node in the initial path or the advanced path, the target object is controlled to stop and wait for the next task after reaching the end node, that is, a new initial path is determined for the target object. The starting node in the new path to be traveled can be considered as the end node of the current segment path in the advanced path.

[0044] In some embodiments, the advanced path carries the target lock area of ​​the target object at each node and each non-node. The target lock area can be considered as the area occupied by the target object at each node or each non-node. If other target objects enter the same lock area at the same time as the target object, it indicates a collision. Figure 4 , the above step S12 may include the following steps:

[0045] Step S121: Based on the size of the target object, determine the size of the target area covered by the target object at a single moment.

[0046] Exemplarily, the target area may be a rectangular area, and the size of the target area may be the size of the rectangular area. If aerial operations are involved, the target area may be a cubic area, and the size of the target area may be the size of the cube.

[0047] Step S122: Determine the target lock area of ​​the target object on each node using the target area size.

[0048] If the target object just moves straight at the node, the target lock area can be a rectangular area. If the target object needs to rotate at the node, the target lock area can be a circular area obtained by rotating the rectangular area at the node.

[0049] Step S123: Based on the running accuracy of the target object and the preset following distance, the interpolation interval between the locking grid areas of each non-node is determined to obtain the target locking grid area of ​​the target object at each non-node.

[0050] In order to accurately control the position of the target object between nodes, the nodes can be interpolated according to a certain distance interval between the nodes, thereby determining the interpolation grid of the target object at the interpolation point, wherein the distance interval is determined by the braking performance of the device and should be greater than the minimum moving distance supported by the device capability, and the number of interpolations between nodes with different distances is different. Optionally, if the target object travels in a straight line between two nodes, the non-nodes between the two nodes are on the same straight line, and the grid areas between adjacent points may overlap. If the target object travels in a non-straight line between the two nodes, such as a Bezier curve, each non-node is on the curve. In the interpolation process of curved driving, the position of the center point of each non-node on the curve can be determined first, and then the driving trajectory of the target object on the curve can be simulated according to the size of the target area to determine the target grid area at each non-node. The interpolation interval can be the distance between the preset positions in the two grid areas. Exemplarily, the target grid areas of each node and non-node obtained can refer to Figure 5 As shown, Figure 5 One of the child nodes between node 1 and node 2 is shown, and the child node is shown as a dotted-line box.

[0051] The driving trajectory of other target objects includes reference lock grid areas of other target objects at at least one reference node, and the conflict relationship includes intersecting lock grid conflict positions between each target lock grid area and each reference lock grid area. The reference node can be a node or a non-node in the driving trajectory of other target objects, that is, the other driving trajectory can include reference lock grid areas of nodes and reference lock grid areas of non-nodes.

[0052] On this basis, the above step S13 may include the following steps: based on the locked grid conflict position, the number of nodes or non-nodes in the advanced path is reduced to obtain the path to be driven. And / or, based on the locked grid conflict position, the connectivity relationship between the nodes or non-nodes in the advanced path is adjusted to obtain the path to be driven.

[0053] Optionally, the advanced path includes a starting node and an ending node. Optionally, the ending node may specifically be a subnode in the range of the ending node. The starting node may also be a subnode in the range of the starting node. The above-mentioned method of reducing the number of nodes or non-nodes in the advanced path based on the grid conflict position to obtain the path to be traveled may be: adjusting the ending node in the advanced path to a target node, and obtaining the target node of the path to be traveled as a node or non-node corresponding to the previous target grid area of ​​the first grid conflict position, and the previous target grid area is the target grid area where the target object travels before the grid conflict position. Among them, the path to be traveled includes the connectivity relationship between each node and each non-node between the starting node and the target node and the action information of the target object on each node.

[0054] As mentioned above, the target lock grid area includes a rectangular lock grid area and a circular lock grid area. Optionally, if the conflicting child node (dangerIPIdx) is the 0th child node of the dangerous node range (dangerIdx), the terminating node range moves forward by one from the dangerous node range dangerIdx, endIdx=dangerIdx-1 is modified, and the terminating child node endIPIdx is the number of child nodes of the new endIdx minus 1. Otherwise, the terminating node range endIdx is modified to the dangerous node range dangerIdx, endIdx=dangerIdx, the terminating child node moves forward by one, and endIPIdx=dangerIdx-1 is modified. If it is a circular lock grid conflict, the terminating node range moves forward by one from the dangerous node dangerIdx, endIdx=dangerIdx-1 is modified, and the terminating child node endIPIdx is the number of child nodes of the new endIdx minus 1.

[0055] In some embodiments, after adjusting the terminating node in the advanced path, the following steps may be performed: determine whether the positional relationship between the target node and the starting node satisfies the positional condition. Exemplarily, check whether the starting node range beginIdx, the starting child node beginIPIdx, the terminating node range endIdx, and the terminating child node endIPIdx represent a reasonable equipment operation distance. The positional condition may include endIdx>beginIdx, or endIdx=beginIdx and endIPIdx>beginIPIdx. That is, the positional condition may be considered to be that the terminating node is between the starting node and the terminating node before the advanced path is adjusted, that is, the target object needs to pass through the starting node first and then the terminating node.

[0056] Then, in response to the position relationship satisfying the position condition, the path to be driven is sent to the target object so that the target object can drive based on the path to be driven. In other words, the path planning is reasonable and the target object can drive according to the path, so the planned path can be sent to the target object. Or, in response to the position relationship not satisfying the position condition, the target object is controlled to stop after driving the last sent path to be driven. In other words, the path planning is unreasonable and needs to be replanned.

[0057] Optionally, the trajectory planning method may further include the following steps: setting the occupancy status of each node and non-node in the path to be traveled to occupied. Specifically, the target lock grid area corresponding to each node and each non-node can be set to occupied. Optionally, the same node may be occupied by different target objects at different times, so the occupancy status of the node by different target objects can be marked by color or other identification, which is convenient for detecting whether there is a conflict in the subsequent path planning process. In response to the target object leaving the node or non-node area, the occupancy status of the node or non-node is set to not occupied by the target object so that other target objects can perform path planning. Optionally, since the occupancy status of the node or non-node is not occupied by the target object, it can be applied for occupation by other target objects.

[0058] That is, whether each node is currently occupied can be represented by the occupancy status, so as to plan the trajectory of other target objects later. During the driving process, the target object can clear the lock grid occupancy information of the area that has been passed in the path to be driven.

[0059] To better understand this solution, please refer to Figure 6 In some specific application scenarios, the path planning method may include the following steps:

[0060] Step S21: Obtain the initial path of the target object.

[0061] The implementation of step S21 may refer to the above step S11, which will not be described in detail here.

[0062] Step S22: interpolating the regions between the nodes in the initial path based on the relevant information of the target object to obtain an advanced path.

[0063] The implementation of step S22 may refer to the above step S12 for details, which will not be described in detail here.

[0064] Step S23: Determine the pre-delivery segment path.

[0065] Specifically, step S23 may include the following steps: determining the pre-issued segment path from the advanced path based on the preset longest path length and the shortest path length; in response to the action information of the node or non-node in the pre-issued segment path being a rotation action, adjusting the terminal node in the pre-issued segment path to the node or non-node corresponding to the rotation action. Or, in response to the attribute of the terminal node in the pre-issued segment path being no parking and waiting, moving the terminal node in the pre-issued segment path forward or backward by at least one node or non-node.

[0066] Step S24: Acquire a set of other target objects to be detected for conflict around the target object.

[0067] Among them, according to the node set contained in the pre-issued segment path, the radiation range of twice the hypotenuse length of the target object, and the segment path information issued by other devices, the target object set that needs to be detected for conflict collision around the pre-issued segment path is calculated.

[0068] Step S25: Select another target object in the target object set to be detected for conflict and collision that has not yet been detected.

[0069] Perform collision detection on the trajectory of each target object in turn.

[0070] Step S26: Detect whether there is a locking grid conflict position between the target object and other target objects.

[0071] Traverse the rectangular lock grids and circular lock grids from the starting node range beginIdx, the starting child node beginIPIdx to the ending node range endIdx, the ending child node endIPIdx from front to back, and calculate whether there is a lock grid conflict position between the target object and other target objects through the collision deadlock detection algorithm.

[0072] Step S27: Determine whether there is a conflicting position.

[0073] If there is a rectangular lock conflict or a circular lock conflict of the rotation action, the traversal in step S26 is terminated. That is, if the judgment result is yes, step S28 is executed, otherwise step S29 is executed.

[0074] Step S28: Update the termination node.

[0075] According to the cross-overlapping relationship between the global path information and the pre-sent segment path of the device and the conflicting device, the collision and deadlock detection algorithm that can identify the possibility of collision and deadlock is used to verify whether the pre-sent segment path of the main device is safe. If there is a risk of conflict and collision with the conflicting device, the number of nodes and sub-nodes contained in the segment path is reduced, the length of the pre-sent segment path is re-determined, and endIdx and endIPIdx are modified. The specific update method can be referred to above and will not be repeated here.

[0076] Step S29: whether there are other target objects that have not been detected in the target object set to be detected for conflict.

[0077] If yes, execute step S25; otherwise, execute step S30.

[0078] Step S30: Determine whether the position relationship satisfies the position condition.

[0079] That is, check whether the starting node range beginIdx, the starting child node beginIPIdx, the ending node range endIdx, and the ending child node endIPIdx represent a reasonable equipment operation distance, that is, confirm that endIdx>beginIdx, or endIdx=beginIdx and endIPIdx>beginIPIdx. If not satisfied, go to step S36. If satisfied, go to step S31.

[0080] Step S31: Send the updated segment path to the target object.

[0081] Specifically, a segment path represented by a starting node range beginIdx, a starting subnode beginIPIdx to an ending node range endIdx, and an ending subnode endIPIdx is sent to the device, occupying a locked grid area of ​​nodes and subnodes included in the segment path.

[0082] Step S32: Control the target object to travel along the segment path.

[0083] The target object executes the issued segment path and travels according to the segment path.

[0084] Step S33: Clear the designated lock grid information.

[0085] When the target object is driving, the lock grid occupancy information of the area it has passed is cleared.

[0086] Step S34: Whether the point reached by the target object is the end point of the task.

[0087] Determine whether the target object has reached the task end point. If so, the task is completed and the program ends. Otherwise, continue to execute step S35.

[0088] Step S35: Whether the next segment path needs to be sent down.

[0089] Exemplarily, based on whether the distance between the device and the end point of the sent segment path is less than the set distance threshold for the additional segment path, check whether the device needs to send the next segment path. If so, go to step S23; otherwise, go to step S32 and continue driving along the segment path, and stop and wait after completing the current segment path.

[0090] Step S36: After completing the current route, stop the vehicle and wait.

[0091] After the current segment of the route is completed, the vehicle stops and waits, and then proceeds to step S23 to perform a safety check on the next segment of the route again.

[0092] See also Figure 7 , Figure 7 It is a structural diagram of an embodiment of the path planning device of the present application. The path planning device 70 can execute the above-mentioned path planning method. The path planning device 70 includes an initial path acquisition module 71, an interpolation module 72 and a path update module 73; the initial path acquisition module 71 is used to obtain the initial path of the target object, and the initial path includes the connectivity relationship between multiple nodes and the action information of the target object at each node; the interpolation module 72 is used to interpolate the areas between each node in the initial path based on the relevant information of the target object, and obtain an advanced path. There is a target node group including multiple nodes and multiple non-nodes in the advanced path, and the relevant information of the target object includes the size of the target object, the running accuracy and / or the preset following distance; the path update module 73 is used to adjust the advanced path based on the conflict relationship between the advanced path and the driving trajectory of other target objects, and obtain the path to be driven by the target object, and the other driving trajectories are the paths to be driven by other target objects.

[0093] In the above scheme, after obtaining the initial path of the target object, considering that there may be situations in the initial path where the nodes are far apart, resulting in the area between two nodes actually being available for parking, waiting or continuing to drive, this scheme interpolates the area between the nodes in the initial path based on factors such as the size of the target object, the operating accuracy or the preset following distance, thereby obtaining an advanced path with multiple nodes and non-nodes, and then adjusting the advanced path according to the conflict between the advanced path and the driving trajectory of other target objects, so that the target object can reduce the probability of collision with other target objects by driving along the advanced path.

[0094] Among them, the functions of each module can be found in the description of the path planning method embodiment, and will not be repeated here.

[0095] See also Figure 8 , Figure 8 80 is a schematic diagram of the structure of an embodiment of an electronic device of the present application. The electronic device 80 includes a memory 81 and a processor 82, and the processor 82 is used to execute program instructions stored in the memory 81 to implement the steps in any of the above-mentioned path planning method embodiments. In a specific implementation scenario, the electronic device 80 may include but is not limited to: a microcomputer, a server, and in addition, the electronic device 80 may also include a carrier device such as a laptop computer and a tablet computer, which is not limited here.

[0096] Specifically, the processor 82 is used to control itself and the memory 81 to implement the steps in any of the above-mentioned path planning method embodiments. The processor 82 can also be called a CPU (Central Processing Unit). The processor 82 may be an integrated circuit chip with signal processing capabilities. The processor 82 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 82 can be implemented by an integrated circuit chip.

[0097] In the above scheme, after obtaining the initial path of the target object, considering that there may be situations in the initial path where the nodes are far apart, resulting in the area between two nodes actually being available for parking, waiting or continuing to drive, this scheme interpolates the area between the nodes in the initial path based on factors such as the size of the target object, the operating accuracy or the preset following distance, thereby obtaining an advanced path with multiple nodes and non-nodes, and then adjusting the advanced path according to the conflict between the advanced path and the driving trajectory of other target objects, so that the target object can reduce the probability of collision with other target objects by driving along the advanced path.

[0098] See also Fig. 9 , Fig. 9 The computer-readable storage medium 90 stores program instructions 901, which implement the steps in any of the above path planning method embodiments when executed by a processor.

[0099] In the above scheme, after obtaining the initial path of the target object, considering that there may be situations in the initial path where the nodes are far apart, resulting in the area between two nodes actually being available for parking, waiting or continuing to drive, this scheme interpolates the area between the nodes in the initial path based on factors such as the size of the target object, the operating accuracy or the preset following distance, thereby obtaining an advanced path with multiple nodes and non-nodes, and then adjusting the advanced path according to the conflict between the advanced path and the driving trajectory of other target objects, so that the target object can reduce the probability of collision with other target objects by driving along the advanced path.

[0100] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0101] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0102] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, units or components can be combined or integrated into another system, or some features can be ignored or not executed. In another image position, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0103] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

Claims

1. A path planning method, characterized in that: include: Acquire an initial path of the target object, wherein the initial path includes connectivity relationships between multiple nodes and action information of the target object on each of the nodes; Based on the relevant information of the target object, the area between each node in the initial path is interpolated to obtain an advanced path, wherein the advanced path includes a target node group including a plurality of nodes and a plurality of non-nodes, and the relevant information of the target object includes the size, running accuracy and / or a preset following distance of the target object; Based on the conflict relationship between the advanced path and the driving trajectories of other target objects, the advanced path is adjusted to obtain the to-be-driven path of the target object.

2. The method according to claim 1, characterized in that The advanced path carries the target lock grid area of ​​the target object at each of the nodes and each of the non-nodes. The area between each node in the initial path is interpolated based on the relevant information of the target object to obtain the advanced path, including: Based on the size of the target object, determining the size of the target area covered by the target object at a single moment; Determine the target lock grid area of ​​the target object on each of the nodes using the target area size; Based on the running accuracy of the target object and the preset following distance, the interpolation interval between the locking grid areas of each non-node is determined to obtain the target locking grid area of ​​the target object at each non-node.

3. The method according to claim 2, characterized in that The driving trajectory of the other target object includes a reference lock grid area of ​​the other target object at at least one reference node, the conflict relationship includes a lock grid conflict position where each of the target lock grid areas and each of the reference lock grid areas intersect, and the advanced path is adjusted based on the conflict relationship between the advanced path and the driving trajectory of the other target object to obtain the to-be-driven path of the target object, including: Based on the locked grid conflict position, the number of nodes or non-nodes in the advanced path is reduced to obtain the path to be traveled; And / or, the connectivity relationship between each of the nodes or non-nodes in the advanced path is adjusted based on the lock grid conflict position to obtain the path to be traveled.

4. The method according to claim 3, characterized in that The advanced path includes a starting node and an ending node, and the number of nodes or non-nodes in the advanced path is reduced based on the lock grid conflict position to obtain the path to be traveled, including: The terminal node in the advanced path is adjusted to a target node, and the target node of the path to be traveled is a node or non-node corresponding to a target grid area before the first grid conflict position, and the previous target grid area is a target grid area where the target object travels before the grid conflict position; The path to be traveled includes connectivity relationships between nodes and non-nodes between the starting node and the target node and action information of the target object at each node.

5. The method according to claim 4, characterized in that The method further comprises: Determine whether the position relationship between the target node and the start node satisfies the position condition; In response to the position relationship satisfying the position condition, issuing the path to be traveled to the target object so that the target object travels based on the path to be traveled; Or, in response to the position relationship not satisfying the position condition, the target object is controlled to stop after completing the last issued path to be traveled.

6. The method according to any one of claims 1 to 5, characterized in that The advanced path is a global path, and the method further includes: Determine a pre-delivery segment path from the advanced path based on a preset longest path length and a preset shortest path length; In response to the action information of the node or non-node in the pre-delivered segment path being a rotation action, adjusting the terminal node in the pre-delivered segment path to the node or non-node corresponding to the rotation action; or, in response to the attribute of the terminal node in the pre-delivered segment path being that parking and waiting is prohibited, moving the terminal node in the pre-delivered segment path forward or backward by at least one node or non-node; The step of adjusting the advanced path based on the conflict relationship between the advanced path and the driving trajectories of other target objects to obtain the to-be-driven path of the target object includes: Based on the conflict relationship between the pre-issued segment path and the driving trajectories of other target objects, the pre-issued segment path is adjusted to obtain the to-be-driven path of the target object.

7. The method according to claim 6, characterized in that The method further comprises: In response to the distance between the current position of the target object and the terminal node of the to-be-traveled path being less than or equal to a preset distance; A new path to be traveled is determined from the advanced path.

8. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Setting the occupancy status of each node and non-node in the path to be traveled to be occupied; In response to the target object leaving the area of ​​the node or non-node, the occupancy status of the node or non-node is set to be not occupied by the target object so as to facilitate path planning for other target objects.

9. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the processor is used to execute program instructions stored in the memory to implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images