Driving path planning method and device, electronic equipment, storage medium and program

Abstract

The embodiment of the invention discloses a driving path planning method and device, electronic equipment, a storage medium and a program, and the method comprises the steps: calculating the node risk degree of each node according to the multi-dimensional risk information of each node in a path planning range; determining an initial optimized driving path from a path starting point to a path ending point in the path planning range according to the node risk degree of each node; and performing regional optimization on the initial optimized driving path again according to the node risk degree of each node to obtain a target planned driving path. According to the technical scheme of the embodiment of the invention, the efficiency, rationality and safety of planning the driving path can be improved, so that the driving risk is reduced, and the driving safety is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of intelligent transportation and route planning technology, and in particular to a method, device, electronic device, storage medium and program for planning driving routes. Background Technology

[0002] With the intelligent evolution of various traffic scenarios, the path planning problem for vehicles has gradually become a research hotspot in the fields of traffic engineering and intelligent transportation. Although traditional driving path planning methods can solve some problems, they often fail to meet the requirements of efficiency and safety in complex and ever-changing driving environments. Summary of the Invention

[0003] This invention provides a driving route planning method, apparatus, electronic device, storage medium, and program, which can improve the efficiency, rationality, and safety of driving route planning, thereby reducing driving risks and improving driving safety.

[0004] According to one aspect of the present invention, a driving route planning method is provided, comprising: The node risk level of each node is calculated based on the multi-dimensional risk information of each node within the path planning range; Based on the node risk level of each node, an initial optimized driving path is determined from the starting point to the ending point within the path planning range; Based on the node risk level of each node, the initial optimized driving path is further optimized regionally to obtain the target planned driving path.

[0005] According to another aspect of the present invention, a driving route planning device is provided, comprising: The node risk calculation module is used to calculate the node risk of each node based on the multi-dimensional risk information of each node within the path planning range. The initial optimized driving route determination module is used to determine the initial optimized driving route from the starting point to the ending point of the path within the path planning range based on the node risk of each node. The initial optimized driving path optimization module is used to further optimize the initial optimized driving path based on the node risk of each node to obtain the target planned driving path.

[0006] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the driving path planning method according to any embodiment of the present invention.

[0007] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the driving path planning method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the driving path planning method described in any embodiment of the present invention.

[0009] This invention calculates the node risk level of each node based on multi-dimensional risk information within the path planning range. Based on the node risk level of each node, an initial optimized driving path is determined within the path planning range from the starting point to the ending point. Furthermore, the initial optimized driving path is further optimized regionally based on the node risk level of each node to obtain the target planned driving path. This solves the problem that existing path planning methods struggle to meet efficiency and safety requirements in complex and changing driving environments. It improves the efficiency, rationality, and safety of planned driving paths, thereby reducing driving risks and enhancing driving safety.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a driving path planning method provided in Embodiment 1 of the present invention; Figure 2 This is a flowchart of a driving path planning method provided in Embodiment 2 of the present invention; Figure 3 This is a flowchart illustrating a driving path planning method provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of a driving path planning device provided in Embodiment 3 of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product or device.

[0015] Example 1 Figure 1 This is a flowchart of a driving route planning method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where the driving route is optimized multiple times based on the risk status of each node within the route planning range. This method can be executed by a driving route planning device, which can be implemented in software and / or hardware, and is generally integrated into an electronic device. This electronic device can be a terminal device or a server device, as long as it can execute the driving route planning method. The present invention does not limit the specific type of electronic device. Correspondingly, as... Figure 1 As shown, the method includes the following operations: S110. Calculate the node risk degree of each node based on the multi-dimensional risk information of each node within the path planning range.

[0016] The path planning range can be the area within which the travel path of a specific target driving device needs to be planned. It is understood that the path planning range can include the starting point and ending point of the target driving device's path, as well as all optional intermediate path nodes from the starting point to the ending point. The target driving device can be any type of device with a driving path planning requirement, such as various transportation equipment including vehicles, ships, and aircraft, as well as intelligent devices such as unmanned transport aircraft, automated guided vehicles, sorting robots, and self-service robots. It can also be terminal devices that can provide path planning functions, such as smartphones, tablets, and personal computers (PCs). This embodiment of the invention does not limit the type of target driving device. Multidimensional risk information can include risk information from multiple dimensions. Node risk level can be a risk level calculated on a node-by-node basis, used to measure the severity of the risk at a node.

[0017] Optionally, for a target driving device that needs to plan its driving path, the geometry including the starting point and ending point of the path can be used as the path planning range of the target driving device. For example, this geometry can be a rectangle with the path starting point to the ending point as its diagonal, or it can be a polygon irregularly expanding outwards from the path starting point and ending point. This embodiment of the invention does not limit the specific type of geometry corresponding to the path planning range. For the path planning range of the target driving device, a node set can be generated based on the driving scenario corresponding to its path planning range. This node set can include multiple nodes. For example, when the driving scenario is a navigation scenario for a ship or aircraft, if the path planning range is a rectangle with the path starting point to the ending point as its diagonal, this rectangle usually does not involve many buildings. Therefore, the distance between nodes in the rectangular path planning range can be directly defined according to the computing power and resolution of the path planning device, thereby converting the rectangular path planning range into a node set. When the driving scenario is for a vehicle, the path planning range can be various alternative routes from the path starting point to the ending point. Each alternative route can then be divided into nodes to obtain the corresponding node set. Therefore, each node has a probability of becoming a location point that the target driving device passes through during its journey.

[0018] Furthermore, multi-dimensional risk information for each node within the path planning range is obtained. For example, when the target vehicle is a vessel, the multi-dimensional risk information for a node may include, but is not limited to, wind speed, current speed, temperature, humidity, sea state, and water depth. When the target vehicle is an aircraft, the multi-dimensional risk information for a node may include, but is not limited to, wind speed, wind direction, temperature and humidity, air pressure, visibility, cloud height, cloud cover, cloud type, precipitation, and turbulence level. When the target vehicle is a vehicle, the multi-dimensional risk information for a node may include, but is not limited to, road surface condition, road slope, curve curvature, lane width, visibility, roadside risk, and traffic facility status. Accordingly, based on the multi-dimensional risk information for each node within the path planning range, a comprehensive assessment value of the risk level of each node can be calculated, serving as the node risk score. Calculating the node risk score through multi-dimensional risk information assessment can improve the accuracy of node risk assessment.

[0019] S120. Determine the initial optimized driving path from the starting point to the ending point of the path within the path planning range based on the node risk level of each node.

[0020] The initial optimized driving route can be the driving route obtained by performing preliminary optimization on the route from the starting point to the ending point.

[0021] After evaluating and calculating the node risk level of each node within the path planning range, we can make full use of the multi-dimensional risk information in the driving environment to compare the node risk levels between adjacent nodes, thereby selecting the node with the lower node risk level as the path node, so as to quickly determine the driving path between the path start point and the path end point within the path planning range, as the initial optimized driving path.

[0022] S130. Based on the node risk level of each node, the initial optimized driving path is optimized again to obtain the target planned driving path.

[0023] The target planned driving path can be the driving path finally planned for the target driving equipment.

[0024] Understandably, while the initial optimized driving path achieves preliminary screening and avoidance of node risk information, its smoothness and obstacle avoidance capabilities are relatively poor. Therefore, after obtaining the initial optimized driving path, the node risk level of each node can be used to further optimize the initial optimized driving path within a specific region. Region optimization can be understood as using a preset region as a baseline for each path node in the initial optimized driving path, and based on the node risk level of each node within that preset region, locally optimizing and adjusting the path nodes in the initial optimized driving path. This results in a smoother final optimized target driving path, reducing sharp turns and obstacles, and ensuring that the optimized target driving path meets requirements such as no collisions and reasonable length.

[0025] Therefore, the aforementioned route planning method rapidly generates an initial optimized route by fully utilizing risk information from the driving environment, and then further optimizes the initial optimized route regionally using the same risk information to achieve better driving distance, lower energy consumption, and higher safety. This route planning method not only effectively addresses the challenges of complex and ever-changing driving environments but also provides important theoretical support and technical reference for the research and development of intelligent transportation and autonomous driving devices.

[0026] This invention calculates the node risk level of each node based on multi-dimensional risk information within the path planning range. Based on the node risk level of each node, an initial optimized driving path is determined within the path planning range from the starting point to the ending point. Furthermore, the initial optimized driving path is further optimized regionally based on the node risk level of each node to obtain the target planned driving path. This solves the problem that existing path planning methods struggle to meet efficiency and safety requirements in complex and changing driving environments. It improves the efficiency, rationality, and safety of planned driving paths, thereby reducing driving risks and enhancing driving safety.

[0027] Example 2 Figure 2 This is a flowchart of a driving route planning method provided in Embodiment 2 of the present invention. This embodiment is a specific implementation based on the above embodiment. In this embodiment, various specific optional implementation methods are given for calculating the node risk degree of each node, determining the initial optimized driving route from the starting point to the ending point of the route, and performing regional optimization on the initial optimized driving route again. Accordingly, as Figure 2 As shown, the method in this embodiment may include: S210. Calculate the node risk degree of each node based on the multi-dimensional risk information of each node within the path planning range.

[0028] First, the distance between nodes can be defined based on the computing power of the path planning device (which can be the target driving device itself or a device module with path planning capabilities integrated into the target driving device) and the preset resolution, thereby converting the geometric map corresponding to the path planning range into a set of nodes. Further, the node risk level is defined as a closed interval [0,1], where a node risk level of 0 indicates no risk, and a node risk level of 1 indicates that the node cannot be passed. For each node's risk information in each single dimension, its single-dimensional risk level can be calculated separately, and the risk levels of each single dimension are weighted and summed to obtain the node's comprehensive risk level. Finally, a two-dimensional list of all node risk levels within the path planning range is obtained.

[0029] In an optional embodiment of the present invention, the multidimensional risk information may include multidimensional marine environmental information; the calculation of the node risk degree of each node based on the multidimensional risk information of each node within the path planning range may include: obtaining wind speed information, wind direction angle information, current velocity information, current direction angle information, temperature information, humidity information, visibility information, sea state level information, and water depth information of each node within the path planning range; and calculating the node risk degree based on the wind speed information, wind direction angle information, current velocity information, current direction angle information, temperature information, and water depth information of each node. Using humidity, visibility, sea state, and water depth information, calculate the risk levels for wind speed, wind direction angle, current velocity, current direction angle, temperature, humidity, visibility, sea state, and water depth for each node. Then, weight the risk levels for each node using these parameters to obtain the node risk level.

[0030] The risk levels are calculated based on the following information: wind speed risk, wind direction angle risk, current speed risk, current direction angle risk, temperature risk, humidity risk, visibility risk, sea state risk, and water depth risk.

[0031] In a specific example, taking a marine navigation scenario, the path planning area can be a rectangular ocean map with the path starting point and ending point diagonally. Correspondingly, the multidimensional risk information of nodes within the path planning area can include multidimensional marine environmental information. When calculating the node risk level of each node based on its multidimensional risk information, the following information can be obtained for each node within the path planning area: wind speed, wind direction angle, current speed, current direction angle, temperature, humidity, visibility, sea state, and water depth. It can be understood that the higher the wind speed, the higher the wind speed risk; the larger the angle between the wind direction and the course, the higher the wind direction angle risk; the faster the current, the higher the current speed risk; the larger the angle between the current direction and the course, the higher the current direction angle risk; the closer the temperature is to the ship's suitable temperature, the lower the temperature risk; the higher the humidity, the higher the humidity risk; the lower the visibility, the higher the visibility risk; and the higher the sea state, the higher the sea state risk. If the water depth is less than the ship's depth, the water depth risk level is 1. As the water depth increases, the water depth risk level decreases.

[0032] Furthermore, based on the wind speed, wind direction angle, current velocity, current direction angle, temperature, humidity, visibility, sea state, and water depth information of each node, the risk levels for each node are calculated, including wind speed risk, wind direction angle risk, current velocity risk, current direction angle risk, temperature risk, humidity risk, visibility risk, sea state risk, and water depth risk. Finally, according to the weight corresponding to each single-dimensional marine environmental information, the risk levels for each node are weighted and normalized to obtain the node risk level.

[0033] For example, in a marine navigation scenario, the formula for calculating the node risk is as follows: Node Risk = Wind Speed ​​Risk w1+ Wind direction angle risk level w2+ Flow Rate Risk w3+ Flow Angle Risk Level w4+ Temperature Risk Level w5+ humidity risk level w6+ Visibility Risk Level w7+ Sea state rating / risk level w8+ water depth risk level w9, where w1-w9 represent the weights corresponding to each single-dimensional marine environmental information. If the final calculated node risk score is greater than 1, it is truncated, meaning the maximum value of the node risk score is 1.

[0034] In an optional embodiment of the present invention, before calculating the node risk degree of each node based on the multidimensional risk information of each node within the path planning range, the method may further include: obtaining the equipment parameter information of the target driving device; and dynamically adjusting the weight of the multidimensional risk information of each node based on the equipment parameter information of the target driving device.

[0035] The equipment parameter information can be relevant parameter information describing the target driving equipment, such as including but not limited to the mass and volume of the target driving equipment. This embodiment of the invention does not limit the specific parameter type of the equipment parameter information.

[0036] Optionally, the weights corresponding to each single-dimensional risk information can be dynamically adjusted based on the relevant equipment parameters of the target vehicle. For example, when the risk information is marine environmental risk information, the target vehicle is a vessel. Accordingly, the weights corresponding to each single-dimensional marine environmental information can be dynamically adjusted based on the vessel's ship type, mass, volume, and other equipment parameters. For instance, the larger the vessel's volume, the smaller the weight of current velocity and the larger the weight of water depth; the larger the vessel's mass, the smaller the weight of wind speed and the larger the weight of sea state.

[0037] S220. Starting from the starting point of the path, determine the intermediate path nodes between the starting point and the ending point of the path in sequence to obtain the initial planned driving path.

[0038] The initial planned driving route can be a driving route that is initially planned without considering risk factors.

[0039] In this embodiment of the invention, a heuristic search algorithm can be employed, leveraging its superior performance in path planning to quickly generate an initial optimized driving path by combining it with risk information from the driving environment. Since heuristic search algorithms suffer from computational inefficiencies and limited adaptability when processing driving environment information, this embodiment pre-compiles the risk information for each node, eliminating the need for the algorithm to process and calculate the driving environment information in real time. Specifically, the location information of the path's starting and ending points, along with a two-dimensional list of node risk levels corresponding to the path planning range, can be input into the heuristic search algorithm. This allows the algorithm to automatically calculate and generate route planning information from the path's starting point to its ending point, or a "no available route" message.

[0040] Specifically, a heuristic search algorithm can be used to start from the path's origin and gradually expand using a priority queue to determine intermediate path nodes between the origin and destination, thus obtaining an initial planned driving path. Specifically, following the general direction of the path, the node with the lowest risk among the current node's neighbors can be selected as the next intermediate path node, until the destination is reached, thereby obtaining an initial planned driving path. Reverse calculations are not allowed during the initial planned driving path calculation process.

[0041] S230. Starting from the end point of the initially planned driving route, backtrack and calculate the node risk of the associated surrounding path nodes of the current path node in turn.

[0042] Among them, the associated surrounding path nodes can be path nodes around the current path node, including adjacent nodes of the current path node and nodes within a preset range of the current path node.

[0043] The initial planned driving path is merely an intermediate path node searched from surrounding neighboring nodes. To further improve the rationality of the initial planned driving path, after obtaining the initial planned driving path, the path can be backtracked sequentially from the end point of the initial planned driving path back to the starting point. During the backtracking process, for the current path node, neighboring nodes and nodes within a preset distance are further identified as its associated surrounding path nodes, and the corresponding node risk degree is calculated for each associated surrounding path node.

[0044] S240. Update the current path node according to the node risk of the associated surrounding path nodes to obtain the initial optimized driving path.

[0045] Furthermore, based on the node risk level of the current path node's associated surrounding path nodes, an analysis is performed. If a more reasonable node can be found among the current path node's associated surrounding path nodes, then nodes selected from the current path node's associated surrounding path nodes can be used to update the current path node. If a more reasonable node cannot be found among the current path node's associated surrounding path nodes, then the current path node can remain unchanged, and the next path node can be updated to the current path node. This process of updating the current path node based on the node risk level of the current path node's associated surrounding path nodes is repeated until all path nodes are updated. This process then performs the first optimization of the initially planned driving path to obtain the initial optimized driving path.

[0046] In an optional embodiment of the present invention, updating the current path node based on the node risk of its associated surrounding path nodes may include: calculating the actual cost and heuristically estimated cost of the associated surrounding path nodes based on their node risk; calculating the total cost of the associated surrounding path nodes based on their actual cost and heuristically estimated cost; filtering target associated surrounding path nodes based on their total cost; and updating the current path node based on the target associated surrounding path nodes.

[0047] In this context, the actual cost of a node refers to the known shortest path cost from the starting point of the path to the current node n. This value is deterministic and can be calculated precisely. The heuristically estimated cost refers to the estimated cost of the path from the current node n to the ending point of the path. This value is predictive and cannot be accurately obtained in advance. The target's associated surrounding path nodes can be those that minimize the total cost among the surrounding path nodes.

[0048] Specifically, the actual cost and heuristically estimated cost of the associated surrounding path nodes can be calculated based on their node risk levels. The actual cost and heuristically estimated cost of each associated surrounding path node are then summed to obtain the total cost for that node. Further, the associated surrounding path node with the smallest total cost is selected as the target associated surrounding path node, and the current path node is updated based on the target associated surrounding path node. It is understood that the target associated surrounding path node can be the current path node itself.

[0049] In an optional embodiment of the present invention, calculating the actual cost and heuristically estimated cost of the associated surrounding path nodes based on the node risk degree of the associated surrounding path nodes may include: calculating the actual cost of the associated surrounding path nodes based on the node risk degree of the associated surrounding path nodes according to the following formula: The heuristic cost estimate for the associated surrounding path nodes is calculated based on the following formula: Where n represents the nth associated surrounding path node, and g(n) represents the actual cost of the nth associated surrounding path node. Let represent the actual cost of the (n-1)th associated surrounding path node, and let sn represent the risk level of the nth associated surrounding path node. Let represent the risk of the (n-1)th associated surrounding path node, h(n) represent the heuristic estimated cost of the nth associated surrounding path node, xn represent the x-coordinate of the nth associated surrounding path node, xend represent the x-coordinate of the path endpoint, yn represent the y-coordinate of the nth associated surrounding path node, and yend represent the y-coordinate of the path endpoint.

[0050] For example, in a marine navigation scenario, xn can represent the dimension of the nth associated surrounding path node, xend can represent the dimension of the path endpoint, yn can represent the longitude of the nth associated surrounding path node, and yend can represent the longitude of the path endpoint. The total cost of associating surrounding path nodes can be expressed as: f(n) = g(n) + h(n). Accordingly, the target associated surrounding path node can be the associated surrounding path node with the smallest f(n).

[0051] S250. Determine the risk zone corresponding to each path node in the initial optimized driving path.

[0052] S260. Calculate the risk assessment value of the risk region based on the node risk of each path node included in the risk region corresponding to the path node.

[0053] The risk level region can be a pre-defined local optimization area for the node. The risk assessment value can be risk assessment information calculated for the entire risk level region.

[0054] In this embodiment of the invention, a secondary optimization process can be performed on the initial optimized driving path using a local optimization approach. This secondary optimization can employ a local region optimization method. Optionally, a geometric region centered on each path node and extending at a distance x from the path node can be designated as the risk region corresponding to that path node. The risk region can be circular or square; this embodiment of the invention does not impose any limitation on this. The length x used to determine the risk region can be adaptively configured based on the device's computing power; this embodiment of the invention does not impose any limitation on the specific value of the length x. Further, the node risk levels of each path node included in the risk region are summed to obtain the risk assessment value of the risk region.

[0055] S270. Determine the target risk area based on the node risk level of each node.

[0056] Among them, the target risk area can be the risk area with the highest local risk level.

[0057] Optionally, nodes with the highest local risk values ​​can be selected from all nodes within the path planning range as risk nodes, and all risk nodes can be added to a risk node set. The risk assessment value of a risk node's risk area is greater than the risk assessment values ​​of the risk areas of all surrounding nodes. Further, a target risk area is determined based on the risk assessment values ​​of the risk areas of each risk node in the risk node set. For example, assuming the risk assessment value of a risk node's risk area is T, the closed region bounded by nodes with risk assessment values ​​of T / 2 or T / 3 can be determined as the target risk area. Typically, the target risk area includes obstacles.

[0058] S280. If it is determined that the target risk area includes the target path node, the target path node is adjusted to obtain an adjusted path node; wherein the adjusted path node is outside the target risk area.

[0059] The target path node can be a path node located in the target risk area within the initial optimized driving path. The adjusted path node can be a path node obtained by adjusting the target path node.

[0060] If some path nodes in the initial optimized driving path are found to fall into the target risk area, these path nodes can be designated as target path nodes. Simultaneously, these target path nodes are adjusted, selecting those that do not fall into the target risk area as adjusted path nodes. The adjusted path nodes are then used to update the corresponding target path nodes. Optionally, there can be multiple target path nodes, and one target path node can correspond to one adjusted path node. After the target path nodes are adjusted, all path nodes in the entire planned path will not fall into the target risk area. Therefore, by readjusting the planned path nodes, the final planned driving path is smoother, reducing sharp turns and obstacles.

[0061] In an optional embodiment of the present invention, adjusting the movement direction of the target path node to obtain the adjusted path node may include: determining the intermediate path start point and intermediate path end point of the target path node; calculating the path loss value for each candidate intermediate path between the intermediate path start point and the intermediate path end point; filtering the candidate intermediate paths from the candidate intermediate paths according to the path loss value of the candidate intermediate paths; and mapping the target path node to the corresponding path node of the target candidate intermediate path to obtain the adjusted path node corresponding to the target path node.

[0062] In this context, the intermediate path start point and intermediate path end point can be two path nodes in the initial optimized driving path. The intermediate path start point can be the first path node located outside the target risk area and before entering it. The intermediate path end point can be the first path node located outside the target risk area and exiting it. Alternative intermediate paths can be any available path consisting of all path nodes between the intermediate path start point and intermediate path end point, and these alternative intermediate paths will not intersect with the target risk area. In other words, alternative intermediate paths can avoid the target risk area. The path loss value measures the risk of the path. The target alternative intermediate path can be the path with the minimum path loss value.

[0063] Optionally, the initial optimized driving path can be further optimized by adjusting the target path nodes that fall into the target risk area. Specifically, the path node about to enter the target risk area in the initial optimized driving path can be first identified as the intermediate path starting point, and the first path node after exiting the target risk area in the initial optimized driving path can be identified as the intermediate path ending point. Further, multiple paths that can avoid the target risk area are calculated for the intermediate path starting point and intermediate path ending point as alternative intermediate paths, and a loss function is set for the alternative intermediate paths. For example, the loss function for the alternative intermediate paths can be: Here, `loss` represents the path loss value, and `sigma()` is the summation function. `sn` represents the risk level of the nth node. `xnpp` is the node at the next x-coordinate (e.g., latitude), where `xn` is the x-coordinate of the current node. `ynpp` is the node at the next y-coordinate (e.g., longitude), where `yn` is the y-coordinate of the current node. `a` represents the step size, which can be set to the same value as the risk level division, for example, a value of 1. `u1` and `u2` represent random parameters.

[0064] The target intermediate path is selected from the alternative intermediate paths using a loss function of the alternative intermediate paths. For example, when parameter 'a' in the loss function is 1, (u1, u2) can take values ​​of (-1, 0), (1, 0), (0, 1), or (0, -1). When the boundary of the target risk area is encountered or the target risk area is within the target risk area, the relevant combination of (u1, u2) is automatically disabled. When reaching the end point of the intermediate path from its starting point, each alternative intermediate path and its path loss value are recorded. The smaller the path loss value, the lower the risk level of the alternative intermediate path. After setting the number of iterations, multiple sets of path loss values ​​for alternative intermediate paths can be obtained. The alternative intermediate path with the smallest path loss value is selected as the target alternative intermediate path. Furthermore, each target path node is mapped to the corresponding path node of the target alternative intermediate path, obtaining the adjusted path node corresponding to the target path node, and the corresponding target path node is updated by replacing the adjusted path node.

[0065] Therefore, it can be seen that the method of further optimizing the initial optimized driving path can dynamically adjust the heuristic estimated cost in the initial optimized driving path, making it more consistent with the actual environmental risk distribution, thereby improving the adaptability and efficiency of path planning.

[0066] The above technical solution utilizes risk information from the driving environment to quickly generate an initial optimized driving path. It then uses this risk information to calculate the risk assessment value of the risk zone where each path node in the initial optimized driving path is located. Subsequently, the target path nodes in the initial optimized driving path that are located in the target risk zone are adjusted again to achieve regional optimization. This ensures that the adjusted path nodes can effectively avoid the target risk zone, thereby realizing automatic planning of driving paths under different driving environment information, optimizing driving routes, reducing driving risks, and improving driving safety.

[0067] Specific application scenarios To more clearly illustrate the technical solutions provided by the embodiments of the present invention, the embodiments of the present invention take a marine navigation scenario as an example to specifically explain the implementation of the navigation path planning method. Figure 3 This is a flowchart illustrating a driving route planning method provided by an embodiment of the present invention. In a specific example, such as... Figure 3 As shown, in a marine navigation scenario, the navigation path planning method may include the following operations: Step 1: Obtain the location information of the ship's path start and end points, as well as the marine environment information within a rectangle with the path start and end points as the diagonal vertices.

[0068] Location information may include the latitude and longitude of the starting and ending points of the path. Marine environmental information may include, but is not limited to, wind speed and direction, current speed and direction, temperature and humidity, visibility, sea state, and water depth.

[0069] Step 2: Based on the map resolution and device computing power, convert the map into nodes, and calculate the marine environmental information of each node into node risk level.

[0070] Specifically, node distance information can be established first, for example, the distance between each node differs by 0.001 nautical miles. A rectangle with the diagonal vertices from the path's starting point to its ending point is divided into node combinations. The node information, along with the marine environmental information for each node, is input into a risk assessment algorithm. The algorithm calculates the risk level for each node based on its marine environmental information. The risk level ranges from a closed interval [0,1], where 0 represents no risk and 1 represents impassable. The node risk level can be manually adjusted to ensure its reasonableness.

[0071] Step 3: Based on the node risk information, a secondary optimization method is used to determine whether an optimal path exists.

[0072] By inputting a two-dimensional list of node risk levels into the path planning algorithm model, the optimal route or no route hint can be obtained. The path planning algorithm model can first determine the initial optimized driving path from the starting point to the ending point within the path planning range based on the node risk level of each node. Then, it can further optimize the initial optimized driving path based on the node risk level of each node to obtain the target planned driving path.

[0073] Step 4: Create a display interface to show the path planning results.

[0074] A drawing tool is used to create a display interface that shows the optimal path from the starting point to the ending point, or a message indicating that no path is available. The optimal path can avoid obstacles 100% and pass through risky areas in the least risky way, effectively reducing the risk of ship navigation.

[0075] The above technical solution utilizes information such as marine environmental factors such as wind, temperature, current, and sea state to calculate the risk level of each area. Through a dual-optimized path planning algorithm, it realizes automatic planning of ship navigation paths under different marine environmental conditions, optimizes ship navigation routes, and reduces ship navigation risks.

[0076] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data comply with the relevant laws, regulations and standards of the relevant regions.

[0077] It should be noted that any arrangement or combination of the technical features in the above embodiments also falls within the protection scope of this invention.

[0078] Example 3 Figure 4 This is a schematic diagram of a driving path planning device provided in Embodiment 3 of the present invention, as shown below. Figure 4 As shown, the device includes: a node risk calculation module 410, an initial optimized driving path determination module 420, and an initial optimized driving path optimization module 430, wherein: The node risk calculation module 410 is used to calculate the node risk of each node based on the multi-dimensional risk information of each node within the path planning range. The initial optimized driving path determination module 420 is used to determine the initial optimized driving path between the starting point and the ending point of the path within the path planning range based on the node risk of each node. The initial optimized driving path optimization module 430 is used to perform regional optimization on the initial optimized driving path again based on the node risk of each node to obtain the target planned driving path.

[0079] This invention calculates the node risk level of each node based on multi-dimensional risk information within the path planning range. Based on the node risk level of each node, an initial optimized driving path is determined within the path planning range from the starting point to the ending point. Furthermore, the initial optimized driving path is further optimized regionally based on the node risk level of each node to obtain the target planned driving path. This solves the problem that existing path planning methods struggle to meet efficiency and safety requirements in complex and changing driving environments. It improves the efficiency, rationality, and safety of planned driving paths, thereby reducing driving risks and enhancing driving safety.

[0080] Optionally, the multidimensional risk information includes multidimensional marine environmental information; the node risk calculation module 410 is further configured to: acquire wind speed information, wind direction angle information, current speed information, current direction angle information, temperature information, humidity information, visibility information, sea state level information, and water depth information of each node within the path planning range; calculate the wind speed risk, wind direction angle risk, current speed risk, current direction angle risk, temperature risk, humidity risk, visibility risk, sea state level risk, and water depth risk of each node based on the wind speed information, wind direction angle information, current speed information, current direction angle information, temperature risk, humidity risk, visibility risk, sea state level risk, and water depth risk of each node respectively; and perform weighted calculation on the wind speed risk, wind direction angle risk, current speed risk, current direction angle risk, temperature risk, humidity risk, visibility risk, sea state level risk, and water depth risk of each node to obtain the node risk of each node.

[0081] Optionally, the node risk calculation module 410 is further configured to: obtain the equipment parameter information of the target driving device; and dynamically adjust the weights of the multidimensional risk information of each node based on the equipment parameter information of the target driving device.

[0082] Optionally, the initial optimized driving path determination module 420 is further configured to: starting from the starting point of the path, sequentially determine the intermediate path nodes between the starting point of the path and the ending point of the path to obtain an initial planned driving path; backtrack from the ending point of the initial planned driving path to sequentially calculate the node risk degree of the associated surrounding path nodes of the current path node; update the current path node according to the node risk degree of the associated surrounding path nodes of the current path node to obtain the initial optimized driving path.

[0083] Optionally, the initial optimized driving route determination module 420 is further configured to: calculate the actual cost and heuristically estimated cost of the associated surrounding path nodes based on the node risk degree of the associated surrounding path nodes; calculate the total cost of the associated surrounding path nodes based on the actual cost and heuristically estimated cost of the associated surrounding path nodes; filter target associated surrounding path nodes based on the total cost of the associated surrounding path nodes; and update the current path node based on the target associated surrounding path nodes.

[0084] Optionally, the initial optimized driving path determination module 420 is further configured to: calculate the actual cost of the associated surrounding path nodes based on the node risk degree of the associated surrounding path nodes according to the following formula: The heuristic cost estimate for the associated surrounding path nodes is calculated based on the following formula: Where n represents the nth associated surrounding path node, and g(n) represents the actual cost of the nth associated surrounding path node. Let represent the actual cost of the (n-1)th associated surrounding path node, and let sn represent the risk level of the nth associated surrounding path node. Let represent the risk of the (n-1)th associated surrounding path node, h(n) represent the heuristic estimated cost of the nth associated surrounding path node, xn represent the x-coordinate of the nth associated surrounding path node, xend represent the x-coordinate of the path endpoint, yn represent the y-coordinate of the nth associated surrounding path node, and yend represent the y-coordinate of the path endpoint.

[0085] Optionally, the initial optimized driving path optimization module 430 is further configured to: determine the risk level region corresponding to each path node in the initial optimized driving path; calculate the risk assessment value of the risk level region based on the node risk level of each path node included in the risk level region corresponding to the path node; determine the target risk region based on the node risk level of each node; and, if the target risk region includes the target path node, adjust the target path node to obtain the adjusted path node; wherein the adjusted path node is outside the target risk region.

[0086] Optionally, the initial optimized driving route optimization module 430 is further configured to: determine the intermediate path start point and intermediate path end point of the target path node; calculate the path loss value for each candidate intermediate path between the intermediate path start point and the intermediate path end point; filter the target candidate intermediate path from the candidate intermediate paths according to the path loss value of the candidate intermediate path; and map the target path node to the corresponding path node of the target candidate intermediate path to obtain the adjusted path node corresponding to the target path node.

[0087] The above-described driving route planning device can execute the driving route planning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the driving route planning method provided in any embodiment of the present invention.

[0088] Since the driving path planning device described above is capable of executing the driving path planning method in the embodiments of the present invention, those skilled in the art can understand the specific implementation methods and various variations of the driving path planning device in this embodiment based on the driving path planning method described in the embodiments of the present invention. Therefore, how the driving path planning device implements the driving path planning method in the embodiments of the present invention will not be described in detail here. Any device used by those skilled in the art to implement the driving path planning method in the embodiments of the present invention falls within the scope of protection of this application.

[0089] Example 4 Figure 5 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0090] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0091] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0092] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as driving path planning methods.

[0093] Optionally, the driving route planning method includes: calculating the node risk degree of each node based on the multidimensional risk information of each node within the route planning range; determining an initial optimized driving route from the starting point to the ending point of the route within the route planning range based on the node risk degree of each node; and performing regional optimization on the initial optimized driving route again based on the node risk degree of each node to obtain the target planned driving route.

[0094] In some embodiments, the driving route planning method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the driving route planning method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the driving route planning method by any other suitable means (e.g., by means of firmware).

[0095] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0096] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0097] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0098] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0099] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0100] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0101] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0102] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for planning a driving route, characterized in that, include: The node risk level of each node is calculated based on the multi-dimensional risk information of each node within the path planning range; Based on the node risk level of each node, an initial optimized driving path is determined from the starting point to the ending point within the path planning range; Based on the node risk level of each node, the initial optimized driving path is further optimized regionally to obtain the target planned driving path.

2. The driving path planning method according to claim 1, characterized in that, The multidimensional risk information includes multidimensional marine environmental information; The calculation of the node risk degree of each node based on the multi-dimensional risk information of each node within the path planning range includes: Obtain wind speed, wind direction angle, current velocity, current direction angle, temperature, humidity, visibility, sea state, and water depth information for each node within the path planning range; Based on the wind speed, wind direction angle, current speed, current angle, temperature, humidity, visibility, sea state, and water depth information of each node, calculate the wind speed risk, wind direction angle risk, current speed risk, current angle risk, temperature risk, humidity risk, visibility risk, sea state risk, and water depth risk of each node respectively. The risk levels of wind speed, wind direction angle, current velocity, current direction angle, temperature, humidity, visibility, sea state, and water depth for each node are weighted and calculated to obtain the node risk level for each node.

3. The driving path planning method according to claim 1 or 2, characterized in that, Before calculating the node risk level of each node based on the multidimensional risk information of each node within the path planning range, the method further includes: Obtain the equipment parameter information of the target driving equipment; The weights of the multidimensional risk information of each node are dynamically adjusted based on the equipment parameter information of the target driving device.

4. The driving path planning method according to claim 1, characterized in that, The step of determining the initial optimized driving path from the starting point to the ending point of the path within the path planning range based on the node risk of each node includes: Starting from the path's starting point, the intermediate path nodes between the path's starting point and the path's ending point are determined sequentially to obtain the initial planned driving path; Starting from the end point of the initially planned driving route, backtracking is performed to calculate the node risk of the surrounding path nodes associated with the current path node in turn. The current path node is updated based on the node risk level of its associated surrounding path nodes to obtain the initial optimized driving path.

5. The driving path planning method according to claim 4, characterized in that, The step of updating the current path node based on the node risk level of its associated surrounding path nodes includes: Calculate the actual cost and heuristically estimated cost of the associated surrounding path nodes based on the node risk degree of the associated surrounding path nodes; The total cost of the associated surrounding path nodes is calculated based on the actual cost and heuristically estimated cost of the associated surrounding path nodes. Filter target associated surrounding path nodes based on the total cost of the associated surrounding path nodes, and update the current path node based on the target associated surrounding path nodes.

6. The driving path planning method according to claim 5, characterized in that, The calculation of the actual cost and heuristically estimated cost of the associated surrounding path nodes based on the node risk degree of the associated surrounding path nodes includes: The actual cost of the associated surrounding path nodes is calculated based on the node risk level of the associated surrounding path nodes using the following formula: The heuristic cost estimate for the associated surrounding path nodes is calculated based on the following formula: Where n represents the nth associated surrounding path node, and g(n) represents the actual cost of the nth associated surrounding path node. Let represent the actual cost of the (n-1)th associated surrounding path node, and let sn represent the risk level of the nth associated surrounding path node. Let represent the risk of the (n-1)th associated surrounding path node, h(n) represent the heuristic estimated cost of the nth associated surrounding path node, xn represent the x-coordinate of the nth associated surrounding path node, xend represent the x-coordinate of the path endpoint, yn represent the y-coordinate of the nth associated surrounding path node, and yend represent the y-coordinate of the path endpoint.

7. The driving path planning method according to claim 1, characterized in that, The step of further optimizing the initial optimized driving path based on the node risk level of each node includes: Determine the risk zone corresponding to each path node in the initial optimized driving path; The risk assessment value of the risk region is calculated based on the node risk of each path node included in the risk region corresponding to the path node. The target risk area is determined based on the node risk level of each node. If the target risk area is determined to include the target path node, the target path node is adjusted to obtain an adjusted path node; wherein the adjusted path node is outside the target risk area.

8. The driving path planning method according to claim 7, characterized in that, The process of adjusting the target path node to obtain the adjusted path node includes: Determine the intermediate path start point and intermediate path end point of the target path node; Calculate the path loss value for each alternative intermediate path between the starting point and the ending point of the intermediate path; Target alternative intermediate paths are selected from the alternative intermediate paths based on the path loss value of the alternative intermediate paths; The target path node is mapped to the corresponding path node of the target alternative intermediate path to obtain the adjusted path node corresponding to the target path node.

9. A driving path planning device, characterized in that, include: The node risk calculation module is used to calculate the node risk of each node based on the multi-dimensional risk information of each node within the path planning range. The initial optimized driving route determination module is used to determine the initial optimized driving route from the starting point to the ending point of the path within the path planning range based on the node risk of each node. The initial optimized driving path optimization module is used to further optimize the initial optimized driving path based on the node risk of each node to obtain the target planned driving path.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that is executed by the at least one processor to enable the at least one processor to perform the driving path planning method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the driving path planning method according to any one of claims 1-8.

12. A computer program product, characterized in that, It includes a computer program / instruction, wherein the computer program / instruction, when executed by a processor, implements the driving path planning method according to any one of claims 1-8.

Images