A path planning method, system, terminal and medium

Abstract

The present invention belongs to the field of route planning and specifically discloses a route planning method, system, terminal, and medium. In response to receiving a transport task instruction, the method obtains road and vehicle information in a target area; based on the transport destination, real-time vehicle location, real-time vehicle battery level, and map information, the method determines at least one candidate route for completing the transport task, each candidate route including at least one lane; based on the road information and vehicle type information, the method determines lane costs corresponding to all lanes in the target area; and based on the lane costs, the method determines an optimal route from the at least one candidate route. The method selects the optimal route by combining actual and future road information, as well as vehicle type information, improving the dynamic changes in road operation information, reducing algorithm complexity, and improving route planning efficiency.

Description

Technical Field

[0001] The present invention belongs to the field of path planning, and in particular relates to a path planning method, system, terminal and medium. Background Art

[0002] With the development of global trade, ports, as key hubs for logistics and transportation, are becoming increasingly important for logistics management. In busy port environments, efficient management of internal cargo transportation has become a core link in ensuring the smooth operation of the entire logistics chain.

[0003] During cargo transportation, planning a reasonable transport route can effectively improve transportation efficiency. Related technologies disclose a method for optimizing energy consumption paths for pure electric vehicles based on road information. This method focuses on semi-physical and semi-empirical calculations of vehicle energy consumption, and optimizes the path planning based on different road environment information and predicted speeds. However, the port environment is complex and ever-changing, and road operation information is updated in real time. This makes the path planned by this method, which relies solely on initially acquired road environment information, difficult to adapt to dynamic changes. Furthermore, the algorithm is complex, affecting the efficiency of path planning. Summary of the Invention

[0004] To solve the above problems, the present invention provides a path planning method, system, terminal and medium, which combine actual road information and future information as well as vehicle model information to select the optimal path, improve the dynamic changes of road operation information, reduce algorithm complexity, and improve path planning efficiency.

[0005] The technical solution of the present invention provides a path planning method, which obtains road information and vehicle information of a target area in response to obtaining a transportation task instruction; the transportation task instruction includes a transportation destination, the road information includes actual road information and future road information, wherein the future road information includes a predicted number of vehicles and a predicted vehicle speed at a future time point, and the vehicle information includes real-time vehicle position, real-time vehicle power, and vehicle model information; based on the transportation destination, real-time vehicle position, real-time vehicle power and map information, at least one candidate path for completing the transportation task on the basis of meeting charging requirements is determined, and each candidate path in the at least one candidate path includes at least one lane; based on the road information and vehicle model information, the lane costs corresponding to all lanes in the target area are determined; based on the lane costs, the optimal path is determined from the at least one candidate path.

[0006] The technical solution of the present invention provides a path planning system, an acquisition module, configured to acquire road information and vehicle information of a target area in response to acquiring a transportation task instruction; the transportation task instruction includes a transportation destination, the road information includes actual road information and future road information, and the vehicle information includes real-time vehicle position, real-time vehicle power, and vehicle model information; a first determination module, configured to determine at least one candidate path for completing the transportation task on the basis of meeting charging requirements based on the transportation destination, real-time vehicle position, real-time vehicle power and map information, each of the at least one candidate path includes at least one lane; a second determination module, configured to determine lane costs corresponding to all lanes in the target area based on the road information and vehicle information; a third determination module, configured to determine the optimal path from at least one candidate path based on the lane costs.

[0007] The present invention provides a route planning method, system, terminal, and medium that, compared to existing technologies, have the following advantages: In response to a transport task, road information, including actual and future road information, is obtained. Actual road information refers to physical road information, while future road information refers to future road operational information. Vehicle-related information is also obtained, and several candidate routes are selected based on the vehicle's battery level. Then, based on the road information and vehicle model information, the route with the lowest lane cost is selected from the candidate routes as the optimal route. By combining actual and future road information with vehicle model information to select the optimal route, the present invention reduces vehicle costs, enhances sensitivity to dynamic changes in road operational information, reduces algorithm complexity, and improves route planning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for the description. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0009] Figure 1 A schematic block diagram of the structure of a path planning system provided by an embodiment of the present invention.

[0010] Figure 2 A schematic flow chart of a path planning method provided by an embodiment of the present invention.

[0011] Figure 3 This is an exemplary flowchart of a method for determining candidate paths according to some embodiments of the present invention.

[0012] Figure 4 This is an exemplary flow chart of a method for determining the power cost and time cost corresponding to a lane, as shown in some embodiments of the present invention.

[0013] Figure 5 This is a schematic diagram of a process for determining a predicted number of vehicles and a predicted vehicle speed based on a prediction model according to some embodiments of the present invention. DETAILED DESCRIPTION

[0014] In order to make the purpose, features, and advantages of the present invention more obvious and easy to understand, the technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings in the specific embodiments. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0016] Figure 1 This is a schematic block diagram of a path planning system structure provided by an embodiment of the present invention. The path planning system can be divided into multiple functional modules according to the functions it performs, such as Figure 1 The functional modules may include: an acquisition module 110, a first determination module 120, a second determination module 130, and a third determination module 140. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can perform fixed functions, which are stored in a memory.

[0017] The acquisition module 110 can be configured to obtain road information and vehicle information of the target area in response to obtaining a transportation task instruction, where the transportation task instruction includes the transportation destination, the road information includes actual road information and future road information, and the vehicle information includes real-time vehicle location, real-time vehicle power, and vehicle model information.

[0018] The first determination module 120 can be configured to determine at least one candidate path for completing the transportation task while meeting the charging requirements based on the transportation destination, real-time vehicle location, real-time vehicle power and map information, and each candidate path in the at least one candidate path includes at least one lane.

[0019] In some embodiments, the first determination module 120 can be further configured to determine at least one alternative path to complete the transportation task based on the transportation destination, real-time vehicle location and map information; for an alternative path, based on the real-time vehicle power and the alternative path, determine the charging requirement corresponding to the alternative path, and the charging requirement includes the number of charging times; in response to the number of charging times being greater than 0, determine whether all lanes of the alternative path include an electric charging lane; in response to including an electric charging lane, determine whether the electric charging lane meets the charging requirement; in response to meeting the charging requirement, determine the alternative path as the candidate path corresponding to the alternative path; in response to not meeting the charging requirement, update the alternative path based on the real-time vehicle power and electric charging distribution, and determine the updated alternative path as the candidate path; in response to not including an electric charging lane, update the alternative path based on the real-time vehicle power and electric charging distribution, and determine the updated alternative path as the candidate path; the updated alternative path meets the charging requirement; and in response to the number of charging times being equal to 0, determine the alternative path as the candidate path.

[0020] The second determination module 130 may be configured to determine lane costs corresponding to all lanes in the target area based on the road information and the vehicle information.

[0021] In some embodiments, actual road information includes lane length, lane slope, lane quality, and the number of lane curves; vehicle information also includes vehicle model information. The second determination module 130 can be further configured to determine, for a lane, the corresponding energy cost and time cost based on the lane length, lane slope, lane quality, the number of lane curves, and vehicle model information; and to determine the lane cost based on the energy cost and time cost.

[0022] In some embodiments, the road information also includes future road information, including the predicted number of vehicles and predicted vehicle speeds for all lanes in the target area at at least one future time point. The second determination module 130 can be further configured to determine, for a future time point, a first energy cost and a first time cost based on the predicted number of vehicles and predicted vehicle speed at the future time point; determine a second energy cost and a second time cost corresponding to the lane based on lane length, lane slope, lane quality, number of lane curves, and vehicle model information; and determine an energy cost and a time cost corresponding to the lane based on the first energy cost, first time cost, second energy cost, and second time cost.

[0023] The third determination module 140 may be configured to determine an optimal path from at least one candidate path based on the lane cost.

[0024] In some embodiments, the time point when the optimal path was last determined is the target time point.

[0025] In some embodiments, the third determination module 140 can be further configured to, in response to satisfying the path update condition, obtain the current number of vehicles and the current vehicle speed of the current lane corresponding to the current vehicle position at the current time point; obtain the historically predicted number of vehicles and the historically predicted vehicle speed of the current lane at the current time point predicted by the target time point; whether the difference between the current number of vehicles and the current vehicle speed and the historically predicted number of vehicles and the historically predicted vehicle speed meets the first preset condition; and in response to satisfying the first preset condition, continue to execute the current optimal path.

[0026] In some embodiments, the third determination module 140 can be further configured to obtain first vehicle information at the current time point and second vehicle information at the target time point in response to satisfying the path update condition; determine whether the difference between the first vehicle information and the second vehicle information satisfies a second preset condition; and continue to execute the current optimal path in response to satisfying the second preset condition.

[0027] In some embodiments, the third determination module 140 can be further configured to obtain updated road information and updated vehicle information of the target area at the current time point in response to the first preset condition or the second preset condition not being met, the updated vehicle information including the current vehicle position, and the updated road information including the actual road information; based on the transportation destination, the current vehicle position and the map information, determine at least one updated candidate path to complete the transportation task, each updated candidate path in the at least one updated candidate path including at least one updated lane; based on the updated road information and the updated vehicle information, update the lane costs corresponding to all lanes in the target area to obtain updated lane costs; and based on the updated lane costs, determine the optimal path from the at least one updated candidate path.

[0028] For more details about the acquisition module 110, the first determination module 120, the second determination module 130 and the third determination module 140, see Figure 2-Figure 5 and its related descriptions.

[0029] An embodiment of a path planning system has been described in detail above. Based on the path planning system described in the above embodiment, an embodiment of the present invention further provides a path planning method corresponding to the system.

[0030] Figure 2 A schematic diagram of a path planning method provided by an embodiment of the present invention. Figure 2 The execution subject may be a path planning system. Depending on different requirements, the order of the steps in the flowchart may be changed, and some may be omitted. In some embodiments, the method flow may be executed by a processing device.

[0031] like Figure 2 As shown, the method includes the following steps.

[0032] Step 210 : In response to obtaining the transport task instruction, obtain road information and vehicle information of the target area.

[0033] The transport task instruction refers to an instruction for planning a vehicle to perform a transport task. In some embodiments, the transport task instruction may include a transport destination.

[0034] The target area refers to the geographic area that a vehicle will pass through when traveling from its real-time vehicle location to its destination. In some embodiments, when a vehicle is loading or unloading cargo within a terminal, the target area may be that terminal. When a vehicle is traveling between terminals, the target area may encompass the area between the terminals.

[0035] Road information refers to data that can reflect road conditions. In some embodiments, the road information may include actual road information. Actual road information may include lane length, lane slope, lane quality, and the number of lane curves. For more information on how to determine lane length, lane slope, lane quality, and the number of lane curves, please see below. In some embodiments, the road information may also include future road information. Future road information may include the predicted number of vehicles and predicted vehicle speeds at a future point in time. For more information on future road information, please see below.

[0036] Vehicle information refers to information reflecting the current status of the vehicle performing the current transport task. This information may include real-time vehicle location, real-time vehicle battery level, and vehicle model information. In some embodiments, the processing device may determine the vehicle's real-time location using an acquisition module, such as GPS positioning. The processing device may also determine the vehicle's real-time battery level using a voltage measurement module.

[0037] Step 220 , based on the transportation destination, the real-time vehicle location, the real-time vehicle power level, and the map information, determine at least one candidate route for completing the transportation task while meeting the charging requirements.

[0038] A candidate path is a feasible route for a vehicle to reach its destination from its real-time location. A candidate path can be composed of at least one lane. A lane is a road segment created by dividing the road. Lanes are described below.

[0039] In some embodiments, the processing device may determine at least one candidate route using various methods. For example, the processing device may establish a first preset table based on historical transport destinations, historical real-time vehicle locations, and historical candidate routes. The first preset table includes correspondences between historical transport destinations, historical real-time vehicle locations, and different historical candidate routes. The processing device may consult the first preset table and determine at least one desired candidate route based on the current transport destination and real-time vehicle location.

[0040] In some embodiments, the processing device may further determine at least one candidate route based on the transportation destination, the real-time vehicle location, and map information using a preset route planning algorithm.

[0041] A path planning algorithm is an algorithm used to plan a vehicle's route. In some embodiments, the preset path planning algorithm is an A* search algorithm. The processing device may determine the real-time vehicle location as a starting point and the transportation destination as an end point. The A* search algorithm is used to determine at least one candidate path.

[0042] In some embodiments, when the vehicle is an electric vehicle, the processing device may consider the vehicle's real-time vehicle power level and the availability of electric charging stations in the lane when determining candidate routes. For more information on how to determine candidate routes in consideration of the vehicle's real-time vehicle power level and the availability of electric charging stations in the lane, see Figure 3 and its related descriptions.

[0043] In some embodiments of this specification, by using a path planning algorithm to determine a candidate path, the calculation time can be effectively reduced and the required candidate path results can be obtained quickly and accurately.

[0044] Step 230 : Determine lane costs corresponding to all lanes in the target area based on the road information and vehicle type information.

[0045] A lane refers to a road segment obtained by dividing a road. In some embodiments, the processing device can determine at least one lane based on map information in a variety of ways. For example, the processing device can divide the road in the map into several equal or approximately equal length segments according to preset lane lengths. For example, every 100 meters or 500 meters is considered a road segment. For another example, the processing device can divide the road based on the road network structure, using intersections, forks, crosswalks, and other locations in the map as nodes. The road between adjacent nodes is divided into lanes.

[0046] Lane cost refers to data or symbols that reflect the loss cost of a vehicle passing through that lane. Lane cost can be expressed as a score between 0 and 100, with higher scores indicating greater loss cost.

[0047] In some embodiments, when the road information only includes actual road information, the lane cost can be a fixed value. In some embodiments, when the road information includes actual road information and future road information, the lane cost can vary with the predicted number of vehicles and predicted vehicle speeds at the future time point. For more information about future road information, please refer to Figure 4 Some related content.

[0048] In some embodiments, the actual road information may include lane length, lane slope, lane quality, and the number of lane curves; the vehicle information may also include vehicle model information.

[0049] Lane length refers to the length of the path a vehicle travels through the lane. Lane slope reflects the steepness of the lane surface. Lane slope can be expressed as the angle of inclination of the lane surface relative to the horizontal plane. A positive or negative inclination angle can indicate an uphill or downhill slope.

[0050] Lane quality is an indicator that reflects the overall quality of a lane's pavement and can be represented by a score. In some embodiments, the smoother the lane surface and the fewer defects such as cracks, potholes, and crazing, the better the lane quality. The processing device can construct a preset lane quality table by correlating lane surface smoothness, the number of road defects, and lane quality. Lane quality is determined by looking up the table.

[0051] In some embodiments, the processing device can obtain lane length using an odometer. It can also obtain road surface smoothness and the number of road surface defects using a vehicle-mounted bump accumulation meter, a continuous roughness meter, or other equipment, and determine lane quality by querying a preset lane quality table. It can also obtain lane slope using an inclinometer, a level, or other equipment. It can also determine the number of curves in the lane using map information.

[0052] Vehicle model information refers to parameters that reflect the inherent properties of a vehicle. In some embodiments, vehicle model information may include information such as the vehicle's range and power consumption per 100 kilometers. The processing device can obtain the corresponding vehicle model information by querying the vehicle's factory log.

[0053] In some embodiments, when the vehicle is an electric vehicle, for a lane, the processing device can also determine the second power cost and second time cost corresponding to the lane based on lane length, lane slope, lane quality, number of lane curves and vehicle model information.

[0054] In some embodiments, the lane cost may include a power cost and a time cost. The power cost may be expressed as the power consumption of the vehicle passing through the lane; the time cost may be expressed as the time taken for the vehicle to pass through the lane.

[0055] In some embodiments, the second power cost of the lane takes into account the impact of lane slope, length, quality and vehicle model information on power. It is assumed that the vehicle consumes more power when going uphill, the lane quality is poor and the lane is long and the vehicle model is heavy.

[0056] For example, for a lane, the processing device may determine the second power cost using formula (1):

[0057]

[0058] in, Indicates the second power cost of the lane, represents the vehicle's electricity consumption per 100 kilometers, B represents the lane length, C represents the lane slope, and D represents the lane quality. is the coefficient.

[0059] In some embodiments, the second time cost of the lane takes into account that the lane slope and the number of curves will affect the time it takes for a vehicle to pass. The better the lane quality, the lower the time cost, and the longer the lane, the higher the time cost.

[0060] For example, for a lane, the processing device may determine the second time cost by using formula (2):

[0061]

[0062] in, represents the time cost of the lane, represents the lane length, E represents the number of lane curves, and D represents the lane quality. is the coefficient.

[0063] In some embodiments of this specification, the lane cost is determined by determining the energy cost and time cost based on factors such as vehicle model information, lane slope, lane quality, and the number of lane curves. This allows for comprehensive consideration of the impact of multiple factors on vehicle driving, thereby improving the accuracy and reliability of the calculation results overall.

[0064] In some embodiments, for a future time point, the processing device may further determine the energy cost and time cost corresponding to the lane based on the first energy cost, the first time cost, the second energy cost, and the second time cost. For more information on this part, please refer to Figure 4 and related instructions.

[0065] Figure 4 This is an exemplary flowchart of a method for determining the power cost and time cost corresponding to a lane according to some embodiments of this specification.

[0066] In some embodiments, the road information may further include future road information, which may include the predicted number of vehicles and predicted vehicle speeds of all lanes in the target area at at least one future time point.

[0067] The number of vehicles refers to the number of vehicles traveling on the lane. The vehicle speed refers to the average speed of all vehicles traveling on the lane. In some embodiments, for lane A in the target area, the corresponding road information can be [( , , ),( , , ),...,( , , )].in,( , , ) represents lane A at a future time point The predicted number of vehicles is , the predicted vehicle speed is .

[0068] In some embodiments, the processing device can obtain road information at a future point in time through various methods. For example, the processing device can perform similarity matching on historical data based on current real-time road information, select the historical road information with the highest similarity as reference road information, and determine the historical vehicle count and historical vehicle speed of the historical road corresponding to the reference road information at at least one second historical time point as the future road information for the current road at a future time point. The reference road information is historical road information for the historical road at a first historical time point, where the first historical time point is earlier than the second historical time point and both are historical time points. Similarity matching algorithms may include, but are not limited to, Manhattan distance methods, support vector machines, and the like.

[0069] In some embodiments, the processing device can determine the predicted number of vehicles in the lane at a future point in time through the number prediction layer of the prediction model; and determine the predicted vehicle speed through the speed prediction layer of the prediction model. For more information on this part, please refer to Figure 5 and its related contents.

[0070] In some embodiments, for a future time point, the processing device may determine a first electricity cost and a first time cost based on a predicted number of vehicles and a predicted vehicle speed at the future time point.

[0071] The first electricity cost is the electricity cost determined based on the predicted number of vehicles and the predicted vehicle speed. The first time cost is the time cost determined based on the predicted number of vehicles and the predicted vehicle speed. For details on how to determine the predicted number of vehicles and the predicted vehicle speed, please refer to the above text.

[0072] In some embodiments, it is assumed that the lower the vehicle speed, the higher the power consumption, and the more vehicles there are, the higher the power consumption (due to the possibility of frequent acceleration and deceleration). The first power cost can be positively correlated with the predicted number of vehicles in the lane and negatively correlated with the vehicle speed. For example, because some power is wasted when a vehicle frequently starts and stops, the power consumption of a vehicle traveling at a constant speed is less than the power consumption of a vehicle traveling at a variable speed. The more vehicles there are in a lane, the more likely a vehicle is to be affected by other vehicles while driving, making it impossible to maintain a constant speed. Therefore, the first power cost can be positively correlated with the predicted number of vehicles in the lane and negatively correlated with the predicted vehicle speed.

[0073] For example, for a lane, the processing device may determine the first power cost by using formula (3):

[0074]

[0075] in, Indicates the first electricity cost, represents the predicted number of vehicles, G represents the predicted vehicle speed, is the coefficient.

[0076] The more vehicles are predicted to be in the lane at a future time point, the slower the vehicle speed is, which means that the vehicle travels slower in the lane and takes longer, that is, the higher the time cost is.

[0077] For example, for a lane, the processing device may determine the first time cost by formula (4):

[0078]

[0079] in, Indicates the first time cost, represents the predicted number of vehicles, G represents the predicted vehicle speed, is the coefficient.

[0080] In some embodiments, the coefficients It can be obtained through linear regression machine learning algorithm, trained based on historical data, or set through expert experience and experiments.

[0081] In some embodiments, the processing device may determine a second energy cost and a second time cost corresponding to the lane based on lane length, lane slope, lane quality, number of lane curves, and vehicle type information. For specific steps for determining the second energy cost and the second time cost, please refer to the above section on determining the energy cost and the time cost.

[0082] The processing device may determine the energy cost and time cost corresponding to the lane based on the first energy cost, the first time cost, the second energy cost, and the second time cost.

[0083] In some embodiments, the processing device can construct a preset energy cost table based on the correlation between the first energy cost, the second energy cost, and the energy cost; the preset energy cost table includes the correspondence between the historical first energy cost, the historical second energy cost, and different historical energy costs. The processing device can determine the energy cost of the corresponding lane based on the current first energy cost and the second energy cost by consulting the preset energy cost table. The correspondence in the preset energy cost table can be: the energy cost is positively correlated with the first energy cost and the second energy cost of the lane.

[0084] In some embodiments, the processing device may construct a preset time cost table based on the correlation between the first time cost, the second time cost, and the time cost. The corresponding relationship in the preset time cost table may be: the time cost is positively correlated with the first time cost and the second time cost of the lane. For more information on constructing the preset time cost table, please refer to the relevant section above regarding constructing the preset power cost table.

[0085] In some embodiments of this specification, the predicted first energy cost and first time cost are combined with the actually measured second energy cost and second time cost to jointly determine the energy cost and time cost of the lane. This allows the resulting energy cost and time cost to be predictive, reflecting the changing trend of the lane at a certain point in time, laying the foundation for subsequently accurately determining the optimal path.

[0086] For example, for a lane, the processing device can determine the power cost using formula (5):

[0087]

[0088] in, is the first electricity cost weight at the future time point t, for a total of N future time points, is the first-time cost at future time point t.

[0089] For example, for a lane, the processing device can determine the power cost using formula (6):

[0090]

[0091] in, is the first time cost weight at the future time point t.

[0092] In some embodiments, the processing device determines the lane cost of the lane based on the power cost and the time cost.

[0093] In some embodiments, the lane cost may be positively correlated with the energy cost and time cost of the lane.

[0094] For example, for a lane, the processing device may determine the lane cost using formula (7):

[0095]

[0096] in, represents the lane cost of the lane, represents the power cost, K represents the time cost, and In some embodiments, the coefficient It can also be determined based on transportation requirements. When transportation pays more attention to electricity cost, The bigger; when transportation pays more attention to time cost, The bigger.

[0097] Step 240 : Determine an optimal path from at least one candidate path based on the lane cost.

[0098] In some embodiments, the processing device may determine the optimal path from at least one candidate path using various methods. For example, the processing device may calculate the total lane cost of each candidate path based on the lanes included in the candidate path. The processing device may then determine the candidate path with the lowest total lane cost among all calculated results as the optimal path.

[0099] In some embodiments, when the road information only includes actual road information, the lane cost is a fixed value. For a candidate path, the processing device may calculate the fixed lane cost values ​​corresponding to all lanes included in the candidate path and determine the total lane cost of the candidate path as the sum of the fixed lane cost values.

[0100] In some embodiments, when the road information includes both actual road information and future road information, the processing device may determine the future time points at which the current vehicle will arrive in different lanes based on the current vehicle speeds in those lanes. A future lane cost for each lane is determined based on the future time points. The total lane cost for the candidate path is calculated by summing the future lane costs for all lanes.

[0101] For example, for a candidate path containing lanes A, B, and C, the future time points at which the current vehicle reaches these three lanes are future time points A, B, and C, respectively. The lane costs for this candidate path can be: the future lane cost of lane A at future time point A + the future lane cost of lane B at future time point B + the future lane cost of lane C at future time point C.

[0102] In some embodiments of the present specification, by selecting the optimal path from at least one candidate path based on lane cost, the driving route can be flexibly adjusted to avoid congested sections, reduce waiting time and power consumption caused by traffic congestion, and improve vehicle driving efficiency.

[0103] It should be noted that the above description of process path planning is for illustrative purposes only and does not limit the scope of application of this specification. Those skilled in the art may make various modifications and changes to process path planning under the guidance of this specification. However, such modifications and changes remain within the scope of this specification.

[0104] In some embodiments, after determining the optimal route, the vehicle will travel along the optimal route from the real-time vehicle position to the transport destination. In some embodiments, after determining the optimal route, if a route update condition is met, the processing device will determine whether to continue executing the current optimal route or re-determine the current optimal route.

[0105] In some embodiments, in response to a path update condition being met, the processing device may obtain the current number of vehicles and the current speed of the current lane corresponding to the current vehicle position at the current time point; obtain the historically predicted number of vehicles and the historically predicted speed of the current lane at the current time point predicted for the target time point; determine whether the difference between the current number of vehicles and the current speed and the historically predicted number of vehicles and the historically predicted speed of the current lane satisfies a first preset condition; continue executing the current optimal path if the first preset condition is met; and redetermine the current optimal path if the first preset condition is not met.

[0106] The target time point refers to the time point when the optimal path was last determined.

[0107] Path update conditions refer to the conditions used to determine whether an optimal path needs to be updated. In some embodiments, lane conditions often change over time. For example, the current optimal path may become unavailable due to traffic congestion, traffic accidents, or other factors, or a lane on a candidate path may have a lower lane cost than the current optimal path due to a decrease in vehicle traffic. In these cases, the processing device may determine whether to continue executing the current optimal path or to re-determine the optimal path.

[0108] In some embodiments, a route update condition may include: performing a route update each time the vehicle travels a preset distance or a preset duration. A route update condition may also include: performing a route update when the total lane cost of the vehicle's current route drops below an update threshold. The update threshold may be determined based on prior experience. In some embodiments, the processing device may perform a route update in response to receiving a route update instruction. The vehicle driver may input the route update instruction into the processing device.

[0109] In some embodiments, the processing device can determine the current number of vehicles in the lane and the average driving speed of the vehicles through monitoring cameras and vehicle speedometers installed on the lane, and then determine the current number of vehicles and current vehicle speed in the lane.

[0110] The historical predicted number of vehicles and the historical predicted vehicle speed refer to the predicted number of vehicles and the predicted vehicle speed at the current time point predicted by the processing device at the target time point. For more information on how to determine the predicted number of vehicles and the predicted vehicle speed, please refer to Figure 5 and its related descriptions.

[0111] In some embodiments, the processing device may determine whether a difference between the current number of vehicles and the current vehicle speed and the historically predicted number of vehicles and the historically predicted vehicle speed satisfies a first preset condition; and in response to satisfying the first preset condition, continue executing the current optimal path.

[0112] The preset conditions are used to determine whether the degree of change in different information exceeds a threshold. In some embodiments, the preset conditions can be divided into a first preset condition for determining the degree of change in the number of vehicles and vehicle speeds, and a second preset condition for determining the degree of change in vehicle information. For more information on the second preset condition, please see below.

[0113] In some embodiments, the processing device may determine whether the first preset condition is met based on situation A and situation B.

[0114] In some embodiments, situation A may be: current vehicle number ≤ historically predicted vehicle number + preset vehicle number. The preset vehicle number can be determined based on prior experience. Specifically, when the current vehicle number is not greater than the historically predicted vehicle number, the lane cost of the current optimal path decreases and no update is required. When the current vehicle number is greater than the historically predicted vehicle number but the increase is less than the preset vehicle number, the lane cost of the current optimal path increases only slightly and no update is required.

[0115] In some embodiments, situation B may be: current vehicle speed ≥ historically predicted vehicle speed - preset vehicle speed. The preset vehicle speed can be determined based on prior experience. Specifically, when the current vehicle speed is not less than the historically predicted vehicle speed, the lane cost of the current optimal path decreases and no update is required. When the current vehicle speed is less than the historically predicted vehicle speed, but the deceleration is less than the preset vehicle speed, the lane cost of the current optimal path increases only slightly and no update is required.

[0116] In some embodiments, when condition A and / or condition B are met, the processing device may determine that the first preset condition is met.

[0117] In some embodiments, the processing device may further determine whether the first preset condition is satisfied based on whether the current transport task instruction is urgent. For example, if the transport task instruction is urgent and nearing a deadline, the first preset condition may be deemed unsatisfied if at least one condition is unsatisfied. Conversely, if the transport task instruction is not urgent, the first preset condition may be deemed unsatisfied only if all conditions are unsatisfied.

[0118] In some embodiments, when the first preset condition is not met, the processing device may determine the optimal path from at least one updated candidate path based on the updated lane cost. More details on this can be found below.

[0119] In some embodiments of the present specification, since the actual conditions of the lanes usually change over time, determining whether the first preset condition is met and judging whether the current optimal path needs to be updated helps to update the optimal path in a timely manner when the optimal path of the vehicle changes.

[0120] In some embodiments, in response to satisfying a path update condition, the processing device may obtain first vehicle information at a current point in time and second vehicle information at a target point in time; determine whether the difference between the first vehicle information and the second vehicle information satisfies a second preset condition; and in response to satisfying the second preset condition, continue to execute the current optimal path; in response to not satisfying the second preset condition, redetermine the current optimal path.

[0121] The first vehicle information refers to the vehicle information at the current time, and the second vehicle information refers to the historical vehicle information at the target time. In some embodiments, the first vehicle information may include a first vehicle location and a first real-time vehicle power level. The second vehicle information may include a second vehicle location and a second real-time vehicle power level.

[0122] In some embodiments, the processing device may determine whether the first preset condition is met based on situation C and situation D.

[0123] In some embodiments, the processing device may calculate the actual distance traveled by the vehicle within the time range from the target time point to the current time point based on the first vehicle position and the second vehicle position. Condition C is considered satisfied when the difference between the actual distance traveled and the theoretical distance traveled within the time range is less than a distance difference threshold. The theoretical distance traveled may be determined based on the product of the historical vehicle speed at the target time point and the time period. The distance difference threshold may be positively correlated with the time period between the target time point and the current time point.

[0124] In some embodiments, the processing device may calculate the actual power consumption of the vehicle when traveling from the second vehicle location to the first vehicle location based on the first real-time vehicle power level and the second real-time vehicle power level. When the difference between the actual power consumption and the theoretical power consumption is less than a power consumption threshold, condition D is considered satisfied. The theoretical power consumption may be the product of the distance traveled from the second vehicle location to the first vehicle location and the power consumption per 100 kilometers. For more information on power consumption per 100 kilometers, please refer to the above.

[0125] In some embodiments, when condition C and / or condition D are met, the processing device may determine that the second preset condition is met.

[0126] In some embodiments, the processing device may also determine whether the second preset condition is satisfied based on whether the current transport task instruction is urgent. The steps for determining whether the second preset condition is satisfied are similar to those for determining whether the first preset condition is satisfied, as described above.

[0127] In some embodiments, when the second preset condition is not met, the processing device may determine the optimal path from at least one updated candidate path based on the updated lane cost. More details on this can be found below.

[0128] In some embodiments of this specification, a determination is made as to whether to continue executing the current optimal route based on a difference between first and second vehicle information. This allows for timely re-determination of the optimal route in the event of an anomaly during driving, such as a rapid or slow decrease in the vehicle's battery life or a deviation in the vehicle's actual driving distance from the theoretical driving distance, to ensure that the driver arrives at their destination promptly and accurately along the optimal route.

[0129] In some embodiments, in response to the first preset condition or the second preset condition not being met, the processing device can obtain updated road information and updated vehicle information of the target area at the current time point, the updated vehicle information includes the current vehicle position, and the updated road information includes actual road information; based on the transportation destination, the current vehicle position and the map information, determine at least one updated candidate path to complete the transportation task, and each updated candidate path in the at least one updated candidate path includes at least one updated lane.

[0130] The updated candidate route refers to a candidate route generated by the processing device based on the newly determined current vehicle position, transportation destination, and map information. For details on generating candidate routes, please refer to the above.

[0131] In some embodiments, the processing device may obtain updated lanes included in the updated candidate path, calculate the energy cost and time cost corresponding to each updated lane, and determine the updated lane cost based on the energy cost and time cost. The steps for determining the updated lane cost are similar to the steps for determining the lane cost, which can be seen above.

[0132] In some embodiments, the processing device determines an optimal path from at least one updated candidate path based on the updated lane cost. For example, the processing device may select the updated candidate path with the smallest total lane cost and determine it as the optimal path.

[0133] In some embodiments of this specification, when the first or second pre-set conditions are not met, the processing device can reacquire relevant data and re-determine the optimal path. This facilitates flexible adjustment of the driving path based on actual road and vehicle conditions while the vehicle is traveling, thereby improving the path planning method's adaptability and ability to resolve unexpected situations.

[0134] Figure 3 is an exemplary flowchart of a method for determining candidate paths according to some embodiments of this specification.

[0135] Step 310 , based on the transport destination, the real-time vehicle location and the map information, determine at least one alternative route for completing the transport task.

[0136] An alternative path is a feasible path from the vehicle's real-time location to the transport destination, without considering charging requirements or the availability of charging stations in the lane. An alternative path can be composed of at least one lane. In some embodiments, at least one alternative path is determined using an A* search algorithm.

[0137] Step 320 : For an alternative route, based on the real-time vehicle power level and the alternative route, determine the charging demand corresponding to the alternative route.

[0138] Charging demand refers to the requirement for charging when the vehicle travels from its real-time vehicle location to its transportation destination via an alternative route. In some embodiments, the charging demand may include the number of charging times. In some embodiments, the charging demand may include the amount of power upon arrival at the charging station being greater than the safety power level. The safety power level refers to a portion of power reserved in the vehicle battery to ensure that the vehicle does not suddenly shut down or malfunction due to depletion of power during operation. The processing device may use the average amount of power required by the vehicle to reach a nearby charging station in historical data as the safety power level.

[0139] In some embodiments, for each alternative route, the processing device can calculate the number of times the vehicle may need to be charged on the route based on the real-time vehicle power, maximum range, power consumption per 100 kilometers, safe power, and the total driving distance of the alternative route. More information about power consumption per 100 kilometers can be found in Figure 2For example, if the vehicle reaches the point where the real-time vehicle battery level equals the safety level but has not yet completed the alternative route, the number of charging times increases by 1. If the vehicle is fully charged from the point where the real-time vehicle battery level equals the safety level and then reaches the point where the real-time vehicle battery level equals the safety level but has not yet completed the alternative route, the number of charging times increases by 1 again, and so on. The processing device can determine the number of charging times.

[0140] It can be understood that the processing device will determine that the number of charging times is equal to 0 only when the real-time vehicle power of the vehicle is greater than the power required to travel the entire alternative route plus the safety power.

[0141] In some embodiments, in response to the number of charging times being greater than 0, the processing device may execute step 340 ; in response to the number of charging times being equal to 0, the processing device may execute step 330 .

[0142] Step 330 : In response to the number of charging times being equal to 0, the alternative path is determined as a candidate path.

[0143] When the processing device determines that the number of charging times is equal to 0, it means that the vehicle has completed the alternative route and does not need to be charged, and the alternative route can be directly determined as the candidate route.

[0144] Step 340: In response to the number of charging times being greater than 0, determine whether all lanes of the alternative path include a charging pile lane.

[0145] Charging lanes are lanes or parking spaces designated on roads or in parking lots for electric vehicle charging. These lanes are typically equipped with charging facilities (such as charging piles) for electric vehicles to charge while driving or while parked. The location and number of charging lanes depend on road planning and the distribution of charging facilities.

[0146] In some embodiments, the processing device can identify the location of the charging facility marked on the map based on map data containing charging facility information, and then determine whether all lanes of the alternative path include an electric charging station lane.

[0147] In some embodiments, in response to all lanes of the alternative path including an electric charging lane, the processing device may execute step 360 ; in response to all lanes of the alternative path not including an electric charging lane, the processing device may execute step 350 .

[0148] Step 350 : Based on the real-time vehicle power level and charging station distribution, the alternative route is updated, and the updated alternative route is determined as the candidate route.

[0149] In some embodiments, in response to the absence of a charging station lane, the vehicle needs to exit the alternative route, charge at a charging station outside the alternative route, and then return to the alternative route. The processing device may add the shortest charging path that meets the charging requirement to the alternative route, thereby determining the updated alternative route as the candidate route. The charging path is the path from the point where the vehicle exits the alternative route to the location of the charging station outside the alternative route, and then from the location of the charging station outside the alternative route to the point where the vehicle returns to the alternative route.

[0150] It is understandable that the updated alternative path meets the charging requirement. For more information on the charging requirement, please refer to the above.

[0151] Step 360: Determine whether the charging lane meets the charging requirements.

[0152] Charging demand refers to the amount of electricity or the number of times a vehicle needs to be charged during operation.

[0153] In some embodiments, the processing device can determine whether the number of charging piles is not less than the number of charging times, and whether the power level upon arrival at the charging pile is greater than the safe power level. The aforementioned charging piles refer to those separated from each other on the charging lane. If the distance between the charging piles is less than a distance threshold, they are considered to be one charging pile. The preset distance can be set manually.

[0154] In some embodiments, in response to the charging lane meeting the charging demand, the processing device may execute step 370 ; in response to the charging lane not meeting the charging demand, the processing device may execute step 380 .

[0155] Step 370: determine the alternative path as the candidate path corresponding to the alternative path.

[0156] Step 380: Update the alternative route based on the real-time vehicle power level and charging station distribution, and determine the updated alternative route as the candidate route.

[0157] In some embodiments, the process of updating the alternative path here is similar to the process of updating the alternative path in step 350, and will not be repeated here.

[0158] In some embodiments of this specification, candidate routes are determined based on the vehicle's real-time battery level and the availability of charging stations in the lane. This ensures that the vehicle can be charged promptly during transportation and avoids mission interruptions due to insufficient battery. Furthermore, the system can update candidate routes based on the distribution of charging stations, selecting more suitable charging stations and further optimizing route planning.

[0159] It should be noted that the above description of the process for determining candidate paths is for illustrative purposes only and does not limit the scope of application of this specification. Those skilled in the art may, under the guidance of this specification, make various modifications and changes to the process for determining candidate paths. However, such modifications and changes remain within the scope of this specification.

[0160] Figure 5 This is a flow chart of determining the predicted number of vehicles and the predicted vehicle speed based on a prediction model according to some embodiments of this specification.

[0161] In some embodiments, the prediction model 520 may be a deep learning neural network model. Exemplary deep learning neural network models may include convolutional neural networks (CNN), deep neural networks (DNN), recurrent neural networks (RNN), etc., or a combination thereof.

[0162] In some embodiments, as Figure 5 As shown, the input of the quantity prediction layer 521 can be time features 511, weather features 512, environmental features 513, lane length 514, lane slope 515, lane quality 516, number of lane curves 517 and future time point 518, and the output can be the predicted number of vehicles 530.

[0163] In some embodiments, as Figure 5 As shown, the input of the speed prediction layer 522 can be time features 511, weather features 512, environmental features 513, lane length 514, lane slope 515, lane quality 516, number of lane turns 517, future time points 518 and the output predicted vehicle number 530 of the quantity prediction layer 521, and the output can be the predicted vehicle speed 540.

[0164] The time feature 511 refers to a feature that can reflect time. For example, the time feature 511 can include a specific date (such as year, month, day), a time point (such as hour, minute), and a day of the week.

[0165] Different times correspond to different numbers and speeds of vehicles. For example, during peak hours in the morning and evening, there are more vehicles and slower speeds.

[0166] Weather characteristics 512 refer to characteristics that can reflect the weather. For example, weather characteristics 512 may include temperature, humidity, wind speed, wind direction, rainfall, snowfall, etc.

[0167] Weather characteristics 512 directly affect road conditions and driving behavior, thereby affecting the number of vehicles and vehicle speeds. For example, rainy days may cause slippery roads, thereby reducing vehicle speeds.

[0168] Environmental characteristics 513 are characteristics that reflect the surrounding environment. For example, environmental characteristics may include geographical features around the road (e.g., topography, urban / suburban / rural area), population density, and road type (e.g., highway, main road, branch road).

[0169] Environmental characteristics 513 can affect road capacity, traffic demand, and driving conditions. For example, roads in city centers typically have higher traffic density and more complex traffic flows, resulting in a higher number of vehicles and lower vehicle speeds. In contrast, roads in suburban or rural areas may be relatively empty and have lower traffic flows, resulting in a lower number of vehicles and higher vehicle speeds.

[0170] For more details about lane length 514, lane slope 515, lane quality 516, number of lane curves 517, and future time point 518, see Figure 2 and Figure 4 and its related descriptions.

[0171] In some embodiments, the output of the quantity prediction layer 521 may be used as the input of the speed prediction layer 522 , and the quantity prediction layer 521 and the speed prediction layer 522 may be jointly trained.

[0172] In some embodiments, the training samples for joint training may include several sets of training data, each set of training data including sample time characteristics, sample weather characteristics, sample environmental characteristics, lane length, sample lane slope, sample lane quality, number of turns in the sample lane, and a second historical point in time, with the label corresponding to the training sample being the actual vehicle speed at the second historical point in time. The first historical point in time is before the second historical point in time, and both the first and second historical points in time are historical points in time. The training samples and their labels may be obtained based on historical data.

[0173] During training, the processing device constructs a loss function based on the actual vehicle speed at the second historical point in the tag and the output of the speed prediction layer 522. Simultaneously, the parameters of the quantity prediction layer 521 and the speed prediction layer 522 are updated until pre-set conditions are met and training is complete. The pre-set conditions may include one or more of the following: the loss function being less than a threshold, convergence, or reaching a threshold during the training cycle.

[0174] The quantity prediction layer 521 and the speed prediction layer 522 can reduce the number of required samples and improve training efficiency by jointly training.

[0175] In some embodiments of the present specification, the predicted number of vehicles and the predicted vehicle speed can be predicted quickly and accurately through the prediction model.

[0176] An embodiment of the present invention provides a terminal comprising: a processor, a memory, and a communication unit. The processor is configured to implement the above-mentioned path planning method when executing a path planning program stored in the memory.

[0177] The present invention also provides a computer storage medium, wherein the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0178] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A path planning method, characterized in that: The following steps are involved: In response to obtaining a transport task instruction, obtaining road information and vehicle information of a target area; the transport task instruction includes a transport destination; the road information includes actual road information and future road information, wherein the future road information includes a predicted number of vehicles and a predicted vehicle speed at a future time point; the vehicle information includes real-time vehicle location, real-time vehicle power, and vehicle model information; the actual road information includes lane length, lane slope, lane quality, and number of lane curves; Determining, based on the transport destination, the real-time vehicle location, the real-time vehicle power level, and map information, at least one candidate route for completing the transport task while meeting the charging requirements, each candidate route in the at least one candidate route including at least one lane; Determine lane costs corresponding to all lanes in the target area based on road information and vehicle type information, including: determining future road information, including determining the predicted number of vehicles and predicted vehicle speed for all lanes in the target area at at least one future time point; for each future time point of each lane, determine a first electricity cost and a first time cost corresponding to the lane based on the predicted number of vehicles and the predicted vehicle speed at the future time point; determine a second electricity cost and a second time cost corresponding to the lane based on lane length, lane slope, lane quality, number of lane curves, and vehicle type information; determine an electricity cost and a time cost corresponding to the lane based on the first electricity cost, the first time cost, the second electricity cost, and the second time cost; An optimal path is determined from at least one candidate path based on the lane costs.

2. The path planning method according to claim 1, characterized in that: Based on the transport destination, real-time vehicle location, real-time vehicle power, and map information, determine at least one candidate route that can complete the transport task while meeting charging requirements, specifically including: Step 1: Determine at least one alternative route to complete the transportation task based on the transportation destination, real-time vehicle location, and map information; Step 2: For each alternative route, based on the real-time vehicle power level and the current alternative route, determine the charging requirement corresponding to the current alternative route, where the charging requirement includes the number of charging times. Step 3: If the number of charging times is equal to 0, the current alternative path is determined as the candidate path; Step 4: If the number of charging times is greater than 0, determine whether all lanes in the current alternative route include a charging lane. If so, proceed to step 5; otherwise, proceed to step 8. Step 5: Determine whether the charging lane meets the charging requirements; Step 6: If the charging requirement is met, the current alternative path is determined as a candidate path; Step 7: If the charging requirement is not met, based on the real-time vehicle power level and charging pile distribution, the lanes included in the current alternative path are updated to meet the charging requirement, and the updated alternative path is determined as the candidate path; Step 8: Based on the real-time vehicle power level and charging pile distribution, the lanes included in the current alternative path are updated to meet the charging requirements, and the updated alternative path is determined as the subsequent path.

3. The path planning method according to claim 1, wherein: Determine the predicted number of vehicles and predicted vehicle speeds for all lanes in the target area at at least one future time point, specifically including: Based on time characteristics, weather characteristics, environmental characteristics, lane length, lane slope, lane quality, number of lane curves and future time points, the number of vehicles predicted in the lane at a future time point is determined through the prediction model's quantity prediction layer; Based on the predicted number of vehicles, time characteristics, weather characteristics, environmental characteristics, lane length, lane slope, lane quality, number of lane curves and future time points, the predicted vehicle speed is determined through the speed prediction layer of the prediction model; the prediction model is a machine learning model, and the number prediction layer and speed prediction layer of the prediction model are obtained through joint training.

4. The path planning method according to claim 3, characterized in that: The method further includes: In response to satisfying the path update condition, obtaining the current number of vehicles and the current vehicle speed in the current lane corresponding to the current vehicle position at the current time point; Obtain the historically predicted number of vehicles and historically predicted vehicle speeds in the current lane at the current time point of the target time point prediction; the target time point is the time point when the optimal path was last determined; Determining whether a difference between the current number of vehicles and the current vehicle speed and the historically predicted number of vehicles and the historically predicted vehicle speed satisfies a first preset condition; If the first preset condition is met, continue to execute the current optimal path.

5. The path planning method according to claim 1, wherein: The method further includes: In response to satisfying the path update condition, obtaining first vehicle information at a current time point and second vehicle information at a target time point; the target time point is the time point at which the optimal path was last determined; determining whether a difference between the first vehicle information and the second vehicle information satisfies a second preset condition; If the second preset condition is met, continue to execute the current optimal path.

6. The path planning method according to claim 4 or 5, characterized in that: The method further includes: If the first preset condition or the second preset condition is not met, obtaining updated road information and updated vehicle information of the target area at the current time point; the updated vehicle information includes the current vehicle position and the current vehicle power; Determining at least one updated candidate path for completing the transport task based on the transport destination, the current vehicle location, the current vehicle power level, and map information, wherein each candidate path in the at least one updated candidate path includes at least one updated lane; Based on the updated road information and vehicle model information, the lane costs corresponding to all lanes in the target area are determined to obtain the updated lane costs; An optimal path is determined from at least one updated candidate path based on the updated lane cost.

7. A path planning system, characterized in that: include: an acquisition module configured to acquire road information and vehicle information of a target area in response to acquiring a transport task instruction; the transport task instruction includes a transport destination; the road information includes actual road information and future road information, wherein the future road information includes a predicted number of vehicles and a predicted vehicle speed at a future time point; the vehicle information includes real-time vehicle location, real-time vehicle charge, and vehicle model information; and the actual road information includes lane length, lane slope, lane quality, and number of lane curves; a first determining module configured to determine, based on a transport destination, a real-time vehicle location, a real-time vehicle power level, and map information, at least one candidate path for completing the transport task while meeting the charging requirement, each candidate path in the at least one candidate path including at least one lane; The second determination module is configured to determine lane costs corresponding to all lanes in the target area based on the road information and the vehicle information, including: determining future road information, including determining a predicted number of vehicles and a predicted vehicle speed for all lanes in the target area at at least one future time point; for each future time point of each lane, determining a first energy cost and a first time cost corresponding to the lane based on the predicted number of vehicles and the predicted vehicle speed at the future time point; determining a second energy cost and a second time cost corresponding to the lane based on lane length, lane slope, lane quality, number of lane curves, and vehicle type information; and determining an energy cost and a time cost corresponding to the lane based on the first energy cost, the first time cost, the second energy cost, and the second time cost; The third determination module is configured to determine an optimal path from at least one candidate path based on the lane cost.

8. A terminal, characterized in that: include: A memory for storing a path planning program; A processor, configured to implement the steps of the path planning method according to any one of claims 1 to 6 when executing the path planning program.

9. A computer-readable storage medium, characterized in that The readable storage medium stores a path planning program, and when the path planning program is executed by the processor, the steps of the path planning method according to any one of claims 1 to 6 are implemented.

Images