Electric vehicle automatic driving path planning method and system based on high-precision positioning

Abstract

The invention provides an electric vehicle automatic driving path planning method and system based on high-precision positioning, and the method comprises the steps: obtaining a first real-time position of an electric vehicle, and obtaining the current electric quantity, battery health state information and a set target position of the electric vehicle; matching with a high-precision map based on the first real-time position, determining first lane information, and determining road information of each road between the first real-time position and the destination position based on the high-precision map; determining the maximum driving mileage based on the current electric quantity and the battery health state information, and determining a target charging pile based on the first real-time position, the maximum driving mileage and the charging pile position information and the current use state information of each charging pile in the high-precision map; and performing path planning based on the first real-time position, the destination position, the first lane information, the road information and the target charging pile to obtain a first automatic driving path. According to the invention, the accuracy and safety of path planning in the automatic driving scene of the electric vehicle are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and system for automatic driving path planning for an electric vehicle based on high-precision positioning. Background Art

[0002] At present, common driving path planning methods are mainly based on electronic maps and navigation algorithms. By obtaining the starting and ending point location information, a path from the starting point to the end point is calculated using road network data and traditional path search algorithms (such as Dijkstra algorithm, A* algorithm, etc.).

[0003] However, traditional path planning methods fail to fully consider the unique needs and real-time status of electric vehicles. For example, electric vehicles have limited range. Failure to consider the distribution of charging stations along the route and the vehicle's real-time battery level during route planning can lead to the vehicle stalling due to depleted batteries. Furthermore, traditional path planning methods lack accurate perception of real-time road conditions when faced with complex road conditions (such as construction sites and traffic control areas), making it impossible to adjust the route in a timely manner. This reduces driving safety and makes it difficult to meet the stringent requirements for path planning accuracy and safety in autonomous electric vehicle scenarios. Summary of the Invention

[0004] The present invention provides a method and system for electric vehicle automatic driving path planning based on high-precision positioning, aiming to improve the accuracy and safety of path planning in electric vehicle automatic driving scenarios.

[0005] In a first aspect, the present invention provides a method for autonomous driving path planning for an electric vehicle based on high-precision positioning, comprising:

[0006] Obtaining a first real-time position of the electric vehicle based on a high-precision positioning device, as well as obtaining current power level, battery health status information, and a set destination position of the electric vehicle;

[0007] Based on the first real-time location, the first lane information of the electric vehicle is determined by matching the first real-time location with a pre-stored high-precision map, and based on the high-precision map, the road information of each road between the first real-time location and the destination location is determined;

[0008] determining a maximum driving range based on the current power level and the battery health status information, and determining a target charging pile based on the first real-time location, the maximum driving range, and the charging pile location information and current usage status information of each charging pile in the high-precision map;

[0009] Path planning is performed based on the first real-time location, the destination location, the first lane information, the road information, and the target charging pile to obtain a first autonomous driving path; the distance between each charging pile in the target charging pile is less than or equal to a first preset distance threshold.

[0010] In a second aspect, the present invention further provides an electric vehicle autonomous driving path planning system based on high-precision positioning, which is applied to the electric vehicle autonomous driving path planning method based on high-precision positioning as described in the first aspect; the electric vehicle autonomous driving path planning system based on high-precision positioning includes:

[0011] A data acquisition module is used to obtain a first real-time position of the electric vehicle based on a high-precision positioning device, as well as the current power level, battery health status information and a set destination position of the electric vehicle;

[0012] a data matching module, configured to match the first real-time location with a pre-stored high-precision map to determine information about a first lane in which the electric vehicle is currently located, and to determine road information about each road between the first real-time location and the destination location based on the high-precision map;

[0013] a charging pile positioning module, configured to determine a maximum driving range based on the current power level and battery health status information, and determine a target charging pile based on the first real-time location, the maximum driving range, and the charging pile location information and current usage status information of each charging pile in the high-precision map;

[0014] A path planning module is configured to perform path planning based on the first real-time location, the destination location, the first lane information, the road information, and the target charging pile to obtain a first autonomous driving path; the road information includes a road speed limit, the number of lanes, the lane direction, and the status of traffic lights; and the distance between each charging pile in the target charging pile is less than or equal to a first preset distance threshold.

[0015] In a third aspect, the present invention also provides an electronic device comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing any one of the above-mentioned methods for automatic driving path planning of an electric vehicle based on high-precision positioning.

[0016] In a fourth aspect, the present invention also provides a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, it implements any of the above-mentioned methods for automatic driving path planning of electric vehicles based on high-precision positioning.

[0017] In a fifth aspect, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for automatic driving path planning of electric vehicles based on high-precision positioning.

[0018] The electric vehicle automatic driving path planning method based on high-precision positioning provided by the embodiment of the present invention determines the current lane information of the electric vehicle and the road information of each road during driving through a high-precision map combined with the real-time position and the destination position, so that the real-time status of the road can be accurately perceived. On the other hand, within the maximum driving mileage determined according to the current power and battery health status information, the charging pile position information and the current usage status information of each charging pile in the high-precision map are combined to screen suitable target charging piles, which effectively solves the problem of electric vehicle range anxiety. Finally, the automatic driving path planned according to the real-time position, destination position, lane information, road information and target charging pile takes into account both the charging pile and the real-time status of the road, effectively avoiding the vehicle breaking down due to power problems. At the same time, it can also perceive the road conditions in real time under complex road conditions, thereby improving the accuracy and safety of path planning in the electric vehicle automatic driving scenario. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is one of the flow charts of the method for automatic driving path planning of an electric vehicle based on high-precision positioning provided by an embodiment of the present invention;

[0020] Figure 2 This is the second flow chart of the method for automatic driving path planning of an electric vehicle based on high-precision positioning provided by an embodiment of the present invention;

[0021] Figure 3 1 is a schematic diagram of the structure of an electric vehicle automatic driving path planning system based on high-precision positioning provided by an embodiment of the present invention;

[0022] Figure 4 An embodiment diagram of an electronic device provided by an embodiment of the present invention;

[0023] Figure 5 An embodiment diagram of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0025] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0026] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0027] Optional, see Figure 1 , Figure 1 This is one of the flow charts of the method for autonomous driving path planning of an electric vehicle based on high-precision positioning provided by the present invention. In the embodiment of the present invention, the execution subject of the method for autonomous driving path planning of an electric vehicle based on high-precision positioning is the vehicle control system. Therefore, the method for autonomous driving path planning of an electric vehicle based on high-precision positioning includes:

[0028] Step 10: obtaining the first real-time position of the electric vehicle based on a high-precision positioning device, as well as obtaining the current power level, battery health status information and the set destination position of the electric vehicle.

[0029] Optionally, the electric vehicle in the embodiment of the present invention can be an electric motorcycle. In a specific scenario, the electric motorcycle automatically drives from the current position to a relatively distant destination. The electric motorcycle is integrated with a vehicle control system, a high-precision positioning device, a battery management system, etc. The high-precision positioning device is a fusion device of a global satellite navigation system (such as GPS, Beidou, etc.) and an inertial navigation system (INS). Therefore, after the electric vehicle is started, the vehicle control system starts the high-precision positioning device to perform real-time positioning of the electric motorcycle and obtain the first real-time position. At the same time, the vehicle control system obtains the current power and battery health status information of the electric motorcycle by communicating with the battery management system (BMS). In addition, the user enters the set destination location in the operation interface of the vehicle control system, and the destination location is transmitted to the vehicle control system.

[0030] In one embodiment, in a certain city, an electric motorcycle is near the intersection of XX Avenue and XX Road. The vehicle control system activates the high-precision positioning device installed on the electric motorcycle, and by receiving Beidou satellite signals and its own inertial navigation data, accurately calculates the first real-time position of the electric motorcycle as (longitude: 118.789012, latitude: 32.001234). Then, the vehicle control system communicates with the battery management system and obtains that the current power is 60%, and the battery health status information shows that the battery capacity decay rate is 8%, which is normal. Subsequently, the user enters the destination as XX Science and Technology Park, which is about 80 kilometers away from the current location, on the touch screen of the vehicle control system.

[0031] Step 20, based on the first real-time position, matching is performed with a pre-stored high-precision map to determine the first lane information in which the electric vehicle is currently located, and based on the high-precision map, road information of each road between the first real-time position and the destination position is determined.

[0032] Furthermore, the vehicle control system matches the acquired first real-time location with a high-precision map pre-stored in the system, and determines the first lane information of the electric motorcycle by comparing the location coordinates with the geographic information on the map. At the same time, the vehicle control system calculates the road information of each road between the first real-time location and the destination location based on the high-precision map, such as querying the high-precision map database to obtain the speed limit regulations (such as 40km / h, 60km / h, etc.), the number of lanes (such as 2 lanes, 4 lanes, etc.), the lane direction (one-way, two-way, etc.), and the traffic light status (red light, green light, yellow light, or signal light failure, etc.) of each road.

[0033] Continuing with the above embodiment, the vehicle control system matches the first real-time position of the electric motorcycle (longitude: 118.789012, latitude: 32.001234) with the high-precision map, and determines that the electric motorcycle is currently in the rightmost lane of XX Avenue from south to north. Then, all possible roads from the current position to XX Science and Technology Park are searched in the high-precision map. Among them, XX Avenue has a speed limit of 60km / h, with four lanes in both directions; the speed limit of a section of the viaduct connecting XX Avenue and the road leading to XX Science and Technology Park is 80km / h, with six lanes in both directions; and the speed limit of some branches is 40km / h, with two lanes in both directions. At the same time, it is obtained that at an intersection on the must-pass road, the current traffic light status is green, and the remaining travel time is 30 seconds.

[0034] Step 30, determine the maximum mileage based on the current power level and battery health status information, and determine the target charging pile based on the first real-time location, the maximum mileage, and the charging pile location information and current usage status information of each charging pile in the high-precision map.

[0035] Furthermore, the vehicle control system calculates the maximum mileage based on the current power level and battery health status information obtained, combined with the electric motorcycle's energy consumption model, where the energy consumption model is established based on factors such as the vehicle's motor efficiency, vehicle weight, and driving speed. Furthermore, the vehicle control system searches the high-precision map for the location information and current usage status information (idle, in use, etc.) of each charging pile. Starting from the first real-time location, the vehicle control system selects charging piles within the driving range based on the maximum mileage, and determines a group of target charging piles based on the constraint that the distance between each charging pile in the target charging piles is less than or equal to a first preset distance threshold (e.g., 5 kilometers), as specifically described in steps 301 to 304.

[0036] In one embodiment, based on the current charge level of 60% and the battery health status, combined with the electric motorcycle's energy consumption model, the vehicle control system calculates a maximum range of 100 kilometers under the current road conditions and driving mode. A high-precision map search reveals 15 charging stations within 100 kilometers of the current location, five of which are idle and ten are in use. A group of three idle charging stations, each less than 5 kilometers apart, is located in a commercial plaza parking lot at 30, 33, and 35 kilometers from the current location, respectively. These three charging stations are then identified as target charging stations.

[0037] Step 40 , performing path planning based on the first real-time location, the destination location, the first lane information, the road information, and the target charging pile to obtain a first autonomous driving path.

[0038] Furthermore, the vehicle control system performs path planning based on the first real-time position, the destination position, the first lane information, the road information, and the target charging pile to obtain a first automatic driving path, as specifically described in the process from step 401 to step 404 .

[0039] The embodiment of the present invention determines the lane information of the electric vehicle and the road information of each road during driving through a high-precision map combined with the real-time position and the destination position, so that the real-time status of the road can be accurately perceived. On the other hand, within the maximum driving mileage determined according to the current power and battery health status information, the charging pile position information and the current usage status information of each charging pile in the high-precision map are combined to screen suitable target charging piles, which effectively solves the problem of electric vehicle range anxiety. Finally, the automatic driving path planned according to the real-time position, destination position, lane information, road information and target charging pile takes into account both the charging pile and the real-time status of the road, effectively avoiding the vehicle from breaking down due to power problems. At the same time, it can also perceive the road conditions in real time under complex road conditions, thereby improving the accuracy and safety of path planning in the electric vehicle automatic driving scenario.

[0040] In one embodiment, the process from step 301 to step 304 includes:

[0041] Step 301 : Based on the first real-time location and the charging pile location information of each charging pile, all charging piles that the electric vehicle can reach within the maximum driving range are screened to obtain reachable charging piles.

[0042] Optionally, the vehicle control system measures the distance between the first real-time position and each charging pile position based on a geospatial distance calculation method, and screens out accessible charging piles whose distance is less than or equal to the maximum mileage by comparing the calculated distance with the maximum mileage of the electric motorcycle.

[0043] Continuing with the above embodiment, in an example where the electric motorcycle is at the intersection of XX Avenue and XX Road (longitude: 118.789012, latitude: 32.001234) and has a maximum mileage of 100 kilometers, the vehicle control system traverses all charging pile location information in the high-precision map. Optionally, in this embodiment of the present invention, the Haversine formula is used to calculate the spherical distance d between the first real-time position and the location of each charging pile:

[0044]

[0045] Among them, r is the average radius of the earth (taken as 6371 kilometers), is the latitude and longitude of the first real-time location of the electric motorcycle, is the latitude and longitude of the charging station location. After calculation, there are 15 charging stations within 100 kilometers of the current location, and these 15 charging stations are determined to be reachable.

[0046] Step 302 : For each of the reachable charging piles, a usage status history sequence within a preset time window is constructed based on its current usage status information, and an idle probability sequence of each charging pile is determined based on the occurrence frequency of the idle state in the usage status history sequence.

[0047] Furthermore, for each accessible charging station, the vehicle control system obtains its usage status information within a preset time window (e.g., the past 24 hours) and constructs a usage status history sequence. The usage status history sequence consists of a series of timestamps and the usage status at the corresponding time (0 indicates idle, 1 indicates occupied). Furthermore, the vehicle control system uses a sliding window algorithm to slide a fixed-length window over the usage status history sequence, calculates the frequency of idle states within each window, and obtains an idle probability sequence for each charging station.

[0048] Taking one of the accessible charging piles A as an example, the vehicle control system obtains its usage status history sequence for the past 24 hours: [(t1,0),(t2,1),(t3,0),...,(t n ,1)]. Set the sliding window length to 1 hour (including 60 time point data) and start sliding from the beginning of the sequence. In the first window, the idle state occurs 30 times and the total data points are 60 times, so the idle probability corresponding to this window is P1=0.5; continue sliding the window and calculate the idle probability of the second window P2=0.4. And so on, we get the idle probability sequence of charging pile A [P1,P2,...,P m ], where m is the total number of sliding windows.

[0049] Step 303 : Based on the current usage status of each charging pile and the driving trajectory of the vehicle within a preset range, the charging time is estimated to obtain the waiting time when the electric vehicle arrives at each charging pile.

[0050] Furthermore, the vehicle control system estimates the charging time based on the current usage status of each charging pile and the driving trajectory data of other vehicles within its preset range to obtain the waiting time when the electric vehicle arrives at each charging pile, as shown in the process from step 3031 to step 3033.

[0051] Step 304 : Determine a target charging pile based on the idle probability sequence and waiting time of each charging pile among the reachable charging piles.

[0052] Furthermore, the vehicle control system determines the target charging pile according to the idle probability sequence and waiting time of each charging pile among the reachable charging piles, as shown in the process from step 3041 to step 3044.

[0053] The embodiment of the present invention can accurately determine the optimal target charging pile based on the real-time position and maximum mileage of the electric motorcycle, taking into account the accessibility, idle probability and waiting time of the charging pile. This fully considers the dynamic changes in the usage status of the charging pile and the vehicle charging waiting situation, improves the accuracy and efficiency of the electric motorcycle in finding a suitable charging pile during long-distance automatic driving, reduces the risk of running out of power due to not being able to find a charging pile, and ensures that the electric motorcycle can successfully complete the long-distance journey.

[0054] In one embodiment, the process from step 3031 to step 3033 includes:

[0055] Step 3031: If the current usage state is the idle state, determine that the waiting time is 0.

[0056] Optionally, if the current usage status is displayed as idle, it means that no vehicle is charging at the charging pile. At this time, the vehicle control system directly determines the waiting time corresponding to the charging pile as 0 minutes, which means that the electric motorcycle can start charging immediately after arriving at this charging pile. Continuing with the above embodiment, in the scenario where the electric motorcycle is at the intersection of XX Avenue and XX Road and is looking for the target charging pile, the vehicle control system obtains that the current usage status of one of the reachable charging piles C is idle. Based on this, the vehicle control system does not need to perform additional calculations and directly determines that the waiting time when the electric motorcycle arrives at charging pile C is 0 minutes.

[0057] Step 3032: If the current usage state is occupied, determine the total number of vehicles currently charging at each charging pile and the number of vehicles expected to arrive first, as well as the remaining charging time of the vehicles currently charging.

[0058] Furthermore, when a charging station is currently occupied, the vehicle control system obtains the number of vehicles currently charging at the station. Simultaneously, using high-precision maps and vehicle trajectory data, it analyzes the number of vehicles expected to arrive at the station before the electric motorcycle arrives at the station. These two vehicle counts are added together to arrive at the total number of vehicles. Furthermore, the vehicle control system uses communication between the charging station and the currently charging vehicle to obtain the remaining charging time for the vehicle currently charging.

[0059] Continuing with the above example, for accessible charging station D, the vehicle control system determines its current usage status as occupied. Upon query, it is determined that one vehicle is currently charging at charging station D. Simultaneously, analysis of driving trajectory data reveals that two more vehicles will arrive at the charging station before the electric motorcycle is expected to reach charging station D. Therefore, the total number of vehicles at this charging station is 1 + 2 = 3. Through communication between the charging station and the charging vehicle, the vehicle control system determines that the charging vehicle has 25 minutes of remaining charging time.

[0060] Step 3033 , based on the total number of vehicles at each charging pile, the remaining charging time, and the average charging operation time of each vehicle, the charging time is estimated to determine the waiting time when arriving at each charging pile.

[0061] Furthermore, the vehicle control system uses a queuing model to estimate the charging time based on the total number of vehicles at each charging pile, the remaining charging time of the charging vehicles, and the average charging operation time of each vehicle (which can be obtained through statistical analysis of historical charging data). The G / G / 1 queuing model based on a random process (general arrival time interval, general service time, single service station) is adopted to consider the randomness of vehicle arrival time and the uncertainty of charging time. The waiting time of the electric motorcycle when it arrives at each charging pile is calculated. The specific calculation formula is as follows: Among them, W qis the average waiting time, ρ = λ / μ is the system utilization rate, λ is the average vehicle arrival rate (obtained through the historical arrival data of vehicles within the preset range), and μ is the average service rate (μ = 1 / T avg , T avg is the average charging operation time for each vehicle), is the variance of vehicle arrival time intervals, is the variance of charging service time.

[0062] Continuing with the example of charging station D, the vehicle control system obtains from historical data statistics that the average vehicle arrival rate in the area is λ = 0.2 vehicles / minute, and the average charging operation time per vehicle is T avg = 30 minutes, then the average service rate μ = 1 / 30 vehicle / minute, and the system utilization rate ρ = = 6. At the same time, the variance of the vehicle arrival time interval is calculated through historical data Variance of charging service time Substituting the parameters into the G / G / 1 queue model formula, the average waiting time is: W q =(6 2 +4+9) / (4*6*1 / 30)=61.25 minutes.

[0063] The embodiment of the present invention can accurately estimate the waiting time of an electric motorcycle when it arrives at each charging pile for charging piles in different usage states, fully considering the uncertainty of vehicle arrival time and the fluctuation of charging service time, and providing accurate waiting time parameters for selecting target charging piles in subsequent path planning. During long-distance automatic driving, the electric motorcycle can reasonably plan the route to the charging pile based on more accurate charging waiting time information, reduce unnecessary waiting, improve charging efficiency and the reliability of trip planning, and ensure that the electric motorcycle can successfully complete long-distance driving.

[0064] In one embodiment, the process from step 3041 to step 30443 includes:

[0065] Step 3041: For each of the reachable charging piles, determine the distance loss value of each charging pile based on the distance between the first real-time position and the charging pile position information of each charging pile, and determine the comprehensive evaluation index of each charging pile based on the distance loss value, idle probability sequence and waiting time of each charging pile.

[0066] Optionally, for each of the accessible charging piles, the vehicle control system uses a geospatial distance algorithm to calculate the distance d between the first real-time position and the position information of the charging pile. i , and construct the distance loss value L based on the distance d (d i), where the distance loss value is used to evaluate the value of the charging pile according to the distance. The longer the distance, the greater the loss. The specific formula is L d (d i )=1 / exp(d i -10).

[0067] Furthermore, the vehicle control system is based on the idle probability sequence P of the charging pile. ij (where i represents the charging pile number and j represents different time points in the time series) and the average idle probability is calculated. Furthermore, the vehicle control system is based on the distance loss value, the average idle probability and the waiting time T i , determine the comprehensive evaluation index E of each charging pile i , the specific formula is:

[0068] Continuing with the above example, the electric motorcycle is at the intersection of XX Avenue and XX Road (longitude: 118.789012, latitude: 32.001234). In step 301, 15 accessible charging piles are obtained. Taking charging pile numbered 1 as an example, the vehicle control system uses the Haversine formula to calculate the distance d1 = 20 kilometers between it and the current location of the electric motorcycle. Therefore, the distance loss value L d (d1)≈0.000045. The idle probability sequence of the charging pile is [0.6, 0.7, 0.8], so the average idle probability is Waiting time T1 = 15 minutes, so the comprehensive evaluation index of the charging pile numbered 1 is E1≈1.97*10 -6 The above calculations were performed on 15 accessible charging piles in turn to obtain their respective comprehensive evaluation indicators.

[0069] In step 3042, the charging piles whose comprehensive evaluation index among the reachable charging piles is greater than or equal to the preset index threshold are determined as candidate charging piles, and the device health index of each charging pile is determined based on the number of failures and cumulative downtime of each charging pile among the candidate charging piles.

[0070] Furthermore, the vehicle control system will comprehensively evaluate the index E i and the preset indicator threshold E th For comparison, E i ≥E th The charging piles are determined as candidate charging piles. For each candidate charging pile, the vehicle control system obtains its historical fault count F i and the cumulative downtime H i , calculate the equipment health index S by establishing an equipment health assessment model i , to measure the reliability of charging pile equipment, the specific formula is:

[0071] S i =1 / [1+αF i +βH i ], α and β are preset coefficients.

[0072] In one embodiment, the preset indicator threshold E th =1*10 -6 , α=0.1,β=0.05, among the 15 accessible charging piles, the comprehensive evaluation index of 5 charging piles is greater than or equal to the threshold, and these 5 charging piles are determined as candidate charging piles. Taking one of the candidate charging piles (numbered 3) as an example, its historical fault count F2=2 times, cumulative downtime H3=10 hours, therefore, the equipment health index S of candidate charging pile numbered 3 is i ≈0.59, and the equipment health index is calculated for each of the five candidate charging piles.

[0073] In step 3043, a charging pile among the candidate charging piles whose device health index is greater than or equal to a preset health threshold and whose distance from the first real-time location is less than or equal to a preset value is determined as a target charging pile.

[0074] Furthermore, the vehicle control system sets a preset health threshold S th and the preset distance threshold D th , the equipment health index S in the candidate charging pile i ≥S th And the distance d from the first real-time position i ≥D th The charging pile of is determined as the target charging pile. In one embodiment, a preset health threshold S is set. th =0.5, preset distance threshold D th = 30 km. Among the five candidate charging piles, the device health index of three charging piles is greater than or equal to 0.5, and the distance between these three charging piles and the current location of the electric motorcycle is less than 30 kilometers. Therefore, the vehicle control system determines these three charging piles as target charging piles.

[0075] The embodiment of the present invention can comprehensively consider multi-dimensional factors such as distance, idle probability, waiting time, and equipment health from the available charging piles to screen out the most suitable target charging pile. Therefore, it comprehensively considers the use value and reliability of the charging piles, and avoids selecting charging piles that are too far away, have too long waiting times, or have unstable equipment. This allows electric motorcycles to accurately plan routes to highly reliable charging piles during long-distance autonomous driving, reducing the risk of trip interruption and ensuring the safety of long-distance driving of electric motorcycles.

[0076] In one embodiment, the process from step 401 to step 404 includes:

[0077] In step 401, a directed graph is constructed using the target charging pile and the road intersections of each road between the first real-time location and the destination location as nodes, the road segments between adjacent intersections and the location distances between the intersections and the target charging pile as edges, and the road speed limits, number of lanes, lane directions, and traffic light states between adjacent intersections and between each intersection and the target charging pile as edge attributes.

[0078] Optionally, the vehicle control system uses the target charging station and each road intersection between the first real-time location and the destination location as nodes, assigning each node a unique identifier. The vehicle control system calculates the road segment distances between adjacent intersections and the location distances between intersections and the target charging station as edges, and assigns rich attributes to the edges, including road speed limits, number of lanes, lane directions, and traffic light status between adjacent intersections and between each intersection and the target charging station, to obtain a directed graph.

[0079] Continuing with the above embodiment, in the scenario where the electric motorcycle is located at the intersection of XX Avenue and XX Road, the destination is XX Science and Technology Park, and 3 target charging piles have been determined, it is identified that there are 8 road intersections between the current location and the destination, plus 3 target charging piles, a total of 12 nodes. The distance between each node is calculated, for example, the distance from node 1 (current location) to node 2 (adjacent intersection) is 1 kilometer, the distance from node 2 to node 3 is 1.5 kilometers, and so on. At the same time, attributes are assigned to the edges, such as the road section from node 1 to node 2 has a speed limit of 60km / h, 4 lanes in both directions, the lane direction is bidirectional, and the current traffic light status is green with 40 seconds remaining; the road section from node 2 to one of the target charging piles has a speed limit of 40km / h, 2 lanes in both directions, the lane direction is one-way, and there is no traffic light, thus constructing a directed graph containing node and edge attributes.

[0080] Step 402 : Filter out valid road segments based on the directed graph according to the road speed limit of each road segment and the safe maximum driving speed of the electric vehicle.

[0081] Furthermore, the vehicle control system obtains the road speed limit v of each road segment based on the constructed directed graph. limit , combined with the electric vehicle's own maximum safe driving speed v max Perform screening. Set the screening conditions. If the speed limit of the road segment is v limit Greater than the safe maximum speed v of the electric vehicle max If there are no special regulations on the road section that allow electric vehicles to travel at their maximum safe speed (such as dedicated lanes for electric vehicles during specific time periods), then this road section will be considered an invalid road section; otherwise, it will be retained as a valid road section.

[0082] In one embodiment, the safe maximum speed of the electric motorcycle is v max=80km / h. In a directed graph, if a road section has a speed limit of 100km / h and no special regulations, the vehicle control system will determine that road section as invalid. On the other hand, if a road section has a speed limit of 70km / h, it will be retained as a valid road section. By performing the above judgment on all road sections in the directed graph, valid road sections that meet the conditions are selected, and road sections where electric vehicles cannot travel at safe speeds are excluded.

[0083] In step 403, based on the directed graph, the first lane information is combined with the lane direction and lane compatibility of each lane in each valid road segment to select a passable lane in the valid road segment that is traversable from the first real-time location. Lane compatibility indicates that the lane type and lane authority of the lane are consistent with the model of the electric vehicle.

[0084] Furthermore, the vehicle control system screens lanes based on the first lane information, combined with the lane direction and lane compatibility of each lane in each valid road segment. Lane compatibility is determined by determining whether the lane type (e.g., motor vehicle lane, non-motor vehicle lane, etc.) and lane authority (e.g., whether electric vehicles are allowed to pass) are consistent with the type of electric vehicle. Only lanes whose lane direction matches the direction of travel of the electric vehicle and are lane compatible are selected as passable lanes from the first real-time location.

[0085] Continuing with the above example, let's assume the electric motorcycle is currently in the rightmost lane (first lane information) of XX Avenue traveling from south to north. Within a certain valid road segment, there are three lanes: the left lane is a dedicated left-turn lane, the middle lane is a mixed lane for straight and left-turn traffic, and the right lane is a straight-through lane that allows electric vehicles. Based on the electric motorcycle's need to travel straight to its destination, the vehicle control system, taking into account lane direction and lane compatibility, selects the right lane of this road segment as a passable lane. Similar screening is performed on all valid road segments to determine the complete set of passable lanes.

[0086] In step 404 , based on the directed graph and the distance between each road segment in the valid road segment and the target charging pile, a target road segment is selected, and path planning is performed based on the directed graph, the passable lanes, and the target road segment to obtain a first autonomous driving path.

[0087] Furthermore, the vehicle control system calculates the position distance between each road segment in the valid road segment and the target charging pile based on the directed graph, and selects the road segment with a distance less than or equal to a threshold as the target road segment.

[0088] Furthermore, the vehicle control system performs path planning based on the directed graph, the drivable lanes, and the target road segment to obtain a first autonomous driving path, as specifically described in the process from step 4041 to step 4044 .

[0089] The embodiment of the present invention converts the actual road network into a structured directed graph, and fully considers the road speed limit, lane direction, lane compatibility and the location of the target charging pile for path planning, ensuring that the planned autonomous driving path not only has a reasonable distance, but also ensures that the electric motorcycle is always in a passable lane during driving and can smoothly reach the target charging pile for charging, thereby improving the safety of autonomous driving and ensuring that the electric motorcycle can complete long-distance journeys.

[0090] In one embodiment, the process from step 4041 to step 4044 includes:

[0091] In step 4041, an initial path is generated based on the connectivity of adjacent lanes in the drivable lanes and the connectivity of adjacent road segments in the target road segment, starting from the first real-time location and ending at the target location. Each path includes multiple consecutive lanes and road segments.

[0092] Optionally, the vehicle control system uses a graph search algorithm (such as a modified version of depth-first search (DFS) or breadth-first search (BFS)) to search for a path based on the connectivity of adjacent lanes in the drivable lanes and the connectivity of adjacent road segments in the target road segment, starting from the first real-time position and ending at the target position. During the search, the connectivity rules of lanes and road segments are strictly followed to ensure that each generated path consists of multiple continuous lanes and road segments, thereby obtaining an initial path set.

[0093] Continuing with the scenario where the electric motorcycle is located at the intersection of XX Avenue and XX Road, with the destination being XX Science and Technology Park, and the accessible lanes and target road segments have been identified, a breadth-first search algorithm is used, starting the search from the current location node. During the search, a specific lane is found that connects from the current accessible lane to the next road segment, and the search range is gradually expanded along the connected lanes and road segments. After the search, three initial paths are generated: Path 1 passes through lane A, road segment a, lane B, and road segment b, etc.; Path 2 passes through lane C, road segment c, lane D, and road segment d, etc.; and Path 3 passes through lane E, road segment e, lane F, and road segment f, etc. All of these paths meet the requirement of consisting of continuous lanes and road segments.

[0094] Step 4042: For each road segment of each path in the initial path, the ideal travel time for each road segment without the influence of traffic lights is determined based on the directed graph combined with the road speed limit and road length of each lane. The actual travel time for each road segment is determined based on the ideal travel time combined with the traffic light cycle, red light duration, and current remaining red light time of each lane.

[0095] Furthermore, for each road segment in the initial path, the vehicle control system obtains the road speed limit v corresponding to each lane based on the directed graph.i and road length l i , through the formula l i / v i Calculate the ideal travel time t without the influence of traffic lights ideal-i Next, combine the signal light cycle T of each lane cycle-i , Red light duration T red-i and the remaining time t of the current red light remain-i , calculate the actual travel time t actual-i If the current light is green and the remaining time is enough to pass the road section, that is, T remain-i ≥t ideal-i , then t actual-i =t ideal-i ; If the light is green but the remaining time is insufficient, T remain-i <t ideal-i , then t actual-i =t ideal-i -T remain-i +T cycle-i ; If the current light is red, then t actual-i =T red-i -T remain-i +t ideal-i .

[0096] Continuing with the example of road segment a in the initial path 1, the corresponding lane speed limit is v a =60km / h, road length l a = 2 km, calculate the ideal travel time t by the formula ideal-a = 2 minutes. The lane signal light cycle T cycle-a = 120 seconds, red light duration T red-a = 40 seconds, the remaining time of the current red light is T remain-a = 10 seconds. Since the traffic light is red, the actual travel time is t actual-a = 40 - 10 + 120 = 150 seconds. The above calculation is performed on all road segments in the initial path in sequence to obtain the actual travel time of each road segment.

[0097] Step 4043 : Based on the location distance between each road segment and the target charging pile, the charging time of each road segment is predicted, and the total road length of each road segment is determined based on the road length of each lane.

[0098] Furthermore, the vehicle control system calculates the distance d between each road segment and the target charging pile. i , combined with the charging power P and current power Q of the electric motorcycle current And the battery capacity Q total , through the formula (where n is the number of all road segments) Predict the charging time t for each road segment during charging charge-i At the same time, directly obtain the road length corresponding to each lane, add up the lengths of all lanes contained in each road segment, and determine the total road length L total-i .

[0099] In one embodiment, for road segment b in route 1, the distance d between it and the target charging pile is b = 3 km, the charging power of the electric motorcycle P = 6kW, the current power Q current =60%, battery capacity Q total =80Ah, assuming there are 5 road segments in total, the sum of their distances to the target charging pile kilometers, so the charging time of road section b is calculated as Seconds. The road segment b consists of two lanes with lengths of 1.2 km and 0.8 km respectively, so the total road length L total-b = 1.2 + 0.8 = 2 kilometers. Perform the above calculation for all road sections to obtain the charging time and total road length.

[0100] Step 4044: Determine a first candidate path based on the total road length, charging consumption time, and actual travel time of each road segment, and determine a first autonomous driving path based on the number of remaining lanes in each path in the first candidate path and the number of charging piles including the target charging pile.

[0101] Furthermore, the theoretical driving time of each road section is calculated based on the total length of each road section and the average driving speed of the electric motorcycle on the road section, and the theoretical driving time, charging consumption time and actual travel time of each road section are added together to obtain the total time consumed for each path.

[0102] Furthermore, the vehicle control system determines a path whose total time is less than or equal to a preset time threshold as a first candidate path, and determines a first automatic driving path based on the number of remaining lanes in each path in the first candidate path and the number of charging piles including the target charging pile, as shown in steps 40441 to 40444.

[0103] The embodiments of the present invention can fully consider factors such as lane connectivity, traffic lights, and charging requirements under complex road network conditions, and screen out the optimal first autonomous driving path from multiple possible paths. It not only accurately calculates travel time and charging time under different conditions, but also comprehensively weighs multiple key indicators of the path through multi-objective optimization to ensure that the planned autonomous driving path can enable the electric motorcycle to reach the destination quickly and efficiently, while also guaranteeing sufficient charging and good lane conditions during driving, thereby improving the practicality of autonomous driving path planning for electric motorcycles.

[0104] In one embodiment, the process from step 40441 to step 40444 includes:

[0105] Step 40441: Determine the path in the first candidate path where the number of remaining lanes is greater than the first preset number and the number of charging piles is greater than the second preset number as the second candidate path.

[0106] Optionally, the vehicle control system evaluates each path in the first candidate path and checks the number of remaining lanes N. lanes and the number of charging piles N including the target charging pile charger . Set the first preset number N lanes-th and a second preset number N charger-th , will satisfy N lanes >N lanes-th And N charger >N charger The path is determined as the second candidate path, ensuring that the retained second candidate path has sufficient lane selection space and charging facilities. Continuing with the above embodiment, the first candidate path has 3 paths. Set the first preset number N lanes-th =1, the second preset number N charger-th = 1. The number of remaining lanes N on path 1 lanes-1 =2, number of charging piles N charger-1 =2; the number of remaining lanes N on path 2 lanes-2 =1, number of charging piles N charger-2 =1; the number of remaining lanes N on path 3 lanes-3 =3, number of charging piles N charger-3 = 2. By comparison, path 1 and path 3 meet the conditions and are determined as the second candidate path.

[0107] In step 40442, the second candidate paths are screened with the goal of minimizing the sum of the rates of change of the steering angles of adjacent road segments in each path, to obtain a third candidate path.

[0108] Furthermore, for each path in the second candidate path, the vehicle control system calculates the sum of the steering angle change rates of adjacent road segments S θ, where the steering angle change rate is the steering angle difference Δθ between adjacent road segments i and road segment length l i ratio.

[0109] Furthermore, the vehicle control system is designed to minimize As the target, filter out S θ The smallest path is selected as the third candidate path to ensure that the path with smooth steering and high driving comfort is selected.

[0110] Continuing with the above example, in the second candidate path, path 1 contains 5 road segments. The steering angle differences between adjacent road segments are 15°, 10°, 5°, and 8°, respectively. The corresponding road segment lengths are 2 km, 1.5 km, 1 km, and 2.5 km, respectively. The sum of the steering angle change rates of path 1 is calculated to be S θ-1 =7.5+6.67+5+3.2=22.37. Path 3 consists of 4 road segments, with the steering angle differences between adjacent road segments being 8°, 6°, and 4°, respectively. The corresponding road segment lengths are 3km, 2km, and 1.5km, respectively. The sum of the steering angle change rates for Path 3 is calculated to be S. θ-3 =2.67+3+2.67=8.34. θ-3 θ-1 , path 3 is determined as the third candidate path.

[0111] In step 40443, the third candidate path is screened with the goal of minimizing the sum of the lane curvatures of adjacent lanes in each road segment in each path to obtain a fourth candidate path.

[0112] Furthermore, for each of the third candidate paths, the vehicle control system calculates the sum of lane curvatures S of adjacent lanes of each road segment. curvature , where the lane curvature is the inverse of the radius of curvature of the lane centerline, i.e. 1 / R i , where R i is the curvature radius of the i-th lane. Further, the vehicle control system minimizes As the target, filter out S curvature The smallest path is selected as the fourth candidate path to ensure that the lane curvature of the selected path is small and driving is safer.

[0113] Continuing with the above example, path 3 contains 4 road segments, and the curvature radius of the adjacent lanes of each road segment is R1 = 500m, R2 = 1000m, R3 = 800m, and R4 = 1200m. Calculate the sum of the lane curvatures S curvature-3 =0.002+0.001+0.00125+0.00083≈0.00508. After comparing with other possible third candidate paths, the S of path 3 is curvature ​is the smallest and is therefore determined as the fourth candidate path.

[0114] In step 40444, the fourth candidate path is screened with the goal of minimizing the sum of the number of adjacent lane changes in each road segment in each path to obtain the first autonomous driving path.

[0115] Furthermore, the vehicle control system calculates the sum N of the number of lane changes of adjacent lanes in each road segment for each of the fourth candidate paths. lane-changes To minimize N lane-changes The goal is to select the path with the least number of lane changes as the first autonomous driving path, in order to reduce unnecessary lane changes and improve driving efficiency and safety.

[0116] Continuing with the above example, the sum of the number of adjacent lane changes in path 3 during the entire journey is N lane-changes-3 =2 times. After comparing with other possible fourth candidate paths, the N of path 3 lane-changes is the minimum, so the vehicle control system determines path 3 as the first autonomous driving path.

[0117] The embodiment of the present invention screens candidate paths from multiple dimensions and ultimately determines the first autonomous driving path with the best overall performance. This not only ensures that the path has sufficient lane selection space and charging facilities, but also improves driving comfort, safety, and efficiency by minimizing the steering angle change rate, lane curvature, and the number of lane changes. This allows for greater emphasis on the detailed features of the path and the actual driving experience, providing practical autonomous driving path planning for electric motorcycles and ensuring smooth long-distance travel for electric motorcycles.

[0118] Optional, see Figure 2 , Figure 2 This is the second flow chart of the method for automatic driving path planning of an electric vehicle based on high-precision positioning provided by the present invention. After step 40, the following steps are also included:

[0119] Step 50 : During the driving of the electric vehicle, based on the second real-time position of the electric vehicle acquired in real time by the high-precision positioning device, determine the second lane information of the electric vehicle in the high-precision map.

[0120] Optionally, while the electric motorcycle is traveling along the first autonomous driving path, the vehicle control system continuously activates a high-precision positioning device, which combines a satellite navigation system with inertial navigation technology to obtain a second real-time position of the electric motorcycle in real time. The vehicle control system then matches the second real-time position with a high-precision map and, by comparing the position coordinates with lane data in the map, determines the second lane information of the electric motorcycle in the high-precision map, including the lane number and lane direction.

[0121] Continuing with the above example, the electric motorcycle travels along the planned first autonomous driving path on XX Avenue. The initial first lane information is the rightmost lane of XX Avenue running from south to north. The vehicle control system uses a high-precision positioning device to obtain the electric motorcycle's second real-time position (longitude: 118.791234, latitude: 32.003456) in real time. After matching this position with the high-precision map, it is determined that the electric motorcycle is currently in the middle lane of XX Avenue running from south to north, thus obtaining the second lane information.

[0122] Step 60: Determine the lateral position deviation, heading angle deviation, and deviation change rate of the electric vehicle during driving based on the second lane information and the first automatic driving path.

[0123] Furthermore, the vehicle control system calculates the lateral position deviation D of the electric motorcycle during driving based on the acquired second lane information and the pre-planned first automatic driving path. lateral , heading angle deviation D heading and the rate of change of deviation R deviation The lateral position deviation is calculated by calculating the vertical distance between the current position of the electric motorcycle and the centerline of the first autonomous driving path. The heading angle deviation is the difference between the current heading angle of the electric motorcycle and the ideal heading angle at the corresponding position of the first autonomous driving path. The deviation change rate is calculated by differentiating the lateral position deviation and heading angle deviation within a certain time interval.

[0124] The calculation formula of the lateral position deviation is as follows:

[0125] Among them, (x0, y0) is the second real-time position coordinate, (x path ,y path ) are the coordinates of the position corresponding to the first autonomous driving path.

[0126] The calculation formula of heading angle deviation is as follows:

[0127] D heading =θ-θ path , where θ is the current heading angle of the electric motorcycle, θ path is the ideal heading angle of the position corresponding to the first automatic driving path.

[0128] The calculation formula for the deviation change rate is as follows:

[0129] R deviation =ΔD lateral / Δt (lateral position deviation change rate, Δt is the time interval), R deviation-heading =ΔD heading / Δt (rate of change of heading angle deviation).

[0130] Step 70: Determine a lane departure risk level based on the lateral position deviation and the heading angle deviation and their corresponding deviation thresholds. The lane departure risk level includes a first risk level and a second risk level, with the second risk level being higher than the first risk level.

[0131] Furthermore, the vehicle control system sets a lateral position deviation threshold D lateral-th And the heading angle deviation threshold D heading-th , the calculated lateral position deviation D lateral and heading angle deviation D heading Compare with the corresponding threshold. If D lateral <D lateral-th and D heading <D heading-th , then the lane departure risk level is the first risk level; if D lateral ≥D lateral-th or / and D heading ≥D heading-th , the lane departure risk level is the second risk level, which is higher than the first risk level.

[0132] In one embodiment, the lateral position deviation threshold D is set lateral-th = 0.002 km, heading angle deviation threshold D heading-th =3°. In the above calculation, D lateral =0.0013 km <D lateral-th , D heading =1° <D heading-th , so the lane departure risk level at this time is risk level 1. If the lateral position deviation becomes 0.003 kilometers in subsequent calculations, the lane departure risk level will become risk level 2 because 0.003>0.002.

[0133] In step 80, if the lane departure risk level is the first risk level, the second real-time location is determined as the starting point for path correction. If the lane departure risk level is the second risk level, a prediction interval is determined based on the deviation change rate, and a path correction starting point is determined based on the second real-time location, the prediction interval, and the current speed and heading angle of the electric vehicle.

[0134] Furthermore, if the lane departure risk level is the first risk level, the vehicle control system directly determines the second real-time position as the path correction starting point and prepares to make a small path adjustment. If the lane departure risk level is the second risk level, the vehicle control system determines the second real-time position as the path correction starting point and prepares to make a small path adjustment. deviation Determine the prediction interval time T predect , the specific formula is T predect =k / |R deviation|, (where k is a constant, such as k=0.1). Further, the vehicle control system is based on the second real-time position, the predicted interval time T predect , the current speed of the electric vehicle v c and the current heading angle θ c , through the formula x1=x0+v c *T predect *sin(θ c +D heading ), y1=y0+v c *T predect *cos(θ c +D heading ), determine the starting point of path correction.

[0135] In one embodiment, when the lane departure risk level is the first risk level, the second real-time position (longitude: 118.791234, latitude: 32.003456) is directly determined as the path correction starting point. When the lane departure risk level becomes the second risk level, the lateral position deviation change rate R deviation = 0.0002 km / s, D heading is 1°, calculate the prediction interval time T predect = 0.1 / 0.0002 = 500 seconds. The current speed of the electric motorcycle v is known. c =20m / s, current heading angle θ c =5°, the second real-time position coordinates are (x0=118.791234, y0=32.003456), and the path correction starting point is calculated as follows: x1=118.791234+20*500*sin(6°) / 1000=118.791234+0.10453≈118.89586, y1=32.003456+20*500*cos(6°) / 1000=32.003456+0.994521≈32.997977.

[0136] Step 90: Correct the first autonomous driving path based on the path correction starting point to obtain a second autonomous driving path.

[0137] Furthermore, the vehicle control system corrects the first automatic driving path according to the path correction starting point to obtain a second automatic driving path, as specifically described in the process from step 901 to step 903 .

[0138] The embodiments of the present invention can monitor the deviation between the vehicle position and the planned path in real time during the driving of the electric motorcycle, accurately determine the lane departure risk level, and reasonably determine the starting point of the path correction according to different risk levels. It not only takes into account the deviation of the lateral position and heading angle, but also takes into account the deviation change rate to dynamically adjust the path correction strategy. It can respond to the deviation during the driving process of the vehicle in a more timely and accurate manner, effectively reduce the safety risks caused by lane departure, ensure that the electric motorcycle always travels along a safe and reasonable path during the automatic driving process, and improve the reliability and safety of the automatic driving.

[0139] In one embodiment, the process from step 901 to step 903 includes:

[0140] Step 901: With the path correction starting point as the center, a search is performed in the high-precision map in combination with a preset search range and the second lane information to generate multiple local candidate paths. Each local candidate path satisfies the vehicle's drivability conditions.

[0141] Optionally, the vehicle control system sets a preset search range (for example, a circular area with a radius of 500 meters) with the path correction starting point as the center, and searches in the high-precision map in combination with the second lane information. During the search process, the vehicle's turning radius, acceleration limit and other drivable conditions are taken into account to generate multiple local candidate paths starting from the path correction starting point. Each local candidate path must meet the vehicle dynamics constraints to ensure that the electric motorcycle can actually drive. In one embodiment, the path correction starting point is located near the intersection of XX Avenue and XX Road, and the second lane information shows that the vehicle is currently located in the middle lane of XX Avenue from south to north. The vehicle control system takes this point as the center and, within a radius of 500 meters, combines the road information in the high-precision map and the vehicle's drivable conditions to generate the following local candidate paths:

[0142] Route A: Continue straight along XX Avenue, and after three intersections, turn right onto XX Road;

[0143] Route B: Continue straight along XX Avenue, turn left after 2 intersections and enter XX Street;

[0144] Route C: Turn right immediately onto XX Branch Road, then merge onto XX Avenue after two intersections.

[0145] Step 902 : Determine a deviation index of each local candidate path based on the lateral position deviation and heading angle deviation of each point in each local candidate path.

[0146] Furthermore, for each point in each local candidate path, the vehicle control system calculates its lateral position deviation D lateral and heading angle deviation D heading, and based on the lateral position deviation and heading angle deviation of each point, determine the deviation index of each local candidate path. In this process, the deviation value and its change rate of each point are considered, and the deviation index of each local candidate path is obtained by weighted summation. Therefore, the calculation formula of the deviation index of each local candidate path is as follows:

[0147] Where n is the number of points on the path, w1, w2, w3, w4 are weight coefficients (here w1 = 0.4, w2 = 0.3, w3 = 0.2, w4 = 0.1), and are the rates of change of lateral position deviation and heading angle deviation, respectively.

[0148] Continuing with the example of local candidate path A, there are 50 points on the path. Calculate the lateral position deviation and heading angle deviation of each point, as well as their rate of change. Assume that after calculation, the deviation index I of path A is deviation-A =12.5. Similarly, the deviation index I of path B is calculated deviation-B =8.3, deviation index I of path C deviation-C =15.7.

[0149] In step 903, the path corresponding to the smallest deviation index among the local candidate paths is determined as the optimal local path, and the optimal local path is merged with the driving path of the first autonomous driving path after the correction starting point to obtain a second autonomous driving path.

[0150] The vehicle control system then compares the deviation indicators of each candidate local path and determines the path with the minimum deviation indicator as the optimal local path. Furthermore, the vehicle control system fuses the optimal local path with the path of the first automated driving path after the correction starting point. During the fusion process, the continuity and differentiability of the paths at the correction starting point are ensured, and a smooth transition function is used to achieve a seamless connection between the two paths, ultimately resulting in the second automated driving path.

[0151] Continuing with the above example, path B has the smallest deviation index and is therefore determined to be the optimal local path. Assuming that the driving path of the first autonomous driving path after the correction starting point is to continue straight along XX Avenue to XX Science and Technology Park, path B (continuing straight along XX Avenue, turning left after two intersections onto XX Street) is merged with the original path, using a quintic polynomial smoothing function to ensure the continuity of the path's position, direction, and curvature at the correction starting point. The second fused autonomous driving path is: starting from the correction starting point, driving along path B to XX Street, and then adjusting the route to XX Science and Technology Park based on actual conditions.

[0152] The embodiment of the present invention can generate multiple candidate paths, evaluate deviation indicators and fuse the optimal path when an electric motorcycle is at risk of lane departure. This not only ensures that the corrected path meets the vehicle dynamics constraints, but also minimizes the deviation from the original planned path and achieves a smooth transition of the path, making it possible to better cope with complex road conditions and emergencies, improving the safety and reliability of automatic driving of the electric motorcycle, and ensuring that the vehicle can reach the destination efficiently and stably along the corrected path.

[0153] Furthermore, the electric vehicle automatic driving path planning system based on high-precision positioning provided by the present invention is described below. The electric vehicle automatic driving path planning system based on high-precision positioning described below and the electric vehicle automatic driving path planning method based on high-precision positioning described above can be referenced to each other.

[0154] Reference Figure 3 , Figure 3 This is a schematic diagram of the structure of the electric vehicle automatic driving path planning system based on high-precision positioning provided by the present invention. The electric vehicle automatic driving path planning system based on high-precision positioning includes:

[0155] The data acquisition module 310 is used to obtain the first real-time position of the electric vehicle based on the high-precision positioning device, as well as the current power level, battery health status information and the set destination position of the electric vehicle;

[0156] a data matching module 320 for matching the first real-time location with a pre-stored high-precision map to determine information about a first lane in which the electric vehicle is currently located, and determining road information about each road between the first real-time location and a destination location based on the high-precision map;

[0157] a charging pile positioning module 330 for determining a maximum driving range based on the current power level and battery health status information, and determining a target charging pile based on the first real-time location, the maximum driving range, and the charging pile location information and current usage status information of each charging pile in the high-precision map;

[0158] A path planning module 340 is configured to plan a path based on the first real-time location, the destination location, the first lane information, the road information, and the target charging station to obtain a first autonomous driving path; the road information includes the road speed limit, the number of lanes, the lane direction, and the traffic light status; and the distance between each charging station in the target charging station is less than or equal to a first preset distance threshold.

[0159] The embodiment of the present invention determines the lane information of the electric vehicle and the road information of each road during driving through a high-precision map combined with the real-time position and the destination position, so that the real-time status of the road can be accurately perceived. On the other hand, within the maximum driving mileage determined according to the current power and battery health status information, the charging pile position information and the current usage status information of each charging pile in the high-precision map are combined to screen suitable target charging piles, which effectively solves the problem of electric vehicle range anxiety. Finally, the automatic driving path planned according to the real-time position, destination position, lane information, road information and target charging pile takes into account both the charging pile and the real-time status of the road, effectively avoiding the vehicle from breaking down due to power problems. At the same time, it can also perceive the road conditions in real time under complex road conditions, thereby improving the accuracy and safety of path planning in the electric vehicle automatic driving scenario.

[0160] See also Figure 4 , Figure 4 This is a diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0161] Obtain the first real-time location of the electric vehicle based on a high-precision positioning device, as well as the current power level, battery health status information and the set destination of the electric vehicle;

[0162] Matching the first real-time location with a pre-stored high-precision map to determine information about a first lane in which the electric vehicle is currently located, and determining road information about each road between the first real-time location and the destination location based on the high-precision map;

[0163] determining a maximum mileage based on the current power level and the battery health status information, and determining a target charging pile based on the first real-time location, the maximum mileage, and the charging pile location information and current usage status information of each charging pile in the high-precision map;

[0164] Path planning is performed based on the first real-time location, the destination location, the first lane information, the road information, and the target charging pile to obtain a first autonomous driving path; the distance between each charging pile in the target charging pile is less than or equal to a first preset distance threshold.

[0165] See also Figure 5 , Figure 5 Detailed description of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. Figure 5As shown, this embodiment provides a computer-readable storage medium 500 on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented:

[0166] Obtain the first real-time location of the electric vehicle based on a high-precision positioning device, as well as the current power level, battery health status information and the set destination of the electric vehicle;

[0167] Matching the first real-time location with a pre-stored high-precision map to determine information about a first lane in which the electric vehicle is currently located, and determining road information about each road between the first real-time location and the destination location based on the high-precision map;

[0168] determining a maximum mileage based on the current power level and the battery health status information, and determining a target charging pile based on the first real-time location, the maximum mileage, and the charging pile location information and current usage status information of each charging pile in the high-precision map;

[0169] Path planning is performed based on the first real-time location, the destination location, the first lane information, the road information, and the target charging pile to obtain a first autonomous driving path; the distance between each charging pile in the target charging pile is less than or equal to a first preset distance threshold.

[0170] On the other hand, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the electric vehicle automatic driving path planning method based on high-precision positioning provided by the above methods, which includes:

[0171] Obtain the first real-time location of the electric vehicle based on a high-precision positioning device, as well as the current power level, battery health status information and the set destination of the electric vehicle;

[0172] Matching the first real-time location with a pre-stored high-precision map to determine information about a first lane in which the electric vehicle is currently located, and determining road information about each road between the first real-time location and the destination location based on the high-precision map;

[0173] determining a maximum mileage based on the current power level and the battery health status information, and determining a target charging pile based on the first real-time location, the maximum mileage, and the charging pile location information and current usage status information of each charging pile in the high-precision map;

[0174] Path planning is performed based on the first real-time location, the destination location, the first lane information, the road information, and the target charging pile to obtain a first autonomous driving path; the distance between each charging pile in the target charging pile is less than or equal to a first preset distance threshold.

[0175] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0176] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0177] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for automatic driving path planning of an electric vehicle based on high-precision positioning, characterized in that: include: Obtaining a first real-time position of the electric vehicle based on a high-precision positioning device, as well as obtaining current power level, battery health status information, and a set destination position of the electric vehicle; Based on the first real-time location, the first lane information of the electric vehicle is determined by matching the first real-time location with a pre-stored high-precision map, and based on the high-precision map, the road information of each road between the first real-time location and the destination location is determined; determining a maximum driving range based on the current power level and the battery health status information, and determining a target charging pile based on the first real-time location, the maximum driving range, and the charging pile location information and current usage status information of each charging pile in the high-precision map; Performing path planning based on the first real-time location, the destination location, the first lane information, the road information, and the target charging pile to obtain a first autonomous driving path; The distance between each charging pile in the target charging pile is less than or equal to a first preset distance threshold.

2. The method for automatic driving path planning of an electric vehicle based on high-precision positioning according to claim 1 is characterized in that: The road information includes a road speed limit, a number of lanes, a lane direction, and a traffic light status; and the performing of path planning based on the first real-time location, the destination location, the first lane information, the road information, and the target charging pile to obtain a first autonomous driving path includes: Construct a directed graph using the target charging pile and each road intersection between the first real-time location and the destination location as nodes, road segments between adjacent intersections and the location distances between intersections and the target charging pile as edges, and road speed limits, number of lanes, lane directions, and traffic light status between adjacent intersections and between each intersection and the target charging pile as edge attributes; Filtering out valid road segments based on the directed graph according to the road speed limit of each road segment and the safe maximum driving speed of the electric vehicle; screening, based on the directed graph and the first lane information, a lane direction and lane compatibility of each lane in each road segment of the valid road segment, a passable lane in the valid road segment that is passable from the first real-time position; the lane compatibility characterizing the lane having a lane type and lane authority that are consistent with the model of the electric vehicle; Based on the directed graph and according to the position distance between each road segment in the valid road segment and the target charging pile, a target road segment is screened out, and path planning is performed based on the directed graph, the drivable lane, and the target road segment to obtain the first autonomous driving path.

3. The method for automatic driving path planning of an electric vehicle based on high-precision positioning according to claim 2 is characterized in that: The performing path planning based on the directed graph, the drivable lane, and the target road segment to obtain the first autonomous driving path includes: generating, based on the directed graph and according to connectivity of adjacent lanes in the drivable lanes and connectivity of adjacent road segments in the target road segment, initial paths with the first real-time location as a starting point and the target location as an end point; each path includes a plurality of consecutive lanes and road segments; For each road segment of each path in the initial path, determine, based on the directed graph and in combination with the road speed limit and road length of each lane, an ideal travel time for each road segment without the influence of traffic lights, and determine, based on the ideal travel time and in combination with the traffic light cycle, red light duration, and remaining time of the current red light for each lane, an actual travel time for each road segment; Based on the distance between each road segment and the target charging pile, the charging time of each road segment is predicted, and the total length of each road segment is determined based on the road length of each lane; A first candidate path is determined based on the total road length, charging consumption time and actual travel time of each road segment, and the first autonomous driving path is determined based on the number of remaining lanes in each path in the first candidate path and the number of charging piles including the target charging pile.

4. The method for automatic driving path planning of an electric vehicle based on high-precision positioning according to claim 3 is characterized in that: The determining the first autonomous driving path based on the number of remaining lanes in each of the first candidate paths and the number of charging piles including the target charging pile includes: Determine a path in the first candidate path where the number of remaining lanes is greater than a first preset number and the number of charging piles is greater than a second preset number as a second candidate path; The second candidate paths are screened with the goal of minimizing the sum of the rates of change of the steering angles of adjacent road segments in each path to obtain a third candidate path; The third candidate path is screened with the goal of minimizing the sum of lane curvatures of adjacent lanes in each road segment in each path to obtain a fourth candidate path; The fourth candidate path is screened with the goal of minimizing the sum of the number of adjacent lane changes in each road segment in each path to obtain the first automatic driving path.

5. The method for automatic driving path planning of an electric vehicle based on high-precision positioning according to claim 1, characterized in that: The determining of a target charging pile based on the first real-time position, the maximum mileage, and the charging pile position information and current usage status information of each charging pile in the high-precision map includes: According to the first real-time location and the charging pile location information of each charging pile, all charging piles that the electric vehicle can reach within the maximum driving range are screened to obtain reachable charging piles; For each of the reachable charging piles, construct a usage status history sequence within a preset time window based on its current usage status information, and determine an idle probability sequence for each charging pile based on the frequency of occurrence of the idle state in the usage status history sequence; The charging time is estimated based on the current usage status of each charging pile and the driving trajectory of the vehicle within the preset range, and the waiting time when the electric vehicle reaches each charging pile is obtained; The target charging pile is determined based on the idle probability sequence and waiting time of each charging pile among the reachable charging piles.

6. The method for automatic driving path planning of an electric vehicle based on high-precision positioning according to claim 5 is characterized in that: The determining the target charging pile based on the idle probability sequence and waiting time of each charging pile among the reachable charging piles includes: For each of the reachable charging piles, determining a distance loss value of each charging pile based on the distance between the first real-time location and the charging pile location information of each charging pile, and determining a comprehensive evaluation index of each charging pile based on the distance loss value, idle probability sequence, and waiting time of each charging pile; Determine the charging piles whose comprehensive evaluation index is greater than or equal to a preset index threshold among the reachable charging piles as candidate charging piles, and determine the device health index of each charging pile based on the number of failures and cumulative downtime of each charging pile among the candidate charging piles; A charging pile among the candidate charging piles whose device health index is greater than or equal to a preset health threshold and whose distance from the first real-time location is less than or equal to a preset value is determined as the target charging pile.

7. The method for automatic driving path planning of an electric vehicle based on high-precision positioning according to claim 5 is characterized in that: The charging time is estimated based on the current usage status of each charging pile and the driving trajectory of the vehicle within a preset range to obtain the waiting time when the electric vehicle arrives at each charging pile, including: If the current usage state is an idle state, determining the waiting time to be 0; If the current usage status is occupied, determine the total number of vehicles currently charging at each charging pile and the number of vehicles expected to arrive first, as well as the remaining charging time of the vehicles currently charging; The charging time is estimated based on the total number of vehicles at each charging pile, the remaining charging time and the average charging operation time of each vehicle, and the waiting time when arriving at each charging pile is determined.

8. The method for automatic driving path planning of an electric vehicle based on high-precision positioning according to any one of claims 1 to 7, characterized in that: After performing path planning based on the directed graph, the drivable lanes, and the target road segment to obtain the first autonomous driving path, the method further includes: During the driving of the electric vehicle, determining the second lane information of the electric vehicle in the high-precision map based on the second real-time position of the electric vehicle obtained in real time by the high-precision positioning device; determining, based on the second lane information and the first automatic driving path, a lateral position deviation, a heading angle deviation, and a deviation change rate of the electric vehicle during driving; determining a lane departure risk level based on the lateral position deviation and the heading angle deviation and their corresponding deviation thresholds; the lane departure risk level including a first risk level and a second risk level, the second risk level being higher than the first risk level; If the lane departure risk level is the first risk level, determining the second real-time position as a path correction starting point; if the lane departure risk level is the second risk level, determining a prediction interval time based on the deviation change rate, and determining a path correction starting point based on the second real-time position, the prediction interval time, and the current driving speed and current heading angle of the electric vehicle; The first autonomous driving path is corrected based on the path correction starting point to obtain a second autonomous driving path.

9. The method for automatic driving path planning of an electric vehicle based on high-precision positioning according to claim 8, characterized in that: The correcting the first autonomous driving path based on the path correction starting point to obtain a second autonomous driving path includes: Taking the path correction starting point as the center, the system searches the high-precision map in combination with the preset search range and the second lane information to generate multiple local candidate paths. Each local candidate path meets the vehicle's drivable conditions. Determining a deviation index of each local candidate path based on the lateral position deviation and the heading angle deviation of each point in each local candidate path; The path corresponding to the smallest deviation index among the local candidate paths is determined as the optimal local path, and the optimal local path is merged with the driving path of the first autonomous driving path after the correction starting point to obtain the second autonomous driving path.

10. A high-precision positioning-based automatic driving path planning system for electric vehicles, characterized in that: The method for autonomous driving path planning of an electric vehicle based on high-precision positioning according to any one of claims 1 to 9 is applied; the system for autonomous driving path planning of an electric vehicle based on high-precision positioning comprises: A data acquisition module is used to obtain a first real-time position of the electric vehicle based on a high-precision positioning device, as well as the current power level, battery health status information and a set destination position of the electric vehicle; a data matching module, configured to match the first real-time location with a pre-stored high-precision map to determine information about a first lane in which the electric vehicle is currently located, and to determine road information about each road between the first real-time location and the destination location based on the high-precision map; a charging pile positioning module, configured to determine a maximum driving range based on the current power level and battery health status information, and determine a target charging pile based on the first real-time location, the maximum driving range, and the charging pile location information and current usage status information of each charging pile in the high-precision map; A path planning module is configured to perform path planning based on the first real-time location, the destination location, the first lane information, the road information, and the target charging pile to obtain a first autonomous driving path; the road information includes a road speed limit, the number of lanes, the lane direction, and the status of traffic lights; and the distance between each charging pile in the target charging pile is less than or equal to a first preset distance threshold.

Images