Vehicle travel path control method, device, intelligent vehicle, and readable storage medium

Abstract

The application relates to a vehicle driving path control method, device, intelligent vehicle and readable storage medium. The method comprises the following steps: in response to the fact that an intelligent vehicle meets a trigger condition for entering a preset driving mode, acquiring a path planning starting point and a path planning range; generating a plurality of initial planning paths according to the path planning starting point and the path planning range; determining a regional division type of a region where the intelligent vehicle is located, and performing screening processing on the initial planning paths according to path shape screening conditions corresponding to the regional division type to obtain candidate planning paths; and in response to a selection instruction on a target planning path in the candidate planning paths, controlling the intelligent vehicle to drive according to the target planning path. The method can improve the intelligent level of the vehicle when performing a roaming driving task without a fixed transportation purpose.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a vehicle driving path control method, device, intelligent vehicle, and readable storage medium. Background Technology

[0002] With the development of artificial intelligence and autonomous driving technology, vehicles have gradually upgraded from traditional means of transportation to intelligent and personalized driving and riding platforms.

[0003] Currently, when vehicles in traditional technologies need to perform roaming tasks without a fixed transportation destination, the vehicle's driving path is often determined entirely by the driver's driving intentions through manual control, or the driver manually modifies the destination multiple times based on subjective judgment to simulate roaming without a fixed transportation destination. The operation is relatively cumbersome and limits the application of intelligent vehicles in roaming scenarios without a transportation destination.

[0004] Therefore, vehicles in traditional technologies have a low level of intelligence when performing roaming missions without a fixed transportation purpose. Summary of the Invention

[0005] Based on this, this application addresses the aforementioned technical problems by providing a vehicle driving path control method, device, intelligent vehicle, computer-readable storage medium, and computer program product that can improve the intelligence level of vehicles when performing roaming driving tasks without a fixed transportation purpose.

[0006] In a first aspect, this application provides a vehicle driving path control method, the method comprising:

[0007] In response to the intelligent vehicle meeting the trigger conditions for entering the preset driving mode, the starting point and range of the path planning are obtained;

[0008] Based on the starting point and the scope of the path planning, multiple initial planned paths are generated;

[0009] The region division type of the area where the intelligent vehicle is located is determined. According to the path shape filtering conditions corresponding to the region division type, the initial planned path is filtered to obtain candidate planned paths. The path shape of the candidate planned path satisfies a preset mapping relationship with the region division type. The preset mapping relationship records the mapping relationship between different region division types and the corresponding path shapes.

[0010] In response to the instruction to select a target planned path from the candidate planned paths, the intelligent vehicle is controlled to drive according to the target planned path.

[0011] The above technical solution has the following advantages or effects: By responding to the triggering condition of the intelligent vehicle entering a preset driving mode, the starting point and range of path planning are obtained; based on the starting point and range, multiple initial planned paths are generated; then, the area division type of the region where the intelligent vehicle is located is determined; according to the path shape filtering conditions corresponding to the area division type, the initial planned paths are filtered to obtain candidate planned paths; the path shape of the candidate planned paths satisfies a preset mapping relationship with the area division type; the preset mapping relationship records the mapping relationship between different area division types and corresponding path shapes; finally, by responding to the selection command of the target planned path among the candidate planned paths, the intelligent vehicle is controlled to drive according to the target planned path; thus... By controlling the vehicle to enter a preset driving mode, the intelligent vehicle generates multiple cruise routes within a specified range. The shape of these cruise routes matches the road network characteristics of the area where the intelligent vehicle is currently located. The vehicle is then controlled to drive on the target planned route selected by the selection command. This effectively improves the automation level of the intelligent vehicle's aimless cruise, balances route diversity and adaptability, simplifies user operation, enhances driving convenience, effectively combines the road network characteristics of the area where the intelligent vehicle is located to adapt the shape of the candidate planned routes, improves the rationality and safety of cruise routes, enhances planning controllability, facilitates strategic management in different areas, optimizes the ride comfort of aimless cruise routes, and improves the intelligence level of the vehicle when performing roaming driving tasks without a fixed transportation purpose.

[0012] In an alternative embodiment of the first aspect, the candidate planned path further meets at least one of the following conditions:

[0013] The longest driving distance of each candidate planned path is greater than or equal to the predicted driving distance, and the shortest driving distance of each candidate planned path is less than or equal to the predicted driving distance. The predicted driving distance is determined based on the set average speed and set driving time of the intelligent vehicle in the preset driving mode.

[0014] or,

[0015] The permissible driving speed of the candidate planned path is within the driving speed limit range preset by the preset driving mode;

[0016] or,

[0017] The permitted travel time for the candidate planned routes includes the current time;

[0018] or,

[0019] The candidate planned path is not configured with a preset road entrance or preset traffic sign; the preset road entrance is a road entrance whose maximum speed limit is greater than the maximum driving speed limit associated with the preset driving mode; the preset traffic sign includes at least one of the following: accident-prone road section traffic sign, construction road section traffic sign, one-way traffic sign, or no-entry road section traffic sign.

[0020] The above technical solution has the following advantages or effects: by combining the preset average vehicle speed and driving time, the predicted driving distance is calculated, and the candidate planned path that surrounds the predicted driving distance is selected. This realizes the transformation of user time requirements into quantifiable distance indicators, so that the path length of the candidate planned path can effectively match the user's time requirements for using the preset driving mode, thereby improving the cruise controllability of intelligent vehicles when performing tasks without a fixed transportation destination.

[0021] In addition, by acquiring traffic description data of the initial planned routes and identifying and eliminating target type routes containing risky traffic signs and controlled traffic signs based on the traffic description data of each initial planned route, it is possible to effectively control intelligent vehicles to avoid entering accident-prone, construction, one-way, and restricted road sections when performing tasks without a fixed transportation destination. This improves the safety and compliance of intelligent vehicles when performing tasks without a fixed transportation destination from the source and enhances the safety guarantee of intelligent vehicles in the destinationless cruise mode.

[0022] Finally, by obtaining the speed limit information of each initial planned path, and based on the speed limit information of each initial planned path, a target speed limit path can be selected as a candidate planned path from the initial planned paths. The allowed driving speed of the target speed limit path is within the preset driving speed limit range, which can effectively reduce the probability of safety hazards caused by excessively high speed limits and inefficient driving caused by excessively low speed limits, thereby improving the driving safety, comfort and smoothness of intelligent vehicles when performing tasks without a fixed transportation destination.

[0023] In an optional embodiment of the first aspect, when the current driving scenario associated with the preset driving mode is a sightseeing scenario, generating an initial planned path based on the path planning starting point and the path planning range includes:

[0024] Obtain map data associated with the route planning area; determine the vehicle's transit points within the route planning area based on the scenic spot information in the map data; match the vehicle's transit points with the scenic spots within the route planning area;

[0025] Generate a cruise route that uses the route planning start point as the initial driving point, passes through at least one location the vehicle travels through, and returns to the route planning start point, thus obtaining the initial planned route.

[0026] The above technical solution has the following advantages or effects: by acquiring map data associated with the route planning range and determining the vehicle route locations that match the attractions in the route planning range based on the scenic area information in the map data, and by generating a cruise route that takes the route planning start point as the initial driving point, passes through at least one vehicle route location, and returns to the route planning start point, at least one suitable scenic spot tour route can be effectively planned within the route planning range, effectively improving the ability of intelligent vehicles to adapt to scenic spot sightseeing scenarios when performing tasks without a fixed transportation destination.

[0027] In an optional embodiment of the first aspect, when the driving scenario associated with the preset driving mode is a waiting scenario for picking up someone, the method further includes:

[0028] Obtain the estimated waiting time and target waiting location for the pickup scenario;

[0029] In response to the intelligent vehicle entering the preset driving mode for a duration that meets the waiting time, the intelligent vehicle is triggered to end the preset driving mode and is controlled to drive to the target waiting location;

[0030] When the driving scenario associated with the preset driving mode is a parking space waiting scenario, the method further includes:

[0031] While the intelligent vehicle is in the preset driving mode, the intelligent vehicle is controlled to search for a target parking space in a parking lot within a preset range; the target parking space is a parking space in which the intelligent vehicle can park.

[0032] In response to the intelligent vehicle finding the target parking space in the parking lot, the intelligent vehicle is triggered to end the preset driving mode and park itself in the target parking space.

[0033] The above technical solution has the following advantages or effects: When the driving scenario associated with the above preset driving mode is a waiting scenario for picking up people, by obtaining the estimated waiting time and target waiting location of the waiting scenario for picking up people, and responding to the fact that the time for the intelligent vehicle to enter the preset driving mode meets the waiting time, the intelligent vehicle is triggered to end the preset driving mode and control the intelligent vehicle to drive to the target waiting location. This enables the intelligent vehicle to effectively and timely identify the conditions for exiting the preset driving mode in the waiting scenario for picking up people, further reducing the operation of the vehicle driver and improving the intelligence level of the intelligent vehicle.

[0034] When the driving scenario associated with the preset driving mode is a parking space waiting scenario, while the intelligent vehicle is in the preset driving mode, it searches for a target parking space in a parking lot within a preset range. In response to the intelligent vehicle finding a target parking space, it terminates the preset driving mode and parks in the target parking space. This effectively avoids illegal parking when the parking lot within the preset range is temporarily full, and also allows the intelligent vehicle to park in a parking space within the preset range when a suitable parking space exists, saving energy and improving the intelligence level of the intelligent vehicle.

[0035] In an optional embodiment of the first aspect, when the driving scenario associated with the preset driving mode is an occupant relaxation scenario, the method further includes:

[0036] Obtain the driving experience quantification value corresponding to each of the candidate planning paths; the driving experience quantification value is obtained by mapping the road greening quantification information, road landscape quantification information, road environment quantification information and road noise quantification information associated with the corresponding candidate planning path;

[0037] According to the driving experience quantification value corresponding to each candidate planning path, the candidate planning paths are sorted to obtain the sorted candidate planning paths.

[0038] The sorted candidate planned paths are displayed on the display device of the intelligent vehicle.

[0039] The above technical solution has the following advantages or effects: by obtaining the driving experience quantification value corresponding to each candidate planning path, which is obtained by mapping the road greening quantification information, road landscape quantification information, road environment quantification information, and road noise quantification information associated with the corresponding candidate planning path, and sorting the candidate planning paths according to the driving experience quantification value corresponding to each candidate planning path, the sorted candidate planning paths are obtained; the sorted candidate planning paths are displayed through the display device of the intelligent vehicle, thereby recommending candidate planning paths with better driving experience to the user, allowing the user to instruct the intelligent vehicle to drive on roads with better driving experience.

[0040] In an optional embodiment of the first aspect, during the process of the intelligent vehicle traveling according to the target planned path, the method further includes:

[0041] According to a preset path update cycle, the untraveled paths of the intelligent vehicle in the target planned path are replanned to obtain a new target planned path;

[0042] Control the intelligent vehicle to travel along the new target planned path;

[0043] The above technical solution has the following advantages or effects: During the process of the intelligent vehicle traveling according to the target planned path, by replanning the untraveled path of the intelligent vehicle in the target planned path according to the preset path update cycle, a new target planned path is obtained, thereby controlling the intelligent vehicle to travel according to the new target planned path, which can effectively realize the dynamic update of the target planned path currently being traveled by the intelligent vehicle.

[0044] In an optional embodiment of the first aspect, during the process of the intelligent vehicle traveling according to the target planned path, the method further includes:

[0045] Based on real-time traffic data, detect whether there are preset detour events on the untraveled paths of the intelligent vehicle in the target planned path;

[0046] In response to detecting the preset detour event of the untraveled path of the intelligent vehicle in the target planned path, the untraveled path of the intelligent vehicle is replanned to obtain a new target planned path;

[0047] Control the intelligent vehicle to travel along the new target planned path.

[0048] The above technical solution has the following advantages or effects: During the process of intelligent vehicles traveling according to the target planned path, by detecting whether there are preset detour events, such as traffic accidents or temporary traffic control, on the untraveled paths of the intelligent vehicles in the target planned path based on real-time traffic data, and by replanning the untraveled paths of the intelligent vehicles to obtain a new target planned path, the intelligent vehicles can be controlled to travel according to the new target planned path, which can effectively reduce the probability of intelligent vehicles entering congested road sections.

[0049] Secondly, this application also provides a vehicle driving path control device, comprising:

[0050] The response module is used to respond to the triggering conditions for the intelligent vehicle to enter the preset driving mode and obtain the starting point and range of the path planning.

[0051] The generation module is used to generate an initial planned path based on the starting point of the path planning and the scope of the path planning; each initial planned path is a cruise path without a fixed transportation destination;

[0052] The filtering module is used to determine the area division type of the area where the intelligent vehicle is located, and to filter the initial planned path according to the path shape filtering conditions corresponding to the area division type to obtain candidate planned paths; the path shape of the candidate planned path satisfies a preset mapping relationship with the area division type; the preset mapping relationship records the mapping relationship between different area division types and the corresponding path shapes;

[0053] The control module is used to control the intelligent vehicle to travel according to the target planned path in response to the selection instruction of the target planned path among the candidate planned paths.

[0054] Thirdly, this application also provides an intelligent vehicle, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0055] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0056] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the above aspects.

[0057] Regarding the beneficial effects of any of the technical solutions in the second to fifth aspects mentioned above, refer to the beneficial effects of the corresponding technical solutions in the first aspect; repeated examples will not be listed here. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a schematic diagram of an optional application environment for a vehicle driving path control method in one embodiment;

[0060] Figure 2 This is a schematic diagram of an optional process for a vehicle driving path control method in one embodiment;

[0061] Figure 3 This is a schematic diagram of an optional process for a vehicle driving path control method in another embodiment;

[0062] Figure 4 This is a schematic diagram of an optional structure of a vehicle driving path control device in one embodiment;

[0063] Figure 5 This is a schematic diagram of an optional internal structure of an intelligent vehicle in one embodiment. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0065] The vehicle driving path control method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, the intelligent vehicle 102 communicates with the server 104 via a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated onto the server 104, or it can be located in the cloud or on another network server.

[0066] The control unit of the intelligent vehicle 102 can obtain the starting point and range of the route planning in response to the triggering condition of the intelligent vehicle entering the preset driving mode. The control unit of the intelligent vehicle 102 can generate an initial planned route based on the starting point and range of the route planning. Each initial planned route is a cruise route without a fixed transportation destination. The control unit of the intelligent vehicle 102 can determine the area division type of the area where the intelligent vehicle is located, and filter the initial planned routes according to the path shape filtering conditions corresponding to the area division type to obtain candidate planned routes. The path shape of the candidate planned routes and the area division type satisfy a preset mapping relationship. The preset mapping relationship records the mapping relationship between different area division types and corresponding path shapes. The control unit of the intelligent vehicle 102 can control the intelligent vehicle to drive according to the target planned route in response to the selection command of the target planned route in the candidate planned routes.

[0067] In practical applications, server 104 can be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0068] In one exemplary embodiment, such as Figure 2 As shown, a vehicle driving path control method is provided, which is applied to... Figure 1The following steps, S202 to S208, are used as an example to illustrate the control unit of the intelligent vehicle 102. The control unit of the intelligent vehicle 102 can refer to a computer device mounted on the intelligent vehicle 102, or it can refer to a cloud server connected to the intelligent vehicle 102.

[0069] Step S202: In response to the intelligent vehicle meeting the triggering conditions for entering the preset driving mode, obtain the starting point and range of the path planning.

[0070] The preset driving mode can refer to a driving mode without a fixed transportation destination. In practical applications, the preset driving mode can be a roaming mode.

[0071] In practice, the autonomous driving system of an intelligent vehicle monitors the vehicle's status and user operations in real time. For example, when it detects that a user clicks on the roaming mode on the vehicle's infotainment screen, the trigger conditions for entering a preset driving mode are met. The control unit of the intelligent vehicle can then respond to the condition that the vehicle meets the trigger conditions for entering the preset driving mode by obtaining the starting point and range of the path planning.

[0072] Furthermore, the autonomous driving system of intelligent vehicles can trigger the entry into a preset driving mode based on real-time conversations between passengers, such as "You get out to get your milk tea, I'll drive around a few times and come back to pick you up." For example, it can also trigger the entry into a preset driving mode based on a user's phone call: "I'm still getting my luggage, you drive around a few times first, I'll be back in about 10 minutes." In the case of intelligent vehicles used for ride-hailing, the autonomous driving system can also infer the passenger's estimated arrival time based on their current location and plan the roaming time of the intelligent vehicle in roaming mode accordingly. When the system indicates that the passenger is approaching their destination or the passenger clicks "I'm in position," the autonomous driving system of the intelligent vehicle automatically ends the roaming mode.

[0073] The starting point for route planning can include the vehicle's current location or a core point set by the user (i.e., an anchor point, such as a residence, workplace, tourist attraction, or pick-up point).

[0074] The path planning range can refer to the path search area of ​​the intelligent vehicle. For example, the path planning range can be an area with a radius of 5km centered on the starting point.

[0075] Step S204: Generate an initial planned path based on the starting point and scope of the path planning.

[0076] In practical applications, the initial planned path can refer to a circular path formed by connecting at least two sub-paths.

[0077] In practical implementation, the intelligent vehicle's control unit can generate multiple initial planned paths based on the aforementioned path planning starting point and path planning range, using a preset road network planning algorithm. Specifically, the intelligent vehicle's control unit can randomly select at least one waypoint within the traffic network corresponding to the path planning range. Then, using the preset road network planning algorithm, the control unit generates candidate planned paths that start from the path planning starting point, pass through the aforementioned at least one waypoint, and return to the path planning starting point. For example, initial planned path 1 is "path planning starting point → branch road A → road B → road C → path planning starting point", initial planned path 2 is "path planning starting point → road D → auxiliary road G → path planning starting point", and initial planned path 3 is "path planning starting point → west road H → road D → path planning starting point". All three initial planned paths can be cruising loop paths without a clearly defined passenger transport destination, used for the intelligent vehicle to roam within the path planning range.

[0078] Step S206: Determine the area division type of the area where the intelligent vehicle is located, and filter the initial planned path according to the path shape filtering conditions corresponding to the area division type to obtain candidate planned paths.

[0079] Among them, the path shape of the candidate planning path and the regional division type satisfy a preset mapping relationship, which records the mapping relationship between different regional division types and corresponding path shapes.

[0080] In practical implementation, the control unit of the intelligent vehicle can call a preset mapping relationship. This preset mapping relationship can be a preset relationship table, which records the correspondence between different area division types and corresponding path shape types. For example: urban core area → small closed loop path (circumference 2-3km), urban branch road area → mixed path of round-trip and short closed loop (circumference 3-5km), suburban road area → large loop path (circumference 5-8km), scenic area → landscape-connected closed loop path. Another example is: southern area → near-circular loop path, northern area → near-square loop path.

[0081] Then, the intelligent vehicle's control unit queries a preset mapping relationship to find the path shape type corresponding to the area division type of the region where the intelligent vehicle is located. The control unit can then select a target shape path that matches the path shape type from the initial planned path, obtaining candidate planned paths. For example, if the intelligent vehicle is located in the northern region, the target shape path could be a near-square loop path. This effectively selects a loop path with "long straight sections," "few turns," and "open visibility at turning intersections" in the initial planned path, avoiding the intelligent vehicle from entering irregular paths such as "long and narrow" or "too many corners."

[0082] For example, if the intelligent vehicle is located in a southern region and the target shape path is a near-circular loop path, the intelligent vehicle can travel on a loop path with continuous curvature and smooth steering in roaming mode, effectively filtering out fragmented and messy ineffective detours and improving the driving comfort of the intelligent vehicle in roaming mode.

[0083] In addition, the intelligent vehicle's control unit can obtain the route filtering conditions matched by the preset driving mode. For example, these conditions may include fewer traffic lights, no construction sections, and the number of lanes. The intelligent vehicle's control unit can filter the initial planned routes. For example, if the initial planned route A contains one construction section, then the initial planned route A is eliminated. If the initial planned routes B and C meet the filtering conditions, the intelligent vehicle's control unit obtains two candidate planned routes.

[0084] The intelligent vehicle's control unit filters out candidate routes suitable for slow driving based on road type (such as side roads, roundabouts, and roads around scenic spots) and speed limits (speed less than or equal to 40km / h).

[0085] Step S208: In response to the instruction to select the target planned path among the candidate planned paths, control the intelligent vehicle to drive according to the target planned path.

[0086] In practice, after the intelligent vehicle's control unit generates multiple candidate planned paths, the control unit can control the intelligent vehicle's display device (e.g., the vehicle's infotainment screen) to display the aforementioned candidate planned paths. Then, the user can input the selection command for the target planned path among the candidate planned paths to the intelligent vehicle's control unit through the voice command "select the second path".

[0087] The control unit of the intelligent vehicle can respond to the selection command of the target planned path among the candidate planned paths and control the intelligent vehicle to drive according to the target planned path until the user triggers the command to exit the above-mentioned preset driving mode. At this time, the intelligent vehicle can switch from the above-mentioned roaming mode to NOA (Navigate on Autopilot) mode.

[0088] In practical applications, the termination conditions for roaming mode can include:

[0089] 1) Destination Arrival: The intelligent vehicle arrives at the user-defined roaming destination (error < 50 meters) (i.e., the destination of the target planned path); the intelligent vehicle completes the number of loops on the target planned path that the user has set; of course, the user may choose not to set the number of loops. The intelligent vehicle's intelligent driving system provides prompts via the central control screen and voice, such as "Arrived at today's roaming destination, about to switch to NOA mode."

[0090] 2) POI coverage complete: The intelligent vehicle has triggered navigation at all marked POIs (Points of Interest) along the target planned path. There are no new POIs added to the remaining route of the target planned path or the user has not manually added any points of interest. At this point, the intelligent vehicle can determine that the conditions for ending the roaming mode have been met.

[0091] 3) Deviating from the preset route: If the intelligent vehicle does not travel on the target planned route within a preset time (e.g., 3 minutes) when the user actively changes lanes or takes a detour, the intelligent vehicle's screen can pop up a confirmation box, such as "Deviated from the roaming route detected. Do you want to return to the original route or end the roaming?", to prompt the user to enter the command to exit the above preset driving mode.

[0092] In addition, occupants of intelligent vehicles can also actively trigger the vehicle to exit roaming mode, specifically including:

[0093] 1) Voice commands: Users can speak preset commands such as "End roaming" or "Return to NOA";

[0094] 2) Physical button operation: Press and hold the roaming button (customizable button) on the steering wheel for 2 seconds (can be bound in advance in the settings);

[0095] 3) Exit roaming mode by clicking on the central control screen;

[0096] 4) Control the smart vehicle to exit roaming mode via a mobile application;

[0097] Of course, the termination conditions for roaming mode can also include environmental safety conditions, which may include:

[0098] 1) Complex Road Condition Intervention: When intelligent vehicles enter construction zones, accident areas, sharp bends, steep slopes, or other NOA (No Access Control) scenarios that cannot be avoided, the intelligent vehicle can issue a voice announcement such as "The road ahead is complex; roaming mode has been paused."

[0099] 2) Severe weather: If the intelligent vehicle detects that it is currently in severe weather, it can actively exit roaming mode.

[0100] 3) Fatigue driving monitoring: When the intelligent vehicle detects fatigue characteristics such as closed eyes / frequent nodding through the cabin camera, the intelligent vehicle can link seat vibration and voice reminder: such as "You may be fatigued, the roaming has been automatically ended and NOA assisted driving has been activated", and find a safe place to pull over as soon as possible.

[0101] In addition, intelligent vehicles can also be triggered to exit roaming mode based on resource limitations, specifically including:

[0102] 1) Insufficient battery / range: When the intelligent vehicle detects that the remaining battery is lower than a preset percentage (e.g., 20%) or the range is insufficient to cover the return route, the intelligent vehicle can provide a voice prompt such as "Battery is low, roaming mode will be turned off to prioritize navigation function".

[0103] 2) Network signal loss: If the intelligent vehicle detects no 4G / 5G signal for a continuous preset time (e.g., 30 seconds), the intelligent vehicle can downgrade to LCC (Lane Centering Assist) mode (Lane Centering Assist does not rely on navigation maps) and find a safe place to pull over as soon as possible.

[0104] Additionally, if the intelligent vehicle is in roaming mode and the exit conditions for intelligent driving are triggered, the intelligent vehicle will also remind the user to exit intelligent driving mode directly.

[0105] The aforementioned vehicle driving path control method, in response to the triggering condition of the intelligent vehicle entering a preset driving mode, obtains the path planning start point and path planning range, and generates an initial planned path based on the path planning start point and path planning range. Each initial planned path is a cruising path without a fixed transport destination. Then, it determines the area division type of the region where the intelligent vehicle is located, and filters the initial planned paths according to the path shape filtering conditions corresponding to the area division type to obtain candidate planned paths. The path shape of the candidate planned paths satisfies a preset mapping relationship with the area division type. The preset mapping relationship records the mapping relationship between different area division types and corresponding path shapes. Finally, in response to the selection command of the target planned path in the candidate planned paths, it controls the intelligent vehicle to follow the target planned path. By controlling the vehicle to enter a preset driving mode, the intelligent vehicle generates multiple cruise routes within a specified range. The shape of these cruise routes matches the road network characteristics of the area where the intelligent vehicle is currently located. The vehicle is then controlled to drive on the target planned route selected by the selection command. This effectively improves the automation level of the intelligent vehicle's aimless cruise, balances route diversity and adaptability, simplifies user operation, enhances driving convenience, effectively combines the road network characteristics of the area where the intelligent vehicle is located with the path shape of the candidate planned routes, improves the rationality and safety of cruise routes, enhances planning controllability, facilitates strategic management in different areas, optimizes the riding comfort of aimless cruise routes, and improves the intelligence level of the vehicle when performing roaming driving tasks without a fixed transportation purpose.

[0106] In one exemplary embodiment, the candidate planned path also meets at least one of the following conditions:

[0107] Condition 1: The longest driving distance of each candidate planned path is greater than or equal to the predicted driving distance, and the shortest driving distance of each candidate planned path is less than or equal to the predicted driving distance. The predicted driving distance is determined based on the set average speed and set driving time of the intelligent vehicle in the preset driving mode.

[0108] Specifically, the route selection criteria include route length selection criteria, and the intelligent vehicle's control unit can obtain the set average vehicle speed V in the preset driving mode. avg And set the driving time T; then, based on the set average vehicle speed V avg Given a set travel time T, determine the predicted travel distance D.

[0109] Then, the intelligent vehicle's control unit can select a path of target length from the initial planned path based on the predicted travel distance, thus obtaining candidate planned paths. Specifically, the intelligent vehicle's control unit can determine the maximum travel distance L for each initially planned path based on map data. max and shortest driving distance L min Then, the intelligent vehicle's control unit can compare the predicted driving distance D with the longest driving distance L of each initially planned path. max and shortest driving distance L min By comparing the initial planned paths, a path of target length is selected to obtain candidate planned paths. The longest travel distance L of the target length path is [not specified in the original text]. max The shortest travel distance L of the target length path is greater than or equal to the predicted travel distance D. min The distance is less than or equal to the predicted travel distance D. In other words, the travel distance of the candidate planned path can satisfy the following relationship:

[0110] L of the i-th candidate planning path min ≤D≤L of the i-th candidate planning path max

[0111] The technical solution of this embodiment is as follows: by combining the preset average vehicle speed and driving time, the predicted driving distance is calculated, and the candidate planned path that surrounds the predicted driving distance is selected. This realizes the transformation of user time requirements into quantifiable distance indicators, so that the path length of the candidate planned path can effectively match the user's time requirements for using the preset driving mode, thereby improving the cruise controllability of intelligent vehicles when performing tasks without a fixed transportation destination.

[0112] Condition 2: The permissible driving speed of the candidate planned route is within the driving speed limit range preset by the preset driving mode.

[0113] In practice, the control unit of the intelligent vehicle can obtain the speed limit information of each initially planned path through the built-in high-precision map module and real-time traffic data interface. This speed limit information is the legal speed limit of each path. For example, the speed limit of the initially planned path A is 15km / h, the speed limit of the initially planned path B is 30km / h, and the speed limit of the initially planned path C is 60km / h.

[0114] The control unit of an intelligent vehicle can select a target speed-limited path from the initial planned path based on the speed limit information of each initial planned path and the preset driving speed limit range, and obtain a candidate planned path.

[0115] For example, if the preset speed limit range is 20km / h ≤ average speed ≤ 50km / h, the intelligent vehicle's control unit will compare the speed limit information of each initial planned path with the speed limit range to determine the target speed limit path as the initial planned path B and obtain the candidate planned path.

[0116] The technical solution of this embodiment obtains the speed limit information of each initial planned path, and selects the target speed limit path as the candidate planned path based on the speed limit information of each initial planned path. The allowed driving speed of the target speed limit path is within the preset driving speed limit range, which can effectively reduce the probability of two situations: safety hazards caused by excessively high speed limits and inefficient driving caused by excessively low speed limits. This improves the driving safety, comfort and smoothness of intelligent vehicles when performing tasks without a fixed transportation destination.

[0117] Condition 3: The allowed travel time for the candidate planned route includes the current time.

[0118] The control unit of an intelligent vehicle can obtain the permitted driving time periods for each initially planned path and determine the initially planned path whose permitted driving time period includes the current time as the candidate planned path. For example, the permitted driving time period for the initially planned path A is from 9:00 AM to 12:00 PM, and the permitted driving time period for the initially planned path B is from 8:00 AM to 12:00 PM; assuming the current time is 8:30 AM, then the initially planned path B is the candidate planned path.

[0119] Condition 4: The candidate planned route does not have a preset road entrance or preset traffic sign.

[0120] The preset road entrance is a road entrance where the maximum speed limit is greater than the maximum speed limit associated with the preset driving mode. In practical applications, the preset road entrance can refer to a highway entrance or an urban expressway entrance.

[0121] Among them, the preset traffic signs include at least one of the following: traffic signs for accident-prone road sections, traffic signs for construction sections, traffic signs for one-way streets, or traffic signs for restricted road sections.

[0122] In practice, the intelligent vehicle's control unit filters the initial planned paths according to the preset driving mode matching path selection conditions to obtain candidate planned paths. During this process, the intelligent vehicle's control unit can obtain traffic description data for each initial planned path through the built-in high-precision map module and real-time traffic data interface. For example, the traffic description data for initial planned path A is "two lanes in both directions, no construction, no special traffic signs"; the traffic description data for initial planned path B is "two lanes in both directions, including construction sections, with construction section traffic signs"; and the traffic description data for initial planned path C is "one lane in one direction, including one-way street, with one-way street traffic signs".

[0123] The control unit of the intelligent vehicle identifies the target type path in the initial planned path based on the traffic description data of each initial planned path. For example, if initial planned path B contains traffic signs for a construction section and initial planned path C contains traffic signs for a one-way street, then initial planned paths B and C are determined to be target type paths.

[0124] Then, the intelligent vehicle's control unit can remove the target type path from the initial planned path (such as the initial planned path B and the initial planned path C mentioned above), retain the initial planned path A as the target planned path, and control the intelligent vehicle to cruise according to the initial planned path A, so that the intelligent vehicle's cruise process in roaming mode is safe and compliant, and prevents traffic violations and safety accidents from occurring.

[0125] The technical solution of this embodiment obtains traffic description data of the initial planned route and, based on the traffic description data of each initial planned route, identifies and eliminates target type routes containing risky traffic signs and controlled traffic signs in the initial planned route. This effectively controls intelligent vehicles to minimize their entry into accident-prone, construction, one-way, and prohibited road sections when performing tasks without a fixed transportation destination. This improves the cruise safety and compliance of intelligent vehicles when performing tasks without a fixed transportation destination from the source and enhances the safety guarantee of intelligent vehicles in the destinationless cruise mode.

[0126] In some embodiments, the initial planned path is filtered according to the path shape filtering conditions corresponding to the region division type to obtain candidate planned paths, including: querying the path shape type corresponding to the region division type of the area where the intelligent vehicle is located from the preset mapping relationship; selecting the target shape path that matches the path shape type in the initial planned path; obtaining the path smoothness of the target shape path; the path smoothness is obtained by quantifying the turning frequency, turning angle and continuous straight length of the target shape path; and determining the candidate planned path from the target shape path according to the path smoothness of the target shape path.

[0127] In practical implementation, the control unit of the intelligent vehicle can call a preset mapping relationship. This preset mapping relationship can be a preset relationship table, which records the correspondence between different area division types and corresponding path shape types. For example: urban core area → small closed loop path (circumference 2-3km), urban branch road area → mixed path of round-trip and short closed loop (circumference 3-5km), suburban road area → large loop path (circumference 5-8km), scenic area → landscape-connected closed loop path. Another example is: southern area → near-circular loop path, northern area → near-square loop path.

[0128] Then, the intelligent vehicle's control unit retrieves the path shape type corresponding to the area division type of the region where the intelligent vehicle is located from a preset mapping relationship. The control unit can then select a target shape path that matches the path shape type from the initial planned path, obtaining candidate planned paths. For example, if the intelligent vehicle is located in the northern region, the target shape path would be a near-square loop path, effectively preventing the intelligent vehicle from entering irregular paths such as "long and narrow" or "with too many corners."

[0129] Then, the intelligent vehicle's control unit can further filter the initially planned path based on thresholds for the length of continuous straight sections and turning angles in the initial planned path, determining that the path smoothness of the target shape path meets a preset threshold. Specifically, the intelligent vehicle's control unit can acquire the turning frequency, turning angle, and length of continuous straight sections of the target shape path, and quantify these parameters. For example, the turning frequency, turning angle, and length of continuous straight sections of the target shape path can be input into a preset path smoothness quantification scoring model to obtain the path smoothness of each target shape path.

[0130] Then, the control unit of the intelligent vehicle can select the target shape path with a path smoothness greater than a preset smoothness threshold as a candidate planning path.

[0131] The technical solution of this embodiment obtains the current vehicle location of the intelligent vehicle, determines the area division type of the area where the intelligent vehicle is located based on the current vehicle location, and then determines the path shape type corresponding to the area division type based on a preset mapping relationship. The preset mapping relationship records the mapping relationship between different area division types and corresponding path shape types. In the initial planned path, a target shape path matching the path shape type is selected to obtain a candidate planned path. This can effectively combine the road network characteristics of the area where the intelligent vehicle is located to adapt the path shape of the candidate planned path, avoid cruise paths that pose a risk to passengers or affect the passenger experience, effectively improve the rationality and safety of cruise paths, enhance the controllability of planning, facilitate strategic management of different areas, and optimize the passenger comfort of aimless cruise routes.

[0132] In an exemplary embodiment, when the current driving scenario associated with the preset driving mode is a sightseeing scenario, an initial planned route is generated based on the route planning start point and the route planning range, including: obtaining map data associated with the route planning range; determining the vehicle's transit points within the route planning range based on the scenic area information in the map data; matching the vehicle transit points with the scenic spots within the route planning range; generating a cruise route that uses the route planning start point as the initial driving point, passes through at least one vehicle transit point, and returns to the route planning start point, thereby obtaining the initial planned route.

[0133] The driving scenarios associated with the aforementioned preset driving modes can include fatigue relaxation scenarios, sightseeing scenarios, waiting to pick up passengers scenarios, and parking scenarios.

[0134] In practice, when the current driving scenario associated with the preset driving mode is a scenic spot sightseeing scenario, the control unit of the intelligent vehicle can obtain the map data associated with the route planning range. This map data is a high-precision map specifically for scenic spots, which includes information on all scenic spots within the scenic area (such as flower sea scenic spots, lake scenic spots, and mountain forest scenic spots), scenic road information, parking information, etc.

[0135] Then, the intelligent vehicle's control unit can determine the vehicle's route locations within the route planning range based on the scenic area information in the map data. These route locations are matched with the attractions within the scenic area. Specifically, the determined route locations are: the entrance to the flower sea attraction, the roads around the viewing platform of the lake attraction, and the roads around the entrance to the mountain forest attraction trail. All three route locations are within the scenic area where vehicles are allowed to pass and can enjoy the views.

[0136] Then, the intelligent vehicle's control unit can use the route planning starting point (e.g., the vehicle's current location) as the initial driving point, and generate multiple initial planned routes by taking a cruise route through at least one location the vehicle passes through and returning to the route planning starting point: for example, initial planned route 1 (vehicle's current location A → entrance to the flower sea scenic spot → surrounding area of ​​the lake view viewing platform → vehicle's current location A), and initial planned route 2 (vehicle's current location A → surrounding area of ​​the mountain forest scenic trail entrance → entrance to the flower sea scenic spot → vehicle's current location A). Both routes are closed-loop cruise routes, allowing the occupants of the intelligent vehicle to enjoy the core scenic spots within the area.

[0137] When the preset driving mode is associated with a fatigue-relaxation scenario, the intelligent vehicle's control unit can also control the vehicle's air conditioning, fragrance, window, seat, music playback, and ambient lighting components to perform corresponding actions to improve the matching degree between the vehicle's interior environment and the fatigue-relaxation scenario. For example, the air conditioning component can simulate natural wind, the fragrance component can release soothing scents such as lavender, the windows and sunroof can be opened, the seat massage function can be activated, and the ambient lighting can be turned on. Music that matches the driving rhythm can also be played, and the volume of the music can be dynamically adjusted according to the vehicle speed.

[0138] The technical solution of this embodiment obtains map data associated with the route planning range and determines the vehicle passage points that match the attractions in the route planning range based on the scenic area information in the map data. By generating a cruise route that takes the route planning start point as the initial driving point, passes through at least one vehicle passage point, and returns to the route planning start point, at least one suitable scenic spot tour route can be effectively planned within the route planning range. This effectively improves the ability of intelligent vehicles to adapt to scenic spot sightseeing scenarios when performing tasks without a fixed transportation destination.

[0139] In an exemplary embodiment, when the driving scenario associated with the preset driving mode is a waiting scenario for picking up someone, the method further includes: obtaining the estimated waiting time and target waiting location of the waiting scenario for picking up someone; in response to the intelligent vehicle entering the preset driving mode for a duration that meets the waiting time, triggering the intelligent vehicle to end the preset driving mode and controlling the intelligent vehicle to drive to the target waiting location.

[0140] In practical implementation, when the preset driving mode is associated with a waiting scenario, the intelligent vehicle's control unit can obtain the estimated waiting time and target waiting location for that scenario. Specifically, the control unit can identify the estimated waiting time and target waiting location based on the voice or communication software interaction information of the occupants. For example, if an occupant says to the intelligent vehicle, "I need to wait for Xiaohong at location A for 30 minutes," the control unit can recognize this voice using a large language model and determine the estimated waiting time as "30 minutes" and the target waiting location as "location A."

[0141] Then, the control unit of the intelligent vehicle can record the duration of the intelligent vehicle in the preset driving mode (i.e., roaming time). When the duration of entering the preset driving mode meets the waiting time, the intelligent vehicle is triggered to end the preset driving mode, and the intelligent driving system of the intelligent vehicle is used to control the intelligent vehicle to drive to the target waiting location.

[0142] The technical solution of this embodiment obtains the estimated waiting time and target waiting location of the pick-up waiting scenario, and triggers the intelligent vehicle to end the preset driving mode when the waiting time is met, and controls the intelligent vehicle to drive to the target waiting location. This enables the intelligent vehicle to effectively and timely identify the conditions for exiting the preset driving mode in the pick-up waiting scenario, further reducing the driver's operation and improving the intelligence level of the intelligent vehicle.

[0143] In an exemplary embodiment, when the driving scenario associated with the preset driving mode is a parking space waiting scenario, the method further includes: while the intelligent vehicle is in the preset driving mode, controlling the intelligent vehicle to search for the existence of a target parking space in a parking lot within a preset range; the target parking space is a parking space in which the intelligent vehicle can park; in response to the intelligent vehicle finding a target parking space in the parking lot, triggering the intelligent vehicle to end the preset driving mode and controlling the intelligent vehicle to park in the target parking space.

[0144] In practice, when the driving scenario associated with the preset driving mode is a parking space waiting scenario, the user can control the intelligent vehicle to be in the preset driving mode when the parking lot within the preset range is temporarily full. While the intelligent vehicle is in the preset driving mode, it can also obtain parking space information of the parking lot within the preset range in real time, and search for parking spaces (i.e., target parking spaces) within the preset range based on the parking space information.

[0145] Then, in response to finding the target parking space, the control unit of the intelligent vehicle can trigger the intelligent vehicle to end the preset driving mode and use the intelligent driving system of the intelligent vehicle to control the intelligent vehicle to park in the target parking space.

[0146] The technical solution of this embodiment, when the driving scenario associated with the preset driving mode is a parking space waiting scenario, controls the intelligent vehicle to search for the existence of a target parking space in a parking lot within a preset range while the intelligent vehicle is in the preset driving mode. In response to the intelligent vehicle finding a target parking space in the parking lot, the intelligent vehicle is triggered to end the preset driving mode and is controlled to park in the target parking space. This can effectively avoid illegal parking when the parking lot within the preset range is temporarily full of vehicles, and can also promptly and effectively control the intelligent vehicle to park in a parking space within the preset range where there is a parking space that the intelligent vehicle can park in, thereby saving energy consumption and improving the intelligence level of the intelligent vehicle.

[0147] In an exemplary embodiment, when the driving scenario associated with the preset driving mode is a passenger relaxation scenario, the method further includes: obtaining the driving experience quantification value corresponding to each candidate planned path; sorting each candidate planned path according to the driving experience quantification value corresponding to each candidate planned path to obtain the sorted candidate planned path; and displaying the sorted candidate planned path through the display device of the intelligent vehicle.

[0148] Among them, the driving experience quantification value is obtained by mapping the road greening quantification information, road landscape quantification information, road environment quantification information, and road noise quantification information associated with the corresponding candidate planning paths.

[0149] In practice, when the driving scenario associated with the preset driving mode is a passenger relaxation scenario, the control unit of the intelligent vehicle can obtain the driving experience quantification value corresponding to each candidate planned path.

[0150] Among them, quantitative information on road greening can refer to the green view rate; quantitative information on road landscape can refer to the landscape value; quantitative information on road environment can refer to the road environment quality score; and quantitative information on road noise can refer to the dynamic quietness index.

[0151] The process of obtaining the green view rate (i.e., the proportion of green landscape) associated with a candidate planning path can be achieved through the following steps: Historical image data collected by vehicle-mounted cameras or street view map APIs can be used to acquire several road street view images associated with the candidate planning path at a preset sampling distance (e.g., every 10 meters). Then, for each road street view image, a pre-trained green area recognition model can be used to identify the green areas (i.e., areas including green plants) within the road street view image. Based on the proportion of the green area to the road street view image, the proportion of the green area in each road street view image can be determined. Finally, the green view rate associated with the candidate planning path can be determined based on the average proportion of the green area corresponding to the several road street view images associated with the candidate planning path.

[0152] To obtain the landscape value (i.e., the proportion of natural and cultural landscapes) associated with a candidate planning path, the following steps can be taken: Historical image data collected by vehicle-mounted cameras or street view map APIs can be used to acquire several street view images associated with the candidate planning path at a preset sampling distance (e.g., every 10 meters). Then, for each street view image, a pre-trained scenic area recognition model can be used to identify whether there are scenic areas (i.e., visible areas including natural landscapes (river / lake views) or distinctive buildings) in the street view image. Then, the number of street view images containing scenic areas can be counted. Based on the ratio between the number of such images and the total number of images in the street view images, the landscape value associated with the candidate planning path can be determined, thus analyzing the visualization degree of natural landscapes (river / lake views) or distinctive buildings on both sides of the road segment and obtaining the landscape value.

[0153] Obtaining the road environment quality score associated with candidate planned paths can be achieved through the following steps: First, historical traffic data of the candidate planned paths can be used to assess road smoothness, resulting in an initial road environment quality score. Then, the brightness of the candidate planned paths during the planned roaming period can be obtained, and the road environment quality score can be corrected based on this brightness to obtain the final road environment quality score. In practical applications, the road environment quality score is based on a percentage system. Specifically, when the planned roaming period falls during daytime, the area of ​​shadows cast by surrounding objects on the candidate planned paths during the current time period can be obtained by calling the map API. This shadow area can then be mapped to a natural light correction score. The final road environment quality score is obtained by summing the natural light correction score and the initial road environment quality score. Specifically, when the current ambient temperature is above a preset temperature threshold, the shadow area is positively correlated with the natural light correction score; when the current ambient temperature is below or equal to the preset temperature threshold, the shadow area is negatively correlated with the natural light correction score. When the planned roaming period falls during nighttime, nighttime lighting data for candidate routes can be obtained by calling the map API (nighttime lighting is used to quantify the brightness of streetlights on candidate routes). This nighttime lighting data can then be mapped to a road light correction score. The final road environment quality score is obtained by summing the road light correction score and the initial road environment quality score. Nighttime lighting data is positively correlated with the road light correction score. For example, given two roads, one bumpy and one smooth (a newly constructed, wide road), the smoother road is prioritized to improve the user experience. Similarly, in summer, areas with large tree canopies are prioritized to avoid direct sunlight. Furthermore, when users are taking a walk at night, roads with more streetlights are prioritized to ensure safety and a pleasant atmosphere during nighttime roaming.

[0154] To obtain the dynamic quietness index associated with candidate planned routes, the following steps can be taken: Real-time traffic flow data can be accessed to predict or reflect the quietness of the candidate planned route during the planned roaming period, thus obtaining the dynamic quietness index. Routes with sparse traffic flow are prioritized to ensure a stress-relieving and quiet experience for users. Specifically, based on traffic flow data, the quantified traffic flow value (e.g., traffic density) and road noise level (road decibels) of the candidate planned route can be determined. Then, the quantified traffic flow value and road noise level of the candidate planned route are weighted and summed to obtain the quantified noise value of the candidate planned route, which serves as the dynamic quietness index associated with the candidate planned route.

[0155] Then, the intelligent vehicle's control unit can map the aforementioned green view rate, landscape value, road environmental quality score, and dynamic quietness index to obtain a quantitative value for the driving experience of the candidate planned route. Specifically, the intelligent vehicle's control unit can convert the green view rate into a road green view score (out of 100), the landscape value into a road landscape score (out of 100), and the dynamic quietness index into a road quietness score (out of 100). Then, the intelligent vehicle's control unit can sum the road green view score, road landscape score, road environmental quality score, and road quietness score to obtain a quantitative value for the driving experience of the candidate planned route.

[0156] The technical solution of this embodiment obtains the driving experience quantification value corresponding to each candidate planning path. This driving experience quantification value is obtained by mapping the road greening quantification information, road landscape quantification information, road environment quantification information, and road noise quantification information associated with the corresponding candidate planning path. By sorting the candidate planning paths according to the driving experience quantification value corresponding to each candidate planning path, the sorted candidate planning paths are obtained. The sorted candidate planning paths are displayed through the display device of the intelligent vehicle, thereby recommending candidate planning paths with better driving experience to the user, allowing the user to instruct the intelligent vehicle to drive on roads with better driving experience.

[0157] In an exemplary embodiment, during the process of the intelligent vehicle traveling according to the target planned path, the method further includes: replanning the untraveled paths of the intelligent vehicle in the target planned path according to a preset path update cycle to obtain a new target planned path; and controlling the intelligent vehicle to travel according to the new target planned path.

[0158] In practice, while the intelligent vehicle is traveling along the target planned path, it can replan the untraveled paths within the target planned path according to a preset path update cycle (e.g., every 10 minutes) to obtain a new target planned path. During the replanning of the untraveled paths within the target planned path, the intelligent vehicle can return to the step of generating an initial planned path based on the path planning starting point and path planning range, and then select a new target planned path from the initial planned path.

[0159] In addition, the intelligent vehicle can also respond to the detection of a preset detour event on the untraveled path in the target planned path, replan the untraveled path of the intelligent vehicle to obtain a new target planned path, and control the intelligent vehicle to drive according to the new target planned path.

[0160] Specifically, intelligent vehicles can also acquire real-time traffic information and, based on this information, detect whether there are pre-set detour events on the untraveled paths within the target planned path. If pre-set detour events exist on the untraveled paths within the target planned path, the untraveled paths can be replanned to obtain a new target planned path. During the replanning process of the untraveled paths within the target planned path, the intelligent vehicle can return to the step of generating an initial planned path based on the path planning start point and path planning range, and then select a new target planned path from the initial planned path.

[0161] The above technical solution has the following advantages or effects: During the process of intelligent vehicles traveling according to the target planned path, by detecting whether there are preset detour events, such as traffic accidents or temporary traffic control, on the untraveled paths of the intelligent vehicles in the target planned path based on real-time traffic data, and by replanning the untraveled paths of the intelligent vehicles to obtain a new target planned path, the intelligent vehicles can be controlled to travel according to the new target planned path, which can effectively reduce the probability of intelligent vehicles entering congested road sections.

[0162] In one exemplary embodiment, such as Figure 3 As shown, a vehicle driving path control method is provided, which is applied to... Figure 1 Taking the control unit of a smart vehicle as an example, the explanation includes the following steps:

[0163] Step S310: In response to the intelligent vehicle meeting the triggering conditions for entering the preset driving mode, obtain the starting point and range of the path planning.

[0164] Step S320: Generate an initial planned route based on the route planning starting point and route planning range; each initial planned route is a cruise route without a fixed transportation destination.

[0165] Step S330: According to the preset driving mode matching path filtering conditions, the initial planned path is filtered to obtain candidate planned paths.

[0166] When the path filtering condition is the path shape filtering condition, step S330 includes:

[0167] Step S3312: Determine the area division type of the area where the intelligent vehicle is located based on the current vehicle position; Step S3314: Determine the path shape type corresponding to the area division type based on the preset mapping relationship; The preset mapping relationship records the mapping relationship between different area division types and corresponding path shape types; Step S3316: Select the target shape path that matches the path shape type in the initial planning path to obtain the candidate planning path.

[0168] When the path filtering condition is path length, step S330 includes:

[0169] Step S3322: Obtain the set average speed and set driving time of the intelligent vehicle in the preset driving mode; Step S3324: Determine the predicted driving distance based on the set average speed and set driving time; Step S3326: Select the target length path from the initial planned path based on the predicted driving distance to obtain the candidate planned path.

[0170] When the path filtering condition is a path type filtering condition, step S330 includes:

[0171] Step S3332: Obtain traffic description data for each initial planned path; Step S3334: Identify target type paths in the initial planned paths based on the traffic description data for each initial planned path; Target type paths include at least a preset road entrance or a preset traffic sign; Step S3336: Eliminate target type paths from the initial planned paths to obtain candidate planned paths.

[0172] When the path filtering condition is a path speed limit filtering condition, step S330 includes:

[0173] Step S3342: Obtain the speed limit information of each initial planned path; Step S3344: Obtain the preset driving speed limit range; Step S3346: Based on the speed limit information and driving speed limit range of each initial planned path, select the target speed limit path from the initial planned paths to obtain the candidate planned path.

[0174] Step S340: In response to the instruction to select the target planned path among the candidate planned paths, control the intelligent vehicle to drive according to the target planned path.

[0175] It should be noted that the specific limitations of the above steps can be found in the specific limitations of a vehicle driving path control method described above, and will not be repeated here.

[0176] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0177] Based on the same inventive concept, this application also provides a vehicle driving path control device for implementing the vehicle driving path control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle driving path control device embodiments provided below can be found in the limitations of the vehicle driving path control method described above, and will not be repeated here.

[0178] In one exemplary embodiment, such as Figure 4 As shown, a vehicle driving path control device is provided, comprising:

[0179] The response module 410 is used to obtain the path planning start point and path planning range in response to the intelligent vehicle meeting the trigger conditions for entering the preset driving mode.

[0180] The generation module 420 is used to generate an initial planned path based on the starting point of the path planning and the path planning range; each of the initial planned paths is a cruise path without a fixed transportation destination;

[0181] The filtering module 430 is used to determine the area division type of the area where the intelligent vehicle is located, and to filter the initial planned path according to the path shape filtering conditions corresponding to the area division type to obtain candidate planned paths; the path shape of the candidate planned path and the area division type satisfy a preset mapping relationship; the preset mapping relationship records the mapping relationship between different area division types and the corresponding path shapes;

[0182] The control module 440 is used to control the intelligent vehicle to travel according to the target planned path in response to the selection instruction of the target planned path among the candidate planned paths.

[0183] In one embodiment, the candidate planned path also meets at least one of the following conditions:

[0184] The longest driving distance of each candidate planned path is greater than or equal to the predicted driving distance, and the shortest driving distance of each candidate planned path is less than or equal to the predicted driving distance. The predicted driving distance is determined based on the set average speed and set driving time of the intelligent vehicle in the preset driving mode.

[0185] or,

[0186] The permissible driving speed of the candidate planned path is within the driving speed limit range preset by the preset driving mode;

[0187] or,

[0188] The permitted travel time for the candidate planned routes includes the current time;

[0189] or,

[0190] The candidate planned path is not configured with a preset road entrance or preset traffic sign; the preset road entrance is a road entrance whose maximum speed limit is greater than the maximum driving speed limit associated with the preset driving mode; the preset traffic sign includes at least one of the following: accident-prone road section traffic sign, construction road section traffic sign, one-way traffic sign, or no-entry road section traffic sign.

[0191] In one embodiment, when the driving scenario associated with the preset driving mode is a sightseeing scenario, the generation module 420 is used to obtain map data associated with the path planning range; determine the vehicle's transit points in the path planning range based on the scenic area information in the map data; match the vehicle's transit points with the scenic spots in the path planning range; generate a cruise route that takes the path planning starting point as the initial driving point, passes through at least one of the vehicle's transit points, and returns to the path planning starting point, thereby obtaining the initial planned route.

[0192] In one embodiment, when the driving scenario associated with the preset driving mode is a pick-up waiting scenario, the device is further configured to obtain the estimated waiting time and target waiting location of the pick-up waiting scenario; in response to the intelligent vehicle entering the preset driving mode for a duration that meets the waiting time, the device triggers the intelligent vehicle to end the preset driving mode and controls the intelligent vehicle to drive to the target waiting location.

[0193] When the driving scenario associated with the preset driving mode is a parking space waiting scenario, the device is further configured to control the intelligent vehicle to search for a target parking space in a parking lot within a preset range while the intelligent vehicle is in the preset driving mode; the target parking space is a parking space in which the intelligent vehicle can park; in response to the intelligent vehicle finding the target parking space in the parking lot, the device triggers the intelligent vehicle to end the preset driving mode and controls the intelligent vehicle to park in the target parking space.

[0194] In one embodiment, when the driving scenario associated with the preset driving mode is a passenger relaxation scenario, the device is further configured to obtain a driving experience quantification value corresponding to each of the candidate planning paths; the driving experience quantification value is obtained by mapping the road greening quantification information, road landscape quantification information, road environment quantification information, and road noise quantification information associated with the corresponding candidate planning path; the candidate planning paths are sorted according to the driving experience quantification value corresponding to each candidate planning path to obtain the sorted candidate planning paths; the sorted candidate planning paths are displayed through the display device of the intelligent vehicle.

[0195] In one embodiment, while the intelligent vehicle is traveling along the target planned path, the device is further configured to replan the untraveled paths of the intelligent vehicle in the target planned path according to a preset path update cycle, to obtain a new target planned path; and control the intelligent vehicle to travel along the new target planned path.

[0196] or,

[0197] The device is further configured to, in response to detecting the presence of the preset detour event on an untraveled path of the intelligent vehicle in the target planned path, replan the untraveled path of the intelligent vehicle to obtain a new target planned path; and control the intelligent vehicle to travel according to the new target planned path.

[0198] In one embodiment, the filtering module 430 is configured to query the path shape type corresponding to the area division type of the area where the intelligent vehicle is located from the preset mapping relationship; select a target shape path that matches the path shape type from the initial planned path; obtain the path smoothness of the target shape path; the path smoothness is obtained by quantifying the turning frequency, turning angle and continuous straight length of the target shape path; and determine the candidate planned path from the target shape path according to the path smoothness of the target shape path.

[0199] Each module in the aforementioned vehicle driving path control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0200] In one exemplary embodiment, an intelligent vehicle is provided, the internal structure of which can be as follows: Figure 5 As shown, the intelligent vehicle includes a processor and a memory. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium storing a computer program. When executed by the processor, the computer program implements an intelligent vehicle control method.

[0201] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the intelligent vehicle to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0202] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0203] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described method embodiments.

[0204] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0205] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0206] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program mentioned can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic resistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0207] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0208] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle travel path control method, characterized in that, The method includes: In response to the intelligent vehicle meeting the triggering conditions for entering a preset driving mode, the starting point and range of the route planning are obtained; the preset driving mode is a driving mode without a fixed transportation destination. Based on the starting point and the scope of the path planning, multiple initial planned paths are generated; The region division type of the area where the intelligent vehicle is located is determined. According to the path shape filtering conditions corresponding to the region division type, the initial planned path is filtered to obtain candidate planned paths. The path shape of the candidate planned path satisfies a preset mapping relationship with the region division type. The preset mapping relationship records the mapping relationship between different region division types and the corresponding path shapes. In response to the instruction to select a target planned path from the candidate planned paths, the intelligent vehicle is controlled to drive according to the target planned path.

2. The method according to claim 1, characterized in that, The candidate planning path also meets at least one of the following conditions: The longest driving distance of each candidate planned path is greater than or equal to the predicted driving distance, and the shortest driving distance of each candidate planned path is less than or equal to the predicted driving distance. The predicted driving distance is determined based on the set average speed and set driving time of the intelligent vehicle in the preset driving mode. or, The permissible driving speed of the candidate planned path is within the driving speed limit range preset by the preset driving mode; or, The permitted travel time for the candidate planned routes includes the current time; or, The candidate planned path is not configured with a preset road entrance or preset traffic sign; the preset road entrance is a road entrance whose maximum speed limit is greater than the maximum driving speed limit associated with the preset driving mode; the preset traffic sign includes at least one of the following: accident-prone road section traffic sign, construction road section traffic sign, one-way traffic sign, or no-entry road section traffic sign.

3. The method according to claim 1 or 2, characterized in that, When the driving scenario associated with the preset driving mode is a sightseeing scenario, the generation of multiple initial planned routes based on the route planning starting point and the route planning range includes: Obtain map data associated with the route planning area; determine the vehicle's transit points within the route planning area based on the scenic spot information in the map data; match the vehicle's transit points with the scenic spots within the route planning area; Generate a cruise route that uses the route planning start point as the initial driving point, passes through at least one location the vehicle travels through, and returns to the route planning start point, thus obtaining the initial planned route.

4. The method according to claim 1 or 2, characterized in that, When the driving scenario associated with the preset driving mode is a waiting scenario for picking someone up, the method further includes: Obtain the estimated waiting time and target waiting location for the pickup scenario; In response to the intelligent vehicle entering the preset driving mode for a duration that meets the expected waiting time, the intelligent vehicle is triggered to end the preset driving mode and is controlled to drive to the target waiting location; When the driving scenario associated with the preset driving mode is a parking space waiting scenario, the method further includes: While the intelligent vehicle is in the preset driving mode, the intelligent vehicle is controlled to search for a target parking space in a parking lot within a preset range; the target parking space is a parking space in which the intelligent vehicle can park. In response to the intelligent vehicle finding the target parking space in the parking lot, the intelligent vehicle is triggered to end the preset driving mode and park itself in the target parking space.

5. The method according to claim 1 or 2, characterized in that, When the driving scenario associated with the preset driving mode is a passenger relaxation scenario, the method further includes: Obtain the driving experience quantification value corresponding to each of the candidate planning paths; the driving experience quantification value is obtained by mapping the road greening quantification information, road landscape quantification information, road environment quantification information and road noise quantification information associated with the corresponding candidate planning path; According to the driving experience quantification value corresponding to each candidate planning path, the candidate planning paths are sorted to obtain the sorted candidate planning paths. The sorted candidate planned paths are displayed on the display device of the intelligent vehicle.

6. The method according to claim 1, characterized in that, During the process of the intelligent vehicle traveling along the target planned path, the method further includes: According to a preset path update cycle, the untraveled paths of the intelligent vehicle in the target planned path are replanned to obtain a new target planned path; Control the intelligent vehicle to travel along the new target planned path; or, In response to detecting a preset detour event in the untraveled path of the intelligent vehicle in the target planned path, the untraveled path of the intelligent vehicle in the target planned path is replanned to obtain a new target planned path; Control the intelligent vehicle to travel along the new target planned path.

7. The method according to claim 1, characterized in that, The step of filtering the initial planned path according to the path shape filtering conditions corresponding to the region division type to obtain candidate planned paths includes: From the preset mapping relationship, retrieve the path shape type corresponding to the region division type of the area where the intelligent vehicle is located; Select a target shape path that matches the path shape type in the initial planning path; The path smoothness of the target shape path is obtained; the path smoothness is obtained by quantifying the turning frequency, turning angle and continuous straight length of the target shape path. The candidate planning path is determined from the target shape path according to the path smoothness of the target shape path.

8. A vehicle travel path control device, characterized in that, The device includes: The response module is used to respond to the triggering conditions of the intelligent vehicle entering the preset driving mode and obtain the starting point and range of the route planning; the preset driving mode is a driving mode without a fixed transportation destination. The generation module is used to generate an initial planned path based on the starting point of the path planning and the scope of the path planning; each initial planned path is a cruise path without a fixed transportation destination; The filtering module is used to determine the area division type of the area where the intelligent vehicle is located, and to filter the initial planned path according to the path shape filtering conditions corresponding to the area division type to obtain candidate planned paths; the path shape of the candidate planned path satisfies a preset mapping relationship with the area division type; the preset mapping relationship records the mapping relationship between different area division types and the corresponding path shapes; The control module is used to control the intelligent vehicle to travel according to the target planned path in response to the selection instruction of the target planned path among the candidate planned paths.

9. An intelligent vehicle, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images