Driving memory method, device, equipment and medium

Abstract

The invention discloses a driving memory method, device and equipment and a medium, and the method comprises the steps: judging whether any lane segment in a current navigation path is on a target road segment, recording the target road segment in a parking road segment record, and recording the parking road segment record as a parking condition record with a time stamp generated after a target vehicle travels from the target road; representing that a stopped vehicle exists in a target road section of the target road within a target time period of the time mark, and the current navigation path is the navigation path of the first vehicle in driving; if any lane segment in the current navigation path is on the target road section, the current time is in the target time period, and a stopped vehicle is judged to exist on the target road section according to the sensing data of the first vehicle, bypassing the second vehicle; and if any lane segment in the current navigation path is not on the target road section, driving according to the current navigation path. In this way, wrong decisions generated when the vehicle encounters the static vehicle in the running process can be reduced, and the decision success rate is increased.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and particularly relates to a memory driving method, device, equipment and medium. Background Art

[0002] Currently, when starting intelligent driving in the city, there will be situations where there are stationary vehicles in the lane. It is usually difficult for ordinary visual cameras to detect the vehicles ahead. Therefore, it is difficult to determine whether these vehicles are parked by the roadside with the engine off or waiting for a red light, which may lead to incorrect decisions.

[0003] Therefore, how to reduce the incorrect decisions generated when encountering stationary vehicles during vehicle driving and improve the decision-making success rate is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a memory driving method, device, equipment and medium, which can reduce the incorrect decisions generated when encountering stationary vehicles during vehicle driving and improve the decision-making success rate. The specific solutions are as follows:

[0005] In the first aspect, this application discloses a memory driving method, including:

[0006] Judge whether any lane segment in the current navigation path is on the target road segment, where the target road segment is recorded in the parking road segment record, and the parking road segment record is a time-stamped parking situation record generated after the target vehicle has driven through the target road, indicating that there are stopped vehicles in the target road segment of the target road during the target time period marked by the time stamp. The target road segment is a road segment in the target lane, and the current navigation path is the navigation path of the first vehicle during driving;

[0007] If any lane segment in the current navigation path is on the target road segment, the current time is within the target time period, and it is determined through the perception data of the first vehicle that there are stopped vehicles on the target road segment, then bypass the second vehicle, where the second vehicle is the stopped vehicle determined based on the perception data to be on the target road segment;

[0008] If none of the lane segments in the current navigation path are on the target road segment, then drive according to the current navigation path.

[0009] Optionally, it further includes:

[0010] If any lane segment in the current navigation path is on the target road segment, the current time is not within the target time period, and it is determined through the perception data of the first vehicle that there are stopped vehicles on the target road segment, then judge whether the preset bypass condition is satisfied based on a preset probability function;

[0011] If the preset detour condition is satisfied, the second vehicle is detoured; if the preset detour condition is not satisfied, the vehicle travels along the current navigation path.

[0012] Optionally, the preset probability function is a probability function determined based on the length of the target time period and a preset time cycle.

[0013] Optionally, if the preset detour condition is satisfied, it further includes:

[0014] Determine a first time range based on the time for detouring the second vehicle;

[0015] Modify the time mark of the target road section based on the first time range, so that the time mark of the target road section covers the first time range.

[0016] Optionally, if the preset detour condition is not satisfied, it further includes:

[0017] Determine a second time range based on the time for detouring the second vehicle;

[0018] If there is an overlapping period between the second time range and the target time period of the time mark, delete the overlapping period from the target time period.

[0019] Optionally, it further includes:

[0020] If any lane segment in the current navigation path is on the target road section, the current time is within the target time period, and it is determined based on the perception data of the first vehicle that there is no stopped vehicle on the target road section, then determine a third time range based on the travel time of the first vehicle on the target road section;

[0021] Determine the overlapping period between the third time range and the target time period of the time mark, and delete the overlapping period from the target time period.

[0022] Optionally, it further includes:

[0023] When the first vehicle travels to the target road, if there is no record of the parking road section, and it is determined based on the perception data of the first vehicle that there is a stopped vehicle on the target lane and the distance between the first vehicle and the stopped vehicle is equal to a preset distance threshold, then record the position where the stopped vehicle is located, and determine the target road section based on the positions of one or more stopped vehicles, and generate a parking road section record with a time mark;

[0024] Wherein, the distance between any adjacent vehicles among the multiple stopped vehicles is less than a preset distance range.

[0025] Second aspect, the present application discloses a memory driving device, including:

[0026] A first judgment module, configured to judge whether any lane segment in the current navigation path is on the target road segment, where the target road segment is recorded in the parking road segment record, and the parking road segment record is a time-stamped parking condition record generated after the target vehicle travels on the target road, indicating that there are stopped vehicles in the target road segment of the target road during the target time period marked by the time stamp, the target road segment is a road segment in the target lane, and the current navigation path is the navigation path of the first vehicle during driving;

[0027] A second judgment module, configured to judge whether the current time is within the target time period and judge whether there are stopped vehicles on the target road segment through the perception data of the first vehicle when the first judgment module determines that any lane segment in the current navigation path is on the target road segment;

[0028] A driving control module, configured to bypass the second vehicle if the first judgment module determines that any lane segment in the current navigation path is on the target road segment, and the second judgment module determines that the current time is within the target time period, and it is determined through the perception data of the first vehicle that there are stopped vehicles on the target road segment, where the second vehicle is the stopped vehicle on the target road segment determined based on the perception data; if the first judgment module determines that any lane segment in the current navigation path is not on the target road segment, drive according to the current navigation path.

[0029] Third aspect, the present application discloses an electronic device, including a memory and a processor, where:

[0030] The memory is used to store a computer program;

[0031] The processor is configured to execute the computer program to implement the foregoing memory driving method.

[0032] Fourth aspect, the present application discloses a computer-readable storage medium, used to store a computer program, where the computer program, when executed by a processor, implements the foregoing memory driving method.

[0033] Fifth aspect, the present application provides a computer program product, including computer programs / instructions, and when the computer programs / instructions are executed by a processor, the foregoing memory driving method is implemented.

[0034] As can be seen from the above solution, the present application provides a memory driving method, including: determining whether any lane segment in the current navigation path is on a target road segment, where the target road segment is recorded in a parking road segment record, and the parking road segment record is a time-stamped parking situation record generated after the target vehicle has traveled on the target road, indicating that there are stopped vehicles in the target road segment of the target road during the target time period marked by the time stamp. The target road segment is a road segment in the target lane, and the current navigation path is the navigation path of the first vehicle during driving; if any lane segment in the current navigation path is on the target road segment, the current time is within the target time period, and it is determined through the perception data of the first vehicle that there are stopped vehicles on the target road segment, then the second vehicle is bypassed, where the second vehicle is the stopped vehicle determined based on the perception data to be on the target road segment; if none of the lane segments in the current navigation path are on the target road segment, then drive according to the current navigation path.

[0035] It can be seen that the beneficial effect of the present application is that: in the case where any lane segment of the current navigation path is on the target road segment in the parking road segment record, if the current time is within the target time period marked by the record, and the perception data determines that there are stopped vehicles on the recorded target road segment, it indicates that the stopped vehicles are stationary rather than pausing at traffic lights. Bypass the stopped vehicles. In this way, by means of the parking road segment record of driving memory and making decisions in combination with perception data, it is possible to reduce incorrect decisions generated when the vehicle encounters stationary vehicles during driving and improve the decision success rate.

[0036] Correspondingly, a memory driving device, equipment, and readable storage medium provided by the present application also have the above technical effects. Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0038] Figure 1 It is a flowchart of a memory driving method provided by an embodiment of the present application;

[0039] Figure 2 It is a schematic diagram of road segmentation provided by an embodiment of the present application;

[0040] Figure 3 It is a schematic diagram of a memory driving scenario provided by an embodiment of the present application;

[0041] Figure 4A schematic diagram of vehicle lane change provided by an embodiment of the present application;

[0042] Figure 5 A schematic diagram of vehicle driving provided by an embodiment of the present application;

[0043] Figure 6 Another schematic diagram of vehicle driving provided by an embodiment of the present application;

[0044] Figure 7 Yet another schematic diagram of vehicle driving provided by an embodiment of the present application;

[0045] Figure 8 A schematic diagram of calculating the position of a stopped vehicle provided by an embodiment of the present application;

[0046] Figure 9 A schematic diagram of time marking provided by an embodiment of the present application;

[0047] Figure 10 A schematic diagram of the structure of a memory driving device provided by an embodiment of the present application;

[0048] Figure 11 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0049] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0050] See Figure 1 As shown, an embodiment of the present application discloses a memory driving method, including:

[0051] Step S11: Determine whether any lane segment in the current navigation path is on the target road section, where the target road section is recorded in the parking road section record, and the parking road section record is a time-marked parking situation record generated after the target vehicle has driven through the target road, indicating that there is a stopped vehicle in the target road section of the target road during the target time period marked by the time mark. The target road section is a road section in the target lane, and the current navigation path is the navigation path of the first vehicle during driving.

[0052] Among them, the current navigation path is the navigation path of the first vehicle, that is, the first vehicle is the vehicle itself. The navigation path can be composed of multiple lane segments. In the embodiments of the present application, the road can be divided into different road segments (i.e., items), each road segment includes multiple lane segments, each item can be numbered to obtain an item id, and each lane segment in each item can be numbered to obtain a lane id. The navigation path is composed of a certain lane segment in multiple adjacent items. As Figure 2 shown Figure 2 is a schematic diagram of a road segment provided by the embodiments of the present application. The lane item is the aforementioned item: the road is divided into segments, and each segment is sorted. The sorting result can be called the successor relationship. The length of each item is not fixed, but there will be a new item at the intersection / lane change (such as changing from 4 lanes to 5 lanes). Each road will be pre-segmented and sorted. Lane id: There are multiple lanes in each item. The lanes will generate ids in the left-right or right-left order, and the ids can also retrieve the left lane and the right lane.

[0053] In the embodiments of the present application, the parking section record can record the target section and the time mark of the target section. The time mark is the time mark corresponding to the target section. Each target section can correspond to a time mark of its own. In an alternative embodiment, one target section can correspond to one parking section record. In another alternative embodiment, one target road can correspond to one parking section record. The parking section record may contain one or more target sections, and each target section corresponds to a time mark respectively. The time mark can be indexed through the target section. In yet another alternative embodiment, all target roads can correspond to one parking section record. The index includes the target road and the target section, so as to locate the time mark corresponding to the target section.

[0054] The target section is the section where a stopped vehicle exists determined after the target vehicle travels through the target road. When there is a stopped vehicle, it can be the area occupied by the stopped vehicle in the target lane. When there are multiple stopped vehicles in the target lane, if the distance between any two adjacent vehicles is within the preset distance range, the target section is the area occupied by the multiple stopped vehicles. If the distance between any two adjacent vehicles is not within the preset distance range, the corresponding target sections will be determined respectively, that is, they will not be assigned to one target section. In this way, it can avoid the problem of frequent lane changes caused by a small distance between two adjacent vehicles. Although there is a certain space, changing lanes into this space and then changing lanes out again is required. For example, the preset distance range is the length of 3 road segments.

[0055] The target vehicle can be the first vehicle, i.e., the host vehicle itself, or it can be other vehicles, i.e., obtain information reported by other vehicles from the server. A parking section record is generated in the host vehicle, or a parking section record generated by the server based on the information reported by each vehicle is obtained from the server. That is to say, driving can be based on the driving memory of the host vehicle or on the shared memory of other vehicles.

[0056] The target road is a road with multiple lanes. The target lane can be the rightmost lane, which is the most common situation. That is, when intelligent driving is enabled in the city, it is often the case that there are stationary vehicles in the rightmost lane, and it is difficult for ordinary vision cameras to perceive the vehicles ahead. Therefore, it is difficult to determine whether these vehicles are parked with the engine off by the roadside or waiting for a red light on the right. As a result, there are often situations where the vehicle mistakenly changes lanes to the right or fails to change lanes to the right and continues to drive forward, resulting in a failed lane change. The embodiments of the present application can solve the problem of incorrect decision-making caused by the presence of parked vehicles in the rightmost lane. For example, refer to Figure 3 as shown Figure 3 which is a schematic diagram of a memory driving scenario provided by an embodiment of the present application. There are multiple vehicles parked in the rightmost lane.

[0057] The target time period is the time period marked after the target vehicle has traveled on the target road. It can be the time point when the position information of the first parked vehicle in the target section is recorded as the starting time, and the time point when the position information of the last stopped vehicle in the target section is recorded as the ending time. Expand the first preset time period forward from the starting time and expand the second preset time period backward from the ending time, and use the time period after the forward and backward expansions as the target time period. For example, expand 1 hour forward and backward respectively. It should be noted that due to the time expansion, the starting time and ending time before the expansion are not limited to the time points described above, and can be time points near the time points described above, such as time points with a preset time interval from the time point of the position information of the first parked vehicle as the starting time, and time points with a preset time interval from the time point of the position information of the last stopped vehicle as the ending time. The position information of the first parked vehicle in the target section can be recorded when the preset conditions are met, such as when the distance from the stopped vehicle is equal to the preset distance threshold, that is, when driving to a distance with a preset distance threshold from the stopped vehicle, start recording. This distance is the longitudinal distance, that is, the distance in the direction parallel to the lane.

[0058] In an alternative embodiment, when the first vehicle travels to the target road, if there is no parking section record, and based on the perception data of the first vehicle, it is determined that there is a stopped vehicle in the target lane, and when the distance between the first vehicle and the stopped vehicle is equal to a preset distance threshold, the position of the stopped vehicle is recorded, and the target section is determined based on the positions of one or more stopped vehicles, and a parking section record with a time stamp is generated; wherein, the distance between any adjacent vehicles among the multiple stopped vehicles is less than a preset distance range.

[0059] In the embodiments of the present application, the perception data is the data of the vehicle surrounding environment obtained based on in-vehicle sensors. The in-vehicle sensors may include radars, vision sensors, etc.

[0060] Among them, recording the position of the stopped vehicle may be the road segment where the vehicle is located, the lane segment in the road segment, the distance between the vehicle and the starting point of the lane segment, which may include a first distance and a second distance. The first distance is the distance from the frontmost point of the vehicle to the starting point of the lane segment, and the second distance is the distance from the rearmost point of the vehicle to the starting point of the lane segment. The distance is the longitudinal distance. For example, the frontmost point is the front bumper of the vehicle, and the rearmost point is the rear bumper of the vehicle. Further, the target section is determined based on the positions of one or more stopped vehicles. If there are multiple stopped vehicles, and the distance between any adjacent vehicles among the multiple stopped vehicles is less than a preset distance range. The target section is the section determined by the positions of the multiple stopped vehicles.

[0061] In an alternative embodiment, when the domain controller (i.e., the autonomous driving domain controller) starts to work, it checks whether there is a lane storage file in the domain controller, that is, the file corresponding to the parking section record. The parking section record can be saved in this file. If not, when the driver activates the function and changes lanes / drives towards a stationary target (i.e., a stationary vehicle), the system will record the start time t0, the lane item where the stationary target is located at the start time, and the length L from the starting point of the lane item. Among them, changing lanes means changing lanes from other lanes to the lane where the stationary target is located, and driving can mean being in the same lane as the stationary target. The judgment method adopted: when the program runs, the system will output a trajectory, which is composed of a series of points, and each point contains information such as the driving speed, acceleration, time t, and distance s (the longitudinal distance from the stationary target) and so on. When the position of the point at the end of the trajectory is behind the stationary vehicle (the judgment of the stationary vehicle is based on the position and speed of the perceived target to determine a flag bit), and the distance between the two vehicles is equal to the preset distance threshold, recording starts, and the current time is the start time t0. For example, see Figure 4 as shown Figure 4A schematic diagram of vehicle lane change provided by an embodiment of the present application. After the driver takes over, if the vehicle drives into a lane that is not on the navigation path or is not activated after 15 items, it is not recorded; otherwise, it is recorded. See Figure 5 as shown Figure 5 A schematic diagram of vehicle driving provided by an embodiment of the present application, Figure 6 Another schematic diagram of vehicle driving provided by an embodiment of the present application. The position of the blue vehicle represents the position where the vehicle function is reactivated, and then the black arrow represents the driving path of the vehicle. As described above, once the trajectory end point is behind the stationary vehicle, the intelligent driving vehicle will not detour, so the driver needs to take over the vehicle. After taking over, the driver may activate the function after changing lanes ( Figure 6 ), or may change lanes and bypass a row of stationary vehicles before reactivating ( Figure 5 ). In either case, the intelligent driving vehicle will record the position of the stationary vehicle. When it meets the condition of reactivating on the navigation path and is activated within 15 items, the information of the lane where the stationary vehicle is located is recorded.

[0062] Among them, the recording method can be: at time t0, obtain the position coordinates of the first stationary vehicle, the lane item where the vehicle is located at that time, and the length from the starting point of the lane item where the vehicle is located. Calculate the lane item where the stationary vehicle is located and the length from the starting point of the lane item where the vehicle is located according to the position of the vehicle itself (if it crosses lane items, it can also be calculated because the map will spit out the successor relationship of the lane and lane item). See Figure 7 as shown Figure 7 Another schematic diagram of vehicle driving provided by an embodiment of the present application. The purple vehicles are all stationary vehicles. Calculate the lane item where each purple vehicle is located and the length from the starting point of the lane item where the vehicle is located, including the length from the front and rear bumpers to the starting point of the lane item where the vehicle is located, and finally integrate them into a target section. That is, take the rear bumper of the nearest purple vehicle and the front bumper of the farthest purple vehicle as the target section (the farthest purple vehicle is given when the vehicle drives forward here, and only a schematic diagram is drawn here). If the rear bumper of the first vehicle is x1 meters away from the vehicle and the vehicle is still x2 meters away from the current lane item, if , directly hang the rear bumper vehicle on the current lane item and lane id, and calculate the hanging position (that is, the distance from the starting point of the current lane item). If , calculate the distance of x1 - x2 and hang it on the next lane item and lane (if it is necessary to calculate the next next lane item, it can be directly calculated). See Figure 8 as shown Figure 8A schematic diagram for calculating the position of a stopped vehicle provided by an embodiment of the present application. Similarly, calculate the lane items and lane IDs occupied by the front and rear bumpers of each vehicle, as well as the distance from the starting point of the current lane item.

[0063] In addition, Figure 7 In the example, multiple vehicles are relatively close. If the distance between two stopped vehicles is greater than one item or two items, that is, less than the preset distance range, then multiple stopped vehicles will also be included in the same target section to ensure the continuity of the target section and prevent the vehicle from changing lanes and then changing back between the two vehicles, resulting in the need to change lanes again.

[0064] Step S12: If any lane segment in the current navigation path is on the target section, the current time is within the target time period, and it is determined based on the perception data of the first vehicle that there is a stopped vehicle on the target section, then bypass the second vehicle, where the second vehicle is the stopped vehicle on the target section determined based on the perception data.

[0065] Among them, the current time is the time when the first vehicle travels to the target section, which can be the time point when the front of the vehicle (such as the front bumper of the vehicle) is flush with the starting point of the target section, or a time point near this time point, such as a time point within a preset time period before or after this time point. The regional range of the target section is obtained by recording in the parking section. If it is determined based on the perception data of the first vehicle that there is a stopped vehicle on the target section, then bypass the second vehicle. During the bypass process, it can start to bypass when it reaches a preset distance from the second vehicle, that is, the situation of the target section may change, so as to avoid bypassing too early.

[0066] Further, in an alternative embodiment, a time range can be determined based on the travel time of the first vehicle on the target section, and the non-overlapping part between the target time period and this time range is extended to the time mark of the target section. The travel time of the first vehicle on the target section can use the time point when the front of the first vehicle (such as the front bumper of the vehicle) is flush with the starting point of the target section as the starting time, and the time point when the rear of the first vehicle (such as the rear bumper of the vehicle) is flush with the end point of the target section as the end time. In the embodiment of the present application, a preset time period is extended forward based on the starting time, and a preset time period is extended backward based on the end time, and the time period after the front and rear extensions is used as the aforementioned time range. It should be noted that due to the time extension, the starting time and end time before the extension are not limited to the time points described above.

[0067] In an alternative embodiment, if any lane segment in the current navigation path is on the target road section, the current time is not within the target time period, and it is determined based on the perception data of the first vehicle that there is a stopped vehicle on the target road section, then it is determined whether the preset detour condition is satisfied based on a preset probability function; if the preset detour condition is satisfied, the second vehicle is detoured, and if the preset detour condition is not satisfied, the vehicle travels along the current navigation path.

[0068] That is, when the current time is not within the target time period and a stopped vehicle is detected on the target road section, it can be determined through a probability function whether the second vehicle is a stationary vehicle, that is, a vehicle that has stalled and parked by the roadside. If it is a stationary vehicle, the second vehicle is detoured. The preset probability function can be a probability function determined based on the length of the target time period. Through the probability function, parking situations can be identified more accurately, avoiding incorrect decisions.

[0069] In an alternative embodiment, the preset probability function is a probability function determined based on the length of the target time period and a preset time period.

[0070] Among them, the preset time period can be 1 day. That is, the target time period in the embodiments of the present application is a time period in a day, such as from 8:00 am to 10:00 am.

[0071] In an alternative embodiment, if the preset detour condition is satisfied, it further includes: determining a first time range based on the time for detouring the second vehicle; modifying the time mark of the target road section based on the first time range so that the time mark of the target road section covers the first time range.

[0072] Among them, the time for detouring the second vehicle can start at the time point when the front of the first vehicle (for example, the front bumper of the vehicle) is flush with the rear of the second vehicle (such as the rear bumper of the vehicle), and end at the time point when the rear of the first vehicle (such as the rear bumper of the vehicle) is flush with the front of the second vehicle (such as the front bumper of the vehicle). In the embodiments of the present application, a preset time period can be extended forward based on the start time point, and a preset time period can be extended backward based on the end time point. The time period after the forward and backward extensions is used as the first time range. It should be noted that due to the time extension, the start time point and end time point before the extension are not limited to the time points described above. In this way, the time mark of the target road section is modified based on the first time range so that the time mark of the target road section covers the first time range, expanding the target time period of the time mark. If there are multiple second vehicles, the end time is determined based on the last vehicle, and the distance between adjacent two of the multiple second vehicles is less than the preset distance range. That is, multiple second vehicles are detoured together.

[0073] In an alternative embodiment, if the preset bypass condition is not satisfied, it further includes: determining a second time range based on the time for bypassing the second vehicle; if there is an overlapping period between the second time range and the target time period of the time mark, deleting the overlapping period from the target time period.

[0074] Wherein, the time for bypassing the second vehicle may take the time point when the front of the first vehicle (such as the front bumper of the vehicle) is flush with the rear of the second vehicle (such as the rear bumper of the vehicle) as the start time, and the time point when the rear of the first vehicle (such as the rear bumper of the vehicle) is flush with the front of the second vehicle (such as the front bumper of the vehicle) as the end time. If there are multiple second vehicles, the end time is determined based on the last vehicle, and the distance between adjacent two of the multiple second vehicles is less than the preset distance range. In the embodiments of the present application, a preset time period may be extended forward based on the start time, and a preset time period may be extended backward based on the end time, and the time period after the forward and backward extensions is used as the second time range. It should be noted that due to the time extension, the start time and end time before the extension are not limited to the time points described above. In the process of deleting the overlapping period and extending the target time period of the time mark, the preset time period for determining the time range extension may be the same or different. For example, both are 1 hour before and after, or 1 hour before and after during the extension, and when deleting, the determined time range is 40 minutes before and after the extension. If the target time period is from 8 o'clock to 10 o'clock, and the second time range overlaps with this period from 8 o'clock to 8:50, then the target time period is modified to 8:50 to 10 o'clock.

[0075] In an alternative embodiment, if any lane segment in the current navigation path is on the target road section, the current time is within the target time period, and it is determined by the sensing data of the first vehicle that there is no stopped vehicle on the target road section, then a third time range is determined based on the driving time of the first vehicle on the target road section; the overlapping period between the third time range and the target time period of the time mark is determined, and the overlapping period is deleted from the target time period.

[0076] Wherein, the driving time of the first vehicle on the target road section may take the time point when the front of the first vehicle (such as the front bumper of the vehicle) is flush with the start of the target road section as the start time, and the time point when the rear of the first vehicle (such as the rear bumper of the vehicle) is flush with the end of the target road section as the end time. In the embodiments of the present application, a preset time period is extended forward based on the start time, and a preset time period is extended backward based on the end time, and the time period after the forward and backward extensions is used as the third time range. It should be noted that due to the time extension, the start time and end time before the extension are not limited to the time points described above.

[0077] If any lane segment in the current navigation path is on the target road section, the current time is not within the target time period, and it is determined based on the perception data of the first vehicle that there are no stopped vehicles on the target road section, then drive according to the current navigation path. Moreover, based on the driving time of the first vehicle on the target road section, determine the fourth time range, determine the overlapping period between the fourth time range and the target time period marked by the time marker, and delete this overlapping period from the target time period.

[0078] Step S13: If any lane segment in the current navigation path is not on the target road section, then drive according to the current navigation path.

[0079] That is to say, when the current navigation path does not involve the target road section in the parking road section record, just drive according to the current navigation path.

[0080] In an alternative embodiment, when the domain control starts to work, it is judged whether any lane segment in the current navigation path is on the recorded target road section. If not, drive normally according to the navigation. If so, then make the following judgments: within the target time period, if a stopped vehicle is sensed on the target road section, then expand the target time period when it is necessary to add a time marker; within the target time period, if it is sensed that there are no stopped vehicles on the target road section, then delete the corresponding time in the target time period based on the foregoing process. If outside the target time period and a stopped vehicle is sensed on the target road section, then judge whether the stopped vehicle is an extinguished and stationary vehicle according to the probability function. The probability function is , where M represents 24 hours. mk represents the recorded target time period. Then drive according to the regulations when P is greater than 0.5 (consider it a stationary vehicle and need to detour), consider expanding the target time period marked by the time marker, and when it is less than 0.5, consider it not a stationary vehicle and drive according to the current navigation path, considering deleting the overlapping period in the time marker. In this way, the influence of stationary vehicles on the lane-changing decision of the vehicle itself can be effectively avoided. For example, refer to Figure 9 as shown in Figure 9 FIG. is a schematic diagram of a time marker provided by an embodiment of the present application. The 24 hours of a day are represented by black circles. In the initial state, there are no marks. If it is judged that there is a stopped vehicle in the right lane of a certain road at a certain moment, then mark the target road section and the target time period in this road ( Figure 9During the time period indicated by the red arrow line), if the vehicle travels on the target road section for the second time and no stationary vehicle is found and the time overlaps, the corresponding overlapping time period is deleted. The green arrow line can indicate that the previously recorded time period has been deleted, that is, the deleted time period. If the current time is within the recorded time, which means that vehicle C1 travels on this road within a certain time (C1 points to the red part), it is defaulted that there is a stationary vehicle on the right, and a decision to avoid changing lanes to the right is required. C2 means that the vehicle does not reach the target road section within the target time period, and it is judged based on the probability function.

[0081] In this way, recording the lane item, lane id and position of the stationary vehicle can effectively identify the truly stationary vehicle, that is, the vehicle that has stalled and parked by the roadside. It can be updated in real time according to time and road section, and can adapt to scenarios such as construction and stationary vehicles at the school gate during morning and evening rush hours in real time. It can reduce the wrong decisions made by vehicles when encountering stationary vehicles under urban road conditions and improve the decision-making success rate. At the same time, it can update the previously recorded data and has strong real-time adaptability.

[0082] In addition, the embodiments of the present application support sharing. Although the vehicle itself has not traveled this section of the road, other vehicles have traveled this section of the road. The vehicle itself can obtain the data collected by other vehicles as if it has traveled by itself. Therefore, the parking section records stored in the domain controller can be shared to the cloud. Different vehicles can record together and cooperate to delete. The recording and deletion methods are as described in the foregoing content, except that the final storage and reading methods are in the cloud rather than in the domain controller.

[0083] It can be seen that in the case where any lane segment of the current navigation path is on the target road section in the parking section record, if the current time is within the target time period marked by the record and the sensing data determines that there is a stopped vehicle on the recorded target road section, it indicates that the stopped vehicle is stationary rather than pausing at a red light. Detour around the stopped vehicle. In this way, by means of the parking section record of driving memory and combining the sensing data for decision-making, the wrong decisions made by the vehicle when encountering stationary vehicles during driving can be reduced, and the decision-making success rate can be improved.

[0084] See Figure 10 As shown, the embodiments of the present application disclose a memory driving device, including:

[0085] The first judgment module 11 is used to judge whether any lane segment in the current navigation path is on the target road section, where the target road section is recorded in the parking section record, and the parking section record is a time-marked parking situation record generated after the target vehicle travels through the target road, indicating that there is a stopped vehicle in the target road section of the target road within the target time period marked by the time mark. The target road section is a section in the target lane, and the current navigation path is the navigation path of the first vehicle during driving;

[0086] A second determination module 12, configured to, when the first determination module determines that any lane segment in the current navigation path is on the target road section, determine whether the current time is within the target time period and determine whether there is a stopped vehicle on the target road section based on the perception data of the first vehicle;

[0087] A driving control module 13, configured to, if the first determination module determines that any lane segment in the current navigation path is on the target road section, and the second determination module determines that the current time is within the target time period, and it is determined through the perception data of the first vehicle that there is a stopped vehicle on the target road section, then bypass the second vehicle, where the second vehicle is the stopped vehicle on the target road section determined based on the perception data; if the first determination module determines that any lane segment in the current navigation path is not on the target road section, then drive according to the current navigation path.

[0088] Further, the device further includes:

[0089] A third determination module, configured to, if any lane segment in the current navigation path is on the target road section, the current time is not within the target time period, and it is determined through the perception data of the first vehicle that there is a stopped vehicle on the target road section, then determine whether a preset bypass condition is satisfied based on a preset probability function; correspondingly, the driving control module 13 is configured to, if the third determination module determines that the preset bypass condition is satisfied, then bypass the second vehicle, and if the third determination module determines that the preset bypass condition is not satisfied, then drive according to the current navigation path.

[0090] In an alternative embodiment, the preset probability function is a probability function determined based on the length of the target time period and a preset time period.

[0091] In an alternative embodiment, the device further includes a record adjustment module, configured to:

[0092] If the preset bypass condition is satisfied, determine a first time range based on the time for bypassing the second vehicle; modify the time mark of the target road section based on the first time range, so that the time mark of the target road section covers the first time range. If the preset bypass condition is not satisfied, determine a second time range based on the time for bypassing the second vehicle; if there is an overlapping period between the second time range and the target time period of the time mark, then delete the overlapping period from the target time period.

[0093] If any lane segment in the current navigation path is on the target road segment, the current time is within the target time period, and it is determined based on the perception data of the first vehicle that there are no stopped vehicles on the target road segment, then determine a third time range based on the driving time of the first vehicle on the target road segment; determine the overlapping period between the third time range and the target time period marked with a time mark, and delete this overlapping period from the target time period.

[0094] Further, the device further includes a recording module, configured to:

[0095] When the first vehicle travels to the target road, if there is no record of the parking road segment, and it is determined based on the perception data of the first vehicle that there is a stopped vehicle on the target lane, and the distance between the first vehicle and the stopped vehicle is equal to a preset distance threshold, then record the location where the stopped vehicle is located, and determine a target road segment based on the locations of one or more stopped vehicles, and generate a parking road segment record with a time mark; wherein, the distance between any two adjacent vehicles among the multiple stopped vehicles is less than a preset distance range.

[0096] See Figure 11 As shown, an electronic device 20 disclosed in an embodiment of the present application includes a processor 21 and a memory 22; wherein, the memory 22 is used to store a computer program; the processor 21 is used to execute the computer program, which is the memory driving method disclosed in the foregoing embodiments.

[0097] For the specific process of the above memory driving method, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0098] Moreover, the memory 22 as a carrier for storing resources can be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc., and the storage method can be short-term storage or permanent storage.

[0099] In addition, the electronic device 20 further includes a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26; wherein, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows is any communication protocol applicable to the technical solution of the present application, and no specific limitation is imposed on it here; the input / output interface 25 is used to obtain external input data or output data to the outside, and its specific interface type can be selected according to specific application requirements, and no specific limitation is imposed on it here.

[0100] Further, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program, wherein when the computer program is executed by a processor, it implements the memory driving method disclosed in the foregoing embodiments.

[0101] For the specific process of the above memory driving method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0102] Further, an embodiment of the present application also provides a computer program product, including a computer program / instructions, which when executed by a processor, implements the memory driving method disclosed in the foregoing embodiments.

[0103] For the specific process of the above memory driving method, reference may be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.

[0104] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference may be made to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and reference may be made to the description of the method part for related parts.

[0105] The steps of the methods or algorithms described in combination with the embodiments disclosed in this article can be implemented directly by hardware, software modules executed by a processor, or a combination of both. The software modules can be placed in a random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0106] The above has introduced in detail a memory driving method, device, equipment and medium provided by the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A memory driving method, characterized in that: include: Determine whether any lane segment in the current navigation path is on a target segment, wherein the target segment is recorded in a parking segment record, the parking segment record is a parking situation record with a time stamp generated after the target vehicle travels through the target road, indicating that within the target time period of the time stamp, there is a stopped vehicle in the target segment of the target road, the target segment is a segment in the target lane, and the current navigation path is the navigation path of the first vehicle in motion; If any lane segment in the current navigation path is on the target road segment, the current time is within the target time period, and it is determined by the perception data of the first vehicle that there is a stopped vehicle on the target road segment, then a second vehicle is detoured, wherein the second vehicle is a stopped vehicle on the target road segment determined based on the perception data; If any lane segment in the current navigation path is not on the target road segment, the vehicle travels according to the current navigation path.

2. The memory driving method according to claim 1, characterized in that: Also includes: If any lane segment in the current navigation path is on the target section, the current time is not within the target time period, and it is determined through the perception data of the first vehicle that there is a stopped vehicle on the target section, then determining whether a preset detour condition is met based on a preset probability function; If the preset detour condition is met, the second vehicle is detoured; if the preset detour condition is not met, the second vehicle is driven according to the current navigation path.

3. The memory driving method according to claim 2, characterized in that: The preset probability function is a probability function determined based on the length of the target time period and a preset time period.

4. The memory driving method according to claim 2, characterized in that: If the preset detour condition is met, the method further includes: determining a first time range based on the time to detour the second vehicle; The time stamp of the target road segment is modified based on the first time range so that the time stamp of the target road segment covers the first time range.

5. The memory driving method according to claim 2, characterized in that: If the preset detour condition is not met, the method further includes: determining a second time range based on the time to detour the second vehicle; If the second time range overlaps with the target time period of the time mark, the overlapping time period is deleted from the target time period.

6. The memory driving method according to claim 1, characterized in that: Also includes: If any lane segment in the current navigation path is on the target section, the current time is within the target time period, and it is determined through the perception data of the first vehicle that there is no stopped vehicle on the target section, determining a third time range based on the travel time of the first vehicle on the target section; An overlap period between the third time range and the target time period of the time mark is determined, and the overlap period is deleted from the target time period.

7. The memory driving method according to any one of claims 1 to 6, characterized in that: Also includes: When the first vehicle drives to the target road, if there is no parking section record, then based on the sensing data of the first vehicle, if it is determined that there is a stopped vehicle on the target lane, and the distance between the first vehicle and the stopped vehicle is equal to a preset distance threshold, then the position of the stopped vehicle is recorded, and the target section is determined based on the positions of one or more stopped vehicles, and a parking section record with a time stamp is generated; Wherein, the distance between any adjacent vehicles among the multiple stopped vehicles is less than a preset distance range.

8. A memory driving device, characterized in that: include: A first judgment module is used to judge whether any lane segment in the current navigation path is on a target road segment, wherein the target road segment is recorded in a parking road segment record, and the parking road segment record is a parking situation record with a time mark generated after the target vehicle travels from the target road, indicating that there is a stopped vehicle in the target road segment of the target road within the target time period of the time mark, the target road segment is a road segment in the target lane, and the current navigation path is the navigation path of the first vehicle in motion; a second judgment module, configured to judge whether the current time is within the target time period and whether there is a stopped vehicle on the target road section by using the sensing data of the first vehicle when the first judgment module determines that any lane segment in the current navigation path is on the target road section; A driving control module, for detouring a second vehicle if the first judgment module determines that any lane segment in the current navigation path is on the target section, and the second judgment module determines that the current time is within the target time period, and it is determined through the perception data of the first vehicle that there is a stopped vehicle on the target section, wherein the second vehicle is a stopped vehicle on the target section determined based on the perception data; and if the first judgment module determines that any lane segment in the current navigation path is not on the target section, driving according to the current navigation path.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store the computer program; The processor is used to execute the computer program to implement the memory driving method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein the computer program, when executed by a processor, implements the memory driving method as described in any one of claims 1 to 7.

Images