Lane planning methods, devices, vehicles and storage media for vehicles

Abstract

This application relates to the field of autonomous driving technology, and particularly to a lane planning method, device, vehicle, and storage medium for a vehicle. The method includes: acquiring the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the road where the vehicle is currently located; determining the optimal lane planning strategy for the current vehicle based on the current lane planning calculation time, current road curvature, and current environmental perception computing power ratio; and adjusting the current lane planning distance and / or the number of lanes planned based on the optimal lane planning strategy. This solves the problems in related technologies, such as poor real-time output of lane planning results and the lack of dynamic optimization methods for lane planning in some complex driving scenarios, leading to lower safety in autonomous driving. It significantly improves the real-time performance of lane planning, thereby enhancing the safety of autonomous driving.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a lane planning method, device, vehicle, and storage medium for a vehicle. Background Technology

[0002] In related technologies, when performing lane planning, it is generally necessary to plan from the first starting lane to N target lanes separately to obtain N lane planning results. If the time required for one search is T, then the time required for one N-lane planning is N*T.

[0003] However, for some more complex driving scenarios, the real-time output of lane planning results in related technologies is poor, and lane planning lacks dynamic optimization methods, resulting in lower safety for autonomous driving, which urgently needs to be addressed. Summary of the Invention

[0004] This application provides a lane planning method, device, vehicle, and storage medium for vehicles to solve the problems in related technologies, such as poor real-time output of lane planning results when performing lane planning in some complex driving scenarios, and the lack of dynamic optimization methods for lane planning, which leads to low safety of autonomous driving. This application greatly improves the real-time performance of lane planning and thus enhances the safety of autonomous driving.

[0005] The first aspect of this application provides a lane planning method for a vehicle, comprising the following steps:

[0006] The system obtains the current road curvature, current environmental perception computing power ratio, and current lane planning calculation time of the road where the vehicle is currently located; determines the optimal lane planning strategy for the current vehicle based on the current lane planning calculation time, the current road curvature, and the current environmental perception computing power ratio; and adjusts the current lane planning distance and / or the current lane planning number of the current vehicle based on the current optimal lane planning strategy.

[0007] Optionally, in some embodiments, determining the optimal lane planning strategy for the current vehicle based on the current lane planning calculation time, the current road curvature, and the current environmental perception computing power ratio includes:

[0008] If the current lane planning calculation time is greater than or equal to the first preset time, then the first target planning lane number and the first target planning distance of the current vehicle are matched according to the current road curvature, and the second target planning lane number and the second target planning distance of the current vehicle are matched according to the current environmental perception computing power ratio, wherein the first target planning lane number is less than the current planning vehicle number, the first target planning distance is less than the current planning distance, the second target planning lane number is less than the current planning vehicle number, and the second target planning distance is less than the current planning distance;

[0009] The final planned lane number of the current vehicle is determined based on the first target planned lane number and / or the second target planned lane number, and the final planned distance of the current vehicle is determined based on the first target planned distance and / or the second target planned distance;

[0010] The optimal lane planning strategy is generated based on the final planned number of lanes and the final planned distance.

[0011] Optionally, in some embodiments, before matching the first target planned lane number and the first target planned distance of the current vehicle according to the current road curvature, the method further includes: obtaining the number of times the current lane planning calculation time is greater than the first preset time within a second preset time; if the number of calculations is less than the preset number, then the lane planning strategy of the current vehicle remains unchanged.

[0012] Optionally, in some embodiments, after adjusting the current lane planning distance and / or the current lane planning number of the current vehicle according to the current optimal lane planning strategy, the method further includes: obtaining a new lane planning calculation time for the current vehicle; if the new lane planning calculation time is greater than or equal to the first preset time, then reducing the first target planning lane number and shortening the first target planning distance according to a preset strategy; adjusting the current lane planning number and / or adjusting the current lane planning distance according to the shortened first target planning lane number and / or the shortened first target planning distance.

[0013] Optionally, in some embodiments, after obtaining the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the road where the vehicle is currently located, the method further includes:

[0014] If the current lane planning calculation time is less than the second preset time, then the third target planning lane number and third target planning distance of the current vehicle are matched according to the current road curvature, and the fourth target planning lane number and fourth target planning distance of the current vehicle are matched according to the current environmental perception computing power ratio.

[0015] The current lane planning number is adjusted according to the third target planning lane number and / or the fourth target planning vehicle number, and / or the current lane planning distance is adjusted according to the first target planning distance and / or the second target planning distance;

[0016] Wherein, the second preset duration is less than the first preset duration, the third target planned lane number is greater than the current planned vehicle number, the third target planned distance is greater than the current planned distance, the fourth target planned lane number is greater than the current planned vehicle number, and the fourth target planned distance is greater than the current planned distance.

[0017] Optionally, in some embodiments, after obtaining the current road curvature, current environmental perception computing power ratio, and current lane planning calculation time of the road where the current vehicle is located, the method further includes: if the current lane planning calculation time is greater than or equal to the second preset time, and the current lane planning calculation time is less than the first preset time, then the lane planning strategy of the current vehicle is maintained unchanged.

[0018] A second aspect of this application provides a lane planning device for a vehicle, comprising:

[0019] The acquisition module is used to acquire the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the current vehicle. The determination module is used to determine the optimal lane planning strategy for the current vehicle based on the current lane planning calculation time, the current road curvature, and the current environmental perception computing power ratio. The planning module is used to adjust the current lane planning distance and / or the current lane planning number of the current vehicle based on the current optimal lane planning strategy.

[0020] Optionally, in some embodiments, the determining module includes:

[0021] The first matching unit is configured to, when the current lane planning calculation time is greater than or equal to the first preset time, match the first target planning lane number and the first target planning distance of the current vehicle according to the current road curvature, and match the second target planning lane number and the second target planning distance of the current vehicle according to the current environmental perception computing power ratio, wherein the first target planning lane number is less than the current planning vehicle number, the first target planning distance is less than the current planning distance, the second target planning lane number is less than the current planning vehicle number, and the second target planning distance is less than the current planning distance;

[0022] The determining unit is configured to determine the final planned lane number of the current vehicle based on the first target planned lane number and / or the second target planned lane number, and to determine the final planned distance of the current vehicle based on the first target planned distance and / or the second target planned distance;

[0023] The generation unit is used to generate the optimal lane planning strategy based on the final planned number of lanes and the final planned distance.

[0024] Optionally, in some embodiments, before matching the first target planned lane number and the first target planned distance of the current vehicle according to the current road curvature, the first matching unit is further configured to:

[0025] Obtain the number of times the current lane planning calculation time is greater than the first preset time within the second preset time period; when the number of calculations is less than the preset number, maintain the current vehicle's lane planning strategy unchanged.

[0026] Optionally, in some embodiments, after adjusting the current lane planning distance and / or the number of current lanes for the current vehicle according to the current optimal lane planning strategy, the planning module further includes:

[0027] The acquisition unit is used to acquire the new lane planning calculation time of the current vehicle;

[0028] The first planning unit is used to reduce the number of the first target planning lanes and shorten the first target planning distance according to a preset strategy when the new lane planning calculation time is greater than or equal to the first preset time.

[0029] The first adjustment unit is used to adjust the current lane planning number based on the shortened first target planning lane number and / or adjust the current lane planning distance based on the shortened first target planning distance.

[0030] Optionally, in some embodiments, after obtaining the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the road where the vehicle is currently located, the acquisition module further includes:

[0031] The second matching unit is used to match the number of third target planning lanes and the third target planning distance of the current vehicle according to the current road curvature when the current lane planning calculation time is less than the second preset time, and to match the number of fourth target planning lanes and the fourth target planning distance of the current vehicle according to the current environmental perception computing power ratio.

[0032] The second adjustment unit is used to adjust the current lane planning number according to the third target planning lane number and / or the fourth target planning vehicle number, and / or adjust the current lane planning distance according to the first target planning distance and / or the second target planning distance;

[0033] Wherein, the second preset duration is less than the first preset duration, the third target planned lane number is greater than the current planned vehicle number, the third target planned distance is greater than the current planned distance, the fourth target planned lane number is greater than the current planned vehicle number, and the fourth target planned distance is greater than the current planned distance.

[0034] Optionally, in some embodiments, after obtaining the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the road where the vehicle is currently located, the acquisition module further includes:

[0035] The second planning unit is used to maintain the current lane planning strategy of the vehicle unchanged when the current lane planning calculation time is greater than or equal to the second preset time and the current lane planning calculation time is less than the first preset time.

[0036] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the lane planning method for the vehicle as described in the above embodiments.

[0037] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the lane planning method for a vehicle as described in the above embodiments.

[0038] Therefore, this application can calculate the optimal lane planning strategy for the current vehicle based on the current road curvature and / or the current environmental perception computing power ratio when the current lane planning calculation time is greater than or equal to a certain time. It then adjusts the current lane planning distance and / or the number of lanes planned for the current vehicle based on the optimal lane planning strategy. This solves the problems in related technologies, such as poor real-time output of lane planning results and the lack of dynamic optimization methods for lane planning in some complex driving scenarios, leading to lower safety in autonomous driving. This significantly improves the real-time performance of lane planning, thereby enhancing the safety of autonomous driving.

[0039] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0040] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0041] Figure 1 This is a flowchart of a vehicle lane planning method provided according to an embodiment of this application;

[0042] Figure 2 This is a flowchart of a lane planning method for a vehicle according to an embodiment of this application;

[0043] Figure 3 This is a block diagram of a lane planning device for a vehicle according to an embodiment of this application;

[0044] Figure 4 This is a block diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0045] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0046] The following description, with reference to the accompanying drawings, describes a lane planning method, apparatus, vehicle, and storage medium for vehicles according to embodiments of this application. Addressing the issues raised in the background art, such as poor real-time output of lane planning results and a lack of dynamic optimization methods for complex driving scenarios, leading to lower safety in autonomous driving, this application provides a lane planning method for vehicles. This method involves acquiring the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the road where the vehicle is currently located; determining the optimal lane planning strategy for the current vehicle based on the current lane planning calculation time, current road curvature, and current environmental perception computing power ratio; and adjusting the current lane planning distance and / or the current number of lanes planned based on the optimal lane planning strategy. This solves the problems in related technologies, such as poor real-time output of lane planning results and a lack of dynamic optimization methods for complex driving scenarios, leading to lower safety in autonomous driving, thereby significantly improving the real-time performance of lane planning and thus enhancing the safety of autonomous driving.

[0047] Before introducing the embodiments of the lane planning method for vehicles in this application, let me briefly introduce the lane planning algorithm involved in this application.

[0048] Currently, autonomous driving algorithms generally include localization algorithms, perception algorithms, prediction algorithms, road planning algorithms, lane planning algorithms, decision-making algorithms, local planning algorithms, and control algorithms. Among these, the output resolution of lane planning refers to the path the vehicle will take, which is a collection of points; that is, the output resolution is the distance between any two points on the path. Planning distance refers to the distance between the starting point and the ending point of lane planning.

[0049] On cost-constrained hardware platforms, limited computing resources pose a significant challenge to the timeliness of algorithm output during autonomous driving planning. As described in the background section above, current lane planning algorithms plan a lane with a fixed look-ahead distance from the current vehicle's lane to the target point. For example, when driving, it is necessary to consider the approximate location of the vehicle 100 meters ahead (the distance to be considered may be greater than 100 meters on highways, while it may be less than 100 meters on congested roads) and how to proceed.

[0050] This application considers the diverse road types in which autonomous vehicles operate, including highways, urban arterial roads, rural roads, urban alleys, mountain bends, market roads, and intersections. Different types of scenarios have different requirements for the timeliness of lane planning algorithms. Therefore, this application proposes a lane planning method for vehicles. Based on the vehicle's environment and combined with multiple factors such as computing power monitoring and road curvature, the planning length and resolution of the lane planning results are dynamically adjusted. This makes the lane planning results more consistent with the current state of the vehicle and improves the real-time performance of lane planning.

[0051] Specifically, Figure 1 This is a schematic flowchart of a vehicle lane planning method provided in an embodiment of this application.

[0052] like Figure 1 As shown, the lane planning method for this vehicle includes the following steps:

[0053] In step S101, the current road curvature, current environmental perception computing power ratio, and current lane planning calculation time of the current vehicle are obtained.

[0054] In this application embodiment, based on the aforementioned related technologies, the current environment perception computing power ratio refers to the ratio of the computing power of the autonomous driving perception module and prediction module to the total computing power of the autonomous driving platform in the current vehicle environment scenario. The current environment can be identified by obtaining the vehicle's current position through localization, or by using visual perception, i.e., inputting environmental information from a camera as a sensor to infer the vehicle's current scene. The current lane planning calculation time in this application embodiment refers to the duration from the start of lane planning by the autonomous driving platform. The calculation method for the current road curvature in this application embodiment can refer to related technologies; to avoid redundancy, it will not be elaborated here.

[0055] It is understandable that the output efficiency of lane planning is related to multiple factors. This application considers that in some scenarios, such as coastal highways, the road curvature is large, while in highway scenarios, the road curvature is small. Furthermore, the computational load for lane planning varies depending on the vehicle's location. For example, in busy intersections, the computational demands on the perception and prediction modules of the autonomous driving algorithm increase. Therefore, it is understandable that the higher the proportion of computational power allocated to environmental perception, the greater the impact on the timeliness of lane planning output.

[0056] Therefore, before planning lanes, this application needs to obtain the current road curvature and the current environmental perception computing power ratio of the road where the vehicle is currently located in order to match an appropriate lane planning strategy. This application also needs to obtain the current lane planning calculation time, and if the current lane planning calculation time is too long, the lane planning strategy will be adjusted in a timely manner to improve the efficiency of lane planning.

[0057] In step S102, the optimal lane planning strategy for the current vehicle is determined based on the current lane planning calculation time, the current road curvature, and the current environmental perception computing power ratio.

[0058] In the embodiments of this application, the lane planning strategy mainly includes two aspects: the distance of the current lane planning and the number of current lane planning.

[0059] Specifically, this application, based on the current lane planning calculation time, current road curvature, and current environmental perception computing power ratio obtained in step S101, matches these with the lane planning strategy provided in this application to obtain the optimal lane planning strategy for the current vehicle. This optimal lane planning strategy makes the lane planning results more consistent with the current vehicle state, improving the real-time performance of lane planning. The following examples illustrate several lane planning strategies provided in this application.

[0060] Optionally, in some embodiments, determining the optimal lane planning strategy for the current vehicle based on the current lane planning calculation time, the current road curvature, and the current environmental perception computing power ratio includes: if the current lane planning calculation time is greater than or equal to a first preset time, matching the current vehicle's first target planning lane number and first target planning distance based on the current road curvature, and matching the current vehicle's second target planning lane number and second target planning distance based on the current environmental perception computing power ratio, wherein the first target planning lane number is less than the current planning vehicle number, the first target planning distance is less than the current planning distance, the second target planning lane number is less than the current planning vehicle number, and the second target planning distance is less than the current planning distance; determining the final planning lane number for the current vehicle based on the first target planning lane number and / or the second target planning lane number, and determining the final planning distance for the current vehicle based on the first target planning distance and / or the second target planning distance; and generating the optimal lane planning strategy based on the final planning lane number and the final planning distance.

[0061] It should be noted that this application provides conditions for adjusting the lane planning strategy. That is, after obtaining the current lane planning calculation time in step S101, it is compared with the first preset time set in this application. When the current lane planning calculation time exceeds the preset value, it is determined that the timeliness of the result output is not met and the lane planning strategy needs to be adjusted to improve the efficiency of lane planning.

[0062] It is understandable that traffic flow is high in high-speed or urban main road scenarios, while vehicle speed is slow in congested urban intersections, such as busy urban intersections. Therefore, the computing power requirements of the perception and prediction modules increase, resulting in a reduction of computing power resources allocated to lane planning by the system. Thus, in order to balance the system's computing power resources and make the lane planning output results of autonomous driving more timely, this application makes the number of planned lanes less than the number of currently planned vehicles and the planned distance less than the current planned distance in scenarios that would reduce computing power resources.

[0063] In addition, considering that users may drive very slowly on deserted or congested roads, the lane planning strategy of this application is matched based on the current road curvature and the current environmental perception computing power ratio to obtain a more accurate and reasonable lane planning strategy.

[0064] Specifically, this application specifies the number of planned lanes, namely, the first target planned lane number obtained by matching the current road curvature and the second target planned lane number obtained by matching the current environmental perception computing power ratio, both of which are less than the current planned number of vehicles. This application also specifies the planned distance, namely, the first target planned distance obtained by matching the current road curvature and the second target planned distance obtained by matching the current environmental perception computing power ratio, both of which are less than the current planned distance. This application does not impose specific limitations on the first target planned lane number, the first target planned distance, the second target planned lane number, and the second target planned distance; those skilled in the art can set these values ​​according to actual circumstances.

[0065] Furthermore, this application may use the number of matched first target planned lanes as the final planned lane number, or the number of matched second target planned lanes as the final planned lane number, or calculate the average of the first target planned lane number and the second target planned lane number and use the average of the two as the final planned lane number; no specific limitation is made here. Optionally, the calculation method for the final planned distance is similar to the method for calculating the final planned lane number described above, and will not be elaborated here to avoid redundancy.

[0066] For example, the first preset time is 60 seconds, the current number of planned vehicles is 5, and the current planned distance is 100 meters. After the current lane planning calculation time exceeds 60 seconds, if the current road curvature is 500 meters, the system determines that the curvature value is too large. Through matching, the first target number of planned lanes is determined to be 4, and the first target planned distance is determined to be 80 meters. The current environmental perception computing power accounts for 80%, and through matching, the second target number of planned lanes is determined to be 2, and the second target planned distance is determined to be 60 meters. Therefore, three lane planning strategies are obtained: determining the final number of planned lanes to be 4, and the final planned distance to be 80 meters; or determining the final number of planned lanes to be 2, and the final planned distance to be 60 meters; or determining the final number of planned lanes to be 3, and the final planned distance to be 70 meters. The optimal lane planning strategy is then selected based on the actual situation.

[0067] Therefore, this application can match the optimal number of planned lanes and the final planned distance based on the current lane planning calculation time, the current road curvature, and the current environmental perception computing power ratio, thereby obtaining the optimal lane planning strategy.

[0068] Optionally, in some embodiments, after obtaining the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the current vehicle, the method further includes: if the current lane planning calculation time is less than a second preset time, then matching the current vehicle's third target planning lane number and third target planning distance according to the current road curvature, and matching the current vehicle's fourth target planning lane number and fourth target planning distance according to the current environmental perception computing power ratio; adjusting the current lane planning number according to the third target planning lane number and / or the fourth target planning vehicle number, and / or adjusting the current lane planning distance according to the first target planning distance and / or the second target planning distance; wherein the second preset time is less than the first preset time, the third target planning lane number is greater than the current planning vehicle number, the third target planning distance is greater than the current planning distance, the fourth target planning lane number is greater than the current planning vehicle number, and the fourth target planning distance is greater than the current planning distance.

[0069] Understandably, in highway or trunk road scenarios, the road curvature is small, the environmental perception computing power accounts for a small proportion, and the vehicle speed is relatively high. Therefore, considering the system's computing power balance, it is necessary to appropriately extend the lane planning distance in this case to better match the current vehicle state and improve the real-time performance of lane planning.

[0070] Specifically, this application sets a second preset time period, which is shorter than the first preset time period mentioned above. When the current lane planning calculation time is less than the second preset time period, the number of third target planning lanes and the third target planning distance can be obtained by matching the current road curvature, and the number of fourth target planning lanes and the fourth target planning distance can be matched based on the current environmental perception computing power ratio. In this embodiment, the number of third target planning lanes and the number of fourth target planning lanes are both greater than the number of currently planned vehicles, and the number of third target planning distances and the fourth target planning distances are both greater than the current planning distance. In addition, this application does not specifically limit the number of third target planning lanes, the third target planning distance, the number of fourth target planning lanes, and the fourth target planning distance; those skilled in the art can set them according to the actual situation.

[0071] Furthermore, this application may use the number of matched third target planned lanes as the final planned lane number, or the number of matched fourth target planned lanes as the final planned lane number, or calculate the average of the third target planned lane number and the fourth target planned lane number, and use the average of the two as the final planned lane number; no specific limitation is made here. Optionally, the calculation method for the final planned distance is similar to the method for calculating the final planned lane number described above, and will not be elaborated here to avoid redundancy.

[0072] For example, if the current planned number of vehicles is 2, the current planned distance is 60 meters, the second preset time is 50 seconds, and the current lane planning calculation time is 30 seconds, and the road curvature is 100 meters, then the third target planned lane number is 4, the third target planned distance is 80 meters, and the current environmental perception computing power ratio is 40%. Therefore, the fourth target planned lane number is 4, the fourth target planned distance is 100 meters. Thus, three lane planning strategies are obtained: determining the final planned lane number as 4, the final planned distance as 80 meters; determining the final planned lane number as 4, the final planned distance as 100 meters; or determining the final planned lane number as 4, the final planned distance as 90 meters. The optimal lane planning strategy is then selected based on the actual situation.

[0073] Therefore, this application can appropriately increase the search distance and number of searches when the vehicle has a small curvature and the environmental perception computing power accounts for a small proportion, and dynamically adjust the planning length of lane planning, so that the lane planning result is more in line with the current state of the vehicle and improves the real-time performance of lane planning.

[0074] Optionally, in some embodiments, after obtaining the current road curvature, current environmental perception computing power ratio, and current lane planning calculation time of the current vehicle, the method further includes: if the current lane planning calculation time is greater than or equal to a second preset time and the current lane planning calculation time is less than a first preset time, then the lane planning strategy of the current vehicle is maintained unchanged.

[0075] It should be noted that after obtaining the current lane planning calculation time, this application needs to judge the time, that is, compare the current lane planning calculation time with the first preset time and the second preset time set by this application. In this way, the range of the current lane planning calculation time can be obtained, and then the lane can be planned to improve the timeliness of lane planning.

[0076] Specifically, in this embodiment, considering that although the current lane planning delay has increased, it does not exceed a certain amount, in order to avoid wasting resources and balance the computing load of the system, the current lane planning strategy of the vehicle is maintained unchanged when the current lane planning calculation time is between the second preset time and the first preset time in this embodiment.

[0077] Optionally, in some embodiments, before matching the first target planned lane number and the first target planned distance of the current vehicle according to the current road curvature, the method further includes: obtaining the number of times the current lane planning calculation time is greater than the first preset time within a second preset time; if the number of calculations is less than the preset number, then the lane planning strategy of the current vehicle remains unchanged.

[0078] Based on the above embodiments, it can be seen that the condition for lane planning is to compare the current lane planning calculation time with a first preset time. When the current lane planning calculation time exceeds the threshold, the lane planning strategy is activated. However, this application takes into account the possibility of misjudgment by the system. Therefore, it is set to plan the lane only when lane delays occur multiple times, effectively avoiding misjudgment and increasing the accuracy of lane planning.

[0079] Specifically, this application sets a second preset time period and counts the number of times within the second preset time period that the current lane planning calculation time exceeds the first preset time period. If this number is less than a preset number, it is determined that lane planning is not required at this time, and the current lane planning strategy of the vehicle should remain unchanged. Therefore, this application can save computing resources and ensure system stability when lane planning is not required. Furthermore, this application does not specify a particular preset number of calculations; those skilled in the art can set it according to actual conditions.

[0080] In step S103, the current lane planning distance and / or the current lane planning number of the current vehicle are adjusted according to the current optimal lane planning strategy.

[0081] Based on the above embodiments, this application can match the current optimal lane planning strategy according to the current road curvature and the current environmental perception computing power ratio, combined with the delay statistics of the output results. Then, it can adjust the lane planning distance or the number of lanes for the current vehicle, or both, according to the current optimal lane planning strategy, thereby making the lane planning result more consistent with the current vehicle state and improving the real-time performance of lane planning.

[0082] Optionally, in some embodiments, after adjusting the current lane planning distance and / or the current lane planning number of the current vehicle according to the current optimal lane planning strategy, the method further includes: obtaining the new lane planning calculation time of the current vehicle; if the new lane planning calculation time is greater than or equal to a first preset time, reducing the number of first target planning lanes and shortening the first target planning distance according to a preset strategy; adjusting the current lane planning number and / or adjusting the current lane planning distance according to the shortened number of first target planning lanes and / or the shortened first target planning distance.

[0083] It should be noted that, in order to improve the real-time performance of lane planning, this application statistically analyzes the duration of lane planning and determines whether it is too long. If the lane planning duration is too long, it may affect the timeliness of the system output and cause inconvenience to users. Therefore, in this case, this application plans the lane again and appropriately reduces the search distance and number of searches to improve the efficiency of the output results.

[0084] To enable those skilled in the art to further understand the vehicle lane planning method of this application, the following embodiments are provided to illustrate the process of the method.

[0085] Specifically, Figure 2 This is a flowchart illustrating the lane planning method for vehicles according to an embodiment of this application, as shown below. Figure 2 As shown, the lane planning method for this vehicle may include the following steps:

[0086] Step S201: Based on the current location or visual perception, infer that the vehicle is currently in scene scen1 (a pedestrian-filled intersection, a congested urban main road, a smooth highway, a winding coastal road, etc.).

[0087] Step S202: Monitor the delay in lane planning result output and perform statistical analysis;

[0088] Step S203: For the current scenario scen1, estimate whether the current computing power load will increase, whether the curvature of the future road is too large, and determine whether the latency has increased and exceeded the threshold. If the latency has increased but has not exceeded the threshold, proceed to step S204; otherwise, proceed to step S205.

[0089] Step S204: Adjust the distance and number of lane planning steps according to scenario scen1;

[0090] Step S205: Combining the vehicle's location and the latency statistics of the output results, match the lane planning strategy with the scenarios listed in the List: When the vehicle is in a highway scenario, appropriately increase the search distance and number of searches; when the vehicle is in an urban main road scenario, due to the large traffic volume, appropriately reduce the search distance and number of searches; when the vehicle is in a congested urban intersection scenario, due to the large perception and prediction load, appropriately reduce the search distance and number of searches; when the vehicle is in a coastal highway scenario, due to the large road curvature, appropriately reduce the search distance.

[0091] Step S206: Perform lane planning based on the optimal lane planning strategy.

[0092] The lane planning method for vehicles proposed in this application obtains the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the road where the vehicle is currently located. Based on these factors, the optimal lane planning strategy for the current vehicle is determined, and the current lane planning distance and / or the number of lanes planned is adjusted according to this optimal strategy. Therefore, this application combines the environmental perception computing power ratio of the vehicle's environment (i.e., system computing power monitoring) with the road curvature factor to dynamically adjust the lane planning length. This solves the problems in related technologies, such as the lack of real-time consideration for lane planning results output and the absence of control or dynamic optimization methods, which may affect the safety of autonomous driving. By controlling lane planning in real-time according to the vehicle's current scenario, the lane planning results better match the current vehicle state, improving the timeliness of lane planning.

[0093] Next, the lane planning device for a vehicle according to an embodiment of this application is described with reference to the accompanying drawings.

[0094] Figure 3 This is a block diagram of a vehicle lane planning device according to an embodiment of this application.

[0095] like Figure 3 As shown, the vehicle's lane planning device 10 includes: an acquisition module 100, a determination module 200, and a planning module 300.

[0096] The acquisition module 100 is used to acquire the current road curvature, current environmental perception computing power ratio, and current lane planning calculation time of the current vehicle; the determination module 200 is used to determine the optimal lane planning strategy for the current vehicle based on the current lane planning calculation time, current road curvature, and current environmental perception computing power ratio; and the planning module 300 is used to adjust the current lane planning distance and / or the current lane planning number of the current vehicle based on the current optimal lane planning strategy.

[0097] Optionally, in some embodiments, the determining module 200 includes: a first matching unit, a determining unit, and a generating unit.

[0098] The system includes a first matching unit, configured to match the number of first target planned lanes and the first target planned distance of the current vehicle based on the current road curvature when the current lane planning calculation time is greater than or equal to a first preset time, and to match the number of second target planned lanes and the second target planned distance of the current vehicle based on the current environmental perception computing power ratio, wherein the number of first target planned lanes is less than the number of currently planned vehicles, the first target planned distance is less than the current planned distance, the number of second target planned lanes is less than the number of currently planned vehicles, and the second target planned distance is less than the current planned distance; a determining unit, configured to determine the final planned lane number of the current vehicle based on the number of first target planned lanes and / or the number of second target planned lanes, and to determine the final planned distance of the current vehicle based on the first target planned distance and / or the second target planned distance; and a generating unit, configured to generate an optimal lane planning strategy based on the final planned lane number and the final planned distance.

[0099] Optionally, in some embodiments, before matching the first target planned lane number and the first target planned distance of the current vehicle according to the current road curvature, the first matching unit is further configured to:

[0100] Obtain the number of times the current lane planning calculation time is greater than the first preset time within the second preset time period; when the number of calculations is less than the preset number, maintain the current vehicle's lane planning strategy unchanged.

[0101] Optionally, in some embodiments, after adjusting the current lane planning distance and / or the current lane planning number of the current vehicle according to the current optimal lane planning strategy, the planning module 300 further includes: an acquisition unit, a first planning unit, and a first adjustment unit.

[0102] The acquisition unit is used to acquire the new lane planning calculation time of the current vehicle; the first planning unit is used to reduce the number of first target planning lanes and shorten the first target planning distance according to a preset strategy when the new lane planning calculation time is greater than or equal to the first preset time; the first adjustment unit is used to adjust the current lane planning number and / or adjust the current lane planning distance according to the shortened number of first target planning lanes and / or the shortened first target planning distance.

[0103] Optionally, in some embodiments, after obtaining the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the road where the vehicle is currently located, the acquisition module 100 further includes: a second matching unit and a second adjustment unit.

[0104] The second matching unit is used to match the number of third target planning lanes and the third target planning distance of the current vehicle according to the current road curvature when the current lane planning calculation time is less than the second preset time, and to match the number of fourth target planning lanes and the fourth target planning distance of the current vehicle according to the current environmental perception computing power ratio; the second adjustment unit is used to adjust the number of current lanes planned according to the number of third target planning lanes and / or the number of fourth target planning vehicles, and / or adjust the current lane planning distance according to the first target planning distance and / or the second target planning distance; wherein the second preset time is less than the first preset time, the number of third target planning lanes is greater than the number of current planning vehicles, the third target planning distance is greater than the current planning distance, the number of fourth target planning lanes is greater than the number of current planning vehicles, and the fourth target planning distance is greater than the current planning distance.

[0105] Optionally, in some embodiments, after obtaining the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the road where the vehicle is currently located, the acquisition module 100 further includes: a second planning unit.

[0106] The second planning unit is used to maintain the current lane planning strategy of the vehicle unchanged when the current lane planning calculation time is greater than or equal to the second preset time and the current lane planning calculation time is less than the first preset time.

[0107] It should be noted that the foregoing explanation of the lane planning method embodiment for vehicles also applies to the lane planning device for vehicles in this embodiment, and will not be repeated here.

[0108] The lane planning device for vehicles proposed in this application obtains the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the road where the vehicle is currently located. Based on these factors, it determines the optimal lane planning strategy for the current vehicle and adjusts the current lane planning distance and / or the number of lanes planned based on the optimal strategy. Therefore, this application combines the environmental perception computing power ratio of the vehicle's environment (i.e., system computing power monitoring) with the road curvature factor to dynamically adjust the lane planning length. This solves the problems in related technologies, such as the lack of real-time consideration for lane planning results output and the absence of control or dynamic optimization methods, which may affect the safety of autonomous driving. By controlling lane planning in real-time according to the vehicle's scenario, the lane planning results better match the current vehicle state, improving the timeliness of lane planning.

[0109] Figure 4 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0110] The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0111] When the processor 402 executes the program, it implements the vehicle lane planning method provided in the above embodiments.

[0112] Furthermore, the vehicle also includes:

[0113] Communication interface 403 is used for communication between memory 401 and processor 402.

[0114] The memory 401 is used to store computer programs that can run on the processor 402.

[0115] The memory 401 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0116] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0117] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0118] Processor 402 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0119] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described vehicle lane planning method.

[0120] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0121] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0122] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0123] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0124] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0125] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A lane planning method for vehicles, characterized in that, Includes the following steps: Obtain the current road curvature, current environmental perception computing power ratio, and current lane planning calculation time of the current vehicle's location; The optimal lane planning strategy for the current vehicle is determined based on the current lane planning calculation time, the current road curvature, and the current environmental perception computing power ratio. as well as Adjust the current lane planning distance and / or the current lane planning number of the current vehicle according to the current optimal lane planning strategy.

2. The method according to claim 1, characterized in that, The step of determining the optimal lane planning strategy for the current vehicle based on the current lane planning calculation time, the current road curvature, and the current environmental perception computing power ratio includes: If the current lane planning calculation time is greater than or equal to the first preset time, then the first target planning lane number and the first target planning distance of the current vehicle are matched according to the current road curvature, and the second target planning lane number and the second target planning distance of the current vehicle are matched according to the current environmental perception computing power ratio, wherein the first target planning lane number is less than the current planning lane number, the first target planning distance is less than the current lane planning distance, the second target planning lane number is less than the current planning lane number, and the second target planning distance is less than the current lane planning distance; The final planned lane number of the current vehicle is determined based on the first target planned lane number and / or the second target planned lane number, and the final planned distance of the current vehicle is determined based on the first target planned distance and / or the second target planned distance; The optimal lane planning strategy is generated based on the final planned number of lanes and the final planned distance.

3. The method according to claim 1 or 2, characterized in that, Before matching the first target planned lane number and first target planned distance of the current vehicle according to the current road curvature, the method further includes: Obtain the number of times the current lane planning calculation time is greater than the first preset time within the second preset time period; If the number of calculations is less than the preset number, the lane planning strategy for the current vehicle will remain unchanged.

4. The method according to claim 1, characterized in that, After adjusting the current lane planning distance and / or the number of current lanes for the current vehicle according to the current optimal lane planning strategy, the method further includes: Obtain the new lane planning calculation time for the current vehicle; If the new lane planning calculation time is greater than or equal to the first preset time, then the number of first target planning lanes is reduced and the first target planning distance is shortened according to the preset strategy. The current lane planning number is adjusted based on the shortened first target planning lane number and / or the current lane planning distance is adjusted based on the shortened first target planning distance.

5. The method according to claim 1, characterized in that, After obtaining the current road curvature, current environmental perception computing power ratio, and current lane planning calculation time of the current vehicle, the following steps are also included: If the current lane planning calculation time is less than the second preset time, then the third target planning lane number and third target planning distance of the current vehicle are matched according to the current road curvature, and the fourth target planning lane number and fourth target planning distance of the current vehicle are matched according to the current environmental perception computing power ratio. The current lane planning number is adjusted according to the third target lane planning number and / or the fourth target lane planning number, and / or the current lane planning distance is adjusted according to the first target planning distance and / or the second target planning distance; Wherein, the second preset duration is less than the first preset duration, the third target planned lane number is greater than the current planned lane number, the third target planned distance is greater than the current lane planned distance, the fourth target planned lane number is greater than the current planned lane number, and the fourth target planned distance is greater than the current lane planned distance.

6. The method according to claim 1, characterized in that, After obtaining the current road curvature, current environmental perception computing power ratio, and current lane planning calculation time of the current vehicle, the following steps are also included: If the current lane planning calculation time is greater than or equal to the second preset time, and the current lane planning calculation time is less than the first preset time, then the lane planning strategy of the current vehicle remains unchanged.

7. A lane planning device for a vehicle, characterized in that, include: The acquisition module is used to acquire the current road curvature, the current environmental perception computing power ratio, and the current lane planning calculation time of the current vehicle. The determination module is used to determine the optimal lane planning strategy for the current vehicle based on the current lane planning calculation time, the current road curvature, and the current environmental perception computing power ratio. as well as The planning module is used to adjust the current lane planning distance and / or the current lane planning number of the current vehicle according to the current optimal lane planning strategy.

8. The apparatus according to claim 7, characterized in that, The determining module includes: The first matching unit is configured to, when the current lane planning calculation time is greater than or equal to a first preset time, match the first target planning lane number and the first target planning distance of the current vehicle according to the current road curvature, and match the second target planning lane number and the second target planning distance of the current vehicle according to the current environmental perception computing power ratio, wherein the first target planning lane number is less than the current planning lane number, the first target planning distance is less than the current lane planning distance, the second target planning lane number is less than the current planning lane number, and the second target planning distance is less than the current lane planning distance; The determining unit is configured to determine the final planned lane number of the current vehicle based on the first target planned lane number and / or the second target planned lane number, and to determine the final planned distance of the current vehicle based on the first target planned distance and / or the second target planned distance; The generation unit is used to generate the optimal lane planning strategy based on the final planned number of lanes and the final planned distance.

9. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the lane planning method for a vehicle as described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the lane planning method for the vehicle as described in any one of claims 1-6.

Images