Speed curve replanning control method and device, vehicle and medium
By predicting the trajectory and driving information of adjacent vehicles, the re-planning of the vehicle speed curve is triggered, and the problem of untimely repeated planning and planning in PECC is solved, which reduces fuel consumption and improves the timeliness of the application of the speed curve.
Patent Information
- Application Number
- CN202411195608.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-11-08
AI Technical Summary
In the prior art In the foreseeable adaptive cruise control system (PECC), the re-planning of the vehicle's optimal speed curve has the problem of repeated planning and untimely planning, resulting in increased fuel consumption.
By predicting the trajectory of adjacent vehicles in the future time period, determining the driving information of vehicles and adjacent vehicles, triggering the re-planning of the speed curve based on the driving information, avoiding repeated planning during the deceleration process, and ensuring timely application of new speed curves To reduce fuel consumption.
It effectively avoids repeated re-planning of the speed curve during deceleration, ensures that the vehicle can drive according to the new speed curve in a timely manner, reduces fuel consumption, and improves the timeliness of re-planning of the speed curve.
Smart Images

Figure CN118907122A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle technology, and in particular to a control method, device, vehicle and medium for replanning a speed curve. Background Art
[0002] At present, due to the continuous rise in oil prices, the cost of driving oil cars is getting higher and higher. In order to solve this problem, the Predictive Economic Cruise Control (PECC) came into being.
[0003] PECC mainly analyzes the road conditions on which the vehicle is traveling and controls the vehicle to travel along a reasonable and economical optimal speed curve. For example, when the vehicle ahead prevents the vehicle from continuing to travel along the optimal speed curve, the driver needs to control the vehicle to drive into other empty lanes or control the vehicle to slow down. When the vehicle slows down, PECC re-plans a new optimal speed curve based on the current speed of the vehicle.
[0004] However, when replanning the optimal speed curve of the vehicle through PECC, the existing technology has problems of repeated planning and untimely planning. Summary of the invention
[0005] The present application provides a control method, device, vehicle and medium for replanning a speed curve to solve the problems of repeated planning and untimely planning in the prior art when replanning the optimal speed curve of a vehicle through PECC.
[0006] In a first aspect, an embodiment of the present application provides a control method for replanning a speed curve, which is applied to a vehicle equipped with a PECC, and the method includes:
[0007] When controlling the vehicle to travel according to the first speed curve planned by the PECC, predicting the first trajectory of the adjacent vehicle in a future time period according to the position information of the adjacent vehicle at multiple sampling moments;
[0008] determining a second trajectory of the vehicle at the future time period;
[0009] Determining driving information of the vehicle and the adjacent vehicle according to the first trajectory and the second trajectory, wherein the driving information is used to indicate whether the vehicle and the adjacent vehicle will collide;
[0010] Replanning of the first speed profile is triggered according to the driving information.
[0011] In one possible design, the adjacent vehicles include adjacent vehicles in the lane where the vehicle is located and adjacent vehicles in other lanes. Whether the vehicle and the adjacent vehicles will collide includes a collision between the vehicle and the adjacent vehicle without changing lanes, and a collision between the vehicle or one of the adjacent vehicles due to changing lanes.
[0012] In a possible design, when the driving information indicates that the vehicle and the adjacent vehicle are likely to collide, the driving information further includes collision information between the vehicle and the adjacent vehicle, and triggering re-planning of the first speed curve according to the driving information includes:
[0013] When the driving information indicates that the vehicle and the adjacent vehicle will not collide, causing the PECC to not trigger re-planning of the first speed curve;
[0014] When the driving information indicates that the vehicle and the adjacent vehicle will collide, and the collision information satisfies a preset re-planning condition, triggering the PECC to re-plan the first speed curve to obtain a second speed curve;
[0015] When the driving information indicates that the vehicle and the adjacent vehicle may collide, but the collision information does not satisfy the preset re-planning condition, the PECC does not trigger re-planning of the first speed curve.
[0016] In a possible design, the collision information includes a collision position between the vehicle and the adjacent vehicle and a first speed difference between the adjacent vehicle and the vehicle at the time of the collision, and when the driving information indicates that the vehicle and the adjacent vehicle will collide, but the collision information does not meet the preset re-planning condition, so that the PECC does not trigger re-planning of the first speed curve, including:
[0017] When the driving information indicates that the vehicle and the adjacent vehicle are about to collide, calculating a first longitudinal distance between the collision position and a current position of the vehicle;
[0018] If the first longitudinal distance is greater than a first preset distance, and / or a first speed difference between the adjacent vehicle and the vehicle is greater than a first preset speed, the PECC does not trigger re-planning of the first speed curve;
[0019] The preset re-planning condition is that the first longitudinal distance does not exceed the first preset distance, and the first speed difference between the adjacent vehicle and the vehicle does not exceed the first preset speed.
[0020] In a possible design, when the driving information indicates that the vehicle and the adjacent vehicle will collide, and the collision information satisfies a preset re-planning condition, triggering the PECC to re-plan the first speed curve to obtain a second speed curve, including:
[0021] When the driving information indicates that the vehicle and the adjacent vehicle will collide, and the first longitudinal distance does not exceed the first preset distance, and the first speed difference between the adjacent vehicle and the vehicle does not exceed the first preset speed, the PECC is triggered to re-plan the first speed curve to obtain a second speed curve.
[0022] In a possible design, when the adjacent vehicle is an adjacent vehicle in the other lane and changes lanes to the lane where the vehicle is located, the method further includes:
[0023] When the driving information indicates that the vehicle and the adjacent vehicle are likely to collide, calculating a second longitudinal distance between a current position of the adjacent vehicle and a current position of the vehicle,
[0024] If the second longitudinal distance is greater than a second preset distance, and / or the second speed difference between the adjacent vehicle and the vehicle is less than a second preset speed, the PECC does not trigger re-planning of the first speed curve.
[0025] In one possible design, the second preset distance is not greater than the first preset distance.
[0026] In a possible design, predicting the first trajectory of the adjacent vehicle in a future time period according to the position information of the adjacent vehicle at multiple sampling moments includes:
[0027] According to the type of the adjacent vehicle, the speed and position information of the adjacent vehicle at multiple sampling moments, a first trajectory of the adjacent vehicle in the future time period is predicted by a preset path prediction model.
[0028] In one possible design, the method further includes:
[0029] When the vehicle is controlled to travel according to the first speed curve, the position information of the adjacent vehicle is collected at a plurality of sampling moments through the front sensing system of the vehicle.
[0030] In a second aspect, an embodiment of the present application provides a control device for replanning a speed curve, which is applied to a vehicle equipped with a PECC, and the device includes:
[0031] A prediction module, configured to predict a first trajectory of the adjacent vehicle in a future time period based on position information of the adjacent vehicle at a plurality of sampling moments when the vehicle is controlled to travel according to the first speed curve planned by the PECC;
[0032] A first determination module, configured to determine a second trajectory of the vehicle in the future time period;
[0033] A second determination module, configured to determine driving information of the vehicle and the adjacent vehicle according to the first trajectory and the second trajectory, wherein the driving information is used to indicate whether a collision will occur between the vehicle and the adjacent vehicle;
[0034] A trigger module is used to trigger re-planning of the first speed curve according to the driving information.
[0035] In one possible design, the adjacent vehicles include adjacent vehicles in the lane where the vehicle is located and adjacent vehicles in other lanes. Whether the vehicle and the adjacent vehicles will collide includes a collision between the vehicle and the adjacent vehicle without changing lanes, and a collision between the vehicle or one of the adjacent vehicles due to changing lanes.
[0036] In a possible design, when the driving information indicates that the vehicle and the adjacent vehicle will collide, the driving information also includes collision information between the vehicle and the adjacent vehicle, and the trigger module is specifically configured to:
[0037] When the driving information indicates that the vehicle and the adjacent vehicle will not collide, causing the PECC to not trigger re-planning of the first speed curve;
[0038] When the driving information indicates that the vehicle and the adjacent vehicle will collide, and the collision information satisfies a preset re-planning condition, triggering the PECC to re-plan the first speed curve to obtain a second speed curve;
[0039] When the driving information indicates that the vehicle and the adjacent vehicle may collide, but the collision information does not satisfy the preset re-planning condition, the PECC does not trigger re-planning of the first speed curve.
[0040] In a possible design, the collision information includes a collision position between the vehicle and the adjacent vehicle and a first speed difference between the adjacent vehicle and the vehicle at the time of the collision, and the trigger module is specifically configured to:
[0041] When the driving information indicates that the vehicle and the adjacent vehicle are about to collide, calculating a first longitudinal distance between the collision position and a current position of the vehicle;
[0042] If the first longitudinal distance is greater than a first preset distance, and / or a first speed difference between the adjacent vehicle and the vehicle is greater than a first preset speed, the PECC does not trigger re-planning of the first speed curve;
[0043] The preset re-planning condition is that the first longitudinal distance does not exceed the first preset distance, and the first speed difference between the adjacent vehicle and the vehicle does not exceed the first preset speed.
[0044] In a possible design, when the driving information indicates that the vehicle and the adjacent vehicle will collide, and the collision information satisfies a preset re-planning condition, the trigger module is specifically configured to:
[0045] When the driving information indicates that the vehicle and the adjacent vehicle will collide, and the first longitudinal distance does not exceed the first preset distance, and the first speed difference between the adjacent vehicle and the vehicle does not exceed the first preset speed, the PECC is triggered to re-plan the first speed curve to obtain a second speed curve.
[0046] In a possible design, when the adjacent vehicle is an adjacent vehicle in the other lane and changes lanes to the lane where the vehicle is located, the trigger module is further used to:
[0047] When the driving information indicates that the vehicle and the adjacent vehicle are likely to collide, calculating a second longitudinal distance between a current position of the adjacent vehicle and a current position of the vehicle;
[0048] If the second longitudinal distance is greater than a second preset distance, and / or the second speed difference between the adjacent vehicle and the vehicle is less than a second preset speed, the PECC does not trigger re-planning of the first speed curve.
[0049] In one possible design, the second preset distance is not greater than the first preset distance.
[0050] In a possible design, the prediction module is specifically used to:
[0051] According to the type of the adjacent vehicle, the speed and position information of the adjacent vehicle at multiple sampling moments, a first trajectory of the adjacent vehicle in the future time period is predicted by a preset path prediction model.
[0052] In a possible design, the speed curve re-planning control device also includes a collection module for collecting position information of the adjacent vehicle at multiple sampling times through the vehicle's front sensing system when controlling the vehicle to travel according to the first speed curve.
[0053] In a third aspect, an embodiment of the present application provides a vehicle, comprising: a vehicle body and a vehicle controller;
[0054] Wherein, the vehicle controller includes a processor and a memory;
[0055] The memory stores computer-executable instructions;
[0056] The processor executes the computer-executable instructions stored in the memory to implement the methods provided in the first aspect, the second aspect and various possible designs.
[0057] In a fourth aspect, an embodiment of the present application may provide a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the first aspect, the second aspect, and various possible designs.
[0058] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, is used to implement the first aspect and the methods provided by various possible designs.
[0059] The control method, device, vehicle and medium for re-planning the speed curve provided in the embodiment of the present application are applied to vehicles deployed with PECC. When controlling the vehicle to travel according to the first speed curve planned by PECC, firstly, the first trajectory of the adjacent vehicle in the future time period is predicted based on the position information of the adjacent vehicle at multiple sampling times. Then, the second trajectory of the vehicle in the future time period is determined; and the driving information of the vehicle and the adjacent vehicle is determined based on the first trajectory and the second trajectory. Finally, the re-planning of the first speed curve is triggered based on the driving information. Among them, the driving information is used to indicate whether the vehicle and the adjacent vehicle will collide. In this technical solution, by predicting whether there will be a collision between the vehicle and the adjacent vehicle, and then predicting whether the vehicle needs to slow down, the first speed curve is triggered to be re-planned when it is predicted that the vehicle will slow down. This can not only avoid repeated re-planning of the first speed curve during the deceleration process, but also ensure that the re-planned second speed curve can be applied in time, thereby reducing the fuel consumption of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0061] Figure 1 A schematic diagram of a scenario of a first embodiment of a control method for replanning a speed curve provided in an embodiment of the present application;
[0062] Figure 2 A schematic diagram of a scenario of a second embodiment of a control method for replanning a speed curve provided in an embodiment of the present application;
[0063] Figure 3 A schematic flow chart of a first embodiment of a control method for replanning a speed curve provided in an embodiment of the present application;
[0064] Figure 4 A schematic flow chart of a second embodiment of a control method for replanning a speed curve provided in an embodiment of the present application;
[0065] Figure 5 A flow chart of a third embodiment of a control method for replanning a speed curve provided in an embodiment of the present application;
[0066] Fig. 6A A schematic diagram of a first embodiment of a second speed curve provided in an embodiment of the present application;
[0067] Figure 6B A schematic diagram of a second speed curve embodiment 2 provided in an embodiment of the present application;
[0068] Figure 7 A schematic diagram of the structure of a first embodiment of a control device for replanning a speed curve provided in an embodiment of the present application;
[0069] Figure 8 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application.
[0070] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION
[0071] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0072] Before introducing the embodiments of the present application, the application background of the embodiments of the present application is first explained:
[0073] Cruise Control System (CC) is a basic driver assistance system, which was originally introduced to solve the driver's fatigue and comfort problems during long-distance highway driving. The driver can set a desired cruising speed in advance, and CC will maintain the vehicle at the cruising speed without the driver having to continuously step on the accelerator pedal, effectively reducing the driver's burden and fatigue on the accelerator pedal.
[0074] However, the traditional CC system cannot adapt to the changes in the vehicle in front, which may cause the driver to be too close or too far away from the vehicle in front. In order to further improve driving safety, the Adaptive Cruise Control (ACC) was introduced. ACC uses sensors such as radar, laser or camera to sense the position and speed of the vehicle in front and automatically adjust the speed to maintain a safe distance. The introduction of ACC improves the reliability and performance of the driving assistance system and reduces the risk of collision between the driver and the vehicle in front.
[0075] Furthermore, ACC and CC have poor performance in energy conservation and environmental protection, especially fuel economy, and high fuel consumption. Based on this, the Predictive Economic Cruise Control (PECC) was introduced. PECC can predict road conditions, such as curves, uphills, downhills, etc. Based on these predictions, the vehicle speed and control strategy are adjusted in advance to achieve more intelligent, efficient and safe driving.
[0076] Specifically, PECC can use GNSS to achieve precise positioning. Then, the positioning information obtained by GNSS is matched with the ADAS map to determine the vehicle position, and then obtain the road ahead information. Finally, according to the road ahead information, the optimal speed curve is planned to optimize the vehicle speed and coordinate the vehicle actuator system to solve the problem of high fuel consumption of ACC.
[0077] The optimal speed curve refers to the speed curve at which the vehicle has the lowest fuel consumption.
[0078] However, the neighboring vehicles in the adjacent lanes will interfere with the vehicle's driving according to the optimal speed curve. In practical applications, assuming that the relative speed of the vehicle ahead is negative, that is, when the vehicle ahead approaches the vehicle, in order for the vehicle to continue to drive according to the optimal speed curve planned by PECC, the driver needs to control the vehicle to switch to another lane.
[0079] However, in most cases, when the adjacent vehicle wants to insert into the lane where this vehicle is located, or the adjacent vehicle wants to quickly cut in and out of the lane where this vehicle is located, or this vehicle wants to change lanes to the lane where the adjacent vehicle is located, it is difficult for the driver to control the vehicle to change lanes in the above situations to maintain the optimal speed curve planned by the current PECC. At this time, it is necessary to control the vehicle to decelerate according to the above specific circumstances.
[0080] It should be understood that during the above deceleration process, PECC will re-plan the optimal speed curve.
[0081] Since PECC needs to re-plan the optimal speed curve according to the current speed of the vehicle, and the speed of the vehicle is constantly changing during deceleration, it is unnecessary to repeatedly re-plan the optimal speed curve. In addition, it takes time for PECC to re-plan the optimal speed curve, and it is impossible to generate a new optimal speed curve in time. During the re-planning process, the vehicle cannot be controlled to travel at the most fuel-efficient speed.
[0082] In summary, when replanning the optimal speed curve of a vehicle through PECC, the existing technology has problems of repeated planning and untimely planning, which makes it impossible to ensure that the vehicle runs with lower fuel consumption.
[0083] Based on the above technical problems, the technical concept of the present application is as follows: when the vehicle is traveling according to the speed curve planned by PECC, it can be predicted whether the vehicle can maintain the speed curve based on the driving conditions of adjacent vehicles and the driving conditions of the vehicle. If not, it triggers a re-planning of the speed curve. In this way, it is possible to avoid multiple re-planning of the speed curve during the speed change process, and because the speed curve is re-planned during the speed change process of the vehicle, it is possible to ensure that the vehicle can continue to travel according to the new speed curve in time after the speed change, thereby reducing fuel consumption as much as possible and avoiding false triggering of the re-planning of the speed curve.
[0084] For example, the speed curve re-planning control method provided in the embodiment of the present application can be applied to Figure 1 The scene diagram shown. Figure 1 Schematic diagram of a scenario of a first embodiment of a control method for replanning a speed curve provided in an embodiment of the present application. Figure 1 As shown, the scenario includes: a host vehicle 11 traveling in a host lane, an adjacent vehicle 12 traveling in an adjacent lane, and a server 13 capable of communicating with the host vehicle 11 and the adjacent vehicle 12. The host vehicle 11 is deployed with PECC.
[0085] In actual applications, the vehicle 11 may be pre-configured with a variety of sensors, such as cameras, laser radars, etc., and the position information of the adjacent vehicles 12 may be collected based on these sensors. The vehicle 11 may also be pre-configured with a front sensing system, and the position information of the adjacent vehicles 12 may be collected based on the front sensing system. The vehicle 11 may also obtain the position information of the adjacent vehicles 11 within a preset range around the vehicle 11 from the server 13. The vehicle 11 may also obtain the position information of the adjacent vehicles 12 within a preset range around the vehicle 11 through vehicle-to-vehicle communication. It should be understood that vehicle-to-vehicle communication may be established in real time, may be established in advance, or may be established by other possible means. The present application does not limit the method of establishing vehicle-to-vehicle communication, nor does it limit the communication method adopted by vehicle-to-vehicle communication.
[0086] It should be understood that the position information of the adjacent vehicle 12 can also be obtained by a combination of the above-mentioned various acquisition methods. For example, there is an adjacent vehicle A on the left side of the vehicle 11 and an adjacent vehicle B on the right side, and the adjacent vehicle A can establish vehicle-to-vehicle communication with the vehicle 11, but the adjacent vehicle B cannot establish vehicle-to-vehicle communication with the vehicle 11. Then, the position information of the adjacent vehicle A can be obtained by vehicle-to-vehicle communication, and the position information of the adjacent vehicle B can be obtained from the server 13.
[0087] Furthermore, the front sensing system is described in detail.
[0088] Figure 2 Schematic diagram of the scenario of the second embodiment of the control method for replanning the speed curve provided in the embodiment of the present application. Figure 2 As shown, the vehicle 11 is equipped with a front sensing system, which can detect adjacent vehicles 12 in adjacent lanes within its field of view (FOV). The larger the FOV of the front sensing system, the wider the field of view of the front sensing system, and the closer the vehicle 11 is to the adjacent vehicle 12 that wants to cut into the lane, the stronger the detection capability.
[0089] The minimum half-lane detection distance generally refers to the shortest distance at which the front sensing system can effectively detect the side half lane (i.e., the lane on one side) when the vehicle 11 is driving. This distance can affect the detection and perception of the vehicle 11's surrounding environment, helping to ensure that the front sensing system can promptly and accurately identify potential obstacles, vehicles, or other traffic conditions. By setting the minimum half-lane detection distance, it can help improve the safety of the vehicle 11 and the effectiveness of the driving assistance function.
[0090] Exemplarily, Table 1 shows the mapping relationship between FOV, lane width, and minimum half-lane detection distance.
[0091] Table 1
[0092]
[0093] Referring to Table 1, when the lane width is the same, the larger the FOV, the smaller the minimum half-lane detection distance, and the larger the field of view of the front sensing system.
[0094] In actual applications, when an adjacent vehicle 12 within 20m of the vehicle 11 wants to insert into the lane, this situation is very dangerous and the vehicle 11 needs to brake immediately and exit the PECC. This process does not involve re-planning of the speed curve. Referring to Table 1, an ordinary narrow field of view (12°) can provide the front sensing system with a detection distance greater than 36m (the distance between the vehicle 11 and the adjacent vehicle 12), which is sufficient to meet most highway scenarios and can ensure that the vehicle 11 has sufficient time to re-plan the PECC. In other words, a front sensing system with an ordinary narrow field of view (12°) can meet the requirements of this application. Of course, in order to further ensure the timeliness of obtaining the position information of the adjacent vehicle 12 and enhance the detection capability of the adjacent vehicle 12, a front sensing system with a larger FOV can also be used. In actual use, the specific FOV of the front sensing system can be determined according to actual needs, and the embodiments of the present application do not impose specific restrictions on this.
[0095] The technical solution of the present application is described in detail below through specific embodiments.
[0096] It should be noted that the following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.
[0097] Firstly, the control scheme for speed curve replanning is elaborated in detail in view of the interference factor of adjacent vehicles.
[0098] Figure 3 The flowchart of the control method for replanning the speed curve provided in the embodiment of the present application is shown in FIG. Figure 3 As shown, the control method for replanning the speed curve may include the following steps:
[0099] S31. When controlling the vehicle to travel according to the first speed curve planned by PECC, predict the first trajectory of the adjacent vehicle in the future time period according to the position information of the adjacent vehicle at multiple sampling moments.
[0100] The embodiments of the present application are applied to a vehicle deployed with PECC, namely the vehicle in the above embodiments.
[0101] In this step, PECC can predict the road conditions on which the vehicle is traveling, generate a first speed curve based on the predicted road conditions, and control the vehicle to travel according to the first speed curve. At the same time, the vehicle also needs to obtain the position information of adjacent vehicles in real time, so as to predict the first trajectory of the adjacent vehicles in the future time period based on the position information of the adjacent vehicles, and then determine whether the adjacent vehicles will affect the vehicle to continue to travel according to the first speed curve.
[0102] Optionally, the adjacent vehicles include adjacent vehicles in the lane where the vehicle is located and adjacent vehicles in other lanes. For example, the adjacent vehicle can be the preceding vehicle of the vehicle or a vehicle traveling in an adjacent lane.
[0103] In a possible implementation, the first trajectory of the adjacent vehicle in the future time period may be predicted by a preset path prediction model according to the type of the adjacent vehicle, the speed and position information of the adjacent vehicle at multiple sampling moments.
[0104] Exemplarily, the preset path prediction model may be at least one of the following three:
[0105] Preset path prediction model 1: The preset path prediction model 1 includes preset formulas and preset parameters corresponding to different vehicle types. The preset path prediction model 1 can determine the corresponding preset formulas and preset parameters according to the type of the adjacent vehicle, and perform real-time extrapolation based on the speed and position information of the adjacent vehicle at multiple acquisition times through the preset formulas and preset parameters, thereby predicting the first trajectory of the adjacent vehicle in the future time period. Among them, the preset path prediction model 1 does not require prior data.
[0106] Preset path prediction model 2: Preset path prediction model 2 can use Gaussian process regression to fit the speed and position information of the adjacent vehicle at multiple sampling times based on the type of the adjacent vehicle, so as to predict the first trajectory of the adjacent vehicle in the future time period. Preset path prediction model 2 can also use Markov chain or Bayesian network, which requires to establish conditional probability in advance through the speed vector of the historical trajectory of different types of vehicles, and then in the prediction process, predict the first trajectory of the adjacent vehicle in the future time period according to the type of the adjacent vehicle, the speed and position information of the adjacent vehicle at multiple sampling times and the pre-established conditional probability.
[0107] Preset path prediction model 3: The preset path prediction model 3 uses neural networks, for example, long short-term memory networks (LSTM), sequence to sequence (seq2seq) and their extended versions. The preset path prediction model 3 needs to be pre-trained using a training set, where the training set is the type and trajectory of the sample vehicle, and the trajectory includes the speed and position of the sample vehicle at each sample time. In the actual prediction process, the type of adjacent vehicles, the speed and position information of adjacent vehicles at multiple sampling times can be input into the preset path prediction model 3, so as to obtain the first trajectory of the adjacent vehicles in the future time period output by the preset path prediction model 3.
[0108] Optionally, the future time period may be a period of time after the current moment, such as 1 minute, 2 minutes, 3 minutes, etc., which may be determined based on actual conditions, and the embodiments of the present application do not impose specific restrictions on this.
[0109] It should be understood that which specific preset path prediction model to use needs to be determined based on actual factors such as available R&D resources, available data, available verification resources, controller computing power and storage capacity, and this application does not impose specific restrictions on this.
[0110] It should be understood that multiple preset path prediction models can also be used simultaneously to jointly predict the first trajectory of adjacent vehicles in future time periods. Exemplarily, the preset path prediction model 1 can be used to predict the first trajectory of the adjacent vehicle, and the first trajectory can be verified in real time during the vehicle's driving. If the verification finds that the accuracy of the first trajectory predicted by the preset path prediction model 1 is low, the preset path prediction model 1 is controlled to replace other preset formulas and / or preset parameters corresponding to the type of the adjacent vehicle and re-predict. If the accuracy of the first trajectory predicted by the preset path prediction model 1 is still low after replacing the preset formulas and / or preset parameters multiple times, other preset path prediction models (such as preset path prediction model 2) are used to predict the first trajectory of the adjacent vehicle.
[0111] Among them, when judging the accuracy of the first trajectory, the first trajectory can be directly compared with the actual driving trajectory of the adjacent vehicle. If the difference is large, it means that the accuracy of the first trajectory is low. On the contrary, if the difference is small, it means that the accuracy of the first trajectory is high. Optionally, since it can be judged in advance whether the adjacent vehicle is going to change lanes according to the state of the turn signal of the adjacent vehicle, the judgment can also be made in combination with the turn signal of the adjacent vehicle. For example, the predicted first trajectory of the adjacent vehicle is to travel along the lane where the adjacent vehicle is located, and the actual driving trajectory of the adjacent vehicle is also to travel along the lane where the adjacent vehicle is located, but the turn signal of the adjacent vehicle is turned on, indicating that the adjacent vehicle has the intention to turn. At this time, although the first trajectory is slightly different from the actual driving trajectory of the adjacent vehicle, the first trajectory does not predict that the adjacent vehicle is going to turn, so it is considered that the accuracy of the first trajectory is low.
[0112] Optionally, during the driving process of the adjacent vehicle, the new position information of the adjacent vehicle can be collected in real time and input into the preset path prediction model, so that multiple first trajectories of the adjacent vehicle can be obtained by combining the previously collected position information for multiple iterations. Furthermore, according to the convergence of the prediction, the uncertainty of each first trajectory can be calculated, and the uncertainty is used to determine the accuracy of the first trajectory.
[0113] For another example, all preset path prediction models can be used to simultaneously predict the initial first trajectories of adjacent vehicles and the uncertainty corresponding to each initial first trajectory, determine the accuracy of each initial first trajectory according to the uncertainty, and determine the initial first trajectory with the highest accuracy as the first trajectory.
[0114] Optionally, if the turn signal of the adjacent vehicle is turned on before the adjacent vehicle changes lanes or when the lane change trend appears, the lane change intention of the adjacent vehicle can be determined by the turn signal, and the correctness of the first trajectory can be judged by the lane change intention, so that the convergence criterion of the preset path prediction model can be set higher, so as to output the prediction result (i.e., the first trajectory) in advance and reduce uncertainty. Otherwise, if the turn signal is performed at the same time as the lane departure action or the turn signal is later than the lane departure action, similar processing of the convergence criterion and uncertainty can be implemented.
[0115] Optionally, when controlling the vehicle to travel according to the first speed curve, it is necessary to obtain the position information of the adjacent vehicle at each collection moment. The specific acquisition method will be described in detail in the following embodiments and will not be repeated here.
[0116] S32: Determine a second trajectory of the vehicle in a future time period.
[0117] In this step, during the driving process of the vehicle, it is also necessary to determine the second trajectory of the vehicle in the future time period, so as to determine whether there is a risk of collision between the vehicle and the adjacent vehicle based on the first trajectory and the second trajectory, and then determine whether the first speed curve needs to be re-planned.
[0118] In a possible implementation, the vehicle's driving trajectory can be input into a preset path prediction model, thereby obtaining a second trajectory of the vehicle in a future time period output by the preset path prediction model. It should be understood that the processing of the preset path prediction model can refer to the relevant content in S31, which will not be repeated here.
[0119] In a possible implementation, the second trajectory of the vehicle may also be determined based on the steering wheel angle of the vehicle, the driving trajectory of the vehicle, and the state of the turn signal.
[0120] In another possible implementation, if an intelligent driving system is deployed in the vehicle, the second trajectory of the vehicle can also be determined by the intelligent driving system.
[0121] S33. Determine driving information of the vehicle and adjacent vehicles according to the first trajectory and the second trajectory.
[0122] In this step, in actual driving, when the driver finds that the vehicle may collide with an adjacent vehicle, he will control the vehicle to decelerate, and the deceleration process will involve re-planning the first speed curve. Therefore, after predicting the first trajectory of the adjacent vehicle and the second trajectory of the vehicle, it is possible to determine whether the vehicle and the adjacent vehicle will collide based on the first trajectory and the second trajectory, that is, determine the driving information of the vehicle and the adjacent vehicle, and the driving information is used to indicate whether the vehicle and the adjacent vehicle will collide. In this way, it is possible to determine whether the first speed curve needs to be re-planned in advance based on the driving information, thereby ensuring the timeliness of the re-planning.
[0123] Among them, whether the vehicle and the adjacent vehicle will collide includes the collision between the vehicle and the adjacent vehicle when neither of them changes lanes, and the collision between the vehicle and one of the adjacent vehicles when changing lanes.
[0124] In a possible implementation, it can be determined whether the first trajectory and the second trajectory have an intersection. If so, driving information indicating that the vehicle and the adjacent vehicle will collide is determined; otherwise, driving information indicating that the vehicle and the adjacent vehicle will not collide is determined.
[0125] S34. Controlling the re-planning of the first speed curve according to the driving information.
[0126] In this step, if the driving information indicates that the vehicle and the adjacent vehicle will not collide in the future time period, it means that the vehicle can maintain the first speed curve, and there is no need to plan the first speed curve. If the driving information indicates that the vehicle and the adjacent vehicle will collide in the future time period, and the driver needs to control the vehicle to slow down in order to avoid the collision, it is necessary to re-plan the first speed curve. Therefore, in this case, the first speed curve can be re-planned in advance, which can effectively improve the timeliness of re-planning and avoid the problem of multiple re-planning.
[0127] In a possible implementation, when the driving information indicates that the vehicle and the adjacent vehicle will collide in the future time period, it can be further determined whether a preset re-planning condition is satisfied. The preset re-planning condition is a condition set in advance and used to further analyze the possibility of collision between the two vehicles. By determining whether the driving information satisfies the preset re-planning condition, the first speed curve is re-planned when the preset re-planning condition is satisfied, and the first speed curve is not re-planned when the preset re-planning condition is not satisfied, thereby further improving the accuracy of re-planning the speed curve.
[0128] It should be understood that the implementation process and principle of this step will be Figure 4 The detailed description is given in the illustrated embodiment and will not be repeated here.
[0129] The control method for replanning the speed curve provided in the embodiment of the present application is applied to vehicles deployed with PECC. When controlling the vehicle to travel according to the first speed curve planned by PECC, firstly, the first trajectory of the adjacent vehicle in the future time period is predicted based on the position information of the adjacent vehicle at multiple sampling times. Then, the second trajectory of the vehicle in the future time period is determined; based on the first trajectory and the second trajectory, the driving information of the vehicle and the adjacent vehicle is determined. Finally, based on the driving information, the replanning of the first speed curve is triggered. Among them, the driving information is used to indicate whether the vehicle and the adjacent vehicle will collide. In this technical solution, by predicting whether there will be a collision between the vehicle and the adjacent vehicle, and then predicting whether the vehicle needs to slow down, the first speed curve is triggered to be replanned when it is predicted that the vehicle will slow down. This can not only avoid repeated replanning of the first speed curve during the deceleration process, but also ensure that the replanned second speed curve can be applied in time, thereby reducing the fuel consumption of the vehicle.
[0130] Optionally, in some embodiments, when controlling the vehicle to travel according to the first speed curve, it is necessary to obtain position information of adjacent vehicles at each collection moment.
[0131] Among them, the location information of adjacent vehicles can be collected at multiple sampling times through the vehicle's front sensing system; when ACC is deployed in the vehicle, the location information of adjacent vehicles can also be collected at multiple sampling times through relevant sensors; the location information of adjacent vehicles can also be obtained from the server.
[0132] Exemplarily, the position information includes the relative distance and azimuth of the adjacent vehicle relative to the vehicle. The image of the adjacent vehicle can be collected by the front sensing system at each sampling time, and the size of the adjacent vehicle can be determined based on the image of the adjacent vehicle, and then the center of the adjacent vehicle can be determined, so as to determine the relative distance and azimuth of the adjacent vehicle relative to the vehicle according to the center of the adjacent vehicle and the center of the vehicle. It should be understood that the center can be the center of the front axle of the vehicle, or the geometric center of the vehicle, or a center defined by other concepts.
[0133] Among them, if the front sensing system can obtain a complete image of the adjacent vehicle, the center of the adjacent vehicle can be directly determined based on the size of the adjacent vehicle; if the front sensing system can only obtain a partial image of the adjacent vehicle, for example, only a side window and a front / rear wheel of the adjacent vehicle can be obtained, the size of the vehicle needs to be estimated based on this. Exemplarily, the size of the vehicle can be determined by looking up a table according to the type of vehicle and the distance between the side window and the front / rear wheel. If the partial image of the adjacent vehicle obtained by the front sensing system includes the model of the adjacent vehicle, the size corresponding to the model can also be directly queried through the network.
[0134] It should be understood that the relative distance between each part of the adjacent vehicle and the center of the adjacent vehicle is fixed, and when more parts of the adjacent vehicle are collected at subsequent collection moments, it is necessary to establish an association between these parts and the center. In this way, at subsequent collection moments, after the part of the vehicle that previously appeared in the field of view of the front sensing system disappears, the midpoint of the adjacent vehicle can still be determined by the part of the vehicle that subsequently appears in the field of view of the front sensing system.
[0135] Optionally, when obtaining the position information of the adjacent vehicle, the speed of the adjacent vehicle may also be obtained at the same time, wherein the speed includes the relative speed and speed direction of the adjacent vehicle relative to the vehicle.
[0136] Exemplarily, the speed of the adjacent vehicles at each collection moment can be directly collected by relevant sensors, and the indirect speed of the adjacent vehicles can be derived based on the difference in position information of the adjacent vehicles at adjacent collection moments, and the indirect speed can be assigned to the previous collection moment in the adjacent collection moments.
[0137] In practical applications, in order to ensure the accuracy of determining the first trajectory of adjacent vehicles, there should be no less than 3 sampling moments. The sampling moment can be determined according to a preset frequency, for example, once per second, once per 5 seconds, once per 10 seconds, etc. If the sampling moment is determined, it can be determined according to actual conditions, and this application does not impose specific restrictions on this.
[0138] Optionally, when the driving information indicates that the vehicle and the adjacent vehicle are likely to collide, the driving information further includes collision information between the vehicle and the adjacent vehicle. Figure 3 In the embodiment shown, by Figure 4 The illustrated embodiment provides an expanded description of S34.
[0139] Figure 4 The flowchart of the second embodiment of the control method for replanning the speed curve provided in the embodiment of the present application is shown in FIG. Figure 4 As shown, S34 can be implemented by the following steps:
[0140] S41. When the driving information indicates that the vehicle and the adjacent vehicle will not collide, enable PECC not to trigger re-planning of the first speed curve.
[0141] In this step, if the driving information indicates that the vehicle and the adjacent vehicle will not collide in the future time period, it means that the vehicle can maintain the first speed curve. At this time, there is no need to re-plan the first speed curve, so that PECC does not trigger the re-planning of the first speed curve, avoiding re-planning caused by vehicle deceleration when changing lanes.
[0142] S42: When the driving information indicates that the vehicle and the adjacent vehicle will collide, and the collision information meets the preset re-planning condition, trigger PECC to re-plan the first speed curve to obtain a second speed curve.
[0143] In this step, when the driving information indicates that the vehicle and the adjacent vehicle will collide, the possibility of a collision between the two in actual application can be further judged based on the driving information, so that when it is judged that the possibility of a collision between the two is high, the PECC is controlled to perform a re-planning of the first speed curve to obtain the second speed curve, thereby further improving the accuracy of the re-planning of the first speed curve.
[0144] In one possible implementation, when driving information indicates that a vehicle and an adjacent vehicle will collide, and the first longitudinal distance does not exceed a first preset distance, and the first speed difference between the adjacent vehicle and the vehicle does not exceed the first preset speed, PECC is triggered to re-plan the first speed curve to obtain a second speed curve.
[0145] In this implementation, the collision information includes the collision position between the vehicle and the adjacent vehicle and the first speed difference between the adjacent vehicle and the vehicle at the time of the collision. When the driving information indicates that the vehicle and the adjacent vehicle will collide, the first longitudinal distance between the collision position and the current position of the vehicle and the first speed difference between the adjacent vehicle and the vehicle at the collision point can be calculated.
[0146] It should be understood that the first speed difference between the adjacent vehicle and the vehicle refers to the speed difference obtained by subtracting the speed of the vehicle at the collision point from the speed of the adjacent vehicle at the collision point.
[0147] When the first longitudinal distance does not exceed the first preset distance, and the first speed difference between the adjacent vehicles does not exceed the first preset speed, it means that the vehicle is close to the collision point, and the speed difference between the vehicle and the adjacent vehicle is small. The possibility of the vehicle and the adjacent vehicle changing lanes again before the collision occurs is very low. Therefore, it is necessary to trigger PECC in advance before the vehicle decelerates to re-plan the first speed curve and obtain the second speed curve so that the second speed curve can be applied in time later.
[0148] It should be understood that the first preset distance and the first preset speed can be pre-set according to actual conditions. Normally, the first preset distance is a larger value, such as 1 km, 1.5 km, 2 km, etc. The first preset distance can provide the driver with a certain amount of time to process lane changes.
[0149] In this implementation, the preset re-planning condition is that the first longitudinal distance does not exceed the first preset distance, and the first speed does not exceed the preset speed.
[0150] S43: When the driving information indicates that the vehicle and the adjacent vehicle will collide, but the collision information does not meet the preset re-planning condition, the PECC does not trigger the re-planning of the first speed curve.
[0151] In this step, when the driving information indicates that the vehicle and the adjacent vehicle will collide, and it is judged that the possibility of a collision between the two in real life is small, PECC does not trigger the re-planning of the first speed curve, so as to avoid re-planning caused by the vehicle's deceleration when changing speed.
[0152] In a possible implementation, if the first longitudinal distance is greater than the first preset distance, and / or the first speed difference between the adjacent vehicles and the vehicle is greater than the first preset speed, PECC does not trigger re-planning of the first speed curve.
[0153] Among them, if the first longitudinal distance is greater than the first preset distance, it means that the collision point is far away from the current position of the vehicle. During the driving process before reaching the collision point, the driver will change lanes according to the actual driving situation, thereby maintaining the vehicle driving according to the first speed curve. Therefore, there is no need to re-plan the first speed curve.
[0154] Among them, since the first speed difference between the adjacent vehicle and the vehicle is greater than the first preset speed, it means that the speed of the adjacent vehicle is much greater than the speed of the vehicle. This situation often occurs when the adjacent vehicle is the rear vehicle of the vehicle and accelerates to hit the vehicle; or when the adjacent vehicle is a vehicle driving on the side and rear of the adjacent lane and accelerates to hit the vehicle when / after changing lanes. In real life, the driver of the adjacent vehicle will also control the speed of the vehicle according to the surrounding environment. The probability of this situation occurring under normal driving is extremely low because there is no need to trigger the re-planning of the first speed curve.
[0155] In the above embodiment, after determining whether a collision occurs between a vehicle and an adjacent vehicle based on driving information, it is also possible to determine whether the collision will actually occur in real life based on preset re-planning conditions, or in other words, determine whether the collision is difficult to avoid in real life, so that when it is determined that the collision will actually occur, that is, the collision is difficult to avoid, the first speed curve is re-planned in advance, otherwise, the PECC re-planning of the first speed curve is not triggered.
[0156] It should be understood that when it is necessary to control PECC to re-plan the first speed curve, PECC can be controlled to re-plan the first speed curve immediately, or PECC can be controlled to re-plan the first speed curve after the vehicle changes lanes to the lane where the adjacent vehicle is located. In other words, the time of executing re-planning can be determined according to actual conditions, and the embodiments of the present application do not impose specific restrictions on this.
[0157] Regarding the case where the adjacent vehicle is an adjacent vehicle in another lane and changes lanes to the lane where the vehicle is located, a specific embodiment is used to explain it.
[0158] Optionally, Figure 5 The flowchart of the control method for replanning the speed curve provided in the present application is a third embodiment. Figure 5 As shown, the speed curve re-planning control method may further include the following steps:
[0159] S51. When the driving information indicates that the vehicle and an adjacent vehicle are likely to collide, calculate a second longitudinal distance between a current position of the adjacent vehicle and a current position of the vehicle.
[0160] In this step, when the driving information indicates that the vehicle and the adjacent vehicle will collide, the second longitudinal distance between the adjacent vehicle and the vehicle is obtained in real time to determine whether the vehicle needs to slow down or even brake to avoid collision with the adjacent vehicle based on the second longitudinal distance.
[0161] S52: If the second longitudinal distance is greater than the second preset distance, and / or the second speed difference between the adjacent vehicles is greater than the second preset speed, the PECC does not trigger the re-planning of the first speed curve.
[0162] In this step, when the distance between the vehicle and the adjacent vehicle is large, or the speed difference between the adjacent vehicle and the vehicle is large, the risk of collision is small, so PECC does not trigger the re-planning of the first speed curve.
[0163] The speed difference between the adjacent vehicle and the own vehicle is the speed difference obtained by subtracting the real-time speed of the own vehicle from the real-time speed of the adjacent vehicle.
[0164] Optionally, the second preset distance is not greater than the first preset distance.
[0165] In this embodiment, it is considered that when an adjacent vehicle cuts into the lane where the vehicle is located, it will prevent the vehicle from traveling according to the planned first speed curve. Therefore, when the driving information indicates that the vehicle and the adjacent vehicle will collide, it is determined whether to trigger the re-planning of the first speed curve according to the real-time speed difference and / or the real-time distance difference between the adjacent vehicle and the vehicle, which effectively avoids the problem of repeated re-planning of the first speed curve during the speed change process and improves the accuracy of re-planning the speed curve.
[0166] Optionally, in some embodiments, if the second longitudinal distance is less than the second preset distance, and / or the second speed difference between the adjacent vehicle and the vehicle is less than the second preset speed, the vehicle is controlled to slow down so that PECC does not trigger re-planning of the first speed curve.
[0167] Specifically, when the distance between the vehicle and the adjacent vehicle is small, the risk of collision is high, and the vehicle needs to be controlled to decelerate. At the same time, since the deceleration time of the vehicle cannot be guaranteed, in order to prevent the first speed curve from being repeatedly re-planned when decelerating, it is also necessary to prevent PECC from triggering the re-planning of the first speed curve.
[0168] The vehicle is controlled to decelerate in response to the driver's braking operation or under the control of ACC.
[0169] In this embodiment, during the vehicle deceleration process, the third longitudinal distance between adjacent vehicles is acquired in real time. Specifically, after the vehicle is controlled to decelerate, the third longitudinal distance between adjacent vehicles continues to be acquired in real time, so as to determine whether the first speed curve can be replanned according to the third longitudinal distance.
[0170] Furthermore, when the third longitudinal distance is greater than the third preset distance, PECC is triggered to re-plan the first speed curve to obtain a third speed curve. Specifically, when the third longitudinal distance between the vehicle and the adjacent vehicle becomes larger, the risk of collision is smaller and the vehicle can travel normally, PECC is triggered to re-plan the first speed curve to obtain a third speed curve.
[0171] In order to explain the embodiment of the present application more clearly, the embodiment is explained through three cases below.
[0172] Case a: The second longitudinal distance between adjacent vehicles is obtained in real time. When the second longitudinal distance is less than the second preset distance, the distance between the adjacent vehicle and the vehicle becomes very close. The vehicle is controlled to decelerate relatively sharply, and then slowly increases the speed to increase the longitudinal distance between the vehicle and the adjacent vehicle, and controls the speed of the vehicle not to be higher than that of the adjacent vehicle. In this process, the third longitudinal distance between the vehicle and the adjacent vehicle is detected in real time. When the third longitudinal distance is greater than the third preset distance, PECC is triggered to perform a re-planning of the first speed curve to obtain the third speed curve.
[0173] Case b: The second longitudinal distance between the adjacent vehicles is obtained in real time. When the second longitudinal distance is greater than the second preset distance, it means that the adjacent vehicle has no direct impact on the vehicle, and no operation is performed. When the second longitudinal distance between the adjacent vehicles gradually decreases to the second preset distance (e.g., 80 meters, 100 meters, 120 meters, etc.), within the time threshold (e.g., 3 seconds, 4 seconds, 5 seconds), the operation in case a is performed.
[0174] Case c: When an adjacent vehicle cuts into the lane where this vehicle is located and its speed is much greater than that of this vehicle, it means that the adjacent vehicle will not have a direct impact on this vehicle and no operation is required.
[0175] In actual applications, ramps are an indispensable part of interchanges. They are roads for up and down traffic to intersect, so vehicles frequently change lanes. Fig. 6A and Figure 6B The influence of vehicles merging at the ramp on the first speed curve is explained respectively.
[0176] Fig. 6AThis is a schematic diagram of the second speed curve embodiment 1 provided in the embodiment of the present application. Fig. 6A As shown, PECC generates a first speed curve according to the terrain of the lane. When the vehicle merges into the adjacent lane, or when the vehicle cuts into the adjacent lane and quickly cuts out, if it is determined that the above situation prevents the vehicle from continuing to drive at the first speed curve, it is necessary to control PECC to re-plan the first speed curve to obtain the second speed curve, that is, Fig. 6A The dotted line in .
[0177] Figure 6B This is a schematic diagram of a second speed curve embodiment 2 provided in the present application. Figure 6B As shown, Fig. 6A Similarly, when an adjacent vehicle merges into the lane where the vehicle is located near the gate and prevents the vehicle from continuing to travel at the first speed curve, it is necessary to control PECC to re-plan the first speed curve to obtain the second speed curve, that is, Figure 6B The dotted line in .
[0178] It should be understood that during the above-mentioned vehicle lane changing process, corresponding traffic regulations need to be complied with.
[0179] Figure 7 This is a schematic diagram of the structure of the first embodiment of the control device for replanning the speed curve provided in the embodiment of the present application. Figure 7 As shown, the speed curve re-planning control device 70 is applied to a vehicle equipped with a PECC, and the speed curve re-planning control device 70 includes:
[0180] A prediction module 71, configured to predict a first trajectory of an adjacent vehicle in a future time period based on position information of adjacent vehicles at multiple sampling moments when controlling the vehicle to travel according to a first speed curve planned by PECC;
[0181] A first determination module 72, configured to determine a second trajectory of the vehicle in a future time period;
[0182] A second determination module 73, used to determine the driving information of the vehicle and the adjacent vehicle according to the first trajectory and the second trajectory, where the driving information is used to indicate whether the vehicle and the adjacent vehicle will collide;
[0183] The trigger module 74 is used to trigger the re-planning of the first speed curve according to the driving information.
[0184] In one possible design, adjacent vehicles include adjacent vehicles in the lane where the vehicle is located and adjacent vehicles in other lanes. Whether the vehicle and the adjacent vehicles will collide includes a collision between the vehicle and the adjacent vehicle without either vehicle changing lanes and a collision between the vehicle or one of the adjacent vehicles changing lanes.
[0185] In a possible design, when the driving information indicates that the vehicle and the adjacent vehicle are likely to collide, the driving information also includes collision information between the vehicle and the adjacent vehicle, and the triggering module 74 is specifically configured to:
[0186] When the driving information indicates that the vehicle and the adjacent vehicle will not collide, the PECC does not trigger the re-planning of the first speed curve;
[0187] When the driving information indicates that the vehicle and the adjacent vehicle will collide, and the collision information meets the preset re-planning condition, the PECC is triggered to re-plan the first speed curve to obtain the second speed curve;
[0188] When the driving information indicates that the vehicle and the adjacent vehicle will collide, but the collision information does not meet the preset re-planning condition, the PECC does not trigger the re-planning of the first speed curve.
[0189] In a possible design, the collision information includes the collision position between the vehicle and the adjacent vehicle and the first speed difference between the adjacent vehicle and the vehicle at the time of the collision, and the trigger module 74 is specifically used to:
[0190] When the driving information indicates that the vehicle and the adjacent vehicle are about to collide, calculating a first longitudinal distance between the collision position and the current position of the vehicle;
[0191] If the first longitudinal distance is greater than the first preset distance, and / or the first speed difference between the adjacent vehicle and the vehicle is greater than the first preset speed, the PECC does not trigger the re-planning of the first speed curve;
[0192] The preset re-planning condition is that the first longitudinal distance does not exceed the first preset distance, and the first speed difference between the adjacent vehicles and the vehicle does not exceed the first preset speed.
[0193] In a possible design, when the driving information indicates that the vehicle and the adjacent vehicle will collide, and the collision information satisfies the preset re-planning condition, the triggering module 74 is specifically used to:
[0194] When the driving information indicates that the vehicle and the adjacent vehicle will collide, and the first longitudinal distance does not exceed the first preset distance, and the first speed difference between the adjacent vehicle and the vehicle does not exceed the first preset speed, PECC is triggered to re-plan the first speed curve and obtain the second speed curve.
[0195] In a possible design, when the adjacent vehicle is an adjacent vehicle in another lane and changes lanes to the lane where the vehicle is located, the triggering module 74 is further used to:
[0196] When the driving information indicates that the vehicle and the adjacent vehicle are about to collide, calculating a second longitudinal distance between a current position of the adjacent vehicle and a current position of the vehicle;
[0197] If the second longitudinal distance is greater than the second preset distance, and / or the second speed difference between the adjacent vehicle and the vehicle is less than the second preset speed, the PECC does not trigger the re-planning of the first speed curve.
[0198] In one possible design, the second preset distance is not greater than the first preset distance.
[0199] In a possible design, the prediction module 71 is specifically configured to:
[0200] According to the type of the adjacent vehicle, the speed and position information of the adjacent vehicle at multiple sampling moments, a first trajectory of the adjacent vehicle in a future time period is predicted by a preset path prediction model.
[0201] In a possible design, the speed curve re-planning control device also includes a collection module for collecting position information of adjacent vehicles at multiple sampling times through the vehicle's front sensing system when controlling the vehicle to travel according to the first speed curve.
[0202] The control device for replanning a speed curve provided in an embodiment of the present application may be used to execute the control method for replanning a speed curve in any of the above embodiments, and its implementation principle and technical effect are similar and will not be described in detail here.
[0203] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, all or part of them can be integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements. They can also be implemented in the form of hardware. Some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. In addition, all or part of these modules can be integrated together or implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.
[0204] Figure 8 This is a schematic diagram of the structure of a vehicle provided in an embodiment of the present application. Figure 8 As shown, the vehicle 11 may include: a vehicle body 81 and a vehicle controller 82;
[0205] The vehicle controller 82 includes a processor 821, a memory 822, and computer program instructions stored in the memory 822 and executable on the processor 821. When the processor 821 executes the computer program instructions, the speed curve replanning control method provided in any of the aforementioned embodiments is implemented.
[0206] Optionally, the above-mentioned components of the vehicle 11 may be connected via a system bus.
[0207] The memory 822 may be a separate storage unit or a storage unit integrated in the processor. The number of processors may be one or more.
[0208] It should be understood that the processor 821 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor.
[0209] The system bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage.
[0210] All or part of the steps of the above-mentioned method embodiments can be completed by hardware related to program instructions. The above-mentioned program can be stored in a readable memory. When the program is executed, the steps of the above-mentioned method embodiments are executed. The above-mentioned memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid state drive, magnetic tape, floppy disk, optical disc and any combination thereof.
[0211] The vehicle provided in the embodiment of the present application can be used to execute the speed curve replanning control method provided in any of the above method embodiments, and its implementation principle and technical effects are similar and will not be repeated here.
[0212] An embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed on a computer, the computer executes the control method for replanning the speed curve.
[0213] The computer-readable storage medium mentioned above can be implemented by any type of volatile or non-volatile storage vehicle or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special purpose computer.
[0214] Optionally, a readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the vehicle as discrete components.
[0215] An embodiment of the present application also provides a computer program product, which includes a computer program. The computer program is stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, the above-mentioned speed curve replanning control method can be implemented.
[0216] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A control method for replanning a speed curve, characterized in that: Applied to a vehicle equipped with a predictive adaptive cruise control system (PECC), the method comprises: When controlling the vehicle to travel according to the first speed curve planned by the PECC, predicting the first trajectory of the adjacent vehicle in a future time period according to the position information of the adjacent vehicle at multiple sampling moments; determining a second trajectory of the vehicle at the future time period; Determining driving information of the vehicle and the adjacent vehicle according to the first trajectory and the second trajectory, wherein the driving information is used to indicate whether the vehicle and the adjacent vehicle will collide; Replanning of the first speed profile is triggered according to the driving information.
2. The method according to claim 1, characterized in that The adjacent vehicles include adjacent vehicles in the lane where the vehicle is located and adjacent vehicles in other lanes. Whether the vehicle and the adjacent vehicles will collide includes whether the vehicle and the adjacent vehicle collide when neither of them changes lanes, and whether the vehicle or one of the adjacent vehicles collides when changing lanes.
3. The method according to claim 1 or 2, characterized in that: When the driving information indicates that the vehicle and the adjacent vehicle are likely to collide, the driving information further includes collision information between the vehicle and the adjacent vehicle, and triggering re-planning of the first speed curve according to the driving information includes: When the driving information indicates that the vehicle and the adjacent vehicle will not collide, causing the PECC to not trigger re-planning of the first speed curve; When the driving information indicates that the vehicle and the adjacent vehicle will collide, and the collision information satisfies a preset re-planning condition, triggering the PECC to re-plan the first speed curve to obtain a second speed curve; When the driving information indicates that the vehicle and the adjacent vehicle may collide, but the collision information does not satisfy the preset re-planning condition, the PECC does not trigger re-planning of the first speed curve.
4. The method according to claim 3, characterized in that The collision information includes a collision position between the vehicle and the adjacent vehicle and a first speed difference between the adjacent vehicle and the vehicle at the time of the collision, and when the driving information indicates that the vehicle and the adjacent vehicle will collide, but the collision information does not meet the preset re-planning condition, so that the PECC does not trigger re-planning of the first speed curve, including: When the driving information indicates that the vehicle and the adjacent vehicle are about to collide, calculating a first longitudinal distance between the collision position and a current position of the vehicle; If the first longitudinal distance is greater than a first preset distance, and / or a first speed difference between the adjacent vehicle and the vehicle is greater than a first preset speed, the PECC does not trigger re-planning of the first speed curve; The preset re-planning condition is that the first longitudinal distance does not exceed the first preset distance, and the first speed difference between the adjacent vehicle and the vehicle does not exceed the first preset speed.
5. The method according to claim 3, characterized in that: When the driving information indicates that the vehicle and the adjacent vehicle will collide, and the collision information satisfies a preset re-planning condition, triggering the PECC to re-plan the first speed curve to obtain a second speed curve, including: When the driving information indicates that the vehicle and the adjacent vehicle will collide, and the first longitudinal distance does not exceed the first preset distance, and the first speed difference between the adjacent vehicle and the vehicle does not exceed the first preset speed, the PECC is triggered to re-plan the first speed curve to obtain a second speed curve.
6. The method according to claim 2, characterized in that When the adjacent vehicle is an adjacent vehicle on the other lane and changes lanes to the lane where the vehicle is located, the method further includes: When the driving information indicates that the vehicle and the adjacent vehicle are likely to collide, calculating a second longitudinal distance between a current position of the adjacent vehicle and a current position of the vehicle; If the second longitudinal distance is greater than a second preset distance, and / or the second speed difference between the adjacent vehicle and the vehicle is greater than a second preset speed, the PECC does not trigger re-planning of the first speed curve.
7. The method according to claim 6, characterized in that The second preset distance is not greater than the first preset distance.
8. The method according to claim 1 or 2, characterized in that: The predicting, based on the position information of the adjacent vehicles at multiple sampling moments, the first trajectory of the adjacent vehicles in the future time period comprises: According to the type of the adjacent vehicle, the speed and position information of the adjacent vehicle at multiple sampling moments, a first trajectory of the adjacent vehicle in the future time period is predicted by a preset path prediction model.
9. The method according to claim 1 or 2, characterized in that: The method further comprises: When the vehicle is controlled to travel according to the first speed curve, the position information of the adjacent vehicle is collected at a plurality of sampling moments through the front sensing system of the vehicle.
10. A control device for replanning a speed curve, characterized in that: Applicable to a vehicle equipped with a predictive adaptive cruise control system PECC, the device comprises: A prediction module, configured to predict a first trajectory of the adjacent vehicle in a future time period based on position information of the adjacent vehicle at a plurality of sampling moments when the vehicle is controlled to travel according to the first speed curve planned by the PECC; A first determination module, configured to determine a second trajectory of the vehicle in the future time period; A second determination module, configured to determine driving information of the vehicle and the adjacent vehicle according to the first trajectory and the second trajectory, wherein the driving information is used to indicate whether a collision will occur between the vehicle and the adjacent vehicle; A trigger module is used to trigger re-planning of the first speed curve according to the driving information.
11. A vehicle, characterized in that: include: A vehicle body and a vehicle controller; Wherein, the vehicle controller includes a processor and a memory; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 9.
12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed by a processor.
13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it is used to implement the method according to any one of claims 1 to 9.
Citation Information
Cited By
Train safety coupling control method based on Ethernet
CN119459814A
