Self-adaptive cruise control method and device, electronic equipment and storage medium

Abstract

The invention provides an adaptive cruise control method and device, electronic equipment and a storage medium. The self-adaptive cruise control method comprises the steps that image data of the ground in front of a vehicle are collected through a first sensor installed on the vehicle; topographic feature extraction is carried out based on the image data; judging whether the ground in front of the vehicle is an unstructured ground based on the topographic feature extraction result; acquiring feature point cloud data of an unstructured ground under the condition that the ground in front of the vehicle is the unstructured ground; performing topographic feature recognition based on the feature point cloud data to obtain obstacle feature parameters of the unstructured ground; based on the obstacle characteristic parameters of the unstructured ground, the maximum trafficable speed of the vehicle is calculated through transverse stability analysis of a vehicle dynamics model; and determining a subsequent cruise speed according to the current cruise speed and the maximum passable speed.

Description

Technical Field

[0001] The present disclosure relates to the field of autonomous driving technology, and particularly to an adaptive cruise control method, apparatus, electronic device, and storage medium. Background Art

[0002] Adaptive Cruise Control (ACC) is an automotive driving assistance system that uses sensors such as millimeter-wave radar, lidar, or cameras to monitor information such as the position and speed of surrounding vehicles, and automatically adjusts the speed of the vehicle based on this information to maintain a safe distance from the vehicle ahead. When the vehicle ahead decelerates or stops, ACC will automatically decelerate or stop, and when the vehicle ahead accelerates, ACC will also accelerate accordingly.

[0003] However, when the vehicle enters a ground surface with significantly changing local features and a certain amount of bumps and depressions (hereinafter simply referred to as: unstructured ground), if the same ACC control strategy as that for structured ground is adopted, it may not be possible to ensure the passability of the vehicle on the unstructured ground. Especially for medium and large-sized vehicles such as commercial vehicles, it is extremely easy to induce instability and even accidents such as rollovers. Summary of the Invention

[0004] The present disclosure is completed to solve the above problems, and aims to provide an adaptive cruise control method, apparatus, electronic device, and storage medium, which ensure the reliability of adaptive cruise on different road surfaces, and at the same time ensure driving safety and driving efficiency.

[0005] According to one aspect of the present disclosure, there is provided an adaptive cruise control method, including: collecting image data of the ground in front of the vehicle through a first sensor installed on the vehicle; extracting terrain features based on the image data; determining whether the ground in front of the vehicle is unstructured ground based on the terrain feature extraction result; obtaining feature point cloud data of the unstructured ground when the ground in front of the vehicle is unstructured ground; performing terrain feature recognition based on the feature point cloud data to obtain obstacle feature parameters of the unstructured ground; calculating the maximum passable speed of the vehicle based on the obstacle feature parameters of the unstructured ground and using vehicle dynamics model lateral stability analysis; and determining a subsequent cruise speed according to the current cruise speed and the maximum passable speed.

[0006] Preferably, in the vehicle dynamics model lateral stability analysis, a rollover index is obtained by combining the influence of the center of gravity / current attitude on stability, the influence of ground forces on stability, and the influence of the overall and internal movement of the vehicle on stability, and it is determined whether the vehicle has a rollover risk according to this rollover index, thereby calculating the maximum passable speed of the vehicle.

[0007] Preferably, when determining the subsequent cruising speed according to the current cruising speed and the maximum passable speed, if the current cruising speed is less than or equal to the maximum passable speed, the current cruising speed is maintained to continue with adaptive cruise control. If the current cruising speed is greater than the maximum passable speed, adaptive cruise control is performed at the maximum passable speed until the obstacle on the unstructured ground is successfully passed.

[0008] Preferably, in the terrain feature extraction based on the image data, the terrain feature extraction includes: depth feature extraction, texture feature extraction, and shape feature extraction.

[0009] Preferably, when obtaining the feature point cloud data of the unstructured ground when the ground in front of the vehicle is unstructured, the feature point cloud data of the unstructured ground is collected by a second sensor installed on the vehicle.

[0010] Preferably, when performing terrain feature recognition based on the feature point cloud data to obtain the obstacle feature parameters of the unstructured ground, it includes: preprocessing the feature point cloud data; and performing terrain feature recognition based on the preprocessed feature point cloud data.

[0011] Preferably, when preprocessing the feature point cloud data, the feature point cloud data is preprocessed by a combined filtering algorithm and a hole filling algorithm.

[0012] Preferably, when performing terrain feature recognition based on the preprocessed feature point cloud data, terrain feature recognition is performed based on a supervoxel segmentation clustering method and geometric analysis, thereby obtaining the obstacle feature parameters of the unstructured ground.

[0013] Preferably, the vehicle is a commercial vehicle.

[0014] According to another aspect of the present disclosure, an adaptive cruise control device is provided, including: a collection module for collecting image data of the ground in front of the vehicle through a first sensor installed on the vehicle; an extraction module for performing terrain feature extraction based on the image data; a judgment module for judging whether the ground in front of the vehicle is unstructured based on the terrain feature extraction result; a point cloud acquisition module for obtaining the feature point cloud data of the unstructured ground when the ground in front of the vehicle is unstructured; a parameter acquisition module for performing terrain feature recognition based on the feature point cloud data to obtain the obstacle feature parameters of the unstructured ground; a calculation module for calculating the maximum passable speed of the vehicle based on the obstacle feature parameters of the unstructured ground and using lateral stability analysis of the vehicle dynamics model; and a determination module for determining the subsequent cruising speed according to the current cruising speed and the maximum passable speed.

[0015] According to another aspect of the present disclosure, there is provided an electronic device, which includes a processor and a memory. At least one instruction or at least one program segment is stored in the memory, and the at least one instruction or the at least one program segment is loaded and executed by the processor to perform the method described in the above aspect.

[0016] According to another aspect of the present disclosure, there is provided a computer storage medium, in which at least one instruction or at least one program segment is stored, and the at least one instruction or the at least one program segment is loaded and executed by a processor to perform the method described in the above aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings exemplarily show embodiments and form a part of the specification, and are used together with the written description of the specification to explain the exemplary embodiments of the embodiments. The shown embodiments are for illustrative purposes only and do not limit the scope of the claims. In all the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0018] Figure 1 It shows a schematic flowchart of the adaptive cruise control method provided by an embodiment of the present disclosure;

[0019] Figure 2 It shows a schematic diagram of the attitude and angle relationship of a commercial vehicle on an inclined plane;

[0020] Figure 3 It shows a schematic diagram of the attitude and angle relationship of a commercial vehicle during in-situ steering;

[0021] Figure 4 It shows a block diagram of the structure of the adaptive cruise control device provided by an embodiment of the present disclosure;

[0022] Figure 5 It shows a block diagram of the structure of the electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] Next, the present disclosure will be further described in detail with reference to the drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related invention and do not limit the invention. In addition, it should be noted that for the sake of convenience of description, only the parts related to the invention are shown in the drawings.

[0024] The terms used herein are for the purpose of describing particular embodiments only and are not intended to limit the present disclosure. As used herein, the singular forms "a" and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. It will also be understood that when the terms "comprises" and / or "composed of" are used in this specification, the specified features, integers, steps, operations, elements, and / or components are present, but one or more other features, integers, steps, operations, elements, components, and / or groups thereof are not excluded.

[0025] The embodiments described herein may be described with reference to plan views and / or cross-sectional views by means of ideal schematic diagrams of the present disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances. Accordingly, the embodiments are not limited to the embodiments shown in the drawings, but include modifications of configurations formed based on manufacturing processes. Therefore, the regions illustrated in the drawings have schematic attributes, and the shapes of the regions shown in the figures illustrate the specific shapes of the regions of the elements, but are not intended to be limiting.

[0026] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0027] Among multiple scenarios of autonomous driving, freight transportation by a platoon of driverless vehicles is one of the scenarios with the clearest commercialization implementation models. However, driverless freight fleets often encounter the situation that they need to drive onto unstructured ground after driving on a highway to reach the freight destination. For structured road surfaces, ACC has currently become a relatively reliable autonomous driving technology. However, unstructured road surfaces often have bumps and potholes. If the same ACC control strategy as that for structured ground is adopted, especially for medium and large-sized vehicles such as commercial vehicles, the passability of the vehicle body on unstructured road surfaces cannot be guaranteed, and instability is easily induced, and even accidents such as rollover may occur.

[0028] The present disclosure provides an adaptive cruise control method, device, electronic device, and storage medium, which ensure the reliability of adaptive cruise on different road surfaces, and at the same time ensure driving safety and driving efficiency. Among them, the method and the device are based on the same concept. Since the principles of the method and the device for solving problems are similar, the implementation of the device and the method can be referred to each other, and the repeated parts will not be elaborated.

[0029] Figure 1The flowchart of the adaptive cruise control method provided by an embodiment of the present disclosure is shown. This specification provides the method operation steps such as in the embodiment or flowchart, but based on routine or non-creative labor, there may be more or fewer operation steps. The step sequence listed in the embodiment is only one way among the execution sequences of numerous steps and does not represent the only execution sequence. When the actual system or server product executes, it can be executed in the order shown in the embodiment or the drawings or executed in parallel (for example, in an environment of parallel processors or multi-threaded processing).

[0030] S101: Collect image data of the ground in front of the vehicle through a first sensor installed on the vehicle.

[0031] Among them, the first sensor may be a camera device installed on the vehicle for collecting image data around the vehicle.

[0032] S102: Extract terrain features based on the image data.

[0033] Among them, terrain features are extracted based on the image data of the ground in front of the vehicle collected in step S101. The terrain feature extraction here may include: depth feature extraction, texture feature extraction, and shape feature extraction. Of course, it is also possible to extract only one or two of the above three features. For example, it can be first determined whether the ground may be an unstructured ground based on whether the extracted depth feature is greater than a preset depth threshold, and then texture features and shape features are extracted for further judgment. In addition, the terrain feature extraction can adopt existing methods and will not be elaborated here.

[0034] S103: Judge whether the ground in front of the vehicle is an unstructured ground based on the terrain feature extraction result.

[0035] Based on the terrain features extracted in step S102, it can be judged whether the ground in front of the vehicle is a structured ground or an unstructured ground.

[0036] S104: Obtain the feature point cloud data of the unstructured ground when the ground in front of the vehicle is an unstructured ground.

[0037] The feature point cloud data of the unstructured ground can be collected by a second sensor installed on the vehicle. The second sensor may be a lidar installed on the vehicle. Of course, the feature point cloud data can also be obtained by other means, such as obtaining it from the cloud.

[0038] S105: Perform terrain feature recognition based on the feature point cloud data to obtain the obstacle feature parameters of the unstructured ground.

[0039] In some embodiments, the step of performing terrain feature recognition based on the feature point cloud data specifically includes:

[0040] Preprocess the feature point cloud data; and

[0041] Perform terrain feature recognition based on the preprocessed feature point cloud data.

[0042] Specifically, the feature point cloud data can be preprocessed by a combined filtering algorithm and a hole filling algorithm. After the preprocessing is completed, terrain feature recognition can be performed based on a supervoxel segmentation clustering method and geometric analysis, thereby obtaining the obstacle feature parameters of the unstructured ground.

[0043] Among them, the combined filtering algorithm, the hole filling algorithm, the supervoxel segmentation clustering method, and the geometric analysis are all existing technologies and will not be elaborated here.

[0044] S106: Based on the obstacle feature parameters of the unstructured ground, and using the lateral stability analysis of the vehicle dynamics model, calculate the maximum passable speed of the vehicle.

[0045] In some embodiments, in the lateral stability analysis of the vehicle dynamics model, a rollover index is obtained by combining the influence of the center of gravity / current attitude on stability, the influence of ground forces on stability, and the influence of the overall and internal movement of the vehicle on stability. According to this rollover index, it is determined whether the vehicle has a rollover risk, and thereby the maximum passable speed of the vehicle is calculated.

[0046] For unstructured ground, medium and large vehicles such as commercial vehicles have a relatively high risk of passability. Therefore, in this embodiment, a commercial vehicle is taken as an example for the lateral stability analysis of the vehicle dynamics model. Figure 2 Shows a schematic diagram of the attitude and angle relationship of the commercial vehicle 10 on an inclined plane. Figure 3 Shows a schematic diagram of the commercial vehicle 10 turning in place. The commercial vehicle includes a hinge structure. Refer to Figure 2 、 Figure 3 To illustrate the lateral stability analysis of the vehicle dynamics model.

[0047] (1) Influence of the center of gravity / current attitude on stability

[0048] Figure 2 In, the commercial vehicle 10 is simply shown by line segments O f A, AO r where point A represents the vehicle hinge point, O f represents the midpoint of the front axle of the vehicle, O f A represents the central axis of the front vehicle body, O r represents the midpoint of the rear axle of the vehicle, O r A represents the central axis of the rear vehicle body. θ is the inclination angle of the inclined plane, θ 01 is the pitch angle of the rear vehicle body, θ 02 is the pitch angle of the front vehicle body, θp is O f O r is the pitch angle of, θ1 is the pitch angle of the rear axle, θ2 is the pitch angle of the front axle, θ r is the pitch angle of the perpendicular line of O in the inclined plane f O r , and the following formula (1) holds.

[0049]

[0050] d r 、d f are the distances from the projections of the lines of action of the gravity of the rear body and the front body on the inclined plane to O f O r . From the geometric relationship, d r 、d f have the pitch angle of θ r , and the following formulas (2) and (3) can be obtained.

[0051] d r =c r sinα r -h r tanθ (2)

[0052] d f =c f sinα f -h f tanθ (3)

[0053] Among them, c r , c f are the mass centers of the rear vehicle body and the front vehicle body respectively. h f is the height of the mass center of the front vehicle body, and H r is the height of the mass center of the rear vehicle body.

[0054] Thus, the moment of gravity on O f O r is shown in the following formula (4).

[0055] L g =[m r gd r +m f gd f cosθ r (4)

[0056] Among them, m f is the mass of the front vehicle body, and m r is the mass of the rear vehicle body.

[0057] (2) Influence of Ground Forces on Stability

[0058] When the angle between the rear axle and the rear body is small, the moment L of the ground support force on O f O r is as shown in the following formula (5). z As shown in the following formula (5).

[0059]

[0060] Among them, F zr is the vertical support force of the rear wheel, F zf is the vertical support force of the front wheel, d is the wheelbase, α is the hinge angle, and t is a constant that can be uniquely determined by the vehicle structure. In the extreme case of off-road terrain, when the angle γ between the rear axle and the rear body cannot be ignored, γ is usually less than 12 degrees. After small-angle approximation, formula (5) can be rewritten as the following formula (6).

[0061]

[0062] (3) Influence of the overall and internal motion of the vehicle on stability

[0063] The inertial forces corresponding to the front body and the rear body are as shown in the following formulas (7) and (8).

[0064] F inr =-m r (a cnr -a rnr ) (7)

[0065] F inf =-m f (a cnf -a rnf ) (8)

[0066] Among them, F inr is the inertial force of the rear body, F inf is the inertial force of the front body, a cnr and a cnf are the accelerations of the front and rear bodies respectively, and a rnr and a rnf are the relative accelerations of the front and rear bodies respectively.

[0067] Thus, the moment generated by the inertial force is as shown in the following formula (9).

[0068] L i =F inr h r +F inf h f (9)

[0069] Then, according to the dynamic relationship, the following formula (10) can be obtained.

[0070] J r wkr +J f w kf = L z +L g +L i (10)

[0071] Among them, J f 、J r are the moments of inertia of the front and rear vehicle bodies rotating around O f O r w kr is the angular acceleration of the rear vehicle body relative to O f O r w kf is the angular acceleration of the front vehicle body relative to O f O r .

[0072] From this, the rollover index avLTR shown in formula (11) can be obtained. The avLTR obtains the instantaneous vehicle body state by acquiring instantaneous information to judge the real-time danger degree of vehicle driving.

[0073]

[0074] It is possible to judge whether the commercial vehicle 10 has a rollover risk according to the rollover index avLTR. For example, it can be judged whether there is a rollover risk according to whether the rollover index avLTR is greater than a preset threshold. In the case of a rollover risk, the maximum passable speed V max of the commercial vehicle 10 can be calculated based on the above vehicle dynamics model.

[0075] S107: Determine the subsequent cruise speed according to the current cruise speed and the maximum passable speed.

[0076] Among them, if the current cruise speed V0 is less than or equal to the maximum passable speed V max , then maintain the current cruise speed V0 to continue adaptive cruise. If the current cruise speed V0 is greater than the maximum passable speed V max , then perform adaptive cruise at the maximum passable speed V max until successfully passing the obstacle on the unstructured ground.

[0077] In this embodiment, a commercial vehicle is taken as an example to conduct a lateral stability analysis of the vehicle dynamics model. Of course, the present disclosure is not limited to this, and the vehicle may also be other vehicles.

[0078] Figure 4 shows the structural block diagram of the adaptive cruise control device provided by the embodiment of the present disclosure. As Figure 4As shown in the figure, the adaptive cruise control device 200 includes: a collection module 201, an extraction module 202, a judgment module 203, a point cloud acquisition module 204, a parameter acquisition module 205, a calculation module 206, and a determination module 207.

[0079] Among them, the collection module 201 is used to collect image data of the ground in front of the vehicle through a first sensor installed on the vehicle. The extraction module 202 is used to extract terrain features based on the image data. The judgment module 203 is used to judge whether the ground in front of the vehicle is unstructured ground based on the terrain feature extraction result. The point cloud acquisition module 204 is used to acquire the characteristic point cloud data of the unstructured ground when the ground in front of the vehicle is unstructured ground. The parameter acquisition module 205 is used to perform terrain feature recognition based on the characteristic point cloud data and acquire the obstacle feature parameters of the unstructured ground. The calculation module 206 is used to calculate the maximum passable speed of the vehicle based on the obstacle feature parameters of the unstructured ground and by using the lateral stability analysis of the vehicle dynamics model. The determination module 207 is used to determine the subsequent cruise speed according to the current cruise speed and the maximum passable speed.

[0080] Figure 5 The structural block diagram of the electronic device provided by the embodiments of the present disclosure is shown. As Figure 5 shown, the present disclosure also provides an electronic device 300, which includes a processor and a memory. At least one instruction or at least one program segment is stored in the memory, and the at least one instruction or the at least one program segment is loaded and executed by the processor to perform the method described in the above embodiments.

[0081] The present disclosure also provides a computer storage medium, in which at least one instruction or at least one program segment is stored, and the at least one instruction or the at least one program segment is loaded and executed by a processor to implement the method described in the above embodiments.

[0082] Optionally, in this embodiment, the above storage medium may be located in at least one of multiple network servers in a computer network. Optionally, in this embodiment, the above storage medium may include, but is not limited to: USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs, etc., various media that can store program codes.

[0083] Those skilled in the art should be able to realize that the modules, units, and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in the form of electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this disclosure.

[0084] Although this disclosure has been described with reference to the current specific embodiments, those of ordinary skill in the art should recognize that the scope of the invention involved in this disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in this disclosure.

Claims

1. An adaptive cruise control method, characterized in that, Including: Collecting image data of the ground in front of the vehicle through a first sensor installed on the vehicle; Performing terrain feature extraction based on the image data; Judging whether the ground in front of the vehicle is unstructured ground based on the terrain feature extraction result; Obtaining the feature point cloud data of the unstructured ground when the ground in front of the vehicle is unstructured ground; Performing terrain feature recognition based on the feature point cloud data to obtain the obstacle feature parameters of the unstructured ground; Based on the obstacle feature parameters of the unstructured ground and using the lateral stability analysis of the vehicle dynamics model to calculate the maximum passable speed of the vehicle; and Determining the subsequent cruise speed according to the current cruise speed and the maximum passable speed.

2. The adaptive cruise control method according to claim 1, characterized in that, In the lateral stability analysis of the vehicle dynamics model, Combining the influence of the center of gravity / current attitude on stability, the influence of ground forces on stability, and the influence of the overall and internal movement of the vehicle on stability to obtain a rollover index, and judging whether the vehicle has a rollover risk according to this rollover index, thereby calculating the maximum passable speed of the vehicle.

3. The adaptive cruise control method according to claim 1 or 2, characterized in that, In determining the subsequent cruise speed according to the current cruise speed and the maximum passable speed, If the current cruise speed is less than or equal to the maximum passable speed, then maintain the current cruise speed and continue with adaptive cruise, If the current cruise speed is greater than the maximum passable speed, then perform adaptive cruise at the maximum passable speed until successfully passing the obstacle of the unstructured ground.

4. The adaptive cruise control method according to claim 1 or 2, characterized in that In performing terrain feature extraction based on the image data, The terrain feature extraction includes: depth feature extraction, texture feature extraction, and shape feature extraction.

5. The adaptive cruise control method according to claim 1 or 2, characterized in that In obtaining the feature point cloud data of the unstructured ground when the ground in front of the vehicle is unstructured ground, The feature point cloud data of the unstructured ground is collected by a second sensor installed on the vehicle.

6. The adaptive cruise control method according to claim 1 or 2, characterized in that In performing terrain feature recognition based on the feature point cloud data to obtain the obstacle feature parameters of the unstructured ground, including: Preprocessing the feature point cloud data; and Performing terrain feature recognition based on the preprocessed feature point cloud data.

7. The adaptive cruise control method according to claim 6, characterized in that In preprocessing the feature point cloud data, Preprocessing the feature point cloud data through a combined filtering algorithm and a hole filling algorithm.

8. The adaptive cruise control method according to claim 6, wherein, In performing terrain feature recognition based on the preprocessed feature point cloud data, Performing terrain feature recognition based on the supervoxel segmentation clustering method and geometric analysis, thereby obtaining the obstacle feature parameters of the unstructured ground.

9. The adaptive cruise control method according to claim 1 or 2, characterized in that The vehicle is a commercial vehicle.

10. An adaptive cruise control device, characterized in that, Including: A collection module for collecting image data of the ground in front of the vehicle through a first sensor installed on the vehicle; An extraction module for performing terrain feature extraction based on the image data; A judgment module for judging whether the ground in front of the vehicle is unstructured ground based on the terrain feature extraction result; A point cloud acquisition module for obtaining the feature point cloud data of the unstructured ground when the ground in front of the vehicle is unstructured ground; A parameter acquisition module for performing terrain feature recognition based on the feature point cloud data to obtain the obstacle feature parameters of the unstructured ground; A calculation module, configured to calculate a maximum passable speed of the vehicle based on the obstacle feature parameters of the unstructured ground and by using lateral stability analysis of a vehicle dynamics model; and A determination module, configured to determine a subsequent cruise speed according to a current cruise speed and the maximum passable speed.

11. An electronic device, characterized in that, The electronic device includes a processor and a memory. At least one instruction or at least one program segment is stored in the memory. The at least one instruction or the at least one program segment is loaded and executed by the processor to perform the method according to any one of claims 1 to 9.

12. A computer storage medium, characterized in that, At least one instruction or at least one program segment is stored in the storage medium. The at least one instruction or the at least one program segment is loaded and executed by a processor to perform the method according to any one of claims 1 to 9.

Images