Passive safety distance control system based on monocular perception

Abstract

The invention provides a passive safety vehicle distance control system based on monocular sensing, and relates to the technical field of vehicle safety distance control, the passive safety vehicle distance control system comprises a monocular sensing module, the monocular sensing module is configured to obtain a real-time relative vehicle distance and a real-time braking force coefficient; the real-time relative vehicle distance is the distance between the head of the vehicle and the tail of the front vehicle, and the real-time braking force coefficient is used for representing the advancing state of the vehicle and the relative advancing state between the vehicle and the front vehicle; the braking calculation module is configured to generate a passive braking control instruction according to the real-time relative vehicle distance, the real-time braking force coefficient, the time-varying vehicle distance data and a passive braking model; the passive braking control instruction comprises time-varying target deceleration; and the braking control module is configured to perform passive braking on the vehicle according to the passive braking control instruction. By means of the system, the problems that an existing vehicle passive braking technology is low in application universality and high in cost are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle safety distance control, and in particular to a passive safety vehicle distance control system based on monocular perception. Background Art

[0002] As a core component of intelligent driving systems, the evolution of vehicle braking force calculation schemes reflects the industry's ongoing pursuit of driving comfort and safety. Early braking control solutions employed a simple "one-touch braking" strategy. While straightforward to implement, this approach exhibited numerous technical limitations in practical applications.

[0003] Traditional single-brake braking employs binary control based on a preset safe vehicle distance threshold. When the system detects that the relative distance falls below the threshold, it immediately applies a fixed braking force until the distance between vehicles returns to a safe range. This control approach suffers from two significant technical drawbacks: First, there are significant step changes at both the start and end of braking, with the braking force suddenly increasing from zero to a preset value or decreasing from a preset value to zero. This discontinuous force change can cause noticeable jerkiness for occupants; second, a fixed braking force is difficult to adapt to complex and changing real-world driving scenarios. Excessive braking force can lead to unnecessary sudden braking, while insufficient braking force can result in excessively long braking distances.

[0004] In response to the above problems, the industry has proposed an improved ramp control solution. This solution introduces a linear increase in braking force at the beginning of braking and a linear decrease in braking force at the end of braking, improving the passenger's physical comfort through this gradual change. However, this improvement solution introduces a new technical challenge: the choice of ramp slope directly affects the quality of braking control. A fixed slope is difficult to adapt to the braking needs under different vehicle speeds, loads and road conditions, and the design of a dynamic slope lacks theoretical guidance and needs to rely on a large amount of experimental data for empirical adjustment. Not only is the development efficiency low, but it is also difficult to ensure the consistency of the control effect.

[0005] In terms of force adaptation, existing technologies mainly use empirical fitting methods based on experimental data. By collecting braking performance data under specific working conditions, an empirical relationship between braking force and working condition parameters is established, and interpolation calculations are performed during actual control. Although this method improves the adaptability of control to a certain extent, it is essentially a black box modeling based on local data and has the following inherent defects: First, the braking process involves the complex coupling of multiple physical quantities, and the empirical model is difficult to fully cover all influencing factors; second, the model has poor interpretability, and it is difficult to conduct effective root cause analysis when control anomalies occur; finally, the model's generalization ability is limited, and performance degradation may occur under working conditions beyond the scope of the training data. Summary of the Invention

[0006] The present application provides a passive safety vehicle distance control system based on monocular perception to solve the problems of low application popularity and high implementation cost of existing vehicle passive braking technology.

[0007] The system comprises: a monocular perception module configured to obtain a real-time relative vehicle distance and a real-time braking force coefficient; the real-time relative vehicle distance is the distance between the front of the own vehicle and the rear of the preceding vehicle; and the real-time braking force coefficient is used to represent the moving state of the own vehicle and the relative moving state between the own vehicle and the preceding vehicle; a braking calculation module configured to generate a passive braking control instruction based on the real-time relative vehicle distance, the real-time braking force coefficient, the time-varying vehicle distance data, and a passive braking model; the passive braking control instruction includes a time-varying target deceleration; the time-varying vehicle distance data is obtained during the passive braking process of the vehicle; A braking control module is configured to perform passive braking on the vehicle according to the passive braking control instruction.

[0008] Preferably, the monocular perception module is configured as follows: Acquire a real-time vehicle distance image; the real-time vehicle distance image is an image of the area between the vehicle and the preceding vehicle; The vehicle distance is calculated according to the real-time vehicle distance image to obtain the real-time relative vehicle distance and the real-time braking force coefficient.

[0009] Preferably, the time-varying vehicle distance data includes time-varying vehicle distance and braking time-varying vehicle distance; The time-varying headway is the change in distance between the vehicle and the preceding vehicle per unit time while the vehicle maintains its original moving state. The braking time-varying headway is the change in distance between the ego vehicle and the preceding vehicle per unit time during the passive braking process of the ego vehicle.

[0010] Preferably, the monocular perception module includes: an image acquisition unit, configured to acquire the real-time vehicle distance image; The vehicle distance calculation unit is configured to calculate the vehicle distance according to the real-time vehicle distance image to obtain the real-time relative vehicle distance and the real-time braking force coefficient.

[0011] Preferably, the vehicle distance calculation unit is further configured to: Importing the real-time vehicle distance image into a preset coordinate; Determining the distance between the vehicle and the preceding vehicle in the preset coordinates to obtain the real-time relative vehicle distance; The real-time braking force coefficient is obtained by calculating the vehicle distance change based on the position change of the plurality of real-time vehicle distance images in the preset coordinates and the real-time vehicle speed.

[0012] Preferably, the system further comprises: A vehicle speed acquisition module, configured to acquire a real-time vehicle speed of the vehicle; The monocular perception module is configured to calculate the vehicle distance based on the real-time vehicle speed and the real-time vehicle distance image to obtain the real-time relative vehicle distance and the real-time braking force coefficient.

[0013] Preferably, the braking calculation module is configured as follows: Determining whether the current vehicle distance meets the safety distance requirement based on the real-time relative vehicle distance and the real-time braking force coefficient; If so, keep the original moving state of the vehicle; If not, a passive braking control instruction is generated according to the real-time relative vehicle distance, the real-time braking force coefficient, the time-varying vehicle distance data and the passive braking model.

[0014] Preferably, the braking calculation module is further configured to: Calculating according to the real-time relative vehicle distance to obtain the time-varying vehicle headway; When the real-time relative vehicle distance does not meet the safety distance requirement, the braking time-varying vehicle distance is calculated based on the real-time relative vehicle distance; the safety distance requirement is a dynamic distance that changes according to the speed of the vehicle; A passive braking control instruction is generated according to the real-time relative vehicle distance, the real-time braking force coefficient, the time-varying vehicle time distance, the braking time-varying vehicle time distance, and the passive braking model.

[0015] Preferably, the braking calculation module includes: a safety distance determination unit configured to determine a safe distance based on the real-time relative vehicle distance and the real-time vehicle speed, and generate safe distance information or unsafe distance information; a time distance calculation unit, configured to calculate according to the real-time relative vehicle distance to obtain the time-varying vehicle time distance; An instruction generation unit is configured to generate an initial passive braking control instruction based on the unsafe vehicle distance information, the real-time relative vehicle distance, the time-varying vehicle time distance, the real-time braking force coefficient, the time-varying vehicle time distance, and the passive braking model; the initial passive braking control instruction is used to control the braking control module to perform initial passive braking on the vehicle.

[0016] Preferably, the time distance calculation unit is further configured to calculate according to the unsafe vehicle distance information and the real-time relative vehicle distance to obtain the braking time-varying vehicle time distance; The instruction generation unit is further configured to generate a target passive braking control instruction based on the unsafe vehicle distance information, the real-time relative vehicle distance, the time-varying vehicle distance, the braking time-varying vehicle distance, the real-time braking force coefficient, the time-varying vehicle distance and the passive braking model; the target passive braking control instruction is used to control the braking control module to perform target passive braking on the vehicle until the real-time relative vehicle distance meets the safe vehicle distance requirement.

[0017] As can be seen from the above content, the present application provides a passive safety vehicle distance control system based on monocular perception, the system comprising a monocular perception module, the monocular perception module being configured to obtain a real-time relative vehicle distance and a real-time braking force coefficient; the real-time relative vehicle distance is the distance between the front of the own vehicle and the rear of the preceding vehicle, and the real-time braking force coefficient is used to characterize the moving state of the own vehicle and the relative moving state between the own vehicle and the preceding vehicle; a braking calculation module, the braking calculation module being configured to generate a passive braking control instruction based on the real-time relative vehicle distance, the real-time braking force coefficient, the time-varying vehicle distance data, and the passive braking model; the passive braking control instruction including the time-varying target deceleration; the time-varying vehicle distance data being obtained during the passive braking process of the own vehicle; and a braking control module, the braking control module being configured to passively brake the own vehicle according to the passive braking control instruction. The present application solves the problems of low application and high implementation cost of existing vehicle passive braking technologies through the above system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a schematic diagram of a passive safety vehicle distance control system based on monocular perception in this application; Figure 2 This is a schematic diagram of a monocular perception module in a passive safety vehicle distance control system based on monocular perception in this application; Figure 3 This is a schematic diagram of a braking calculation module in a passive safety vehicle distance control system based on monocular perception in this application; Figure 4 A diagram showing changes in braking force during passive braking of a first type of conventional vehicle; Figure 5 A diagram showing changes in braking force during passive braking of a second conventional vehicle; Figure 6 This is a diagram showing the changes in braking force during passive braking of a vehicle using the solution of the present application.

[0020] Legend: 100-monocular perception module; 200-braking calculation module; 300-braking control module; 400-vehicle speed acquisition module; 110-image acquisition unit; 120-vehicle distance calculation unit; 210-safety distance judgment unit; 220-time distance calculation unit; 230-instruction generation unit. DETAILED DESCRIPTION

[0021] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] It should be noted that the brief descriptions of terms in this application are only for the purpose of facilitating the understanding of the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and usual meanings.

[0023] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0024] When a vehicle is driving on the road, if the relative distance between the vehicle and the vehicle in front is less than the safe distance due to distraction, dangerous driving, deceleration of the vehicle in front, being overtaken, being squeezed in, etc., the vehicle is in a high-risk state and the probability of a rear-end collision will increase significantly. This high-risk driving state not only brings great risks to the driver of the vehicle, but also brings risks to other road users, causing a greater adverse impact on the overall traffic safety.

[0025] In order to reduce the traffic risks caused by the small safe vehicle distance, based on the current industry technology foundation, it is entirely possible to use the ADAS controller to actively control the brake deceleration and expand the relative distance between vehicles, thereby reducing the traffic risks caused by the relative distance being less than the safe vehicle distance, improving the safety of the traffic system and improving the safety of the vehicle itself.

[0026] If the safe vehicle distance is controlled by technical means, the following basic requirements must be met: The ADAS system can sense the vehicle ahead (knowing there is a vehicle ahead); The ADAS system can identify lane lines and other road users (used to judge working conditions); The ADAS system can detect the real-time distance between the vehicle and the vehicle ahead; ADAS systems can detect the relative speeds between vehicles; The ADAS system can obtain information such as the vehicle's speed, acceleration, angular acceleration, and body parameters; There are many technical solutions that can meet the above requirements, but different technical solutions have their own advantages and disadvantages. The advantages and disadvantages of different technical solutions are shown in Table 1.

[0027] Table 1

[0028] From the perspective of technical solution selection, there are many solutions that can meet the safe vehicle distance requirements. The reason we chose monocular perception is that its cost is low enough and the hardware product form is simple. The problem it brings is that the perception results are not particularly accurate. For example: the ranging error is large (meter level), the relative speed error is large, and the lateral position and speed accuracy are insufficient.

[0029] It can be seen from the ADAS products on the market that almost all ADAS products with braking functions have at least monocular + millimeter-wave radar perception. This is limited by the industry level of monocular perception capabilities and the ability to develop ADAS braking functions based on monocular perception.

[0030] ADAS products are defined as assisted driving, which mainly intervenes passively at critical moments rather than obtaining complete vehicle control from the driver's side. Therefore, the passive safety distance maintenance function is completely different from the active assisted driving technology requirements, and needs to be analyzed and technical solutions designed from different angles.

[0031] The solution for calculating vehicle braking force has undergone significant changes in the industry. Initially, it was a one-brake method, that is, once the relative distance is less than the safe distance, a fixed force is applied until the relative distance meets the requirement. The disadvantage of this solution is that no matter how strong the force is, it starts from 0 and directly gives a value greater than zero; at the end, it starts from a fixed value greater than zero and instantly changes to 0, which makes the physical feeling very poor. Figure 4 shown.

[0032] Poor adaptability. In some scenarios, the force feels too strong and the braking is too harsh; in some scenarios, the force feels too weak and the brakes cannot be stopped. A fixed value is difficult to meet the needs of all scenarios.

[0033] Based on the above problems, revision plans have emerged one after another. The basic ideas are: Regarding body sensation: Add a slash at the beginning and end of braking, such as Figure 5 shown.

[0034] This optimization approach is relatively straightforward, but it also presents a significant challenge: determining the slope of the braking force for both climbing and descending slopes. Using a fixed value for this slope can lead to inconsistent performance under different operating conditions: the force can build up too slowly, too quickly, decrease too quickly, or decrease too slowly. If a fixed value isn't suitable, designers will need to design a dynamic climbing rate based on actual test results. This is a tedious task, and its effectiveness is limited by the limitations of the approach itself.

[0035] For force adaptability: For the optimization of force adaptation capability, the more common solution is: direct on-road testing, based on the actual braking effect, to find a set of more ideal force values ​​under various working conditions, and then perform one-dimensional or multi-dimensional data fitting on these empirical values. When used, interpolation is performed according to the actual scenario to achieve the goal of force adaptation.

[0036] This optimization idea is very intuitive, and the technical route is simple and crude. However, the problem with this optimization solution is also obvious, that is, the relationship between braking force and physical sensation is multivariable and nonlinear, and it is difficult to traverse all variables. It can only collect data by fixing most variables in some scenarios, so its adaptive ability is also locally adaptive. Once the actual working conditions are different from the working conditions when the test data was collected, it is difficult to guarantee whether the impact of its adaptive ability is positive or negative.

[0037] In general, the fundamental problem with this black-box algorithm lies in the lack of an explainable mathematical model, its generalization ability is insufficient, and the paths to analyzing the problem are basically blocked. Ultimately, it can only achieve limited adaptability in certain characteristic scenarios based on the consumption of manpower and time.

[0038] Based on the above problems, the present application provides the following embodiments.

[0039] Figure 1 This is a schematic diagram of a passive safety vehicle distance control system based on monocular perception in this application.

[0040] See also Figure 1 It can be seen that this embodiment provides a passive safety vehicle distance control system based on monocular perception, and the system includes: The monocular perception module 100 is configured to obtain a real-time relative vehicle distance and a real-time braking force coefficient; the real-time relative vehicle distance is the distance between the front of the own vehicle and the rear of the preceding vehicle, and the real-time braking force coefficient is used to characterize the moving state of the own vehicle and the relative moving state between the own vehicle and the preceding vehicle.

[0041] Specifically, in conventional relative vehicle distance and relative vehicle speed acquisition technologies, binocular perception technology, a combination of monocular perception and lidar, or a combination of binocular perception technology and lidar are often used to improve the accuracy and stability of relative vehicle speed and relative vehicle distance acquisition.

[0042] However, this embodiment only uses the monocular perception module 100 to acquire images, the purpose of which is to reduce the cost of the image acquisition equipment, and the corresponding acquisition accuracy is compensated by the subsequent calculation algorithm, thereby reducing costs and improving the generalization of technical applications while maintaining calculation accuracy and stability.

[0043] It should be noted that the monocular perception module 100 used in this embodiment is only one implementation method, and can be achieved by using other technical combinations such as binocular perception, a combination of binocular perception and lidar, and a combination of monocular perception and lidar.

[0044] The system further comprises: The braking calculation module 200 is configured to generate a passive braking control instruction based on the real-time relative vehicle distance, the real-time braking force coefficient, the time-varying vehicle distance data, and the passive braking model; the passive braking control instruction includes a time-varying target deceleration; and the time-varying vehicle distance data is obtained during the passive braking process of the vehicle.

[0045] Specifically, in this embodiment, the vehicle distance calculation is performed by the braking calculation module 200, wherein the main variable in the algorithm based on the braking calculation module 200 is the relative vehicle distance, and speed variables such as relative vehicle speed and acceleration are all secondary variables. It can be understood that the calculation weight of the vehicle distance in the braking calculation module 200 is much greater than the speed variable, thereby offsetting the problem of the low speed variable acquisition ability of the monocular perception module 100.

[0046] The calculation of the passive braking performed by the braking calculation module 200 can be understood as “anthropomorphism”, which can be understood as: In daily motor vehicle driving, the driver cannot accurately obtain the distance between the vehicle and the vehicle in front and the exact speed of the vehicle during the braking process. As the speed of the vehicle increases, the safe braking distance must also be continuously increased to ensure that the vehicle does not collide with the vehicle in front. During this braking process, the driver must rely on the time required to safely stop the vehicle within a certain distance from the vehicle in front to specify the time. This embodiment converts the vehicle distance from the distance space domain to the time domain according to this braking method, and uses the time domain to measure the safe distance between the vehicle and the vehicle in front, thereby achieving passive braking.

[0047] For example, assume that the safe braking time of the vehicle using the system provided by this embodiment is 1s. This safe braking time is the minimum braking time required for the vehicle to suddenly stop when the preceding vehicle stops. When the safe braking time represented by the relative vehicle distance is less than 1s, it is necessary to reduce the vehicle speed by a certain amount through passive braking, and completely stop the passive braking when the speed is restored to 1s. During the passive braking process, the braking force gradually increases from the beginning to the same level and then gradually decreases, thereby achieving smooth passive braking. The change in braking force is shown in FIG. Figure 6 .

[0048] The time-varying vehicle distance data includes the time-varying inter-vehicle distance and the braking-varying inter-vehicle distance. The time-varying inter-vehicle distance is the change in distance per unit time between the vehicle and the preceding vehicle while the vehicle maintains its original moving state. The braking-varying inter-vehicle distance is the change in distance per unit time between the vehicle and the preceding vehicle while the vehicle is passively braking. Both the time-varying inter-vehicle distance and the braking-varying inter-vehicle distance are calculated by the braking calculation module 200 based on the real-time relative vehicle distance and time.

[0049] The system further comprises: The braking control module 300 is configured to perform passive braking on the vehicle according to the passive braking control instruction.

[0050] Specifically, in this embodiment, the braking control module 300 is used to directly perform passive braking on the vehicle, and its specific form will not be described in detail in this embodiment.

[0051] The system further comprises: The vehicle speed acquisition module 400 is configured to acquire the real-time vehicle speed of the vehicle.

[0052] Specifically, in this embodiment, since the above-mentioned "safe braking time" changes continuously with the vehicle speed, the vehicle speed is also an influencing factor in the calculation process of the "safe braking time". Therefore, the vehicle speed acquisition module 400 is set to obtain the real-time vehicle speed of the vehicle.

[0053] Figure 2 This is a schematic diagram of a monocular perception module in a passive safety vehicle distance control system based on monocular perception in this application.

[0054] See also Figure 2 It can be seen that, further, in some embodiments, the monocular perception module 100 includes: An image acquisition unit 110, configured to acquire the real-time vehicle distance image; The vehicle distance calculation unit 120 is configured to perform vehicle distance calculation according to the real-time vehicle distance image to obtain the real-time relative vehicle distance and the real-time braking force coefficient.

[0055] Specifically, in this embodiment, in order to improve generalization, the monocular perception module 100 only uses a conventional monocular perception device. Conventional monocular perception devices inevitably have image acquisition and image processing components. Therefore, the image acquisition unit 110 and the vehicle distance calculation unit 120 are respectively provided in the monocular perception module 100. The actual image is acquired by the image acquisition unit 110, and the vehicle distance calculation unit 120 calculates the vehicle distance and vehicle speed based on the image.

[0056] See also Figure 3 It can be seen that, further, in some embodiments, the braking calculation module 200 includes: The safety distance determination unit 210 is configured to determine a safe vehicle distance based on the real-time relative vehicle distance and the real-time vehicle speed, and generate safe vehicle distance information or unsafe vehicle distance information.

[0057] Specifically, in this embodiment, a safety distance judgment needs to be performed before passive braking is performed. When the relative vehicle distance does not meet the safety distance, subsequent passive braking is performed. The safety distance judgment unit 210 does not simply measure whether the safety distance is met by the vehicle distance, but makes a joint judgment by combining the real-time relative vehicle distance and the real-time vehicle speed of the current vehicle. It can be understood that the judgment means is the "safe braking time" mentioned above, and the "safe braking time" is used to measure whether the vehicle is currently at a safe distance.

[0058] The braking calculation module 200 further includes: The time distance calculation unit 220 is configured to calculate according to the real-time relative vehicle distance to obtain the time-varying vehicle time distance.

[0059] Specifically, in this embodiment, the time distance calculation unit 220 is used to perform relevant calculations on the vehicle distance and vehicle speed, thereby generating changes in the vehicle distance and vehicle speed within a unit time.

[0060] The braking calculation module 200 further includes: The instruction generation unit 230 is configured to: generating an initial passive braking control instruction based on the unsafe vehicle distance information, the real-time relative vehicle distance, the time-varying vehicle headway, the real-time braking force coefficient, the time-varying vehicle headway, and the passive braking model; the initial passive braking control instruction is used to control the braking control module 300 to perform initial passive braking on the vehicle; The unsafe vehicle distance information, the real-time relative vehicle distance, the time-varying vehicle time distance, the braking time-varying vehicle time distance, the real-time braking force coefficient, the time-varying vehicle time distance and the passive braking model generate a target passive braking control instruction; the target passive braking control instruction is used to control the braking control module 300 to perform target passive braking on the vehicle until the real-time relative vehicle distance meets the safe vehicle distance requirement.

[0061] Specifically, in this embodiment, the instruction generation unit 230 generates instructions based on the vehicle distance related data, wherein the vehicle distance related data includes the braking time-varying vehicle time distance, and the braking time-varying vehicle time distance is data generated when passive braking has begun. Therefore, the braking time-varying vehicle time distance does not exist at the beginning of passive braking, or it can also be defined as 0, and the value continues to change with the process of passive braking.

[0062] It can be understood that the passive braking control instruction changes continuously along with the passive braking process.

[0063] The specific implementation of this embodiment is as follows: During the actual R&D process, we deeply analyzed the problems of the black box solution and derived and verified a set of mathematical models to calculate the braking force under different working conditions. The specific mathematical model is as follows: ; Where A(t): is the time-varying target deceleration, dimension: m / s 2 ; D(t): time-varying relative vehicle distance, dimension: m; HT(t): time-varying vehicle distance, dimension: s; HT thr : is the time distance between vehicles at the start of braking, dimension: s (Note: depending on the actual scenario, this variable can also be a time variable); a: is the force control coefficient, the independent variables include relative speed Δv(t), vehicle speed V ego (t), vehicle acceleration a ego(t), relative acceleration Da(t), etc. Here is only a typical model, and other variables / signals / information related to the braking force can also be included.

[0064] The HT is used to represent the distance between vehicles, which is converted from the distance space to the time domain. One feature of this model is that when the braking starts, the time-varying HT == HT thr At this time, the calculated A is almost 0, and as time changes, the distance will become closer and closer, and HT will naturally become smaller. At this time, A gradually becomes larger. The rate of change of A is mainly affected by the change of HT, i.e. mainly affected by the change of relative distance. The faster the relative distance changes, the faster A grows, otherwise it is slower. At this time, the starting braking sense is ensured, and it is an adaptive sense, and does not have to rely on experience to set.

[0065] Another feature of this model is that the braking end process is the inverse of the braking start process, i.e. due to braking, the ego vehicle speed becomes smaller and smaller, the relative distance gradually approaches the safe distance, and A becomes smaller and smaller until HT == HT thr At this time, the braking force A = 0, and the braking process ends, which ensures that the braking end process is also a time-varying continuous zero process, and does not produce a sudden change in braking force. At the same time, the change of relative distance is directly reflected on the rate of change of A, which is called the speed of the braking recovery in this embodiment. At this time, for the black box model, the adaptive characteristics of this mathematical model are obvious, and the principle is clear.

[0066] At this time, the adaptive control of the sense of the model relative to the black box control model has been completely solved, and the adaptive force ramping and force recovery can be achieved without artificial design experience values, different numerical nets are established for interpolation, but a perfect solution is provided through an interpretable mathematical model.

[0067] The next problem is the solution of the force adaptive ability of the entire braking process. Compared with the black box model, the third feature of this mathematical model is that the output force A is mainly affected by the distance. In the entire braking process when the relative distance is less than the safe distance, the smaller the relative distance, the larger the A. Here, the time-varying system characteristic is considered, i.e. the faster the relative distance changes, the faster the A becomes. Until the relative distance is less than or equal to the safe distance. At this time, it can be found in this embodiment that in addition to the starting force and the ending force change, which can ensure that it starts from 0 and ends with zero, the force change in the entire braking process is adaptive, and is mainly controlled by the distance change. At this time, the distance between vehicles in the entire braking process becomes a closed-loop feedback variable of this model, and finally forms a force adaptive calculation model based on closed-loop control of distance.

[0068] Next, this embodiment reviews the time-varying characteristics of the braking force from a temporal perspective: Since the initial force starts from 0, the speed of the own vehicle does not drop significantly during the initial braking phase, so the relative distance will decrease rapidly, and the difference between the relative distance and the safe distance will become larger and larger, becoming increasingly unsafe. At this time, A will increase rapidly. As A increases, the speed of the own vehicle begins to decrease, and the relative distance becomes closer and closer to the safe distance (the safe distance is related to the speed of the own vehicle. Generally speaking, the lower the speed of the own vehicle, the smaller the safe distance; otherwise, it is larger.) Then A will begin to decrease again. Before A decreases, the braking force continues to increase until the relative distance between the two vehicles becomes closer and closer to the safe distance, and then the braking process begins. For the braking force variation curve of the entire process, see Figure 6 .

[0069] At present, this embodiment has not yet discussed the role of the force coefficient a, but has analyzed how the model simultaneously solves the basic logic of braking sensation and braking force adaptation. The following embodiment explains why the force coefficient a is added to the model.

[0070] This example shows that without a, the mathematical model has a problem: how to ensure that the safe distance can be controlled within the safe distance range before a collision occurs? This is achieved through a. The force coefficient a controls the force of the entire braking process. Its main function is to adjust the basic force according to the real-time working conditions to ensure that the relative distance is maintained within the safe distance range when avoiding a collision. Specifically: Based on the relative speed and relative acceleration, the collision time, collision distance and other information can be calculated, and this information can be converted into a force control coefficient. When the expected collision time is short, the force coefficient a becomes larger and the force is increased. When the expected collision time is long, the force coefficient a becomes smaller to ensure that the force is not too large.

[0071] As an open sub-mathematical model, the force coefficient a can be defined according to the actual application scenario and ultimately serves as a supplement to the main model (as shown in the following formula).

[0072] ; At this point, the force coefficient a has ensured the effectiveness of the entire braking process and increased the flexibility of the model. However, the role of the main model must be primary to ensure the three characteristics described above.

[0073] The above mathematical model has been simulated and tested and is consistent with the design objectives. It is even compatible with characteristics such as delay and control deviation of the braking system. At the same time, it does not require high accuracy of relative speed and relative distance, so it can achieve safe vehicle distance maintenance based on monocular perception. When other perception models are applied, when higher-precision perception results can be obtained, it is still applicable and can even further expand and optimize the force control coefficient a.

[0074] This embodiment has the following advantages: The system displays expressions, solving the problem of insufficient interpretability compared to black box models; The system's interpretability is the foundation of its scalability. Based on this, force calculation methods for other scenarios can be derived, and customized scenario development can be supported. The system's design draws inspiration from human drivers' reflections and analysis of their own driving behavior. The algorithm was developed through extensive analysis of the designers' own driving experience, using mathematical methods to describe and model braking decisions during driving. Therefore, the model possesses anthropomorphic characteristics.

[0075] The system uses a model with small mathematical operations and almost no requirements for external computing power, and can be used in most embedded systems; The system primarily relies on sensory ranging results. As long as the single-mode sensory ranging results are continuous and smooth, errors within a certain range are tolerable due to the low initial force. Whether or not to rely on high-precision relative velocity and acceleration depends primarily on the configuration of external sensors; if they are available, they are used; if not, they are not. Therefore, this model also offers good scalability.

[0076] For ease of explanation, the above description has been made in conjunction with specific embodiments. However, the above discussion of some embodiments is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Based on the above teachings, various modifications and variations can be obtained. The above embodiments are selected and described to better explain the content of this disclosure, thereby enabling those skilled in the art to better use the embodiments.

Claims

1. A passive safety vehicle distance control system based on monocular perception, characterized in that: The system comprises: A monocular perception module (100), the monocular perception module (100) being configured to obtain a real-time relative vehicle distance and a real-time braking force coefficient; the real-time relative vehicle distance is the distance between the front of the own vehicle and the rear of the preceding vehicle, and the real-time braking force coefficient is used to characterize the traveling state of the own vehicle and the relative traveling state between the own vehicle and the preceding vehicle; A braking calculation module (200), the braking calculation module (200) being configured to generate a passive braking control instruction based on the real-time relative vehicle distance, the real-time braking force coefficient, the time-varying vehicle distance data, and a passive braking model; the passive braking control instruction includes a time-varying target deceleration; the time-varying vehicle distance data is obtained during the passive braking process of the vehicle; A braking control module (300) is configured to perform passive braking on the vehicle according to the passive braking control instruction.

2. The passive safety vehicle distance control system based on monocular perception according to claim 1, characterized in that: The monocular perception module (100) is configured as follows: Acquire a real-time vehicle distance image; the real-time vehicle distance image is an image of the area between the vehicle and the preceding vehicle; The vehicle distance is calculated according to the real-time vehicle distance image to obtain the real-time relative vehicle distance and the real-time braking force coefficient.

3. The passive safety vehicle distance control system based on monocular perception according to claim 2, characterized in that: The time-varying vehicle distance data includes the time-varying vehicle distance and the braking time-varying vehicle distance; The time-varying headway is the change in distance between the vehicle and the preceding vehicle per unit time while the vehicle maintains its original moving state. The braking time-varying headway is the change in distance between the ego vehicle and the preceding vehicle per unit time during the passive braking process of the ego vehicle.

4. The passive safety vehicle distance control system based on monocular perception according to claim 3 is characterized in that: The monocular perception module (100) comprises: An image acquisition unit (110), the image acquisition unit (110) being configured to acquire the real-time vehicle distance image; A vehicle distance calculation unit (120) is configured to perform vehicle distance calculation based on the real-time vehicle distance image to obtain the real-time relative vehicle distance and the real-time braking force coefficient.

5. The passive safety vehicle distance control system based on monocular perception according to claim 4, characterized in that: The vehicle distance calculation unit (120) is further configured to: Importing the real-time vehicle distance image into a preset coordinate; Determining the distance between the vehicle and the preceding vehicle in the preset coordinates to obtain the real-time relative vehicle distance; The real-time braking force coefficient is obtained by calculating the vehicle distance change based on the position change of the plurality of real-time vehicle distance images in the preset coordinates and the real-time vehicle speed.

6. The passive safety vehicle distance control system based on monocular perception according to claim 3, characterized in that: The system further comprises: A vehicle speed acquisition module (400), wherein the vehicle speed acquisition module (400) is configured to acquire the real-time vehicle speed of the vehicle; The monocular perception module (100) is configured to calculate the vehicle distance based on the real-time vehicle speed and the real-time vehicle distance image, and obtain the real-time relative vehicle distance and the real-time braking force coefficient.

7. The passive safety vehicle distance control system based on monocular perception according to claim 6, characterized in that: The braking calculation module (200) is configured to: Determining whether the current vehicle distance meets the safety distance requirement based on the real-time relative vehicle distance and the real-time braking force coefficient; If so, keep the original moving state of the vehicle; If not, a passive braking control instruction is generated according to the real-time relative vehicle distance, the real-time braking force coefficient, the time-varying vehicle distance data and the passive braking model.

8. The passive safety vehicle distance control system based on monocular perception according to claim 7, characterized in that: The braking calculation module (200) is further configured to: Calculating according to the real-time relative vehicle distance to obtain the time-varying vehicle headway; When the real-time relative vehicle distance does not meet the safety vehicle distance requirement, calculating according to the real-time relative vehicle distance to obtain the braking time-varying vehicle distance; The safe vehicle distance requirement is a dynamic distance that changes according to the vehicle's speed; A passive braking control instruction is generated according to the real-time relative vehicle distance, the real-time braking force coefficient, the time-varying vehicle time distance, the braking time-varying vehicle time distance, and the passive braking model.

9. The passive safety vehicle distance control system based on monocular perception according to claim 8, characterized in that: The braking calculation module (200) comprises: A safety distance judgment unit (210), the safety distance judgment unit (210) being configured to judge a safe vehicle distance based on the real-time relative vehicle distance and the real-time vehicle speed, and generate vehicle distance safety information or vehicle distance unsafe information; A time distance calculation unit (220), the time distance calculation unit (220) being configured to calculate according to the real-time relative vehicle distance to obtain the time-varying vehicle time distance; An instruction generation unit (230) is configured to generate an initial passive braking control instruction based on the unsafe vehicle distance information, the real-time relative vehicle distance, the time-varying vehicle time distance, the real-time braking force coefficient, the time-varying vehicle time distance, and the passive braking model; the initial passive braking control instruction is used to control the braking control module (300) to perform initial passive braking on the vehicle.

10. The passive safety vehicle distance control system based on monocular perception according to claim 9, characterized in that: The time distance calculation unit (220) is further configured to calculate according to the vehicle distance unsafe information and the real-time relative vehicle distance to obtain the braking time-varying vehicle distance; The instruction generation unit (230) is further configured to generate a target passive braking control instruction according to the unsafe vehicle distance information, the real-time relative vehicle distance, the time-varying vehicle time distance, the braking time-varying vehicle time distance, the real-time braking force coefficient, the time-varying vehicle time distance and the passive braking model; The target passive braking control instruction is used to control the braking control module (300) to perform target passive braking on the vehicle until the real-time relative vehicle distance meets the safety vehicle distance requirement.

Images