Auxiliary safety control method and system based on driver behavior intention recognition model
Through the automatic emergency braking control method based on the driver's behavior intention identification model, the application difficulties of ADAS technology in immature driver vehicles are solved, the safety and fairness of driving test vehicles are improved, and the cost of labor supervision is reduced. Enhanced the intelligence and unmanned driving tests.
Patent Information
- Application Number
- CN202411298952.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-18
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-09-18
AI Technical Summary
The existing ADAS technology is difficult to effectively apply in driving test vehicles operated by immature drivers, making driving safety difficult to ensure, and the cost of relying on manpower is high, making it difficult to achieve fairness and transparency.
Automatic emergency braking control method and system based on the driver's behavioral intention identification model, a model is established through the driver's behavioral habit database, combined with environmental perception and vehicle data, the driver's intention is judged, and terminal braking commands are output to avoid collisions.
Effectively adapt to driving test scenarios, improve driving safety, reduce labor supervision costs, improve examination fairness and transparency, basically replace the role of safety officers on the vehicle, and enhance the intelligence and unmanned driving tests.
Smart Images

Figure CN119058667A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent driving tests and automobile intelligent driving, and in particular to an auxiliary safety system control method and system based on a driver behavior intention recognition model. Background Art
[0002] Intelligent driving tests have been a hot topic in the driving test industry in recent years. It aims to introduce existing advanced technologies, combine the business characteristics of driving test scenarios, reduce human intervention in the test through intelligent products, and ensure the fairness and transparency of the driver's license test process. At present, assisted driving technology (ADAS) has been widely used in road vehicles and has performed well in reducing road accidents. However, ADAS technology is currently mainly aimed at mature drivers and only provides assisted driving functions, and there will still be certain cases of misbraking and missed braking. Since the drivers of driving test vehicles do not have full driving capabilities and their driving behavior is immature, it is difficult for the current ADAS technology to be directly introduced and applied to driving test vehicles operated by non-mature drivers.
[0003] At present, driving safety during the driving test is mainly achieved through the intervention of the on-board safety officer in the co-pilot seat. It is difficult to avoid human prompts and even cheating in this process. Although there is a supervision system for on-board safety officers, it is difficult to supervise the entire process due to the large amount of data. At the same time, the manpower investment of on-board safety officers also causes huge operating costs. Therefore, it is necessary to develop a set of auxiliary safety products suitable for the driving test process, which can effectively improve the fairness and transparency of the driving test on the one hand, and effectively save labor costs on the other. Summary of the invention
[0004] In order to solve the problem that the existing automatic emergency braking technology cannot adapt to driving test vehicles, the present invention provides an automatic emergency braking control method and system based on a driver behavior intention recognition model. By introducing the driver behavior model and performing terminal braking command judgment, it can effectively adapt to the driving test application scenario and ensure driving safety during the driving test, especially driving safety in the absence of a safety officer.
[0005] The first aspect of the present invention discloses an auxiliary safety control method based on a driving test actor model, comprising:
[0006] Establishing a driver behavior intention recognition model based on a driver behavior habit database; the driver behavior habit database contains a correspondence between driver behavior characteristics and vehicle response data at corresponding moments, and the vehicle response data is used to reflect the driver's behavior intention;
[0007] The spatial attribute values of the target objects within the sensing range are obtained through the environmental sensing module on the test vehicle;
[0008] Acquire vehicle basic data through the CAN bus, and calculate the current vehicle motion trajectory based on the vehicle basic data;
[0009] Target objects are screened according to the spatial attribute values of the target objects, and the targets of interest closest to the vehicle in each pre-divided area are screened;
[0010] Calculate the relative motion relationship between the vehicle and the target of interest based on the spatial attribute values of the vehicle and the target, and classify the target of interest;
[0011] Calculate the collision time threshold under the current vehicle motion trajectory, correct the collision time threshold according to the motion relationship between the vehicle and the target of interest, calculate the collision time between the target of interest and the vehicle, and output the corresponding collision signal if the collision time is less than the corrected collision time threshold;
[0012] After receiving the collision signal, the driver's behavior characteristics collected by the visual sensor are obtained, and the driver's behavior characteristics are input into the driver's behavior intention recognition model to obtain the current driver's behavior intention;
[0013] Whether to output a terminal braking instruction is determined according to the behavioral intention: if the driver has no subjective behavioral intention to avoid a collision, the terminal braking instruction is output to the execution terminal; otherwise, the terminal braking instruction is not output.
[0014] Furthermore, the auxiliary safety control method also includes: the execution terminal actively brakes the vehicle after receiving a braking command.
[0015] An auxiliary safety control system based on a driving test actor model, characterized in that it includes a main control module, and a visual sensor electrically connected to the main control module, a vehicle response data acquisition module, an environment perception module, and a vehicle basic data acquisition module;
[0016] The visual sensors include two sets installed on the top and bottom of the cockpit in the vehicle, which are used to obtain the driver's hand and head postures and movements, and the driver's leg postures and movements respectively;
[0017] The vehicle response data acquisition module is connected to the vehicle OBD and is used to acquire vehicle dynamics response data;
[0018] The environment perception module is used to dynamically perceive the road environment around the vehicle and output the spatial attribute values of the target objects within the perception range;
[0019] The vehicle basic data acquisition module is connected to the CAN bus, and uses the CAN communication network to perform data analysis and synchronization to acquire vehicle basic data;
[0020] The main control module includes a processor and a memory, and the memory stores a computer program; the processor calls the computer program to execute the automatic emergency braking control method based on the driving test behavior model described in the first aspect of the present invention.
[0021] Furthermore, the main control module is also externally connected to a brake actuator; after receiving a brake command sent by the main control module, the brake actuator executes a brake response.
[0022] The automatic emergency braking control method and system based on the driver behavior intention recognition model of the present invention can effectively adapt to the application scenario of the driving test by introducing the driver behavior model and judging the terminal braking command. At the same time, by screening the target objects in various areas around the vehicle and calculating the collision time respectively, it not only avoids the occurrence of front collision, but also realizes the collision control of the side and rear vehicles, which can basically replace the role of the on-board safety officer, improve the intelligent and unmanned degree of the driving test, and fundamentally solve the controversy of safety officer supervision and premature intervention in the driving test, and further improve the transparency and fairness of the test process. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 It is a flowchart of the auxiliary safety system control method based on the driver behavior intention recognition model;
[0024] Figure 2 Schematic diagram of environmental perception;
[0025] Figure 3 Schematic diagram of the region of interest;
[0026] Figure 4 This is a block diagram of an auxiliary safety control system based on the driver behavior intention recognition model. DETAILED DESCRIPTION
[0027] In order to understand the present invention, the technical solution of the present invention is further explained below in conjunction with specific embodiments.
[0028] Combination Figure 1 As shown, the embodiment of the present invention discloses an auxiliary safety system control method based on a driver behavior intention recognition model, which mainly includes the following steps:
[0029] S1: Based on the driver behavior habit database, a driver behavior intention recognition model is established to identify the driver's behavior intention.
[0030] Before establishing a driver behavior intention recognition model, it is necessary to first create a driver behavior habit database, and use the data in the database to train the initially constructed model to obtain the required driver behavior intention recognition model.
[0031] The driver behavior database contains the corresponding relationship between the driver behavior characteristics and the vehicle response at the corresponding time. For example, when the driver steps on the brake pedal, the vehicle speed decreases; when the driver turns the steering wheel left, the vehicle starts to change lanes to the left.
[0032] Among them, the driver's behavior characteristics can be collected through visual sensors installed in the cockpit of the test vehicle. Specifically, visual sensors can be installed on the top and bottom of the cockpit in the car, among which the top visual sensor is mainly used to identify the driver's hand and head posture and movement, and the bottom visual sensor is mainly used to identify the driver's leg posture and movement. The collected behavioral characteristics mainly include hand holding steering wheel characteristics, accelerator pedal operation characteristics, brake pedal operation characteristics, clutch pedal operation characteristics, head rotation characteristics, line of sight transfer characteristics, etc. Furthermore, the collected driver behaviors can be filtered in advance to eliminate behaviors such as touching the head and scratching the ears, and screen out effective driver behavior characteristics.
[0033] Among them, the vehicle response data, that is, the vehicle dynamic response, can be obtained through the vehicle OBD (on-board automatic diagnostic system). Specifically, the vehicle response data at the corresponding moment of the driver's behavior characteristics is collected through OBD, so as to form the corresponding relationship data between different driver behavior characteristics and vehicle responses. The vehicle response data mainly includes: vehicle acceleration, vehicle deceleration, vehicle changing lanes to the left, vehicle changing lanes to the right, vehicle turning left, vehicle turning right, vehicle turning around, etc.
[0034] After the two types of data are acquired, a one-to-one correspondence is established between the effective driver behavior characteristics and vehicle response data, thereby obtaining a driver behavior habit database. The samples in the data database can be represented as X i (A i , B i ), where A i represents the effective behavior characteristics of the i-th driver, B i Represents the vehicle dynamic response corresponding to the effective behavior characteristics of the i-th driver.
[0035] It is understandable that the vehicle response data is usually an objective reflection of the driver's behavioral intention. In other words, after collecting the vehicle response data, the driver's behavioral intention can be known. Therefore, the driver's behavioral intention is also mainly divided into several categories, such as acceleration, deceleration, left lane change, right lane change, left turn, right turn, and U-turn. Taking the accelerator pedal as an example, the driver's behavioral characteristic is stepping on the accelerator pedal, and the corresponding vehicle response data is that the vehicle speed increases, which means that the driver has the intention to accelerate; the driver's behavioral characteristic is lifting the foot and leaving the accelerator pedal, and the corresponding vehicle response data is that the vehicle speed decreases, which means that the driver has the intention to decelerate; taking the steering wheel as an example, the driver's behavioral characteristic is holding the steering wheel and turning slightly to the left, and the corresponding vehicle response data is that the vehicle starts to change lanes to the left, which means that the driver has the intention to change lanes.
[0036] Based on the pre-built driver behavior habit database, the required driver behavior intention recognition model is established to dynamically identify the driver's behavior intention. The model establishment process mainly includes:
[0037] Construct an initial deep neural network (DNN) model, which includes an input layer, a hidden layer, and an output layer. The hidden layer neuron model is y = f (ΣW i *X i +b), where W i is the corresponding weight, b is the bias term, f is the activation function, f(x) = sigmoid(x); the weight is updated to W i =W i-1 -η*(ΔL / Δw), where η represents the learning rate, ΔL / Δw represents the gradient of the loss function relative to the weight, and L represents the total number of forward layers; obtain the data sample X in the driver behavior habit database i (A i , B i ) is used as training data to train the deep neural network; after the training is completed, the required driver behavior intention recognition model is obtained. Based on this model, after the driver's behavior characteristics are input, the corresponding vehicle dynamics response can be output, and the driver's behavior intention can be obtained.
[0038] S2: Obtain the spatial attribute values of the target objects within the perception range through the environmental perception module on the test vehicle.
[0039] The environment perception module is mainly used to dynamically perceive the road environment around the vehicle and output the spatial attribute values of the target objects within the perception range. The spatial attribute values mainly include position information, speed information, acceleration information, category information, size information, orientation information and other information.
[0040] like Figure 2As shown in the figure, the environment perception module installed on the test vehicle mainly includes millimeter-wave radar, camera, laser radar and other equipment. Among them, the laser radar is installed on the top of the vehicle to collect point cloud data within the 360° range of the vehicle; the cameras are installed at the front, rear and both sides of the vehicle, two on each side, for fusion with the laser radar point cloud, target clustering and identification; the millimeter-wave radar is installed at the four corners of the vehicle, mainly used to correct the speed of the target.
[0041] S3: Obtain vehicle basic data based on the CAN bus and calculate the current vehicle motion trajectory.
[0042] Before calculating the vehicle motion trajectory, it is necessary to first obtain the basic vehicle data. The basic vehicle data can be obtained through the basic vehicle data acquisition module. The basic vehicle data acquisition module is connected to the CAN bus and uses the CAN communication network to perform data analysis and synchronization to obtain the basic vehicle data. The basic vehicle data mainly includes real-time data such as vehicle speed, gear position, steering wheel angle, yaw rate, braking, and throttle.
[0043] After the basic vehicle data is obtained, the current vehicle motion trajectory can be calculated based on the basic vehicle data.
[0044] For example, the vehicle motion trajectory is calculated as follows:
[0045] First, based on the steering wheel angle α, calculate the current front wheel angle θ:
[0046] θ = K * α, where K is the vehicle steering ratio;
[0047] Based on the obtained front wheel turning angle θ, the turning radius R of the vehicle is calculated:
[0048] R = vehicle wheelbase / sin(θ),
[0049] Therefore, the current vehicle trajectory is the turning radius R±vehicle width*0.5.
[0050] S4: Screening targets according to the spatial attribute values of the targets provided by the environment perception module, and screening out the targets of interest closest to the vehicle in each pre-divided area.
[0051] Before selecting the target object, the space around the vehicle is divided into eight areas: left front, front, right front, left rear, rear, right rear, left side, and right side. Figure 3 As shown; then, according to the spatial attribute value of the target (mainly referring to the position information and size information), the target objects in each area are screened respectively, and the target object closest to the vehicle in each area is found, and it is taken as the target of interest in the corresponding area.
[0052] S5: Calculate the relative motion relationship between the vehicle and the target of interest based on the spatial attribute values of the vehicle and the target object, and classify the target of interest.
[0053] Based on the spatial attribute values of the target object obtained by the environment perception module, the relative motion relationship between the vehicle and each target of interest is calculated. The calculation method is as follows: define the X-axis of the vehicle plane coordinate system to coincide with the center axis of the vehicle, pointing to the front direction of the vehicle as positive, and the Y-axis to be perpendicular to the X-axis, pointing to the left side of the driver as positive; define the relative speed Vr between the target of interest and the vehicle as Vr = speed of the target of interest – speed of the vehicle, and the relative speed direction along the coordinate axis is positive.
[0054] According to the relative speed and relative speed direction, that is, the relative motion relationship between the vehicle and the target object, the targets of interest in each area are classified into stationary targets, distant targets, targets approaching at a constant speed, targets approaching at an accelerated speed, and targets approaching at a decelerated speed.
[0055] S6: Calculate the collision time threshold under the current vehicle motion trajectory, correct the collision time threshold according to the motion relationship between the target of interest and the vehicle, and then calculate the collision time between the target of interest and the vehicle. If the collision time is less than the corrected collision time threshold, it means that the basic trigger condition is met and the corresponding collision signal is output.
[0056] Specifically, firstly, TTCT0 (time to collision threshold) under the current vehicle motion trajectory is calculated based on the current vehicle speed, and the collision time threshold is proportional to the vehicle speed.
[0057] TTCT0=(V+value) / factor,
[0058] Wherein, V represents the current vehicle speed, value represents the speed compensation, and factor represents the coefficient. In the embodiment of the present invention, value=80 and factor=78.5 may be set.
[0059] Next, according to the classification of the objects of interest in each area, the objects close to the vehicle in each area (i.e., objects that may collide) are screened out, and the collision time thresholds of the objects close to the vehicle in each area are corrected respectively, wherein TTCT0 is increased for the objects approaching at an accelerated speed, the objects approaching at a constant speed, and the objects approaching at a stationary speed, and TTCT0 is reduced for the objects approaching at a decelerated speed. For example, the correction can be made according to the following formula:
[0060] Stationary target: TTCT = TTCT0 + 0.2;
[0061] Accelerate to approach the target: TTCT = (TTCT0 + 0.2) * (0.1794 + 0.026 * Vr);
[0062] Decelerate approaching the target Target: TTCT = (TTCT0 + 0.2) * (0.11888 - 0.00456 * Vr);
[0063] Approach the target at a constant speed: TTCT = (TTCT0 + 0.2) * (0.095 + 0.024 * Vr);
[0064] In the formula, TTCT represents the corrected collision time threshold; Vr represents the relative speed between the target of interest and the vehicle.
[0065] Then, calculate TTC (time to collision), that is, based on the attribute values (speed, acceleration, and distance from the vehicle) of the target of interest in each area, calculate the time required for the vehicle to collide with the target of interest if the current motion relationship is maintained.
[0066] TTC = S / Vr,
[0067] In the formula, S represents the relative distance between the target of interest and the vehicle, and Vr represents the relative speed of the target of interest compared to the vehicle.
[0068] Finally, compare the calculated collision time TTC with the corrected collision time threshold TTCT: If the TTC of the target in the area < TTCT, output the basic collision signal (B1).
[0069] S7: After receiving the basic collision signal, decide whether to output the terminal collision signal according to the classification result of the driver behavior intention recognized by the driver behavior intention recognition model: If the driver has no subjective intention to avoid collision, output a braking instruction to the execution terminal, otherwise do not output a braking instruction.
[0070] After receiving the basic collision signal, obtain the driver behavior characteristics collected by the vision sensor, and input the driver behavior characteristics into the driver behavior intention recognition model to obtain the current driver's behavior intention.
[0071] The system makes a decision based on the classification result of the driver behavior intention: If the driver has no subjective intention to avoid collision, output the corresponding braking instruction (B2) to the execution terminal; if the driver has a subjective intention to avoid collision, suspend the output of the braking instruction.
[0072] For example, during the straight - line driving of the vehicle, after receiving the basic collision signal in the front - directly - ahead area, the classification result output by the driver behavior model is that the driver has no subjective intention to avoid collision (for example, the driver still maintains or increases the current throttle pedal stroke). At this time, a braking instruction should be output to the execution terminal to avoid an accident.
[0073] The execution terminal actively brakes the vehicle after receiving the braking command. If it is determined that the driver has no subjective intention to avoid a collision, the execution terminal (also known as the "brake actuator") actively brakes the vehicle after receiving the braking command (B2) issued by the system decision to avoid a collision and ensure the safety of the driving test process.
[0074] It can be understood that the execution subject of this step is an external execution terminal. As an optional method, the external brake actuator is mainly composed of a controller, a motor, a wire rope, and a connector. The controller is connected to the system communication through a serial port communication. When the controller receives a braking command, it controls the motor to rotate forward, retracts the wire rope, presses the brake pedal, and actively brakes; when the controller receives a brake release command, it controls the motor to reverse, release the wire rope, and release the brake pedal.
[0075] It can be understood that the implementation steps of the auxiliary safety control method based on the driver behavior intention recognition model disclosed in the embodiment of the present invention are not completely fixed and can be adjusted according to actual conditions.
[0076] Combination Figure 4 As shown, another embodiment of the present invention discloses an automatic emergency braking control system based on a driver behavior intention recognition model, which mainly includes a main control module, and a visual sensor electrically connected to the main control module, a vehicle response data acquisition module, an environmental perception module, and a vehicle basic data acquisition module.
[0077] Among them, the visual sensors mainly include two groups installed on the top and bottom of the cockpit, which are used to obtain the driver's hand and head postures and movements, as well as the driver's leg postures and movements. The vehicle response data acquisition module is connected to the vehicle OBD to obtain the vehicle dynamic response data. The environmental perception module is mainly used to dynamically perceive the road environment around the vehicle and output the spatial attribute values of the target objects within the perception range. It is usually composed of millimeter wave radar, camera, laser radar and other equipment. Its workflow is as follows: Figure 2 The vehicle basic data acquisition module is connected to the CAN bus, and uses the CAN communication network to perform data analysis and synchronization to obtain the vehicle basic data. In addition, the main control module is also connected to the controller in the actuator so as to issue a braking instruction to the actuator, and the actuator executes the braking action to avoid a collision. Among them, the main control module includes a processor and a memory, and the memory stores a computer program for implementing the automatic emergency braking control method based on the driver behavior intention recognition model described in the above embodiment; the processor calls the computer program in the memory to execute the automatic emergency braking control method. The functional characteristics and specific implementation methods of the above modules can be found in the aforementioned method embodiments, and will not be described in detail.
[0078] Finally, it should be noted that although the embodiments of the present invention are described above in conjunction with the accompanying drawings, the present invention is not limited to the above-mentioned specific embodiments and application fields, and the above-mentioned specific embodiments are only illustrative and instructive, rather than restrictive. Under the guidance of this specification, a person of ordinary skill in the art can also make many forms without departing from the scope of protection of the claims of the present invention, all of which belong to the scope of protection of the present invention.
Claims
1. An auxiliary safety control method based on a driving test actor model, characterized in that: include: Establishing a driver behavior intention recognition model based on a driver behavior habit database; the driver behavior habit database contains a correspondence between driver behavior characteristics and vehicle response data at corresponding moments, and the vehicle response data is used to reflect the driver's behavior intention; The spatial attribute values of the target objects within the sensing range are obtained through the environmental sensing module on the test vehicle; Obtain vehicle basic data through the CAN bus, and calculate the current vehicle motion trajectory based on the vehicle basic data; screen the target objects according to the spatial attribute values of the target objects, and screen out the targets of interest that are closest to the vehicle in each pre-divided area; Calculate the relative motion relationship between the vehicle and the target of interest based on the spatial attribute values of the vehicle and the target, and classify the target of interest; Calculate the collision time threshold under the current vehicle motion trajectory, correct the collision time threshold according to the motion relationship between the vehicle and the target of interest, calculate the collision time between the target of interest and the vehicle, and output the corresponding collision signal if the collision time is less than the corrected collision time threshold; After receiving the collision signal, the driver's behavior characteristics collected by the visual sensor are obtained, and the driver's behavior characteristics are input into the driver's behavior intention recognition model to obtain the current driver's behavior intention; Whether to output a terminal braking instruction is determined according to the behavioral intention: if the driver has no subjective behavioral intention to avoid a collision, the terminal braking instruction is output to the execution terminal; otherwise, the terminal braking instruction is not output.
2. The auxiliary safety control method according to claim 1, characterized in that: The driver's behavior characteristics include hand gripping steering wheel characteristics, accelerator pedal operation characteristics, brake pedal operation characteristics, clutch pedal operation characteristics, head rotation characteristics, and line of sight shift characteristics; The vehicle response data includes: vehicle acceleration, vehicle deceleration, vehicle changing lanes to the left, vehicle changing lanes to the right, vehicle turning left, vehicle turning right, and vehicle U-turn; correspondingly, the driver's behavioral intention includes acceleration, deceleration, turning left, turning right, turning left, turning right, and U-turn.
3. The auxiliary safety control method according to claim 1 or 2, characterized in that: According to the driver behavior habit database, a driver behavior intention recognition model is established, including: The driver's behavior characteristics are collected through the visual sensor installed in the cockpit of the test vehicle, and the effective driver's behavior characteristics are obtained after filtering; Obtain vehicle response data, i.e. vehicle dynamics response, through vehicle OBD; Establish an effective one-to-one correspondence between driver behavior characteristics and vehicle response data to obtain a driver behavior habit database. The data sample is represented by X i (A i , B i ), where A i represents the effective behavior characteristics of the i-th driver, B i represents the vehicle dynamics response corresponding to the effective behavior characteristics of the i-th driver; Construct an initial deep network model, which includes an input layer, a hidden layer, and an output layer. The hidden layer neuron model is y = f (ΣW i *X i +b), where W i is the corresponding weight, b is the bias term, f is the activation function, f(x) = sigmoid(x); the weight is updated to W i =W i-1 -η*(ΔL / Δw), where η represents the learning rate, ΔL / Δw represents the gradient of the loss function relative to the weight, and L represents the total number of forward layers; the data sample X in the driver behavior habit database is i (A i , B i ) is used as training data to train the deep neural network; after the training is completed, the required driver behavior intention recognition model is obtained.
4. The auxiliary safety control method according to claim 1 or 2, characterized in that: The spatial attribute values include position information, speed information, acceleration information, size information, and orientation information; the vehicle basic data includes vehicle speed, gear position, steering wheel angle, yaw angular velocity, braking, and throttle.
5. The auxiliary safety control method according to claim 1 or 2, characterized in that: Targets are screened according to the spatial attribute values of the target objects, and the targets of interest closest to the vehicle in each pre-divided area are screened out, specifically including: Before selecting the target object, the space around the vehicle is divided into eight areas: left front, front, right front, left rear, rear, right rear, left side, and right side. Then, according to the spatial attribute value of the target object, the target objects in each area are screened respectively, and the target object closest to the vehicle in each area is found and regarded as the target of interest in the corresponding area.
6. The auxiliary safety control method according to claim 1 or 2, characterized in that: The relative motion relationship between the vehicle and the target is calculated based on the spatial attribute values of the vehicle and the target, and the targets of interest are classified. Specifically, the relative motion relationship between the vehicle and each target of interest is calculated based on the spatial attribute values of the target obtained by the environment perception module. The calculation method is as follows: Define the vehicle plane coordinate system as follows: the X-axis coincides with the vehicle centerline, pointing to the front of the vehicle is positive, and the Y-axis is perpendicular to the X-axis, pointing to the left of the driver is positive; Define the relative speed between the target of interest and the vehicle Vr = target of interest speed – vehicle speed, the relative speed direction is positive along the coordinate axis; According to the relative speed and relative speed direction, that is, the relative motion relationship between the vehicle and the target of interest, the targets of interest in each area are classified. The classification categories include stationary targets, distant targets, uniformly approaching targets, accelerating approaching targets, and decelerating approaching targets.
7. The auxiliary safety control method according to claim 6, characterized in that: The calculation formula of the collision time threshold is: TTCT0=(V+value) / factor In the formula, TTCT0 represents the collision time threshold, V represents the current vehicle speed, value represents the speed compensation, and factor represents the coefficient; The calculation formula of the collision time is: TTC=S / Vr Where S represents the relative distance between the target of interest and the vehicle, and Vr represents the relative speed of the target of interest compared to the vehicle.
8. The auxiliary safety control method according to claim 7, characterized in that: The collision time threshold is modified according to the motion relationship between the vehicle and the target of interest, including: Stationary target: TTCT = TTCT0 + 0.2; Accelerate to approach the target: TTCT = (TTCT0 + 0.2) * (0.1794 + 0.026 * Vr); Slow down to approach the target target: TTCT = (TTCT0 + 0.2) * (0.11888 - 0.00456 * Vr); Approaching the target at a constant speed: TTCT = (TTCT0 + 0.2) * (0.095 + 0.024 * Vr); Where TTCT represents the corrected collision time threshold; Vr represents the relative speed between the target of interest and the vehicle.
9. The auxiliary safety control method according to claim 1 or 2, characterized in that: The vehicle motion trajectory is calculated as follows: First, based on the steering wheel angle α, calculate the current front wheel angle θ: θ = K * α, where K is the vehicle steering ratio; Based on the obtained front wheel turning angle θ, calculate the turning radius R of the vehicle: R = vehicle wheelbase / sin(θ), Therefore, the current vehicle trajectory is: turning radius R±vehicle width*0.
5.
10. An auxiliary safety control system based on a driving test actor model, characterized in that: It includes a main control module, and a visual sensor electrically connected to the main control module, a vehicle response data acquisition module, an environment perception module, and a vehicle basic data acquisition module; The visual sensors include two sets installed on the top and bottom of the cockpit in the vehicle, which are used to obtain the driver's hand and head postures and movements, and the driver's leg postures and movements respectively; The vehicle response data acquisition module is connected to the vehicle OBD and is used to acquire vehicle dynamics response data; The environment perception module is used to dynamically perceive the road environment around the vehicle and output the spatial attribute values of the target objects within the perception range; The vehicle basic data acquisition module is connected to the CAN bus, and uses the CAN communication network to perform data analysis and synchronization to acquire vehicle basic data; The main control module includes a processor and a memory, and the memory stores a computer program; the processor calls the computer program to execute the automatic emergency braking control method based on the driving test actor model as described in any one of claims 1 to 9.
Citation Information
Patent Citations
Vehicle auxiliary control method for driving training and related equipment
CN118269995A
Device for controlling automobile brake
CN216185090U
Traveling Control Device, Vehicle, and Traveling Control Method
US20210394752A1
Cited By
Low-cost dynamic trigger test method and system for automatic driving multi-target vehicle conflict sequence in closed site
CN120742855A
