A traffic conflict-based aeb triggering method, device, medium

Abstract

This invention relates to an AEB (Autonomous Emergency Braking) triggering method, device, and medium based on traffic conflict, comprising the following steps: identifying at least one target vehicle in the environment; determining the vehicle type of the target vehicle based on a preset target detection model; matching a preset target vehicle mass based on the vehicle type; calculating the difference in braking distance based on the acquired relative distance between the vehicle and the target vehicle and the target vehicle speed; calculating the collision loss momentum based on the target vehicle speed, the target vehicle mass, the acquired vehicle speed, and preset vehicle mass information; calculating the risk level based on the difference in braking distance and the collision loss momentum, and according to the vehicle type; and triggering AEB when the risk level meets predetermined conditions. Compared with the prior art, this invention ensures vehicle driving safety while also considering comfort.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to an AEB triggering method, device, and medium based on traffic conflict. Background Technology

[0002] The Automatic Emergency Braking (AEB) system uses radar to measure the distance to a target vehicle or obstacle. Then, a data analysis module compares the measured distance with the warning distance and the safe distance. If the distance is less than the warning distance, an alarm is issued. If the distance is less than the safe distance, the AEB system will activate and automatically brake the car even if the driver has not had time to press the brake pedal, thus ensuring safe travel.

[0003] Currently, most vehicle-mounted AEB (Autonomous Emergency Braking) systems employ emergency braking strategies based on longitudinal safe distance and longitudinal safe time models. Existing models rely on radar sensors to obtain the target's speed and displacement, using this as the sole criterion for judgment. Because some drivers have aggressive driving habits, they can avoid collisions even when the distance between their vehicle and the target vehicle is within a dangerous range. In such cases, the fixed safety model frequently triggers AEB, reducing driving comfort.

[0004] Chinese patent application CN202110428417.8 discloses an autonomous driving control method and apparatus. In this method, the current vehicle displacement parameters and the current object displacement parameters of traffic participants are obtained; based on the current vehicle displacement parameters and the current object displacement parameters, a collision risk probability is determined; if the collision risk probability exceeds the risk threshold, an emergency braking operation is performed; if the collision risk probability is less than or equal to the risk threshold, a reinforcement learning model is invoked to determine the target vehicle operation information corresponding to the current vehicle displacement parameters and the current object displacement parameters, and the vehicle is controlled to operate according to the target vehicle operation information.

[0005] The aforementioned applications ensure vehicle safety and traffic efficiency during autonomous driving. However, they lack specificity because they do not employ the same strategies for controlling different vehicles. Furthermore, current AEB systems are mostly closed-loop systems, meaning their risk assessment parameters are fixed. Faced with increasingly busy road traffic systems, they struggle to adapt to the diverse needs of different driving environments. Traditional safety distance and safety time models, using fixed safety distance indicators, find it difficult to balance vehicle safety and comfort in complex road conditions. Fixed safety distance indicators also exhibit significant differences in adaptability at high and low speeds; a smaller safety distance may not prevent collisions at high speeds, while a larger safety distance at low speeds can reduce driving comfort due to frequent triggering.

[0006] In summary, there is currently a lack of an AEB triggering method that can ensure vehicle driving safety while also taking comfort into account. Summary of the Invention

[0007] The purpose of this invention is to overcome the shortcomings of the prior art by providing an AEB triggering method, device, and medium based on traffic conflict, which ensures vehicle driving safety while also taking comfort into account.

[0008] The objective of this invention can be achieved through the following technical solutions:

[0009] One aspect of the present invention provides an AEB (Automatic Emergency Braking) triggering method based on traffic conflict, comprising the following steps:

[0010] Identify at least one target vehicle in the environment, determine the vehicle type of the target vehicle based on a preset target detection model, and match a preset target vehicle quality based on the vehicle type;

[0011] Based on the relative distance between the vehicle and the target vehicle and the speed of the target vehicle, the difference in braking distance is calculated;

[0012] Based on the target vehicle speed, the target vehicle mass, the obtained vehicle speed, and the preset vehicle mass information, the collision loss momentum is calculated;

[0013] Based on the difference in braking distance and the momentum lost in the collision, and calculating the risk level according to the vehicle type, AEB is triggered when the risk level meets predetermined conditions.

[0014] As a preferred technical solution, the risk level is calculated using the following formula:

[0015]

[0016] in, For the aforementioned risk level, k 1、k2 represents the collision severity index coefficient and parking distance index coefficient determined based on vehicle type, and k3 represents the system response time constant. The parking distance index is calculated based on the difference in braking distances. This is the collision severity index calculated based on the momentum loss during the collision.

[0017] As a preferred technical solution, the vehicle types include small cars, medium-sized cars, and large cars, and the collision severity index coefficient... The principle for determining the value is: the value for small cars is less than the value for medium / large cars.

[0018] As a preferred technical solution, the parking distance index is obtained using the following formula:

[0019]

[0020] in, The difference in braking distance, The speed of the target vehicle. , These are the emergency braking distances of the target vehicle and the vehicle itself, respectively.

[0021] As a preferred technical solution, the collision severity index is obtained using the following formula:

[0022]

[0023] in, c This is the proportionality coefficient. b It is a constant. x The momentum lost in the collision.

[0024] As a preferred technical solution, the difference in braking distance is obtained using the following formula:

[0025]

[0026]

[0027] in, The difference in braking distance, , These are the emergency braking distances of the target vehicle and the vehicle itself, respectively. The relative distance between the target vehicle and this vehicle. It is the braking reaction time. , These are the speeds of the target vehicle and the current vehicle, respectively. , It is the preset target vehicle and the maximum braking deceleration of this vehicle.

[0028] As a preferred technical solution, the relative distance and the target vehicle speed are obtained by millimeter-wave radar.

[0029] As a preferred technical solution, the predetermined conditions are as follows:

[0030] The risk level is equal to the expected collision time.

[0031] In another aspect, an electronic device is provided, comprising: one or more processors and a memory, wherein the memory stores one or more programs, the one or more programs including instructions for executing the above-described traffic conflict-based AEB triggering method.

[0032] In another aspect, the present invention provides a computer-readable storage medium including one or more programs executable by one or more processors of an electronic device, said one or more programs including instructions for performing the above-described traffic conflict-based AEB triggering method.

[0033] Compared with the prior art, the present invention has the following advantages:

[0034] (1) Ensuring vehicle driving safety while also considering comfort: Traditional safety distance models and safety time models use fixed safety distance indicators, which make it difficult to balance vehicle driving safety and comfort when facing complex road conditions. Unlike existing solutions, this invention adopts an AEB triggering method based on traffic conflict, which can adjust the braking strategy in real time according to the vehicle type and motion state of the target vehicle and the vehicle itself, thereby maximizing passenger comfort while ensuring safety.

[0035] (2) A traffic conflict model is constructed for different types of vehicles to calculate the risk level, resulting in high safety: The present invention identifies the category of the target vehicle through the target detection model and determines the corresponding parameters according to different vehicle categories to calculate the risk level, thus achieving higher safety when facing different target vehicles. Attached Figure Description

[0036] Figure 1 This is a flowchart of the AEB triggering method based on traffic conflict in the embodiment;

[0037] Figure 2 This is a structural diagram of the risk conflict model in the embodiment;

[0038] Figure 3 This is a diagram illustrating a rear-end collision. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0040] Example 1

[0041] This invention proposes an AEB (Autonomous Emergency Braking) triggering method based on traffic conflict, applicable to any computer device equipped with AEB functionality. This computer device can be an electronic device such as a vehicle controller or electronic control unit.

[0042] See Figure 1 The risk conflict model structure diagram of this invention specifically includes the following steps:

[0043] S1 acquires environmental information about the vehicle's surroundings through vehicle sensors, including ultrasonic radar and cameras.

[0044] S2, based on the data from step S1, filters out targets that may collide with the target vehicles and extracts their driving status data and image data. Using a trained target detection model, the vehicle type of the target is identified.

[0045] S3, see S3. Figure 2 Based on the data from step S2, different risk assessment models are built. That is, different traffic conflict models are used and different AEB control strategies are formulated according to the different vehicle types of the current vehicle and the target vehicle types.

[0046] S4 obtains the driving status of the target vehicle and its own vehicle through sensors, and sets the risk assessment index REI based on this. Finally, this value is output to the decision control module as the time threshold of the AEB braking strategy.

[0047] Vehicle speed, displacement, and target vehicle image data are acquired using vehicle sensors. The Yolov3 target detection algorithm is used to identify the type of target vehicle and match it with the vehicle types in Table 1 to determine the corresponding mass parameters. The mass parameters of this vehicle are determined through pre-setting.

[0048] Table 1. Vehicle Classification for Target Detection

[0049]

[0050] Traffic conflict assessment models include distance and energy indicators:

[0051] The distance indicator is:

[0052] (1)

[0053] In the formula, S1 represents the braking distance of the target vehicle during emergency braking, and S2 represents the braking distance of the vehicle during emergency braking. a1 represents the maximum braking deceleration of the target vehicle, a2 represents the maximum braking deceleration of the vehicle, and S... h t represents the relative distance between the target vehicle and the current vehicle. r V1 represents the initial speed of the target vehicle, and V2 represents the initial speed of the vehicle itself. For safety reasons, the maximum braking deceleration of both the target vehicle and the vehicle is uniformly set to a1 = a2 = -8 m / s². 2 Braking reaction time t r It is a pre-set average braking reaction time of the driver, calculated from statistics in SG-NDS.

[0054] Therefore, the difference in braking distance ΔS during vehicle operation is:

[0055] (2)

[0056] The Parking Distance Index (VSI) is expressed as:

[0057] (3)

[0058] According to the above formula, when the emergency braking distance S2 of this vehicle is less than the emergency braking distance S1 of the target vehicle, the vehicle can avoid a collision, and the parking distance index is 0.

[0059] When the braking distance of this vehicle is greater than that of the target vehicle, there is a risk of collision. The parking distance index is expressed as VSI = △S / V1.

[0060] The energy index is:

[0061] According to the law of conservation of momentum, the change in momentum before and after the collision is shown in the following equation:

[0062] (4)

[0063] In the formula, m1 represents the mass of the target vehicle, and m2 represents the mass of the vehicle itself. V1 represents the initial velocity of the target vehicle, and V2 represents the initial velocity of the vehicle itself. ＇ V2 represents the speed of the target vehicle after the collision. ＇ This indicates the vehicle's speed after the collision; see details below. Figure 3 .

[0064] At the time of a collision, the kinetic energy recovery coefficient e is defined as the ratio of the speed difference between the vehicle and the target vehicle after the collision to the speed difference between the vehicle and the target vehicle before the collision, as shown in the following formula:

[0065] (5)

[0066] Because the kinetic energy recovery coefficient is affected by factors such as the material of the vehicle body, the shape of its surface, and the speed of the collision, a large amount of experimental data is required.

[0067] According to formulas (4) and (5), the speeds of the vehicle and the target vehicle after the collision are defined as follows:

[0068] (6)

[0069] (7)

[0070] Based on the vehicle speed after the collision obtained from formulas (6) and (7), the momentum lost after the collision is shown in the following formula:

[0071] (8)

[0072] Because different evaluation indicators have different dimensions, they need to be unified through linear transformation. Therefore, the Collision Severity Index (CSI) can be expressed as:

[0073] (9)

[0074] In the formula, c is the proportionality coefficient, b is a constant, and x is the input energy lost after the collision.

[0075] By combining the collision severity index and the stopping distance index, the risk assessment index REI during vehicle operation can be obtained:

[0076] (10)

[0077] In the formula, k1 is the coefficient of the collision severity index, k2 is the coefficient of the parking distance index, and k3 is the system response time constant.

[0078] Depending on the type of target vehicle, different collision severity indices (k1) are set. When the target vehicle is a small car, the driving strategy is more aggressive compared to medium and large vehicles, and a smaller k1 value is set. As the mass parameter of the target vehicle increases, the k1 value also increases accordingly, providing more braking time and increasing the safe distance between the vehicle and the target vehicle.

[0079] Vehicle speed, displacement, and target vehicle image data are acquired using vehicle sensors. The Yolov3 target detection algorithm is used to identify the type of target vehicle and match it with the vehicle types in Table 1 to determine the corresponding mass parameters. The mass parameters of this vehicle are determined through pre-setting.

[0080] When the target vehicle and the vehicle's speed are similar, the risk assessment index (REI) derived by the risk assessment model will be smaller, and the estimated time to collision (TTC) will also be lower. b When the risk assessment index (REI) is equal to the target vehicle's risk level (TTC), the vehicle will trigger emergency braking, and the shortest distance between the vehicle and the target vehicle during braking will be smaller than the safe distance set by the fixed safe distance model. b Predicted collision time, referring to the terms and definitions in GB / T 38186—2019, is an indicator used in the AEB safe time model to assess collision risk.

[0081] When the speed difference between the target vehicle and the vehicle itself is significant, the risk assessment index (REI) derived by the risk assessment model will be higher, and the estimated time to collision (TTC) will also be higher. b When the risk assessment index (REI) is equal to the target vehicle's risk level, the vehicle will trigger emergency braking, and the shortest distance between the vehicle and the target vehicle during braking will be greater than the safe distance set by the fixed safe distance model.

[0082] This example integrates the speed, displacement, and mass parameters of both the target vehicle and the vehicle itself, considering the vehicle's parking performance and the severity of a collision, to design a risk-based conflict model for traffic collisions. Compared to traditional fixed-distance safety distance models, this risk-based conflict model, designed for different vehicle categories, can adapt to complex traffic environments. It maximizes driving comfort while ensuring safety.

[0083] In this example, a monocular camera is installed on the top of the vehicle to acquire image information of vehicles in front, and the vehicle type is identified by the YOLO v3 object detection algorithm based on the collected image information to obtain the quality of the target vehicle.

[0084] In this example, the front of the vehicle is equipped with a millimeter-wave radar to acquire target information on the road, select potential collision targets, and obtain the relative distance S between the target vehicle and the vehicle. h And the speed V1 of the target vehicle.

[0085] Example 2

[0086] This embodiment provides an electronic device, including: one or more processors and a memory, wherein the memory stores one or more programs, the one or more programs including instructions for executing the traffic conflict-based AEB triggering method as described in Embodiment 1.

[0087] Example 3

[0088] This embodiment provides a computer-readable storage medium including one or more programs executable by one or more processors of an electronic device, the one or more programs including instructions for performing the traffic conflict-based AEB triggering method as described in Embodiment 1.

[0089] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A traffic conflict-based AEB triggering method, characterized in that, Includes the following steps: Identify at least one target vehicle in the environment, determine the vehicle type of the target vehicle based on a preset target detection model, and match a preset target vehicle quality based on the vehicle type; Based on the relative distance between the vehicle and the target vehicle and the speed of the target vehicle, the difference in braking distance is calculated; Based on the target vehicle speed, the target vehicle mass, the obtained vehicle speed, and the preset vehicle mass information, the collision loss momentum is calculated; Based on the difference in braking distance and the momentum lost in the collision, and calculating the risk level according to the vehicle type, AEB is triggered when the risk level meets predetermined conditions.

2. The AEB triggering method based on traffic conflict according to claim 1, characterized in that, The risk level is calculated using the following formula: in, For the stated risk level, k 1、 k2 represents the collision severity index coefficient and parking distance index coefficient determined based on vehicle type, and k3 represents the system response time constant. The parking distance index is calculated based on the difference in braking distances. This is the collision severity index calculated based on the momentum loss during the collision.

3. The AEB triggering method based on traffic conflict according to claim 2, characterized in that, The vehicle types mentioned include small cars, medium-sized cars, and large cars, and the collision severity index coefficient... The principle for determining the value is: the value for small cars is less than the value for medium / large cars.

4. The AEB triggering method based on traffic conflict according to claim 2, characterized in that, The parking distance index is obtained using the following formula: in, The difference in braking distance. The speed of the target vehicle. , These are the emergency braking distances of the target vehicle and the vehicle itself, respectively.

5. The AEB triggering method based on traffic conflict according to claim 2, characterized in that, The collision severity index is obtained using the following formula: in, c This is the proportionality coefficient. b It is a constant. x The momentum lost in the collision.

6. The AEB triggering method based on traffic conflict according to claim 1, characterized in that, The difference in braking distance is obtained using the following formula: in, The difference in braking distance. , These are the emergency braking distances of the target vehicle and the vehicle itself, respectively. The relative distance between the target vehicle and this vehicle. It is the braking reaction time. , These are the speeds of the target vehicle and the current vehicle, respectively. , It is the preset target vehicle and the maximum braking deceleration of this vehicle.

7. The AEB triggering method based on traffic conflict according to claim 1, characterized in that, The relative distance and the speed of the target vehicle are obtained using millimeter-wave radar.

8. The AEB triggering method based on traffic conflict according to claim 1, characterized in that, The predetermined conditions are as follows: The risk level is equal to the expected collision time.

9. An electronic device, characterized in that, include: One or more processors and a memory, wherein the memory stores one or more programs, the one or more programs including instructions for executing the traffic conflict-based AEB triggering method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, Includes one or more programs that are executed by one or more processors of an electronic device, said one or more programs including instructions for performing the traffic conflict-based AEB triggering method as described in any one of claims 1-8.

Images