Self-adaptive avoidance method for coping with vehicle rear-end collision and corresponding device

Abstract

The invention discloses a self-adaptive avoidance method for coping with vehicle rear-end collision and a corresponding device. The method comprises the following steps: monitoring a rear view range through a vehicle-mounted rearview sensor, identifying a rear vehicle, calculating relative parameters of a target self-vehicle and the rear vehicle, determining that the target self-vehicle has a potential rear-end collision risk by combining vehicle information of the target self-vehicle, and when the target self-vehicle is in a static state and a vehicle exists in front, starting the vehicle-mounted rearview sensor; calculating and executing a first deflection angle of the target self-vehicle, so that the target self-vehicle generates a preset lateral deflection trend, and generates a deflection displacement towards the lateral front side when the rear vehicle collides, thereby reducing the collision to the front vehicle; and when the target self-vehicle is in a low-speed driving state and the rear-end collision of the front vehicle and the rear vehicle is inevitable, planning and executing an avoidance track of the lateral target adjacent lane so as to avoid the rear-end collision of the rear vehicle and the collision of the target adjacent lane. According to the invention, timely avoidance control can be carried out on the rear vehicle, driving accidents are reduced or avoided, and the driving safety is improved.

Description

Technical Field

[0001] This application relates to the field of vehicle safety technology, specifically to the fields of vehicle avoidance and autonomous driving, and particularly to an adaptive avoidance method and corresponding device for dealing with rear-end collisions. Background Technology

[0002] Rear-end collisions are the most common type of accident in road traffic, occurring extremely frequently at congested urban intersections and highway exits. They not only cause significant economic losses but are also a major cause of neck injuries or other personal injuries to drivers and passengers. Existing active safety technologies for vehicles (such as AEB and FCWS) primarily focus on forward collision warning and emergency braking, leaving a significant technological gap in addressing the risk of rear-end collisions. Specific deficiencies are as follows: The perception layer is missing: rear risks rely entirely on the driver's subjective observation through the rearview mirror, which has blind spots and the risk of fatigue and distraction; existing rearward sensors are only suitable for low-speed parking scenarios, cannot accurately calculate the relative speed and distance of vehicles behind, and lack fusion analysis with the target vehicle's status and navigation data, so the risk cannot be quantified.

[0003] The decision-making and early warning systems are sluggish: the early warning is only directed at the driver of the target vehicle, lacking proactive warnings to vehicles behind (such as hazard lights and horns); there is no graded response strategy, making it impossible to distinguish different risk levels, and there is no effective decision-making logic in stationary scenarios where the vehicle is "surrounded" from both sides, leaving the driver in a dilemma.

[0004] The execution layer is lacking: existing technologies rely entirely on driver evasive maneuvers and do not utilize the precise control capabilities of actuators such as electric power steering; they lack strategies for actively adjusting the vehicle's attitude before a collision, and passive safety systems can only mitigate post-collision injuries, unable to avoid or reduce collision impact. Therefore, there is an urgent need to find an adaptive avoidance scheme to deal with rear-end collisions and solve the above-mentioned technical problems. Summary of the Invention

[0005] This application provides an adaptive avoidance method and corresponding device for dealing with rear-end collisions, in order to solve the problem that the lack of a timely avoidance control scheme for rear-end collisions in the prior art leads to driving accidents and fails to guarantee driving safety.

[0006] The technical solution is as follows: Firstly, an adaptive avoidance method for dealing with rear-end collisions is provided, including: Real-time acquisition of images within the field of view behind the target vehicle, and identification and tracking of vehicles behind based on the images, and calculation of the first relative distance and first relative speed between the vehicles behind and the target vehicle; If the first relative distance is less than the first safe distance threshold and the first relative speed is less than zero, then it is determined that there is a potential rear-end collision risk between the target vehicle and the vehicle behind it. When the target vehicle is stationary and there are other vehicles in front, the second relative distance and the second relative speed between the vehicle in front and the target vehicle are calculated; based on the first relative distance, the first relative speed, the second relative distance and the vehicle information of the target vehicle, the first deflection angle is calculated, and the steering wheel of the target vehicle is deflected by the first deflection angle, so that when the vehicle behind rear-ends the target vehicle, the target vehicle can be controlled to generate a side-forward offset under the rear-end thrust, thereby reducing the collision with the vehicle in front; When the target vehicle is traveling at a low speed and there are other vehicles in front, and a rear-end collision with the vehicle behind is unavoidable, the available target adjacent lane is determined based on the position and speed of the vehicles in front and behind in the left and right adjacent lanes. The avoidance trajectory of the target vehicle is planned and executed, and an external warning is issued in coordination to avoid a rear-end collision with the vehicle behind and a secondary accident in the target adjacent lane.

[0007] In one possible implementation, the first deflection angle is calculated based on the first relative distance, the first relative speed, the second relative distance, and the vehicle information of the target vehicle, specifically including: Based on the first relative distance, the first relative speed, the second relative distance, and relevant parameters in the vehicle information of the target vehicle, the target lateral offset of the target vehicle is determined; The target lateral offset of the target vehicle is converted into the first deflection angle of the steering wheel of the target vehicle.

[0008] In one possible implementation, the target lateral offset of the target vehicle is determined based on the first relative distance, the first relative speed, the second relative distance, and relevant parameters in the vehicle information of the target vehicle, specifically including: Based on the second relative distance and the first type of relevant parameters in the vehicle information of the target vehicle, the maximum offset of the target vehicle is calculated; wherein, the first type of relevant parameters includes at least: absolute minimum safety margin, lateral space constraint, and minimum lateral safety margin; Based on the first relative speed and the first relative distance, as well as the second type of relevant parameters in the vehicle information of the target vehicle, the expected minimum offset for the collision of the target vehicle is calculated; wherein, the second type of relevant parameters include at least: offset gain coefficient and collision relative time; By combining the set physical constraints with the maximum and minimum offsets of the target vehicle, the target lateral offset of the target vehicle is determined.

[0009] In one possible implementation, based on the positions and speeds of vehicles ahead and behind in the left and right adjacent lanes, the available target adjacent lanes are determined, the avoidance trajectory of the target vehicle is planned and executed, specifically including: The safe distances to the front and rear of each adjacent lane are calculated based on the positions of the vehicles in front and behind in the left and right adjacent lanes, and the available target adjacent lanes are determined by combining the speeds of the vehicles in front and behind in the left and right adjacent lanes. Based on the safe distances in front of and behind the target in adjacent lanes, and the speed of the target vehicle, a smooth and controllable avoidance trajectory is planned. The avoidance trajectory is automatically executed.

[0010] In one possible implementation, the method further includes: Based on the avoidance trajectory, determine the minimum longitudinal safe distance between the target vehicle and the vehicles in front and behind in the target adjacent lane, as well as the safe conditions for entering the target adjacent lane; When both the minimum longitudinal safety distance and the safety conditions are met, the vehicle cuts into the lane adjacent to the target and actively avoids the target vehicle based on the avoidance trajectory.

[0011] Secondly, an adaptive avoidance device for dealing with rear-end collisions is provided, including: The calculation module is used to acquire images within the field of view behind the target vehicle in real time, identify and track vehicles behind based on the images, and calculate the first relative distance and the first relative speed between the vehicles behind and the target vehicle. The determination module is used to determine that if the first relative distance is less than a first safe distance threshold and the first relative speed is less than zero, then the target vehicle and the vehicle behind it have a potential rear-end collision risk. The control module is used to calculate the second relative distance and the second relative speed between the target vehicle and other vehicles in front when the target vehicle is stationary and there are other vehicles in front; calculate the first deflection angle based on the first relative distance, the first relative speed, the second relative distance and the vehicle information of the target vehicle, and trigger the control of the steering wheel of the target vehicle to deflect the first deflection angle, so that when the target vehicle is rear-ended by a vehicle behind, the target vehicle can be controlled to generate a side-forward offset under the rear-end collision thrust, thereby reducing the collision with the vehicle in front; The control module is also used to determine the available target adjacent lane based on the position and speed of the vehicles in front and behind in the left and right adjacent lanes when the target vehicle is traveling at a low speed and there are other vehicles in front and rear, and a rear-end collision is unavoidable. It plans and executes the avoidance trajectory of the target vehicle and provides external early warnings to avoid rear-end collisions and secondary accidents in the target adjacent lane.

[0012] Thirdly, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods described above and any possible implementations.

[0013] Fourthly, a computer-readable storage medium is provided, wherein at least one instruction is stored therein, the at least one instruction being loaded and executed by a processor to implement the aspects described above and any possible implementation thereof.

[0014] Fifthly, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the aspects and any possible implementations described above.

[0015] In a sixth aspect, an autonomous vehicle is provided, including the electronic devices described above.

[0016] The beneficial effects of the technical solution provided in this application include at least the following: As can be seen from the above technical solution, the embodiments of this application monitor the rear field of view using an onboard rear-view sensor, identify vehicles behind, and calculate the relative parameters between the target vehicle and the vehicles behind. Combining the vehicle information of the target vehicle, it is determined that there is a potential rear-end collision risk between the target vehicle and the vehicles behind. When the target vehicle is stationary and there is a vehicle in front, a first deflection angle of the target vehicle is calculated and executed, causing the target vehicle to generate a preset lateral offset trend. In the event of a rear-end collision, the target vehicle will shift to the side and forward, reducing the impact on the vehicle in front. When the target vehicle is traveling at low speed and there is a vehicle in front, and a rear-end collision is unavoidable, an avoidance trajectory to the adjacent lane is planned and executed to avoid both a rear-end collision and a collision with the adjacent lane. This application can provide timely avoidance control for rear-end collisions, reducing or avoiding driving accidents and ensuring driving safety.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the steps of the adaptive avoidance method for dealing with rear-end collisions provided in the embodiments of this application.

[0020] Figure 2 This is a schematic diagram of a process for determining the first steering wheel deflection angle of a target vehicle in a stationary state, according to another embodiment of this application.

[0021] Figure 3 This is a schematic diagram illustrating the process of a target vehicle planning and executing an avoidance trajectory at low speed, according to one embodiment of this application.

[0022] Figure 4 This is a structural block diagram of an adaptive avoidance device for dealing with vehicle rear-end collisions provided in another embodiment of this application.

[0023] Figure 5 This is a block diagram of an electronic device used to implement the adaptive avoidance method for dealing with rear-end collisions according to the embodiments of this application. Detailed Implementation

[0024] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These embodiments should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0025] Obviously, the described embodiments are only a part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this application.

[0026] It should be noted that the terminal devices involved in the embodiments of this application may include, but are not limited to, smart devices such as mobile phones, personal digital assistants (PDAs), wireless handheld devices, and tablet computers; the display devices may include, but are not limited to, personal computers, televisions, and other devices with display functions.

[0027] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0028] Given the lack of timely avoidance control schemes for rear-end collisions in existing technologies, which leads to compromised driving safety in the event of an accident, this application proposes an adaptive avoidance scheme to address rear-end collisions. The main inventive concept involves: monitoring the rear field of view using an onboard rear-view sensor, identifying rear vehicles, calculating the relative parameters between the target vehicle and the rear vehicles, and combining this with the target vehicle's vehicle information to determine a potential rear-end collision risk. When the target vehicle is stationary and there is a vehicle in front, a first deflection angle is calculated and executed, causing the target vehicle to exhibit a preset lateral offset tendency. Upon a rear-end collision, this offset displacement to the side and forward reduces the impact on the vehicle in front. When the target vehicle is traveling at low speed and there is a vehicle in front, making a rear-end collision unavoidable, an avoidance trajectory to the adjacent lane is planned and executed to avoid both a rear-end collision and a collision with the adjacent lane. This application can provide timely avoidance control for rear-end collisions, reducing or preventing driving accidents and ensuring driving safety.

[0029] The present application will be described in detail below through specific embodiments.

[0030] Reference Figure 1 The diagram illustrates the steps of an adaptive avoidance method for handling rear-end collisions provided in this embodiment of the application. The method may include the following steps: Step 102: Acquire images within the field of view behind the target vehicle in real time, identify and track vehicles behind based on the images, and calculate the first relative distance and the first relative speed between the vehicles behind and the target vehicle.

[0031] In this application, an image sequence of the rear view of the vehicle can be continuously acquired by an in-vehicle rearview camera; an image processing algorithm is used to identify and track the vehicle behind, and to calculate the first relative distance D_r and the first relative speed V_r between the vehicle behind and the target vehicle.

[0032] Step 104: If the first relative distance is less than the first safe distance threshold and the first relative speed is less than zero, then it is determined that there is a potential rear-end collision risk between the target vehicle and the vehicle behind it.

[0033] In specific implementation, a first safe distance threshold D_safe1 can be set, the value of which is calculated by a preset algorithm based on the current speed of the target vehicle and the road surface adhesion coefficient. When the first relative distance D_r is less than D_safe1 and the first relative speed V_r (relative speed = target vehicle speed - rear speed) < 0, it indicates that the vehicle behind is rapidly approaching, and it is determined that there is a potential rear-end collision risk between the target vehicle and the vehicle behind.

[0034] Optionally, in this application, when a potential rear-end collision risk is determined, a primary warning can be issued, namely, displaying a visual prompt on the vehicle's display screen that reads "A vehicle is approaching from behind, please be careful"; at the same time, the vehicle's hazard warning lights (double flashers) are automatically activated and the horn is controlled to sound intermittently to warn drivers of vehicles behind.

[0035] Furthermore, in this application, navigation map data can be used to determine whether the target vehicle is stationary (e.g., queuing at a traffic light intersection) or moving at a low speed (e.g., speed below 5 km / h).

[0036] Step 106: When the target vehicle is stationary and there are other vehicles in front, calculate the second relative distance and the second relative speed between the vehicle in front and the target vehicle; calculate the first deflection angle based on the first relative distance, the first relative speed, the second relative distance and the vehicle information of the target vehicle, and trigger the steering wheel of the target vehicle to deflect the first deflection angle, so that when the vehicle behind rear-ends the target vehicle, the target vehicle can be controlled to generate a side-forward offset under the rear-end thrust, thereby reducing the collision with the vehicle in front.

[0037] Optionally, when calculating the first deflection angle based on the first relative distance, the first relative speed, the second relative distance, and the vehicle information of the target vehicle, the target lateral offset of the target vehicle can be determined based on relevant parameters in the first relative distance, the first relative speed, the second relative distance, and the vehicle information of the target vehicle; and the target lateral offset of the target vehicle can be converted into the first deflection angle corresponding to the steering wheel of the target vehicle.

[0038] Furthermore, when determining the target lateral offset of the target vehicle based on the first relative distance, the first relative speed, the second relative distance, and relevant parameters in the vehicle information of the target vehicle, specifically, the maximum offset of the target vehicle can be calculated based on the second relative distance and the first type of relevant parameters in the vehicle information of the target vehicle; wherein, the first type of relevant parameters includes at least: absolute minimum safety margin, lateral space constraint, and minimum lateral safety margin; the minimum offset expected by the target vehicle in a collision is calculated based on the first relative speed, the first relative distance, and the second type of relevant parameters in the vehicle information of the target vehicle; wherein, the second type of relevant parameters includes at least: offset gain coefficient and collision relative time; the target lateral offset of the target vehicle is determined by combining the set physical constraints and the maximum and minimum offsets of the target vehicle.

[0039] Specifically, step 106 can be achieved through the following steps: Step 1: When the target vehicle is stationary (e.g., waiting at a traffic light) and there is a vehicle in front (detected by a forward-facing camera or radar at a distance D_f from the vehicle in front), and Step 1 determines that there is a high-risk rear-end collision vehicle behind, the system enters advanced alert mode.

[0040] Step 2: Based on the real-time relative speed V_r and relative distance D_r of the vehicles behind, combined with the distance D_f between the target vehicle and the vehicle in front, as well as the target vehicle's width and lane width information, calculate an optimal steering wheel deflection angle θ.

[0041] It should be noted that the goal of calculating the steering wheel deflection angle θ is to cause the front of the target vehicle to deflect by an amount ΔS towards the side front, without colliding with the vehicle in front or crossing the lane line, and the steering wheel angle is calculated based on the amount of deflection.

[0042] Among them, reference Figure 2 As shown, step 2 can be achieved through the following sub-steps: Sub-step 21: Calculate the maximum offset of the target vehicle.

[0043] The theoretical maximum allowable deviation is the limit of lateral movement of the center point of the vehicle's front end, provided that no secondary collision occurs and the vehicle does not leave its lane. The formula is as follows: ΔS_max = min( (D_f - D_safe_min), ( (W_lane - W_veh) / 2 - M_clear) ) Wherein, D_f - D_safe_min is the longitudinal space constraint; D_safe_min is the absolute minimum safety margin (set to 0.3m) that the system sets to maintain with respect to the vehicle in front, ensuring that even after being rear-ended, the front of the target vehicle should not collide with the vehicle in front; ((W_lane - W_veh) / 2 - M_clear) is the lateral space constraint; M_clear is the minimum lateral safety margin (set to 0.2m) that the vehicle is required to maintain with respect to the lane lines.

[0044] Sub-step 22: Calculate the minimum expected offset for the target vehicle to collide with.

[0045] The minimum expected offset (ΔS_des) required to absorb a collision is the deviation of the vehicle's direction of motion from the direct collision path with the vehicle in front after being rear-ended. The calculation formula is as follows: ΔS_des = α * (|V_r| * T_collision) Where α is the offset gain coefficient, 0 < α < 1; the offset gain coefficient is a key empirical calibration parameter that balances the offset effect with stability; the larger α is, the greater the offset sought, but it may cause the vehicle attitude to tilt more; the initial value can be calibrated through simulation and real vehicle testing (set to 0.3-0.6). (|V_r| * T_collision) is the estimated collision push distance, where T_collision is the estimated relative time from the start of the collision to the complete stop of the vehicle (empirical value is 0.5-1.0 seconds). |V_r| is the approach speed of the following vehicle, and this product roughly estimates the distance the vehicle would be pushed straight forward without offset.

[0046] Sub-step 23: Determine the target lateral offset of the target vehicle.

[0047] The target lateral offset (ΔS_target) is determined by combining physical constraints and desired values ​​to establish an executable safety target, and the calculation formula is as follows: ΔS_target = min(ΔS_des, ΔS_max) To ensure absolute safety during the offset operation, the smaller value between the expected value and the maximum value is selected.

[0048] Sub-step 24: Convert the target offset to the steering wheel angle θ.

[0049] First, calculate the corresponding front wheel deflection angle δ.

[0050] Based on the geometry of circular arcs, for a small target offset, it can be approximated that after the front wheels deflect, the vehicle will move a short distance along an arc of radius R. A more practical simplification is to assume that the system causes the vehicle to have a lateral displacement tendency of ΔS_target with a fixed steering angle δ in a very short time. This can be approximated by the following formula: δ ≈ arctan((2 * L_wb * ΔS_target) / (K) ); where L_wb is the wheelbase, i.e., the horizontal distance between the center of the front axle and the center of the rear axle; K is a calibration factor related to the expected vehicle response. It can be associated with a hypothetical "equivalent forward distance". For example, it can be assumed that at the instant of the collision, the vehicle is equivalently "forward" by a distance of approximately (D_r / 2) due to the impact. Then the formula is: δ = arctan( (2 * L_wb * ΔS_target) / (D_r) ).

[0051] Next, calculate the steering wheel transmission ratio i_s.

[0052] θ = δ * i_s; where i_s is the steering system gear ratio of the vehicle (set to 15:1).

[0053] Then, apply system limiting and calculate the steering wheel angle θ.

[0054] The steering wheel angle is calculated using the following formula: θ = clamp(θ, -δ_max * i_s, δ_max * i_s); where clamp(x) is a constraint function used to force an input value to be limited to a specified upper and lower limit; the final output steering wheel angle value is limited to the maximum safe steering angle allowed by the system.

[0055] Step 3: Perform the steering wheel deflection angle θ through the electric power steering system.

[0056] Step 4: While performing the steering maneuver, illuminate the corresponding turn indicator light on the instrument panel and display the text "Steering has deviated, please be careful" to inform the driver that the system has intervened in steering control, so that the driver can straighten the steering wheel after the risk has been eliminated or when needed.

[0057] Step 108: When the target vehicle is traveling at a low speed and there are other vehicles in front, and a rear-end collision with the vehicle behind is unavoidable, the available target adjacent lane is determined based on the position and speed of the vehicles in front and behind in the left and right adjacent lanes. The avoidance trajectory of the target vehicle is planned and executed, and an external warning is issued in coordination to avoid a rear-end collision with the vehicle behind and a secondary accident in the target adjacent lane.

[0058] Optionally, based on the positions and speeds of the vehicles in front of and behind in the left and right adjacent lanes, determine the available target adjacent lanes, plan the avoidance trajectory of the target vehicle and execute it. Specifically, it can calculate the front and rear safety distances of each adjacent lane based on the positions of the vehicles in front of and behind in the left and right adjacent lanes, and combine the speeds of the vehicles in front of and behind in the left and right adjacent lanes to determine the available target adjacent lanes; plan a smooth and controllable avoidance trajectory based on the front and rear safety distances of the target adjacent lanes and the speed of the target vehicle; trigger the automatic execution of the avoidance trajectory.

[0059] Furthermore, it can also determine the minimum longitudinal safety distance between the target vehicle and the vehicles in front of and behind in the target adjacent lane based on the avoidance trajectory, as well as the safety conditions for entering the target adjacent lane; when both the minimum longitudinal safety distance and the safety conditions are met, cut into the target adjacent lane and control the target vehicle to perform active lateral avoidance based on the avoidance trajectory.

[0060] When specifically implemented, refer to Figure 3 As shown, step 108 may include the following processes: When it is determined that the target vehicle meets the following conditions 1-4, trigger the highest-priority emergency response.

[0061] Condition 1, the state of the target vehicle: the vehicle speed is in the low-speed range (e.g., 5 km / h < V_ego < 45 km / h), and it is in a straight-line / following driving state under autonomous driving or driver control. Condition 2, rear risk: the rear-end perception system determines that a rear-end collision is inevitable. The criteria are: the relative distance D_r is less than the emergency threshold D_emergency, and the relative speed V_r is extremely high (e.g., |V_r| > 50 km / h), and the predicted time to collision TTC < 1.0 second. Condition 3, front space: the distance D_f from the vehicle in front is greater than the minimum longitudinal safety distance D_f_min required for performing avoidance. Condition 4, system self-check: the steering, braking, and power systems of the vehicle are working properly, and the electronic stability program is in a ready state.

[0062] Avoidance direction decision logic, the system needs to decide the avoidance direction (left or right) within milliseconds, and the decision is based on the following rules sorted by priority: First, evaluate the availability of the adjacent lane space.

[0063] The system uses lateral radar / camera (lateral perception module) to acquire the real-time position and speed of vehicles (SV_front, SV_rear) in front and behind the target vehicle in adjacent lanes. The system employs a safe lane-changing spatial model to calculate a safe "spatiotemporal window" for the target vehicle to enter. Forward safe distance: The distance to the vehicle in front (SV_front) in the target lane must be greater than S_front_min. S_front_min is not a fixed value but is dynamically calculated based on the relative speed of SV_front, ensuring at least 2 seconds of distance after the vehicle enters. Rear safe distance: The distance to the vehicle behind (SV_rear) in the target lane must be greater than S_rear_min. Crucially, the system must calculate whether SV_rear has sufficient time / distance to avoid or follow the target vehicle without abrupt braking after it enters. This requires evaluating the relative speed V_sv_rear_rel of SV_rear.

[0064] If SV_rear is rapidly approaching (V_sv_rear_rel has a large negative value), the system will determine that side has a higher risk. Ideally, choose the side where vehicles behind are moving slower or are farther away. If there is sufficient space on both sides, the system will default to the left (usually the fast lane, where vehicles behind may be moving at a higher speed, but there are usually no direct obstacles ahead), or choose the side with fewer exits based on navigation information to avoid complex road conditions.

[0065] At the same time, road boundary constraints are adopted, combined with lane line recognition and high-precision maps, to exclude the side with no physical space such as road shoulders, guardrails, walls or non-motorized vehicle lanes.

[0066] Then, plan and execute the avoidance trajectory.

[0067] After deciding on the direction, the system immediately plans and executes a smooth, controlled avoidance trajectory. This trajectory is a sinusoidal curve that deviates towards the target lane, aiming to minimize lateral acceleration (typically limited to 0.3g - 0.4g) while avoiding a rear-end collision, ensuring vehicle stability. The longitudinal component of the trajectory includes a small amount of cooperative acceleration. The goal is not to speed, but to quickly establish a longitudinal distance difference with dangerous vehicles behind, allowing for a smoother merge with the vehicle in front (SV_front) in the target lane.

[0068] Among these, cutting into the adjacent lane at the right time is crucial. Therefore, it is necessary to determine the minimum longitudinal safety distance and the cut-in safety distance in order to determine the appropriate cut-in time.

[0069] Minimum longitudinal safety distance (D_f_min): D_f_min = V_ego * T_reaction + (V_ego^2 -(V_ego + ΔV)^2) / (2 * a_max_brake) + D_buffer; where, T_reaction: system execution delay (approximately 0.1s); ΔV: speed increase for coordinated acceleration; a_max_brake: maximum safe deceleration of the target vehicle; D_buffer: final buffer distance with the vehicle in front (e.g., 2 meters); this formula ensures that after avoidance, if the vehicle in front suddenly brakes, the target vehicle still has room to stop safely.

[0070] Lateral cut-in safety conditions: For the target lane following vehicle SV_rear, the following condition must be met: (S_rear / max(|V_sv_rear_rel|, 0.1))>T_cutin_safe; where S_rear is the current distance between the target vehicle and SV_rear; V_sv_rear_rel: SV_rear is the speed relative to the target vehicle (the target vehicle is the reference frame). T_cutin_safe is the minimum time interval required for a safe cut-in (usually ≥ 2.5 seconds), which ensures that vehicles to the side and rear have sufficient time to react.

[0071] Next, coordinated control is implemented.

[0072] Steering System: EPS applies precise steering torque according to the planned trajectory, controlling the vehicle to travel along the target path. Powertrain System: ECU controls the engine or electric motor to output a gentle but decisive acceleration request (e.g., generating 0.2g - 0.3g longitudinal acceleration). Electronic Stability System: ESP / ESC continuously monitors the vehicle's attitude, ready to intervene to prevent any signs of instability.

[0073] Simultaneously, it enables early warning for human-computer interaction and external collaboration.

[0074] To avoid confusion or secondary accidents caused by the target vehicle's emergency swerving maneuvers, the system implements enhanced internal and external communication. This includes proactive external prompts and internal driver notifications. Turn Signal: The system forcibly activates the turn signal in the target direction at the moment the turn signal begins (or even 100-200 milliseconds in advance). This is crucial, as it is the only standardized signal informing drivers in adjacent lanes of the target vehicle's intention. Hazard Warning Lights (Hazard Flashers): The hazard flashers remain active throughout the avoidance maneuver, emphasizing that the target vehicle is in an emergency. Horn Warning (Optional Strategy): At the moment the avoidance maneuver begins, the horn emits a short but loud blast. This is not mandatory, but can serve as an additional audible warning to vehicles on the side in certain regulatory circumstances and critical situations.

[0075] Display clear warning icons (such as a large red avoidance icon) and text (such as "Emergency avoidance in progress!") on the dashboard or HUD. At the same time, inform the driver that the system has taken over through steering wheel vibration or sound prompts. Prompt the driver to be ready to take over at any time, and after the avoidance is completed, prompt "Please take over the steering wheel" or automatically resume driver control.

[0076] Thus, through a highly integrated crisis response system, including a complex automation sequence of multi-source perception, real-time risk assessment, trajectory planning, vehicle dynamics control, and internal and external collaborative communication. In the milliseconds when the driver fails to respond in time, the system acts as an experienced "defensive driving expert", executes the precise operation that is the only possible way to avoid danger, and at the same time broadcasts its intentions to surrounding traffic participants as much as possible through lights and signals, so as to maintain the safety and order of the entire traffic flow while avoiding its own risks, and move from "passive warning" to "active defense" high-level driving.

[0077] Example 1 The driver is driving vehicle A queuing up to wait for a red light. There is vehicle B in front, and vehicle C behind fails to decelerate in time due to the driver's distraction. Vehicle A recognizes through the rear-view camera that vehicle C is approaching rapidly and the distance is less than the safety threshold D_safe1. The system immediately displays a warning on the in-vehicle computer of the driver's vehicle A and turns on the hazard lights and sounds the horn. At the same time, the system detects that the distance to the vehicle B in front is relatively close and is at risk of "being sandwiched front and back". The system quickly calculates a steering wheel deflection angle θ to the right (assuming more space on the right lane) and executes it through the EPS system. The front of vehicle A then slightly deviates to the right by about 15 - 30 cm. At this time, the right turn signal on the dashboard flashes and displays "The steering has deviated, please pay attention". Moments later, vehicle C rear-ends the rear of vehicle A. Since the front of vehicle A has deviated to the right, the collision causes vehicle A to slide forward and to the right, avoiding its front from completely hitting the rear of the vehicle B in front, effectively reducing the damage and the risk of personnel injury. After the accident, the driver easily returns the steering wheel to the correct position according to the prompt.

[0078] Example 2 The driver is driving vehicle D at a speed of 15 km / h following a vehicle on an urban road. A vehicle E behind is approaching at high speed due to a brake failure. Vehicle D detects a very high-risk rear-end collision signal (D_r < D_safe2). The system determines that the following distance to the vehicle in front is sufficient and there is no vehicle in the left lane. So the system intervenes instantly, turns slightly to the left and accelerates slightly, causing vehicle D to move about half a vehicle body position to the left front. The vehicle E behind finally passes by the right rear side of vehicle D from the original lane, avoiding a serious front-end collision. After feeling the vehicle's dynamics and seeing the prompt, the driver stabilizes the vehicle and resumes normal driving.

[0079] Through the above technical solutions, a complete rear-end risk protection scheme is constructed, filling the technological gap in the entire process from rear-end risk perception, quantitative assessment, graded early warning to active physical intervention, and achieving closed-loop protection. For high-risk "front-and-rear sandwich" scenarios, a pioneering method for pre-adjusting vehicle orientation while stationary is proposed. This method can convert some of the forward impact energy into lateral motion when a collision is unavoidable, effectively reducing the risk of "whiplash" injuries to occupants' necks and minimizing or avoiding secondary collisions. Based on the target vehicle's status (stationary / low speed), environmental constraints (distance to the vehicle in front, lane space), and risk level, different response strategies, from warnings to active avoidance, are automatically selected, demonstrating a high degree of intelligence. During automatic control, clear prompts inform the driver, ensuring their right to know; simultaneously, active external warnings via lights and sounds enhance the safety awareness of all road users, reflecting a collaborative safety concept. Functional upgrades can be made based on existing rearview cameras, EPS, ESP, and other hardware, resulting in relatively low implementation costs and ease of promotion.

[0080] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0081] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0082] Figure 4 This invention provides a structural block diagram of an adaptive avoidance device for rear-end collisions according to an embodiment of the present application. Figure 4As shown. The adaptive collision avoidance device 400 for responding to vehicle rear-end collisions in this embodiment may include a calculation module 401, a determination module 402, and a control module 403. The calculation module 401 is used to acquire images within the rear field of view of the target vehicle in real time, identify and track vehicles behind based on the images, and calculate a first relative distance and a first relative speed between the rear vehicle and the target vehicle. The determination module 402 is used to determine that there is a potential rear-end collision risk between the target vehicle and the rear vehicle if the first relative distance is less than a first safe distance threshold and the first relative speed is less than zero. The control module 403 is used to calculate the second relative distance and the second relative speed between the target vehicle and other vehicles when the target vehicle is stationary and there are other vehicles in front; calculate the first deflection angle based on the first relative distance, the first relative speed, the second relative distance, and the vehicle information of the target vehicle, and trigger the steering wheel of the target vehicle to deflect the first deflection angle, so that when a vehicle rear-ends the target vehicle, the target vehicle can be controlled to generate a side-forward offset under the rear-end collision thrust, reducing the collision with the vehicle in front. The control module 403 is also used to determine the available target adjacent lane based on the position and speed of the vehicles in front and behind in the left and right adjacent lanes when the target vehicle is traveling at a low speed and there are other vehicles in front, and a rear-end collision is unavoidable, plan and execute the avoidance trajectory of the target vehicle, and provide external warnings to avoid rear-end collisions and secondary accidents in the target adjacent lane.

[0083] It should be noted that some or all of the adaptive avoidance device for dealing with vehicle rear-end collisions in this embodiment may be an application located on a local terminal, or it may be a plugin or software development kit (SDK) or other functional unit set in an application located on a local terminal, or it may be a processing engine located on a network-side server, or it may be a distributed system located on the network side, such as a processing engine or distributed system in a network-side autonomous driving platform, etc. This embodiment does not impose any particular limitations on this.

[0084] It is understood that the application can be a native program installed on the local terminal, or it can be a web application of a browser on the local terminal. This embodiment does not limit this.

[0085] Optionally, in one possible implementation of this embodiment, when the control module 403 calculates the first deflection angle based on the first relative distance, the first relative speed, the second relative distance, and the vehicle information of the target vehicle, it specifically determines the target lateral offset of the target vehicle based on relevant parameters in the first relative distance, the first relative speed, the second relative distance, and the vehicle information of the target vehicle; and converts the target lateral offset of the target vehicle into a first deflection angle corresponding to the steering wheel of the target vehicle.

[0086] Optionally, in one possible implementation of this embodiment, when the control module 403 determines the target lateral offset of the target vehicle based on the first relative distance, the first relative speed, the second relative distance, and relevant parameters in the vehicle information of the target vehicle, it is specifically used to calculate the maximum offset of the target vehicle based on the second relative distance and the first type of relevant parameters in the vehicle information of the target vehicle; wherein, the first type of relevant parameters includes at least: absolute minimum safety margin, lateral space constraint, and minimum lateral safety margin; calculate the minimum offset expected by the target vehicle in the collision based on the first relative speed, the first relative distance, and the second type of relevant parameters in the vehicle information of the target vehicle; wherein, the second type of relevant parameters includes at least: offset gain coefficient and collision relative time; and determine the target lateral offset of the target vehicle by combining the set physical constraints and the maximum and minimum offsets of the target vehicle.

[0087] Optionally, in one possible implementation of this embodiment, when the control module 403 determines the available target adjacent lanes based on the positions and speeds of vehicles in front and behind in the left and right adjacent lanes, plans and executes the avoidance trajectory of the target vehicle, it specifically calculates the front and rear safety distances of each adjacent lane based on the positions of vehicles in front and behind in the left and right adjacent lanes, and determines the available target adjacent lanes in combination with the speeds of vehicles in front and behind in the left and right adjacent lanes; plans a smooth and controllable avoidance trajectory based on the front and rear safety distances of the target adjacent lanes and the speed of the target vehicle; and triggers the automatic execution of the avoidance trajectory.

[0088] Optionally, in one possible implementation of this embodiment, the control module 403 is further configured to determine, based on the avoidance trajectory, the minimum longitudinal safe distance between the target vehicle and the vehicles in front and behind in the target adjacent lane, as well as the safety conditions for entering the target adjacent lane; when both the minimum longitudinal safe distance and the safety conditions are met, the target vehicle enters the target adjacent lane and controls the target vehicle to perform active lateral avoidance based on the avoidance trajectory.

[0089] In this embodiment, the rear field of view can be monitored using an onboard rear-view sensor to identify vehicles behind and calculate the relative parameters between the target vehicle and the vehicles behind. Combining this with the target vehicle's information, a potential rear-end collision risk is determined. When the target vehicle is stationary and there is a vehicle in front, a first deflection angle is calculated and executed, causing the target vehicle to exhibit a preset lateral offset tendency. Upon collision with a rear-end vehicle, this results in a shift displacement to the side and forward, reducing the impact on the vehicle in front. When the target vehicle is traveling at low speed and there is a vehicle in front, making a rear-end collision unavoidable, an avoidance trajectory to the adjacent lane is planned and executed to avoid both a rear-end collision and a collision with the adjacent lane. This application can provide timely avoidance control for rear-end collisions, reducing or preventing driving accidents and ensuring driving safety.

[0090] One embodiment of this application provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the adaptive avoidance method for responding to vehicle rear-end collisions as described above.

[0091] One embodiment of this application provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the adaptive avoidance method for responding to vehicle rear-end collisions as described above.

[0092] One embodiment of this application provides an autonomous driving vehicle, including the electronic devices described above. Specifically, the autonomous driving vehicle can be a Level 2 or higher vehicle.

[0093] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0094] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of this application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the application described and / or claimed herein.

[0095] like Figure 5As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. The RAM 503 may also store various programs and data required for the operation of the electronic device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0096] Multiple components in electronic device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows electronic device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0097] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as an adaptive avoidance method for dealing with vehicle rear-end collisions. For example, in some embodiments, the adaptive avoidance method for dealing with vehicle rear-end collisions may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the adaptive avoidance method for dealing with vehicle rear-end collisions described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured by any other suitable means (e.g., by means of firmware) to perform an adaptive avoidance method for responding to vehicle rear-end collisions.

[0098] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, at least one input device, and at least one output device.

[0099] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0100] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0101] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0102] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0103] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0104] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this application can be achieved, and this is not limited herein.

[0105] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An adaptive avoidance method for coping with rear-end collision of a vehicle, characterized by, The method comprises the following steps: real-time image acquisition of the target vehicle rear view range, and according to the image recognition tracking rear vehicle, the first relative distance and the first relative speed between the rear vehicle and the target vehicle are calculated; if the first relative distance is less than the first safety distance threshold, and the first relative speed is less than zero, it is determined that the target vehicle and the rear vehicle have potential rear-end risk; when the target vehicle is in a static state and there are other vehicles in front, the second relative distance and the second relative speed between the front vehicle and the target vehicle are calculated; the first deflection angle is calculated according to the first relative distance, the first relative speed, the second relative distance and the vehicle information of the target vehicle, and the steering wheel of the target vehicle is deflected by the first deflection angle, so that when the rear vehicle rear-ends the target vehicle, the target vehicle can produce a deflection displacement to the side front under the rear-end thrust, reducing the collision with the front vehicle; when the target vehicle is in a low-speed driving state and there are other vehicles in front, and the rear-end collision of the rear vehicle is inevitable, the available target adjacent lane is determined based on the position and speed of the front and rear vehicles in the left and right adjacent lanes, the avoidance trajectory of the target vehicle is planned and executed, and external collaborative warning is performed, so as to avoid the rear-end collision of the rear vehicle and the secondary accident of the target adjacent lane.

2. The method of claim 1, wherein, According to the first relative distance, the first relative speed, the second relative distance and the vehicle information of the target vehicle, the first deflection angle is calculated, which specifically comprises: determining the target lateral offset of the target vehicle according to the relevant parameters in the first relative distance, the first relative speed, the second relative distance and the vehicle information of the target vehicle; the target lateral offset of the target vehicle is converted into the first deflection angle corresponding to the steering wheel of the target vehicle.

3. The method of claim 2, wherein, According to the first relative distance, the first relative speed, the second relative distance and the vehicle information of the target vehicle, the target lateral offset of the target vehicle is determined, which specifically comprises: calculating the maximum offset of the target vehicle according to the second relative distance and the first type of relevant parameters in the vehicle information of the target vehicle; wherein the first type of relevant parameters at least includes: absolute minimum safety margin, lateral space constraint and minimum lateral safety margin; calculating the minimum offset expected by the target vehicle collision according to the first relative speed, the first relative distance and the second type of relevant parameters in the vehicle information of the target vehicle; wherein the second type of relevant parameters at least includes: offset gain coefficient, collision relative time; determining the target lateral offset of the target vehicle by combining the physical constraints, the maximum offset and the minimum offset of the target vehicle.

4. The method of claim 1, wherein, Based on the position and speed of the front and rear vehicles in the left and right adjacent lanes, the available target adjacent lane is determined, the avoidance trajectory of the target vehicle is planned and executed, which specifically comprises: The front and rear safety distances of each adjacent lane are calculated based on the positions of the front and rear vehicles in the left and right adjacent lanes, and the speeds of the front and rear vehicles in the left and right adjacent lanes are combined to determine a target adjacent lane that is available; A smooth and controllable avoidance trajectory is planned based on the front and rear safety distances of the target adjacent lane and the speed of the target vehicle; The avoidance trajectory is triggered to be automatically executed.

5. The method of claim 4, wherein, The method further comprises: The minimum longitudinal safety distance of the target vehicle from the front and rear vehicles in the target adjacent lane and the safety condition for the target vehicle to enter the target adjacent lane are determined based on the avoidance trajectory; When both the minimum longitudinal safety distance and the safety condition are met, the target vehicle is cut into the target adjacent lane, and the target vehicle is controlled to actively avoid based on the avoidance trajectory.

6. An adaptive avoidance device for responding to a rear-end collision of a vehicle, characterized by, The method further comprises: The first relative distance and the first relative speed between the rear vehicle and the target vehicle are calculated based on images collected in real time in the rear field of view of the target vehicle and the rear vehicle is tracked and identified based on the images; If the first relative distance is less than a first safety distance threshold and the first relative speed is less than zero, it is determined that there is a potential rear-end risk between the target vehicle and the rear vehicle; When the target vehicle is in a stationary state and there is another vehicle in front of the target vehicle, the second relative distance and the second relative speed between the front vehicle and the target vehicle are calculated, and a first deflection angle is calculated based on the first relative distance, the first relative speed, the second relative distance, and vehicle information of the target vehicle, and the steering wheel of the target vehicle is deflected by the first deflection angle, so that when the rear vehicle rear-ends the target vehicle, the target vehicle can be controlled to produce a displacement to the side and front under the rear-end thrust, reducing the collision with the front vehicle; When the target vehicle is in a low-speed driving state and there is another vehicle in front of the target vehicle, and the rear-end collision with the rear vehicle is unavoidable, the available target adjacent lane is determined based on the positions and speeds of the front and rear vehicles in the left and right adjacent lanes, the avoidance trajectory of the target vehicle is planned and executed, and external collaborative warning is performed, so as to avoid the rear-end collision with the rear vehicle and secondary accidents in the target adjacent lane.

7. An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-5.

8. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method according to any one of claims 1-5.

9. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-5.

10. An autonomous vehicle comprising the electronic device according to claim 7.

Images