Vehicle obstacle avoidance control method and device and vehicle

Abstract

The invention discloses a vehicle obstacle avoidance control method and device, and the method comprises the steps: predicting a vehicle driving track according to the environment sensing data of a vehicle and the vehicle driving state parameters under the condition that the vehicle driving state parameters meet a low-speed driving condition; respectively constructing vehicle contour envelopes for a plurality of vehicle track points in the vehicle driving track so as to generate corresponding vehicle contour envelope sequences; detecting a target vehicle contour envelope which is spatially overlapped with the obstacle for the first time from the vehicle contour envelope sequence, and determining obstacle collision time based on a target trajectory prediction point moment corresponding to the target polygon; and according to the obstacle collision time and the accelerator pedal state information of the vehicle, vehicle obstacle avoidance cooperative control operation is executed. Therefore, false alarm and false braking in the low-speed working condition are remarkably reduced, and the recognition sensitivity of the active safety system to the real collision risk is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of assisted driving systems, and in particular to a vehicle obstacle avoidance control method and device and a vehicle. BACKGROUND

[0002] With the growth of the number of cars, traffic accidents such as collisions and scratches in urban low-speed driving scenarios have become increasingly frequent. Although these accidents are usually not fatal, they have a significant impact on driving safety and user experience due to their high probability of occurrence, high cumulative repair costs, and the potential to cause congestion.

[0003] Currently, active safety technologies such as Autonomous Emergency Braking (AEB) are commonly used to monitor the surrounding environment through sensors and provide warnings or automatic braking in potential danger. However, these technologies and their core decision-making models are largely optimized for scenarios such as highways, with relatively direct risk assessment logic based on pre-set and simplified dynamic relationship determination models.

[0004] However, when this logic, which is primarily designed for high-speed scenarios, is directly applied to low-speed environments with complex road conditions and varying driving intentions (such as following a car, starting, or parking), its inherent limitations are exposed and amplified. Due to the highly complex interaction between vehicles and the surrounding environment in low-speed conditions, the simplified determination model described above cannot accurately distinguish between real danger and normal driving operations, leading to a disconnect between the system's judgment and the driver's actual intentions and real risks.

[0005] On the one hand, unnecessary interventions occur when the driver is accelerating normally, following a car, or passing through a narrow area, and frequent false alarms and false brakes seriously interfere with driving and reduce user trust. On the other hand, when faced with some real collision risks, the decision-making model may not be able to comprehensively consider key risk factors such as driver misoperation, resulting in insufficient response or late braking. Ultimately, this not only affects user experience and driving safety, but also limits the further development and application of low-speed active safety technology. SUMMARY

[0006] Embodiments of the present application provide a vehicle obstacle avoidance control method, system, device, storage medium, and program product to at least solve one of the above technical problems.

[0007] In a first aspect, embodiments of the present application provide a vehicle obstacle avoidance control method, comprising: in a case where a vehicle driving state parameter is detected to satisfy a low-speed driving condition, predicting a vehicle driving trajectory according to environmental perception data of the vehicle and the vehicle driving state parameter; constructing a vehicle contour envelope for each of a plurality of vehicle trajectory points in the vehicle driving trajectory to generate a corresponding vehicle contour envelope sequence; the vehicle contour envelope sequence is combined in order of trajectory point prediction time; detecting a target vehicle contour envelope that first spatially overlaps with an obstacle from the vehicle contour envelope sequence, and determining an obstacle collision time based on a target trajectory prediction point time corresponding to the target polygon; and performing a vehicle obstacle avoidance collaborative control operation according to the obstacle collision time and accelerator pedal state information of the vehicle.

[0008] In a second aspect, embodiments of the present application provide a vehicle, comprising: an environmental perception sensor configured to collect environmental perception data around the vehicle; and a vehicle controller configured to perform any of the vehicle obstacle avoidance control methods described above.

[0009] In a third aspect, embodiments of the present application provide a storage medium having one or more programs including execution instructions stored therein, the execution instructions being readable and executable by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to perform any of the vehicle obstacle avoidance control methods described above.

[0010] In a fourth aspect, a computer device is provided, 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 any of the vehicle obstacle avoidance control methods described above.

[0011] In a fifth aspect, embodiments of the present application further provide a computer program product, comprising a computer program stored on a storage medium, the computer program comprising program instructions, which when executed by a computer, cause the computer to perform any of the vehicle obstacle avoidance control methods described above.

[0012] The beneficial effects of embodiments of the present application are as follows: By introducing trajectory prediction based on environment perception and driving state when the vehicle meets low-speed driving conditions, and constructing a time-ordered envelope sequence for vehicle contour envelope at multiple trajectory points, the continuity and geometric modeling of vehicle future space occupation are realized. Thus, the moment when the vehicle contour first overlaps with the obstacle in space can be accurately identified and the collision time can be determined, so that the risk assessment in low-speed scenarios is improved from rough judgment based on distance or speed to physical collision prediction based on real contour evolution. On this basis, the system further combines the accelerator pedal state to judge the actual intention of the driver, so as to intervene in time when there is an imminent collision risk and the driver's operation is inconsistent with the safety demand, and to suppress unnecessary braking triggering under normal low-speed operation. Thus, not only the false alarm and false braking in low-speed working conditions are significantly reduced, the identification sensitivity of the active safety system to the real collision risk is improved, but also the collaborative control more in line with the driver's intention is realized, taking into account safety, comfort and system reliability. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0014] Figure 1 A flow chart of an example of a vehicle obstacle avoidance control method according to an embodiment of the present application is shown; Figure 2 An operation flow chart of an example of performing vehicle obstacle avoidance collaborative control operation according to obstacle collision time and vehicle accelerator pedal state information according to an embodiment of the present application is shown; Figure 3 A speed-time variation relationship diagram of a vehicle during driver braking operation is shown; Figure 4 An operation flow chart of another example of performing vehicle obstacle avoidance collaborative control operation according to obstacle collision time and vehicle accelerator pedal state information according to an embodiment of the present application is shown; Figure 5 An operation flow chart of an example of determining obstacle collision time by contour envelope according to an embodiment of the present application is shown; Figure 6 A flow chart of an example of a vehicle obstacle avoidance control method according to an embodiment of the present application is shown; Figure 7 An effect diagram of an example of collision field points when a typical vehicle is driving at low speed is shown; Figure 8 A structural block diagram of an example of a vehicle according to an embodiment of the present application is shown; Figure 9 Structure schematic diagram of an embodiment of an electronic device of the present application. DETAILED DESCRIPTION

[0015] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0016] It should also be noted that, in this document, the terms “comprising” and “including” not only include those elements, but also include other elements not explicitly listed, or further include elements inherent in the process, method, article or device. Without more limitations, the elements defined by the statement “comprising” do not exclude the presence of other identical elements in the process, method, article or device comprising the elements.

[0017] It should be noted that, as the number of vehicles continues to rise, the number of minor traffic accidents such as collisions and scratches in urban low-speed driving scenarios also shows a significant increasing trend. Statistics show that accidents related to low-speed (below 20 km / h) scenarios account for more than 30% of the total traffic accidents, and in urban driving situations, they account for the majority. Although such accidents usually do not cause serious personal injury, they have a high frequency of occurrence, a large cumulative repair cost, and can easily cause road congestion. In the case of mispressing the accelerator pedal (e.g., the throttle or the accelerator), it may cause serious consequences (such as the risk of rushing into a crowd scenario), so low-speed anti-collision, accelerator pedal mispress protection and other active safety capabilities are of great significance to improve driving safety.

[0018] In related related technologies, some manufacturers implement low-speed AEB and accelerator pedal mispress protection functions based on single or multiple sensing devices, and generally use collision time (TTC, Time-To-Collision) and collision reaction time (TTR, Time-To-React) as the triggering basis. For example, TTC is usually calculated based on the distance and relative speed of the obstacle, and TTR is a time evaluation index that can be used by the driver to take evasive action.

[0019] However, some technical approaches that directly calculate TTC or TTR based on vehicle longitudinal distance and relative speed are primarily designed for high-speed straight-line scenarios. In urban conditions such as low speeds, high-curvature steering, and lateral approach, the spatial relationships and motion patterns of vehicles are more complex. The calculated TTC / TTR results often deviate significantly from the actual collision time, leading to numerous false triggers or missed triggers in low-speed conditions. Furthermore, obstacle recognition based on a single sensing source (such as vision or ultrasound only) is susceptible to factors such as occlusion, blind spots, and material reflections, further amplifying the risk of misjudgment.

[0020] It should be understood that the above description of the relevant technologies is intended only to help the public better understand the inventive spirit and motivation of this application, and is not intended to limit this application. Furthermore, the technical solutions described in the above-mentioned relevant technologies are not prior art, and may also be undisclosed technical solutions, such as those under research or in the laboratory stage.

[0021] The technical solutions in this application, including the collection, storage, use, processing, transmission, provision, and disclosure of users' personal information, comply with relevant laws and regulations and do not violate public order and good morals.

[0022] Figure 1 A flowchart illustrating an example of a vehicle obstacle avoidance control method according to an embodiment of this application is shown.

[0023] Regarding the execution subject of the method in the embodiments of this application, it can be any controller or processor with computing or processing capabilities. In some examples, the method in the embodiments of this application can be integrated and configured in an electronic device or terminal through software, hardware or a combination of software and hardware, and the type of terminal or electronic device can be diverse, such as mobile phone, tablet computer, desktop computer or vehicle terminal, etc.

[0024] For example, the execution subject of the method in this application embodiment can be integrated into the vehicle obstacle avoidance control controller. Based on the characteristics of low-speed scenarios, the trajectory prediction, contour envelope construction and collision time calculation process are reorganized. In low-speed complex road conditions (such as congested following, queuing start, parking, narrow road meeting, etc.), a more granular evaluation method that is more in line with the actual vehicle motion characteristics can be adopted, which significantly reduces the frequency of false alarms and false braking, and improves the applicability and effectiveness of low-speed active safety control.

[0025] like Figure 1 As shown, in step S110, when the vehicle driving state parameters are detected to meet the low-speed driving conditions, the vehicle driving trajectory is predicted based on the vehicle's environmental perception data and the vehicle driving state parameters.

[0026] In some embodiments, real-time driving state parameters such as current vehicle speed, longitudinal acceleration, steering angle, steering wheel angular velocity, gear state, throttle opening rate, etc. are obtained from the vehicle CAN network, power system controller or chassis controller. Then, based on a preset low-speed threshold (e.g. 0-20 km / h, which can be calibrated according to the vehicle model), it can be determined whether the vehicle is in a low-speed working condition. If the conditions are met, the trajectory prediction model can be enabled.

[0027] Here, the type of trajectory prediction model can be diverse, such as based on single-track or double-track vehicle kinematic model, short-time dynamic model or path deduction model combining inertial navigation and vision / radar, etc. Using the current vehicle speed, acceleration, steering angle and prediction time domain length, the trajectory points at multiple discrete time points in the future are generated. In the prediction process, the vehicle's environmental perception data (from vision, millimeter wave radar, ultrasonic, laser radar, etc.) can also be fused to confirm the road boundary, obstacle position and vehicle passable area, so as to ensure the rationality of the trajectory prediction and not to generate trajectory points inconsistent with the physical environment. In addition, the prediction time domain window can be self-defined or adjustable, for example, it can cover 1-3 seconds, and the prediction points can also be generated at fixed time intervals (e.g. 50ms-100ms) to ensure the time continuity of the trajectory points and achieve accurate description of the vehicle's future path.

[0028] Regarding the details of data collection, in some examples of the embodiments of the present application, corresponding raw environmental perception data is collected based on each environmental perception sensor. Each collected raw environmental perception data is fused to generate an obstacle point cloud, which at least represents the spatial position information of the obstacle. The environmental perception sensors include one or more of the following: ultrasonic radar distributed in the front, rear and side of the vehicle, millimeter wave radar arranged in the front and / or rear of the vehicle, body surround camera and laser radar.

[0029] In some embodiments, to improve the accuracy of the surrounding environment description in the low-speed trajectory prediction process, after obtaining the vehicle driving state parameters and determining that the vehicle is in a low-speed working condition, raw environmental perception data can be further collected based on multiple source environmental perception sensors, including ultrasonic radar distributed in the front, rear and side of the vehicle, millimeter wave radar arranged in the front and / or rear of the vehicle, body surround camera and laser radar, etc. Since different sensors have complementary characteristics in terms of detection distance, angular resolution, texture perception and speed measurement, first, the raw data collected by each sensor is time-synchronized and converted to the same coordinate system, so that it can describe the spatial environment information at the same time in the vehicle coordinate system. Then, using feature association, point cloud fusion and target matching, etc., the detection results from different data sources are spatially fused to form an obstacle point cloud representing the real spatial position and shape of the obstacle.

[0030] The obstacle point cloud generated by the above multi-source fusion not only contains the three-dimensional spatial position information of the obstacle, but also further carries the size, shape and category characteristics of the obstacle, thereby providing reliable environmental boundary constraints. With the help of the obstacle point cloud, the trajectory prediction model can more accurately identify the passable area around the vehicle, avoid generating a predicted path that crosses the obstacle or does not conform to the actual road structure, thereby significantly improving the rationality and safety of trajectory prediction. Especially in low-speed following, parking, narrow channel meeting and other environments, the distance between the obstacles is close and the types are various. Through the fusion processing of multi-source sensor data, the fusion point cloud can effectively reduce the missed detection or false detection problems that may occur in a single sensor, realize robust detection of obstacles in complex environments, and improve the actual perception ability in complex near-field environments.

[0031] In step S120, a vehicle contour envelope is constructed for each of the plurality of vehicle trajectory points in the vehicle driving trajectory to generate a corresponding vehicle contour envelope sequence, which is combined in order of the trajectory point prediction time.

[0032] It should be noted that the trajectory prediction obtains the vehicle centroid trajectory, but the vehicle collision risk is related to the actual contour of the vehicle body, not the centroid point itself, so the physical shape of the vehicle at each prediction time is accurately modeled, and a contour envelope sequence evolving over time is formed.

[0033] Specifically, for each trajectory point obtained by prediction, a vehicle contour envelope at the corresponding time is constructed for the vehicle according to the contour parameters of the vehicle (such as vehicle length, vehicle width, front and rear suspension length, wheelbase, etc.), combined with the heading angle of the vehicle at that time (calculated from the steering wheel angle). The envelope can use a rectangular polygon model (adapted to most passenger cars), or in an advanced version, an approximate convex polygon model can be used to make the vehicle body pose more accurate, for example, taking the trajectory point as the coordinate reference, rotating the coordinates according to the vehicle heading angle, generating the contour vertex coordinates according to the vehicle size, and forming a polygon representing the vehicle boundary. Subsequently, the system arranges all the envelopes in order of the trajectory time to form a vehicle contour envelope sequence, which completely describes the real space occupied by the vehicle in the future hundreds of milliseconds to several seconds.

[0034] In step S130, a target vehicle contour envelope that first spatially overlaps with the obstacle is detected from the vehicle contour envelope sequence, and the obstacle collision time is determined based on the target trajectory prediction point time corresponding to the target polygon.

[0035] It should be noted that the essence of the collision between the vehicle and the obstacle is the spatial overlap of the geometric boundaries of the two, so only when the vehicle contour envelope first enters the obstacle occupied space, can this time be confirmed as the earliest collision point, and thus the first overlap is judged in the envelope sequence traversal manner to accurately locate the collision time.

[0036] More specifically, a geometric collision detection algorithm (such as convex polygon intersection detection, etc.) can be employed to detect each envelope in the vehicle envelope sequence with the known obstacle profile one by one, to determine whether there is an intersection between the vehicle envelope polygon and the obstacle envelope. If there is an overlap, the envelope corresponding to the trajectory prediction time is recorded; if it is the first overlap in the sequence, the time is confirmed as the obstacle collision time. In addition, the obstacle can be a stationary or low-speed moving target, whose position and shape are provided in real time by the vehicle environment perception system, and if there is no overlap in the envelope sequence, the system determines that there is no collision risk for the vehicle within the prediction time domain. Through the first overlap detection based on the multi-time envelope, the collision time with actual physical meaning can be obtained.

[0037] In step S140, according to the obstacle collision time and the accelerator pedal state information of the vehicle, a vehicle obstacle avoidance collaborative control operation is performed.

[0038] It should be noted that the driver's operation intention in the low-speed scenario is complex, and mispressing the accelerator, abnormally accelerating to approach the obstacle, etc. are common, so relying solely on the collision time to trigger braking can cause false alarms or interfere with driving. By combining the accelerator pedal state, the system can introduce driver intention judgment in risk assessment, so that the control strategy can not only accurately intervene in dangerous situations, but also suppress unnecessary intervention in normal operation. It should be understood that the accelerator pedal can be a throttle pedal or an electric pedal to support the implementation of different types of vehicle acceleration control. In the description of some examples herein, a simplified description will be expressed in combination with the throttle, but it should be understood that it can also refer to the electric pedal.

[0039] In some embodiments, various factors can be considered comprehensively, such as the length of the obstacle collision time (e.g., less than 3 seconds is determined as high risk), the current throttle opening and opening rate, whether the driver is in a continuous acceleration, light throttle, or releases the throttle, etc. Thus, the control system can perform a multi-level obstacle avoidance collaborative control strategy. For example, for imminent collision risk and obvious acceleration behavior, fast braking or traction force limitation can be used; for low-risk normal fine-tuning behavior, no active intervention or only prompting can be performed; in the case of no collision risk, the current vehicle dynamics state is maintained. In addition, the braking intensity can be nonlinearly enhanced with the real-time shortening of the collision time, so as to balance safety and comfort.

[0040] By the embodiments of the present application, the collision time and the accelerator pedal state are fused, which can effectively distinguish different situations such as normal driving, intentional approach, misoperation, and real danger, so that the low-speed obstacle avoidance control is no longer single, but a collaborative control mode with scene understanding ability. Thus, the false braking events are significantly reduced, and the timely response ability of the system to emergency risks is also improved, thereby improving driving comfort, enhancing driving safety, and improving user trust.

[0041] Figure 2 A flowchart illustrating an example of a vehicle obstacle avoidance cooperative control operation performed according to an embodiment of this application, based on obstacle collision time and vehicle accelerator pedal state information.

[0042] like Figure 2 As shown, in step S210, it is monitored whether the obstacle collision time exceeds a first collision time threshold. Here, the urgency of the current collision risk is assessed using the first collision time threshold to distinguish between low-risk and high-risk situations and determine whether emergency obstacle avoidance control is necessary.

[0043] Here, a reasonable first collision time threshold (e.g., 3 seconds) can be set based on different vehicles, driving environments, and safety standards. If the collision time is greater than this value, it indicates that the collision occurred a long time ago, and the risk between the vehicle and the obstacle can be considered low. If the collision time is less than this value, it means that the collision risk is imminent, and the system will proceed to the next step of risk assessment.

[0044] In step S221, when the obstacle collision time exceeds the first collision time threshold, the driving state is determined to be safe.

[0045] Once the system determines that the collision time with an obstacle exceeds the first collision time threshold, it indicates that the collision risk is relatively low, and no emergency obstacle avoidance maneuver is required. This effectively avoids unnecessary system intervention in low-risk scenarios, ensuring the driver maintains normal vehicle control while increasing driver trust in the active safety system and reducing the psychological burden of over-reliance on it.

[0046] In step S223, when the obstacle collision time does not exceed the first collision time threshold, it is identified whether the accelerator pedal state information matches the preset strong acceleration intention condition. The accelerator pedal state information includes accelerator pedal opening information and / or accelerator pedal change rate.

[0047] At low speeds, a driver's accelerator pedal operation can be affected by unclear intentions or misoperation. Especially when encountering obstacles, the driver may unintentionally increase the accelerator, causing the vehicle to approach the obstacle rapidly, thus increasing the risk of collision. Therefore, identifying the accelerator pedal's state information (including accelerator pedal opening information and rate of change) can help determine whether the driver intends to accelerate strongly and prevent accidental accelerator pedal presses.

[0048] In some embodiments, the opening degree of the accelerator pedal (e.g., the specific position of the accelerator pedal) can be obtained in real time through an on-board sensor (such as a pedal sensor), and the pedal change rate (i.e., the rate of change of the accelerator opening degree) can be calculated. In addition, based on years of driving data and vehicle dynamic models, the system sets certain strong acceleration intention conditions through machine learning or rules. For example, when the accelerator pedal opening degree exceeds a certain set threshold (such as more than 70%), and the change rate is fast (such as greater than a certain value, such as a 30% opening degree change speed), it can be determined that the driver has a strong acceleration intention.

[0049] In step S230, in the case where it is identified that the accelerator pedal state information matches the strong acceleration intention condition, the accelerator pedal misstep protection function is activated to perform a vehicle drive power output restriction control operation.

[0050] Here, after identifying the strong acceleration intention, control measures can be taken to avoid collisions caused by misstepping the accelerator. By limiting the drive power output of the vehicle (such as limiting the accelerator signal, adjusting the engine torque output, etc.), the control system can effectively slow down the acceleration process of the vehicle, thereby reducing the risk of collision.

[0051] By accurately identifying the accelerator pedal state and the driver's intention, it can be effectively determined whether the driver has entered a dangerous area due to misstepping the accelerator. Once the system detects that the accelerator pedal state meets the strong acceleration intention condition, the accelerator pedal misstep protection function is immediately activated, not only preventing accidental collisions caused by misoperation, but also improving the system's adaptability to the driver's true intention, making it more intelligent. For example, when the obstacle is very close and the collision time is short, the control effort will be greater; while the collision risk is far away, the control effort will be lighter.

[0052] Thus, by activating the accelerator pedal misstep protection function, it is ensured that the vehicle will not excessively approach the obstacle under strong acceleration intention, reducing the probability of collision. Through intelligent speed limit control, the system can flexibly intervene in the driver's operation, avoid sudden braking intervention, provide a smooth and comfortable driving experience, and at the same time ensure safety.

[0053] In some examples of embodiments of the present application, to improve the accuracy of collision risk judgment in the accelerator pedal misstep scenario, the system further determines the longitudinal power link response delay based on the accelerator pedal state information, and combines the obstacle collision time and the actual braking process time of the vehicle to calculate the first collision reaction time TTR AMAP for triggering the misstep protection function.

[0054] Figure 3A schematic diagram of the speed-time relationship of the vehicle during the braking operation of the driver is shown, wherein V represents the vehicle speed, T is the time axis, V0 is the current speed, V1 is the response speed after the pedal operation, t1-t3 correspond to the acceleration stage, uniform speed stage and braking stage respectively.

[0055] First, the longitudinal power link response delay corresponding to the accelerator pedal state information is determined.

[0056] After the vehicle receives the accelerator pedal input, it will not immediately show the acceleration change, but needs to go through the response process of the engine, motor, transmission and other longitudinal power links. Therefore, there is a certain link response delay t1 for the influence of the accelerator pedal operation on the actual speed of the vehicle. In order to accurately predict the speed evolution trend of the vehicle in the case of mispressing the accelerator, the delay should be determined first and included in the calculation of the collision time.

[0057] Specifically, the system monitors the pedal opening and pedal change rate in real time, and obtains accurate input through the pedal sensor. Based on the link response modeling of vehicle calibration, the power link delay t1 is obtained by calibration test of different vehicles, which can include throttle signal filtering delay, engine / motor torque build-up time, transmission hydraulic pressure build-up time or tire longitudinal force build-up process, etc. For example, the actual delay is generally tens to hundreds of milliseconds.

[0058] Exemplarily, according to the throttle opening-acceleration mapping table calibrated by the vehicle, the target acceleration a1 of the vehicle at the current pedal opening is obtained, and by combining the above parameters, it can be determined that the pedal operation will cause the vehicle to continuously accelerate from V0 to V1 within t1 period. By modeling the accelerator pedal state, power link characteristics and acceleration mapping system, a real and effective vehicle dynamic response basis is provided for collision time prediction, especially in the case of mispressing the accelerator leading to short-time rapid acceleration, which can significantly improve the real-time and accuracy of risk assessment.

[0059] According to the obstacle collision time, the longitudinal power link response delay and the braking process time, the first collision reaction time is calculated.

[0060] It should be noted that the traditional TTC calculation is only based on the speed-distance relationship, without considering the acceleration change caused by the accelerator, and without considering the link delay, brake start delay and other factors, which cannot accurately cover the mispressing accelerator scenario.

[0061] As Figure 3The speed-time relationship shown is divided into an acceleration stage, a uniform speed stage and a braking stage. In the acceleration stage, the acceleration is a1 and the duration is t1. Although the driver has released the accelerator or begun to prepare for braking operation, the longitudinal power link composed of the engine / motor, transmission and tires has a non-negligible response delay. During this delay period, the vehicle continues to maintain the original driving force and continues to accelerate or maintain power output, causing the vehicle speed to rise.

[0062] In the uniform speed stage, the driver has not yet applied effective braking, and the vehicle speed remains relatively stable for a short time, which represents the effective time window in which the driver can respond to braking and is a key section that needs to be considered by the system when calculating the collision reaction time, with a duration of t2. In the braking stage, the acceleration is a3 and the braking process time (or driving reaction time) is t3. When the driver's braking operation actually takes effect, the vehicle enters the braking process stage, at which time the vehicle decelerates at an acceleration a3 (such as the maximum braking acceleration) until it comes to a complete stop or avoids contact with the obstacle.

[0063] In the acceleration stage, from acceleration to braking, after the pedal is depressed, the vehicle maintains an acceleration a1 for a power link delay time t1.

[0064] According to the kinematic formula, the speed rises to: Equation (1) The speed rises from V0 to V1.

[0065] In the uniform speed stage, the vehicle enters a short uniform speed stage (corresponding to the speed platform segment in Figure 3 ) after reaching V1, in order to solve the intermediate segment t2 in the target collision time window TTR_AMAP.

[0066] Let s1 be the displacement in the acceleration stage: Equation (2) Let s3 be the displacement required in the braking stage (a3 is the braking acceleration): Equation (3) In the equation, is the relative speed of the obstacle, which can be obtained in real time by a millimeter wave radar, a laser radar or a vision-radar fusion algorithm, for example, by differentiating the speed of the obstacle detected by the sensor from the current speed of the ego vehicle to obtain the real-time relative speed of the obstacle relative to the ego vehicle.

[0067] The remaining distance of the obstacle The distances of the three stages satisfy: Equation (4) Constant speed phase time: , equation (5) In the braking phase, the vehicle brakes with deceleration a3 until collision avoidance or vehicle stop, the final AMAP reaction time TTR AMAP is This is the effective time window left for the driver or active safety system to identify the risk and make braking decisions.

[0068] Considering the throttle-acceleration mapping, actuator / powertrain link response delay and subsequent braking capability, the time margin before the latest braking decision moment that can be preserved for collision avoidance can be calculated based on the current pedal opening and vehicle state.

[0069] In the case of detecting that the first collision reaction time is less than the first reaction time threshold, the accelerator pedal misoperation protection function is activated.

[0070] When it is detected that TTR AMAP is less than the preset first reaction time threshold, it can be determined that the driver's available reaction time is insufficient, and the accelerator pedal misoperation protection is triggered in combination with the strong acceleration intention condition. If the driver still continuously applies high throttle input, it is highly probable that the throttle pedal is misoperated, at which time the driving force output should be limited to immediately limit the acceleration capability to avoid further risks, thereby ensuring the safety distance between the vehicle and the obstacle.

[0071] Figure 4 An operation flowchart showing another example of performing a vehicle obstacle avoidance collaborative control operation according to obstacle collision time and vehicle accelerator pedal state information according to an embodiment of the application is shown.

[0072] In step S410, in the case where it is identified that the accelerator pedal state information does not match the accelerator pedal strong acceleration intention condition, a second collision reaction time is calculated according to the obstacle collision time and the braking process time.

[0073] Here, when the driver's accelerator pedal state information does not satisfy the strong acceleration intention condition (for example, the accelerator pedal opening is low and the change rate is gentle), it can be considered that the driver currently has no obvious active acceleration demand, at which time the future motion trend of the vehicle will not be significantly deviated due to the obvious acceleration change caused by the throttle.

[0074] Therefore, in such a situation, it is not necessary to use the braking model considering the throttle-acceleration mapping and actuator response delay, but can directly return to a more simplified and more conservative collision time model, i.e. the traditional TTR (Time To Collision Reaction), which estimates the time window that the driver or system must start braking to avoid collision based on the current vehicle speed, relative speed with the obstacle and response time of the braking system.

[0075] Specifically, the following real-time data can be acquired: current vehicle speed relative speed of the obstacle initial distance between the ego vehicle and the obstacle response time of the vehicle braking system (braking process time) maximum available deceleration .

[0076] Exemplarily, the total braking distance required to avoid collision at the maximum deceleration can be calculated first , formula (6) and then the total collision reaction time is calculated based on the remaining distance: , formula (7) The braking process time is deducted from the TTR, so that the final collision reaction time is: , formula (8) wherein, represents the second collision reaction time.

[0077] Thus, by adopting the second collision reaction time, the system execution efficiency is improved by avoiding overly complex AMAP calculation when no strong acceleration intention is involved, so that a more stable and conservative risk assessment result is obtained for low-speed scenarios, thereby accurately measuring the effective reaction time possessed by the driver under the current pedal state.

[0078] In step S420, the second collision reaction time is compared with a second reaction time threshold and a third reaction time threshold, wherein the second reaction time threshold is greater than the third reaction time threshold.

[0079] Here, in order to realize the hierarchical safety intervention, two response thresholds are preset, i.e., a larger second reaction time threshold and a smaller third reaction time threshold , and these two thresholds are used to divide different collision urgency levels into three grades.

[0080] In step S431, in the case where the second collision reaction time is detected to be less than the second reaction time threshold and greater than or equal to the third reaction time threshold, a vehicle collision warning operation is performed.

[0081] Here, the early warning mode is diversified, which can be in the form of sound and light alarm (buzzer + instrument prompt), HUD display collision path or seat vibration or steering wheel vibration, etc. Thus, the driver's risk perception ability is significantly improved without forced intervention, avoiding the comfort and experience problems caused by misbraking, and greatly reducing the collision probability in the medium risk situation.

[0082] In some examples of the embodiments of the present application, the position of the collision point when the target vehicle contour envelope and the obstacle overlap in space is obtained. Specifically, after detecting the first spatial overlap with the obstacle based on the vehicle contour envelope sequence, the position information of the collision point is further determined according to the specific position of the overlapping area in the vehicle coordinate system. For example, it is identified whether the danger comes from the front, front left corner, front right corner, side or rear side area of the vehicle, so as to accurately reflect the spatial direction in which the future collision is most likely to occur.

[0083] Further, the vehicle collision warning operation is performed according to the position of the collision point. Specifically, after obtaining the position of the collision point, the system can perform targeted collision warning operation based on the position, so that the driver can perceive the dangerous direction in the shortest time. For example, when the collision position is located at the front left corner of the vehicle, the left side area of the instrument or HUD can be highlighted, or the left side of the seat can be vibrated; when the risk comes from the side, the corresponding side door panel indicator light or steering wheel side vibration module can issue a prompt. Thus, by making the warning signal consistent with the dangerous direction in space, the driver can quickly locate the risk source without additional judgment and make corresponding deceleration or avoidance operation, thereby further enhancing the system safety and user experience.

[0084] In step S433, in the case where the second collision reaction time is detected to be less than the third reaction time threshold, a vehicle driving force output restriction control operation is performed.

[0085] Exemplarily, when the risk level is determined to be low risk, no intervention is given; when the risk level is determined to be medium risk, a warning is triggered; and when the risk level is determined to be high risk, driving force limitation is triggered.

[0086] In the embodiments of the present application, by using the double threshold grading mechanism, the situations of early warning that can be avoided and braking that cannot be avoided are distinguished, the response accuracy of the system to different risk levels is improved, and all risks are avoided to be handled by forced intervention, thereby improving the driving comfort and user acceptance.

[0087] Figure 5 An operation flowchart of an example of determining the obstacle collision time by the contour envelope according to the embodiments of the present application is shown.

[0088] ​​​In step S510, according to the vehicle contour envelope sequence, a neighboring trajectory prediction point time instant before the target trajectory prediction point time instant is determined.

[0089] It should be noted that in the vehicle contour envelope sequence, the target trajectory prediction point time instant is the time instant at which the vehicle contour envelope is first detected to have spatial overlap with the obstacle. However, the time resolution of trajectory prediction is usually determined by a fixed sampling step (such as 50 ms, 100 ms), which may not be sufficient to accurately depict the actual time point at which the vehicle comes into contact with the obstacle. Therefore, the nearest neighboring prediction point before the target time instant can also be found from the original trajectory point sequence, so as to perform finer time interpolation therebetween.

[0090] Specifically, the time index of the target prediction point is read from the vehicle contour envelope sequence, for example, t k , and the neighboring previous prediction point t k-1 is taken forward. This neighboring prediction point ensures that the vehicle has not yet touched the obstacle at this time instant, and therefore there must be a spatial state transition interval between t k-1 and t k , during which the vehicle contour envelope changes from "non-overlap" to "overlap", which serves as the starting point for subsequent iterative interpolation.

[0091] In step S520, at least one time interpolation process is performed on the target trajectory prediction point time instant and the neighboring trajectory prediction point time instant to obtain at least one interpolated prediction time instant.

[0092] Specifically, between t k-1 and t k , the vehicle contour envelope state changes from safe to collision. In order to improve the time accuracy of the collision time, the time period is interpolated to further subdivide the originally coarse sampling time instants. The interpolated prediction time instants after interpolation can refine the time granularity of envelope change, making the collision detection closer to the actual time instant of occurrence, for example, linear interpolation, cubic spline interpolation, etc. Further, each interpolated time instant corresponds to a more accurate predicted position and pose of the vehicle in the future, and the number of interpolated time instants is flexibly adjusted according to the scene, and one or more iterations of interpolation can be performed. Thus, the trajectory prediction is upgraded from coarse-grained time resolution to fine-grained time resolution, thereby improving the accuracy of collision time calculation and significantly improving the sensitivity to time during low-speed driving.

[0093] In step S530, for each interpolated prediction time instant arranged in sequence, an interpolated vehicle contour envelope corresponding to the interpolated prediction time instant is constructed, and it is detected whether the interpolated vehicle contour overlaps with the obstacle in space.

[0094] It should be noted that the future posture and position of the vehicle continuously change over time. Even if the state of the vehicle and the obstacle does not change significantly between the original prediction points, the vehicle contour may just overlap at a small time step. Therefore, the vehicle contour envelope can be reconstructed for each interpolation time, and whether it overlaps with the obstacle in space is judged separately using a polygon intersection algorithm, based on dynamic fine-grained detection, to improve the collision time prediction accuracy in low-speed scenarios.

[0095] In step S540, the first interpolation prediction time at which the spatial overlap is first detected in each interpolation vehicle contour envelope is determined, and the obstacle collision time is determined based on the first interpolation prediction time.

[0096] Since the interpolated prediction time has a higher time resolution, the interpolation time at which the vehicle contour envelope first overlaps with the obstacle can represent a more accurate approximation of the real collision time, which is used as the final obstacle collision time by the system.

[0097] Specifically, in the time series of the interpolated contour envelope, the first interpolation time containing the overlap state is found and marked as the first interpolation prediction time. This time is used as the obstacle collision time of this prediction, which significantly improves the collision time judgment accuracy in low-speed and low-dynamic scenarios, avoids misjudgment or delay caused by insufficient time resolution, and improves the execution reliability and user experience of the entire low-speed active safety system.

[0098] By introducing adjacent time interpolation, constructing an interpolated contour envelope, and detecting overlaps one by one, the time dimension is refined based on the original trajectory prediction model, enabling the system to obtain the real collision time of the vehicle and the obstacle with higher accuracy. Thus, it does not need to rely on high-frame-rate sensors, but achieves time refinement at the algorithm level through interpolation, which has high adaptability and cost performance, and can achieve fine collision prediction and safety control in low-speed traffic environments at low cost.

[0099] In some examples of the embodiments of the present application, the time interval between the first interpolation prediction time and the adjacent second interpolation prediction time before the first interpolation prediction time is less than a preset time interval threshold.

[0100] Specifically, after obtaining the first interpolation prediction time at which the spatial overlap first occurs Then, the system can further determine whether the time interval between the interpolation time and the previous interpolation prediction time is less than a preset time interval threshold. For example, when When the time span between the first and second interpolation prediction time is less than a threshold value (e.g., 5 ms, 10 ms), it is considered that the current interpolation accuracy is sufficient to depict the state transition from non-contact to contact, and there is no need to continue to perform denser interpolation. Thus, unnecessary calculation overhead is reduced by avoiding continuing to perform interpolation operations when sufficient time accuracy has been reached.

[0101] Additionally or alternatively, the time interpolation process employs a median interpolation process based on time interval dichotomy.

[0102] Specifically, when the time span between the first and second interpolation prediction time is large, a median interpolation method based on time interval dichotomy can be employed to further refine the collision time. By taking the time median (e.g., ) between the two interpolation times as a new interpolation prediction time, the corresponding interpolated vehicle profile envelope is reconstructed and it is determined whether spatial overlap with the obstacle occurs. If the profile at the median time still does not overlap with the obstacle, the median is taken as a new "non-collision time", and a new interpolation interval is formed with the "collision time" behind it; if the profile at the median time has already overlapped, the median is taken as a new "collision time", and a new interpolation interval is formed with the "non-collision time" in front of it. Through the above dichotomy iterative process, until the time interval between adjacent interpolation times meets the preset time interval threshold, the median time at this time can be taken as a more accurate collision time.

[0103] Figure 6 A flowchart showing an example of a vehicle obstacle avoidance control method according to an embodiment of the present application is shown, which describes the complete decision-making process of the system in low-speed working conditions, based on multi-sensor perception fusion, vehicle trajectory prediction, collision time calculation, and throttle / brake collaborative control, to achieve omnidirectional anti-collision and throttle misstep protection.

[0104] As shown in Figure 6 , first, it is determined whether the vehicle meets the functional activation conditions, such as whether the vehicle speed is in the low-speed range (e.g., below 20 km / h), whether the gear is in the forward / reverse / neutral position, whether the driver's seat belt is fastened, and whether various environmental perception sensors are in normal working condition, including surround-view cameras, millimeter-wave radars, ultrasonic radars, laser radars, and other sensor health state checks. When the working conditions are met, the system collects vehicle surrounding environment data based on multi-type sensors such as ultrasonic radars, millimeter-wave radars, surround-view cameras, and laser radars, and generates a unified obstacle point cloud through a multi-source perception fusion strategy. This obstacle point cloud can contain information such as the position, height, reflection characteristics, and type of the obstacle, thereby fully characterizing the obstacle features in all directions around the vehicle. Thus, near-distance accurate perception of static, dynamic, and lateral obstacles around the vehicle is achieved, which is particularly suitable for lateral distance mapping problems in turning scenarios.

[0105] After obtaining the obstacle point cloud, the omnidirectional collision detection module combines the current speed, longitudinal acceleration, steering wheel angle, and other driving state information of the vehicle to perform short-time prediction on the future trajectory of the vehicle, and generates a time-sequenced vehicle polygonal envelope based on the predicted trajectory. Subsequently, the system performs omnidirectional collision detection on the vehicle envelope and the obstacle point cloud based on a binary traversal method or other efficient spatial collision detection algorithms, obtains the obstacles that may collide, and determines the obstacle with the smallest collision time and the corresponding collision point position. When the TTC is greater than a threshold 1 (such as 3 seconds), it indicates that the vehicle does not have an imminent risk, and the system does not perform intervention; but when the TTC is less than the threshold 1, the system enters the risk assessment and control strategy execution phase.

[0106] In the risk assessment phase, the system first identifies whether there is an abnormal accelerator pedal operation of the driver. For example, when the throttle opening exceeds a set threshold or the throttle opening change rate exceeds a preset threshold, the system predicts the vehicle longitudinal acceleration based on the throttle-acceleration mapping table, and calculates the collision reaction time TTR AMAP considering the influence of the throttle in combination with the actuator response delay. If TTR AMAP is less than a preset threshold, i.e., the latest braking possible time to collision under the continuous action of the throttle has been compressed, the system determines that it is a potential throttle misoperation scene, and activates the throttle misoperation protection function in time, including limiting the driving force output, engine torque interruption, and mild braking intervention if necessary.

[0107] If the accelerator pedal input of the driver is normal, the system performs risk level assessment based on the generally defined collision reaction time TTR, which takes into account the current speed, acceleration, brake system response time, actuator delay, and other factors of the vehicle. When TTR is less than threshold 2 but not less than threshold 3, the system triggers directional collision warning, including audible and visual alarms, steering wheel or seat vibration prompts, and pops up the obstacle picture of the corresponding collision position in the vehicle display screen or 360° panoramic image interface, guiding the driver to take active braking or avoidance operation. When TTR is less than threshold 3, the system immediately performs emergency braking and power cut-off operation to maximize the avoidance of collision or reduce the risk of collision.

[0108] In the vehicle starting phase, since the driver's attention may not be focused and the obstacle distance is closer, the system will preferentially inhibit the throttle signal when detecting a collision risk to prevent throttle misoperation during low-speed starting from causing collision or injuring vulnerable road users. In the low-speed driving phase after the vehicle starts, if a collision risk is detected, the system will perform precise braking based on the collision time and reaction time to achieve the effect of active safety control of timely intervention before collision.

[0109] Therefore, the system can comprehensively realize omnidirectional anti-collision warning, emergency braking intervention and accelerator misstep protection functions in low-speed starting, reversing, narrow road passing and urban congestion and the like working conditions, realize multiple active safety capabilities, and effectively improve the safety, reliability and user experience of the vehicle in a low-speed complex environment.

[0110] Figure 7 An effect diagram of an example of a collision field point when a typical vehicle turns in a low-speed scenario is shown.

[0111] In the embodiments of the present application, an omnidirectional collision point and collision time calculation method is proposed, which can accurately obtain the real collision point position and collision time TTC between the vehicle and each obstacle based on the obstacle point cloud generated based on fused perception information and the vehicle predicted trajectory, effectively overcome the distance distortion problem that easily occurs when the traditional TTC calculation only relies on the distance or trajectory projection distance, and avoid the missed collision control caused by overestimated TTC or the low-speed AEB false triggering caused by underestimated TTC.

[0112] Specifically, the fused multi-sensor perception result is transmitted to the decision planning layer in the form of a point cloud, a corresponding obstacle polygon is generated for each cluster of obstacle point clouds, and collision correlation verification is performed in combination with the obstacle speed, drivable area and the like information to screen the target obstacle that is likely to collide with the vehicle.

[0113] As shown in Figure 7 The four obstacle points shown in the diagram represent four typical collision scenarios commonly encountered during low-speed driving of the vehicle. Specifically, the obstacle point 1 is located in front of the vehicle but not in the vehicle driving domain, and the vehicle does not have a collision risk when driving according to the current predicted trajectory; the obstacle point 2 is located in the vehicle driving domain and the collision point is in front of or behind the vehicle; the obstacle point 3 is located in the vehicle drivable domain and is in the side front of the vehicle, and the vehicle will come into contact with the obstacle from the side front when driving according to the current trajectory; and the obstacle point 4 is located in the side of the vehicle, and the vehicle will collide with the side of the vehicle when driving according to the current trajectory. For the collision points of the obstacle point 3 and the obstacle point 4 in the process of lateral or turning, if the traditional method of projecting the obstacle position to the predicted trajectory and then calculating the distance is used, the projection point may have fallen into the inside of the vehicle body contour at the time shown in the diagram, so that the calculated TTC has a large deviation from the time when the vehicle actually collides.

[0114] In order to further meet the requirement of accurate control in the low-speed and large-curvature working condition, an omnidirectional TTC calculation method based on vehicle polygon traversal and time interval dichotomy can also be used. As shown in Figure 7As shown, the trajectory points of the vehicle at each future time are predicted in time steps from the current time, and a corresponding vehicle polygon outline is generated at each predicted time. Then, these vehicle polygons are sequentially traversed in time order, and when it is detected that a vehicle polygon at a certain time first contains the target obstacle point, it is determined that there is a change interval from the "non-collision" state to the "collision" state between this time and the previous time. Next, interpolation is performed between the two adjacent predicted times using time interval bisection to obtain new intermediate trajectory points and regenerate the vehicle polygon, and it is judged whether the intermediate time polygon contains the obstacle point. If the intermediate time has already contained the obstacle point, the intermediate time is taken as a new "collision endpoint", and the bisection is continued with the previous "non-collision endpoint". If the intermediate time still does not contain the obstacle point, it is taken as a new "non-collision endpoint", and the bisection is continued with the rear "collision endpoint". Through repeated bisection traversal process, when the time difference between the trajectory points corresponding to the vehicle polygon containing the obstacle point and the vehicle polygon not containing the obstacle point is less than a preset time threshold (for example, 0.05 seconds), it is considered that the real collision time has been approached in time.

[0115] On this basis, the time corresponding to the median of the above two times is taken, and the difference with the current time is obtained, that is, the high-precision collision time TTC of the obstacle point is obtained. Since this method directly performs omnidirectional traversal based on the spatial overlap relationship between the complete vehicle contour and the geometric position of the obstacle, rather than simply using the forward distance or trajectory projection distance, it can be uniformly applied to forward, rearward and various lateral collision scenarios, especially in low-speed, large-curvature turning, obstacle-avoiding detour and other working conditions, significantly improving the accuracy and stability of TTC calculation, thereby providing a more reliable time basis for subsequent warning, braking intervention and throttle misstep protection.

[0116] In the embodiments of the present application, in order to solve the problem that the traditional distance-based or trajectory projection-based TTC calculation is prone to distance distortion and high risk of misjudgment in low-speed and large-curvature working conditions, a polygon traversal method for accurately calculating omnidirectional collision points and collision time of a vehicle is proposed. Specifically, the vehicle polygon is generated by generating the vehicle predicted trajectory points and performing omnidirectional collision detection, and then the time interval of collision occurrence is gradually narrowed by using bisection approximation and encrypted trajectory, so as to obtain high-precision collision time TTC. It should be understood that the implementation scope of the embodiments of the present application is not only applicable to the bisection search method based on equal time interval trajectory prediction, but also can be extended to the approximation method based on equal distance trajectory points, or directly constructing high-density trajectories and then sequentially detecting collisions, thereby supporting various implementation paths under different precision requirements and calculation resource conditions.

[0117] In addition, the embodiments of the present application are not only applicable to static obstacles, but also can realize accurate collision time and collision distance calculation of moving targets by synchronously updating the positions of dynamic obstacles at each predicted time during traversal, further enhancing the applicability of the system in real traffic scenarios. Through omnidirectional obstacle perception and collision prediction, the system can effectively cover visual blind area scenarios such as low-speed, turning, moving, and reversing of the vehicle, and provide more comprehensive risk identification capability for passenger vehicles, commercial vehicles, and other types of vehicles.

[0118] Therefore, by combining higher-precision collision time estimation, low-speed anti-collision and accelerator misoperation protection are cooperatively designed to build a multi-layer protection system from early warning, active anti-collision to accelerator misoperation protection, which can trigger corresponding brake control, accelerator suppression or directional warning according to different risk levels, thereby significantly reducing the mis-triggering event, improving user experience, and greatly enhancing the active safety performance of the vehicle in a low-speed complex environment.

[0119] Figure 8 A structural block diagram of an example of a vehicle according to an embodiment of the present application is shown.

[0120] As shown in Figure 8 The vehicle 800 includes an environment perception sensor 810 and a vehicle controller 820.

[0121] The environment perception sensor 810 is used to collect environment perception data around the vehicle.

[0122] The environment perception data can be diverse and can be provided in different forms by multiple types of sensors, including near-distance obstacle distance data from ultrasonic radars distributed in front, rear, and side directions of the vehicle, obstacle relative speed and distance information from millimeter wave radars, image semantic information from surround-view cameras, and three-dimensional spatial point cloud data from laser radars. By synchronously processing the above multi-dimensional sensor data in space and time and sensor calibration, the vehicle can be provided with environmental features such as obstacle position, shape, type, and motion state covering all directions around the vehicle, providing reliable input for subsequent trajectory prediction and collision risk calculation.

[0123] The vehicle controller 820 is used to perform the vehicle obstacle avoidance control method according to any one of the embodiments of the present application.

[0124] In some embodiments, the vehicle controller 820 is executed by other electronic control units with equivalent functions, such as a vehicle control unit (VCU), an automatic driving domain controller, an ADAS controller, etc., and can achieve the same or similar technical effects as described in the present application. For more details, refer to or combine the description in the method embodiments above, which will not be repeated here.

[0125] It should be noted that, for the foregoing method embodiments, for the purpose of simple description, they are all described as a series of actions, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other orders or at the same time. Secondly, those skilled in the art should know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application. In the above embodiments, the description of each embodiment is focused on, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0126] In some embodiments, the present application also provides a computer program product, which comprises a computer program stored on a non-volatile computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform any one of the vehicle obstacle avoidance control methods described above.

[0127] In some embodiments, the present application also provides 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 vehicle obstacle avoidance control method.

[0128] The device of the above-mentioned embodiments of the present application can be used to execute the vehicle obstacle avoidance control method of the embodiments of the present application, and accordingly achieve the technical effects of the above-mentioned embodiments of the present application in implementing the vehicle obstacle avoidance control method. Here, the relevant functional modules in the embodiments of the present application can be realized by a hardware processor.

[0129] Figure 9 is a hardware structure schematic diagram of an electronic device for executing the vehicle obstacle avoidance control method provided by another embodiment of the present application, as shown in Figure 9 The device comprises: one or more processors 910 and a memory 920, Figure 9 In the above-mentioned embodiments, the processor 910 is taken as an example.

[0130] The device for executing the vehicle obstacle avoidance control method can further comprise an input device 930 and an output device 940.

[0131] The processor 910, the memory 920, the input device 930 and the output device 940 can be connected through a bus or other means, Figure 9 In the above-mentioned embodiments, the connection through the bus is taken as an example.

[0132] The memory 920, as a non-volatile computer readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the vehicle obstacle avoidance control method in the embodiments of the present application. The processor 910 executes various functions and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 920, that is, implements the vehicle obstacle avoidance control method of the above method embodiments.

[0133] The memory 920 can include a program storage area and a data storage area, wherein the program storage area can store an operating system and application programs required by at least one function; the data storage area can store data created during use of the device, etc. In addition, the memory 920 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state memory device. In some embodiments, the memory 920 can optionally include a memory disposed remotely with respect to the processor 910, and these remote memories can be connected to the device through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0134] The input device 930 can receive input digital or character information, and generate signals related to user settings and function control of the device. The output device 940 can include a display device such as a display screen.

[0135] The one or more modules are stored in the memory 920, and when executed by the one or more processors 910, perform the vehicle obstacle avoidance control method in any of the above method embodiments.

[0136] The above product can perform the method provided by the embodiments of the present application, and has the corresponding function modules and beneficial effects of performing the method. Technical details not described in detail in the embodiments can be referred to the method provided by the embodiments of the present application.

[0137] The electronic device of the embodiments of the present application exists in various forms, including but not limited to: (1) Mobile communication device: the feature of this kind of device is to have mobile communication function, and to provide voice and data communication as the main target. This kind of terminal includes: smart phone (such as iPhone), multimedia phone, functional phone, and low-end phone, etc.

[0138] (2) Ultra-mobile personal computer device: this kind of device belongs to the category of personal computer, has computing and processing function, and generally also has the feature of mobile Internet. This kind of terminal includes: PDA, MID and UMPC device, etc., such as iPad.

[0139] (3) Portable entertainment device: This kind of device can display and play multimedia content. This kind of device includes: audio, video player (such as iPod), handheld game machine, electronic book, and smart toy and portable car navigation device.

[0140] (4) Server: A device providing computing services, the composition of the server includes processor, hard disk, memory, system bus, etc. The server is similar to the general computer architecture, but due to the need to provide high-reliable services, it has higher requirements in processing capacity, stability, reliability, security, scalability, manageability, etc.

[0141] (5) Other electronic devices with data interaction function.

[0142] In some embodiments, the present application also provides a mobile platform, which is installed with the computer device described in any of the embodiments of the present application. The mobile platform includes but is not limited to vehicles, tracked robots, biped robots, quadruped robots, etc., wherein the vehicles can be passenger cars, pickup trucks, trucks, etc. It should be noted that the above are only examples, and the present application does not limit the specific form of the mobile platform.

[0143] The device embodiments described above are only schematic, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e. they can be located in one place or distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment.

[0144] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions essentially or say the part that contributes to the related art can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, server, or network device, etc.) execute the methods described in each embodiment or some part of the embodiment.

[0145] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A vehicle obstacle avoidance control method, comprising: When the vehicle's driving status parameters are detected to meet the low-speed driving conditions, the vehicle's driving trajectory is predicted based on the vehicle's environmental perception data and vehicle driving status parameters. For each of the multiple vehicle trajectory points in the vehicle's driving trajectory, a vehicle contour envelope is constructed to generate a corresponding vehicle contour envelope sequence; the vehicle contour envelope sequence is combined according to the order of the trajectory point prediction time. The target vehicle contour envelope that first spatially overlaps with the obstacle is detected from the vehicle contour envelope sequence, and the obstacle collision time is determined based on the target trajectory prediction point time corresponding to the target polygon. Based on the obstacle collision time and the vehicle's accelerator pedal status information, the vehicle obstacle avoidance cooperative control operation is executed.

2. The method according to claim 1, wherein, The step of performing vehicle obstacle avoidance cooperative control operations based on the obstacle collision time and the vehicle's accelerator pedal state information includes: When the collision time with the obstacle exceeds the first collision time threshold, it is determined to be a safe driving state; When the obstacle collision time does not exceed the first collision time threshold, the accelerator pedal status information is identified as matching the preset strong acceleration intention condition; the accelerator pedal status information includes accelerator pedal opening information and / or accelerator pedal change rate. If the accelerator pedal status information is found to match the strong acceleration intention condition, the accelerator pedal mis-pressing protection function is activated to perform vehicle driving force output limiting control operation.

3. The method according to claim 2, wherein, The activation of the accelerator pedal mis-pressing protection function includes: Determine the longitudinal power link response delay corresponding to the accelerator pedal state information; The first collision reaction time is calculated based on the obstacle collision time, the longitudinal power link response delay, and the braking process time. If the reaction time to the first collision is less than the first reaction time threshold, the accelerator pedal mis-pressing protection function is activated.

4. The method according to claim 2, wherein, After identifying whether the accelerator pedal status information matches a preset strong acceleration intention condition, the method further includes: If it is found that the accelerator pedal state information does not match the strong acceleration intention condition of the accelerator pedal, the second collision reaction time is calculated based on the obstacle collision time and the braking process time. If the second collision reaction time is detected to be less than the second reaction time threshold and greater than or equal to the third reaction time threshold, a vehicle collision warning operation is performed; the second reaction time threshold is greater than the third reaction time threshold. If the second collision reaction time is detected to be less than the third reaction time threshold, a vehicle driving force output limiting control operation is performed.

5. The method according to claim 4, wherein, The execution of the vehicle collision warning operation includes: Obtain the location of the collision point when the target vehicle's outline envelope overlaps with the obstacle in space; Execute a vehicle collision warning operation based on the location of the collision point.

6. The method according to claim 1, wherein, The step of detecting the target vehicle contour envelope that first spatially overlaps with the obstacle from the vehicle contour envelope sequence, and determining the obstacle collision time based on the target trajectory prediction point time corresponding to the target polygon, includes: Based on the vehicle contour envelope sequence, determine the time of the adjacent trajectory prediction point before the time of the target trajectory prediction point; At least one time interpolation process is performed on the target trajectory prediction point time and the adjacent trajectory prediction point time to obtain at least one corresponding interpolated prediction time. For each of the sequentially arranged interpolation prediction times, an interpolated vehicle contour envelope corresponding to the interpolation prediction time is constructed, and it is detected whether the interpolated vehicle contour spatially overlaps with the obstacle. The first interpolation prediction time is detected in the envelope of each interpolated vehicle profile, and the obstacle collision time is determined based on the first interpolation prediction time.

7. The method according to claim 6, wherein, The time interval between the first interpolation prediction time and the adjacent second interpolation prediction time before the first interpolation prediction time is less than a preset time interval threshold; And / or, the time interpolation process employs median interpolation based on time interval bisection.

8. The method according to claim 1, further comprising: Each environmental sensing sensor collects its corresponding raw environmental sensing data. The collected raw environmental perception data are fused together to generate obstacle point clouds; The obstacle point cloud is used at least to characterize the spatial location information of the obstacles; The environmental perception sensors include one or more of the following: ultrasonic radars distributed in the front, rear and sides of the vehicle, millimeter-wave radars installed in the front and / or rear of the vehicle, surround-view cameras, and lidar.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory, wherein, The processor executes the computer program to implement the steps of the method according to any one of claims 1-8.

10. A vehicle comprising: Environmental perception sensors are used to collect environmental perception data around the vehicle; A vehicle controller for performing the steps of the method as described in any one of claims 1-8.

Images