Method and apparatus for early warning protection of automatic parking assistance

Abstract

The application provides a kind of automatic parking auxiliary early warning protection method and equipment, it is related to the joint control technical field of different types or different function vehicle subsystems.The method comprises: generating a planning path trajectory;Determine the preview point according to the speed;Predict whether there is an obstacle point in the inflation model between the current target path point and the preview point, and issue a first early warning when there is, control the speed to drop to not higher than the first speed;Generate kinematic path by predicting through vehicle kinematic model;Predict whether there is an obstacle point in the inflation model on the kinematic path, and issue a second early warning when there is, and control the speed to drop to not higher than the second speed;Issue a third early warning and control to enter the emergency stop state when there is an obstacle point in the inflation model and the obstacle point is outside the body model and in the current direction of travel.The application ensures the accuracy and safety of automatic parking function.

Description

Technical Field

[0001] This invention relates to the field of joint control technology for vehicle subsystems of different types or functions, specifically to the field of predicting or avoiding possible or impending collisions and automatic operation technology for parking, and more specifically, to a warning and protection method and device for automatic parking assistance. Background Technology

[0002] Automated Parking Assist (APA) is a type of Advanced Driving Assistance System (ADAS). APA uses sensor fusion and algorithmic control to detect obstacle positions and plan parking paths, automatically controlling the steering wheel to complete the parking maneuver. This system primarily relies on environmental perception, parking space recognition and assessment, and dynamic path planning to achieve automatic parking. Compared to other ADAS functions, APA is more suitable for low-speed scenarios.

[0003] As a popular automated driving assistance feature, APA has spawned a series of warning and protection functions. Currently, APA's warning and protection largely depends on the hardware performance of the ultrasonic sensors. When users of this feature are not paying attention, the disappearance or shifting of ultrasonic noise may lead to a poor driving experience. Summary of the Invention

[0004] To address the aforementioned problems in the prior art, in a first aspect, embodiments of the present invention provide a warning and protection method for automatic parking assistance. The method includes: generating a planned path trajectory based on the vehicle's initial pose and information about a target parking space, the planned path trajectory including multiple planned path points; determining a pre-aiming point on the planned path trajectory that is farther than the current target path point based on the vehicle's real-time speed; predicting whether an obstacle point exists within the vehicle's expansion model when the vehicle reaches a point between the current target path point and the pre-aiming point, and, if an obstacle point exists, issuing a first-level warning to the driver and controlling the vehicle's speed to decrease to no higher than a first speed; and based on the vehicle's real-time... The vehicle's position, real-time speed, and direction of travel are used to predict and generate a kinematic path for a predetermined time period in the future using a vehicle kinematic model. The system then predicts whether there are any obstacles within the vehicle's expansion model when the vehicle is traveling along the kinematic path. If obstacles exist, a level two warning is issued to the driver, and the vehicle's speed is reduced to a level no higher than a second speed, where the second speed is lower than the first speed. Based on the vehicle's real-time position, real-time speed, and direction of travel, if an obstacle exists within the vehicle's expansion model but is outside the vehicle's main body model and within the current direction of travel, a level three warning is issued to the driver, and the vehicle is brought to an emergency stop.

[0005] In some implementations, the method further includes: triggering the regeneration of the planned path trajectory in response to controlling the vehicle to enter an emergency stop state.

[0006] In some implementations, the method further includes: releasing the vehicle from emergency stop status when the driver takes over the vehicle or receives a regenerated planned path trajectory.

[0007] In some implementations, after controlling the vehicle to enter an emergency stop state, the method further includes: predicting and generating a re-predicted kinematic path for a predetermined future time period based on the vehicle's real-time position, real-time speed, and direction of travel using a vehicle kinematic model; predicting whether there are obstacle points within the vehicle body model when the vehicle is traveling on the re-predicted kinematic path; detecting whether the distance between the vehicle and the obstacle points increases based on the vehicle's real-time position; and deactivating the vehicle's emergency stop state if there are no obstacle points within the vehicle body model and the distance between the vehicle and the obstacle points increases.

[0008] In some implementations, the warning sensitivity is adjustable based on one or more of the following: the boundary expansion size of the vehicle expansion model relative to the vehicle body model; the number of path points between the pre-aiming point and the current target path point; and the length of the predetermined time period.

[0009] In some implementations, the method further includes: predicting whether there are obstacle points within the vehicle expansion model when the vehicle passes through the plurality of planned path points, and sending a prompt message to the vehicle driver if there are obstacle points.

[0010] In some implementations, the frequency of generating kinematic paths for a predetermined future time period by predicting them using a vehicle kinematics model is greater than or equal to 30 Hz and less than or equal to 100 Hz.

[0011] In some implementations, the vehicle's real-time speed is calculated based on pulse values ​​measured by wheel speed pulse meters mounted on the rear wheels of the vehicle.

[0012] In some implementations, the initial pose of the vehicle is determined based on the vehicle's position, speed, and direction of travel when the automatic parking assist function is activated.

[0013] In a second aspect, embodiments of the present invention provide an automatic parking assistance warning and protection device, the device including a memory and a processor, the memory storing a computer program that, when executed by the processor, implements the automatic parking assistance warning and protection method described in any of the above embodiments.

[0014] The automatic parking assist warning and protection method and device proposed in the embodiments of the present invention ensure the accuracy of function triggering by combining vehicle speed with real-time positioning and estimating vehicle pose using a vehicle kinematic model at a certain frequency; combining the kinematic model with the planning collision model pose estimation ensures the accuracy of the vehicle emergency stop function and optimizes the operating experience of the APA function when the function is triggered; combining the vehicle kinematic model to add obstacle collision prediction for the vehicle promotes the continuity of the APA function and ensures the normal deployment of the function; and multi-party verification through multiple model predictions ensures passenger safety in the automatic parking state. Attached Figure Description

[0015] The above and other objects, features, and advantages of embodiments of the present invention will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated in the drawings by way of example and not limitation, wherein:

[0016] Figure 1 A flowchart of a warning protection method for automatic parking assistance according to an embodiment of the present invention is shown.

[0017] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0018] The principles and spirit of the invention will now be described with reference to several exemplary embodiments. It should be understood that these embodiments are given merely to enable those skilled in the art to better understand and implement the invention, and are not intended to limit the scope of the invention in any way.

[0019] In one aspect, embodiments of the present invention provide a warning and protection method for automatic parking assistance. (See reference...) Figure 1 The diagram illustrates a flowchart of a pre-warning protection method for automatic parking assistance according to an embodiment of the present invention. The method includes steps S101-S106.

[0020] In step S101, a planned path trajectory is generated based on the vehicle's initial pose and the target parking space information. The planned path trajectory includes multiple planned path points. The initial pose includes the vehicle's initial position and attitude. As an embodiment of the present invention, the vehicle's initial pose is determined based on the vehicle's position, speed, and direction of travel when the automatic parking assist function is activated. For example, the vehicle's speed when the automatic parking assist function is activated can be calculated based on the pulse values ​​measured by wheel speed pulse meters installed on the rear wheels of the vehicle. The direction of travel can be obtained based on gear information (e.g., N, P, R, D gears).

[0021] The planned path trajectory can be generated based on any suitable path planning algorithm, both existing and those that may emerge in the future.

[0022] In step S102, a pre-aiming point farther than the current target path point is determined on the planned path trajectory based on the vehicle's real-time speed.

[0023] In one embodiment of the present invention, the real-time speed of the vehicle is calculated based on the pulse value measured by a wheel speed pulse meter installed on the rear wheel of the vehicle.

[0024] The current target path point refers to the next path point that the vehicle is currently tracking as it travels along the planned path. The preview point is calculated backwards along the planned path based on the current target path point. For example, if the vehicle speed is high, the preview point is set to be a larger distance from the current target path point, meaning there are more path points between them. In other words, on the planned path, the preview point is a path point traversed backwards based on the vehicle speed; if the vehicle speed is high, more points are traversed as preview points. As an example, the preview point can be 8-15 path points (inclusive) away from the current target path point.

[0025] In step S103, it is predicted whether there is an obstacle point within the vehicle's expansion model when the vehicle travels to a point between the current target path point and the pre-aimed point. If an obstacle point exists, a first-level warning is issued to the driver, and the vehicle's speed is reduced to no more than a first speed. The first-level warning may be, for example, reminding the driver to prepare to brake.

[0026] As one embodiment of the present invention, the first speed can be a predefined fixed value. As an example only, the first speed can be set to a value within the range of 3 m / s or greater and 5 m / s or less, for example, it can be set to 4 m / s.

[0027] As another embodiment of the present invention, the first speed can be dynamically set according to the distance between the obstacle and the vehicle at that time.

[0028] The vehicle expansion model is a model generated by setting expansion parameters based on the dimensions of the vehicle body. Intuitively, the outline of the vehicle expansion model is larger than the outline of the vehicle body model, and the area it covers forms a warning range. As an example, the boundary of the vehicle expansion model can extend beyond the boundary of the vehicle body model by a distance between 10cm and 20cm. As another example, the rear axle center point pose can be calculated based on wheel speed positioning, and then the vehicle expansion model can be drawn on a map based on the rear axle center point pose, vehicle parameters, and expansion parameters.

[0029] In step S104, based on the vehicle's real-time position, real-time speed, and direction of travel, a kinematic path for a predetermined future time period is predicted and generated using a vehicle kinematics model. As one embodiment of the invention, the execution frequency for predicting and generating the kinematic path for the predetermined future time period using the vehicle kinematics model is greater than or equal to 30Hz and less than or equal to 100Hz.

[0030] Generally speaking, a vehicle kinematics model calculates the path within a predetermined time frame based on the vehicle's real-time position, speed, and direction. Unlike path planning when the parking function is activated, the kinematics model does not need to consider the orientation of the target parking space.

[0031] As an example only, the above-mentioned predetermined time period can be set to 600ms, 800ms, 1000ms, etc.

[0032] In step S105, it is predicted whether there are obstacle points within the vehicle's expansion model when the vehicle is traveling on the kinematic path. If an obstacle point is present, a secondary warning is issued to the driver, and the vehicle's speed is controlled to decrease to a second speed no higher than the first speed. The secondary warning could, for example, be a reminder to the driver to apply the brakes immediately. As an example only, the second speed could be set within the range of greater than or equal to 0.8 m / s and less than or equal to 2.5 m / s; for example, it could be set to 1.5 m / s.

[0033] In step S106, based on the vehicle's real-time position, real-time speed, and direction of travel, if an obstacle point exists within the vehicle's expanded model but is outside the vehicle's main model and within the current direction of travel, a level three warning is issued to the driver, and the vehicle is controlled to enter an emergency stop (ESTOP) state. The level three warning may indicate to the driver that the emergency braking function has been activated.

[0034] As an example, determining whether an obstacle is in the current direction of travel can be based on the positional relationship of the obstacle point relative to the vehicle body model.

[0035] An emergency stop is a sudden stop for the entire vehicle. For example, lateral control issues a steering wheel angle to the current angle, while longitudinal control issues a deceleration command of -5 to ensure the vehicle comes to a stop. The ESTOP state can be sent from the decision-making level to the planning and control section via relevant message middleware.

[0036] As one embodiment of the present invention, the method may further include: in response to controlling the vehicle to enter an emergency stop state, triggering the regeneration of the planned path trajectory.

[0037] As one embodiment of the present invention, the method may further include: releasing the vehicle from emergency stop state when the driver takes over the vehicle or receives a regenerated planned path trajectory.

[0038] As one embodiment of the present invention, after controlling the vehicle to enter an emergency stop state, the method may further include: predicting and generating a re-predicted kinematic path within a predetermined future time period using a vehicle kinematic model based on the vehicle's real-time position, real-time speed, and direction of travel; predicting whether there are obstacle points within the vehicle body model when the vehicle is traveling on the re-predicted kinematic path; detecting whether the distance between the vehicle and the obstacle points increases based on the vehicle's real-time position; and deactivating (or releasing) the vehicle's emergency stop state if there are no obstacle points within the vehicle body model and the distance between the vehicle and the obstacle points increases. Otherwise, the ESTOP state is maintained to ensure vehicle safety during the operation of the vehicle's APA function.

[0039] In one embodiment of the present invention, the warning sensitivity is adjustable based on one or more of the following: the boundary expansion dimension of the vehicle expansion model relative to the vehicle body model; the number of path points between the pre-aiming point and the current target path point; and the length of a predetermined time period. As an example, by setting the above values, two, three, or more levels of sensitivity settings can be achieved. When set to high sensitivity, the warning time is advanced, allowing for a longer braking distance, but false warnings are more likely. Conversely, when set to low sensitivity, the warning time is delayed, requiring more urgent braking, which reduces interference caused by false warnings.

[0040] For example, for the boundary expansion dimensions of a vehicle expansion model, three levels of sensitivity can be set, such as setting the boundary expansion dimensions to 10cm, 20cm, and 30cm. Alternatively, four levels of sensitivity can be set, such as setting the boundary expansion dimensions to 15cm, 20cm, 25cm, and 30cm.

[0041] The sensitivity can be set to two levels, such as 10 or 15 path points, between the pre-aiming point and the current target path point. Alternatively, a three-level sensitivity can be set, such as 8, 12, or 16 path points.

[0042] The duration of the predetermined time period can be set with two levels of sensitivity, for example, the predetermined time period can be set to 500ms and 1500ms respectively, or four levels of sensitivity can be set, for example, the predetermined time period can be set to 500ms, 1000ms, 1500ms and 2000ms respectively.

[0043] In addition to the Level 1, Level 2, and Level 3 warnings described above, as an embodiment of the present invention, the method may further include: predicting whether there are obstacle points within the vehicle expansion model when the vehicle passes through multiple planned path points, and sending a prompt message to the vehicle driver if obstacle points are present.

[0044] On the other hand, embodiments of the present invention provide an automatic parking assistance warning and protection device, the device including a memory and a processor, the memory storing a computer program, which, when executed by the processor, implements the automatic parking assistance warning and protection method described in any of the above embodiments.

[0045] The automatic parking assist warning and protection method and device proposed in this invention, by combining with the planning and control algorithm in the APA function, are more suitable for APA functions than existing general parking distance control methods. The automatic parking assist warning and protection technology proposed in this invention adds speed limit warnings, braking warnings, and emergency stop warnings to the parking process in different scenarios based on three levels of warning information. Furthermore, it adds a state recovery interface when the function is triggered by an obstacle. Based on wheel speed pulses, vehicle motion posture, steering wheel angle, and other factors combined with replanning path points, it calculates the vehicle collision risk and determines whether the vehicle's emergency stop state is triggered / deactivated, thereby optimizing the automatic parking function experience and providing good assistance and backup protection for APA.

[0046] The automatic parking assistance warning and protection method and device proposed in the embodiments of the present invention jointly construct a collision risk assessment model based on the automatic parking function through modules such as path planning module, kinematic model, vehicle expansion model, and vehicle body model.

[0047] The automatic parking assistance warning and protection method and device proposed in the embodiments of the present invention realize the functions of emergency braking and secondary judgment recovery during parking. This function has a significant performance optimization for ensuring the safety of vehicles when parking in parking spaces and the continuity of parking functions in complex scenarios, especially dead-end roads and horizontal parking spaces.

[0048] The automatic parking assist warning and protection method and device proposed in the embodiments of the present invention combine vehicle wheel speed pulse meter with real-time positioning, and estimate the vehicle pose using a vehicle kinematic model at a certain frequency (e.g., a frequency greater than or equal to 30Hz and less than or equal to 100Hz), ensuring the accuracy of function triggering; the kinematic model is combined with the planned collision model pose estimation to ensure the accuracy of the vehicle emergency stop function and optimize the operating experience of the APA function when the function is triggered; combined with the vehicle kinematic model, obstacle collision prediction is added to the vehicle, promoting the continuity of the APA function and ensuring the normal deployment of the function; multi-party verification is performed through multiple model predictions to ensure passenger safety in the automatic parking state.

[0049] The foregoing description of embodiments of the invention has been given for illustrative purposes and is not exhaustive, nor is it intended to limit the invention to the exact forms disclosed. Those skilled in the art will understand that various changes can be made without departing from the scope of the invention, and elements therein can be substituted with equivalents. Furthermore, many modifications can be made to adapt particular situations or materials to the teachings of the invention without departing from the basic scope of the invention. Therefore, the invention is not intended to be limited to the specific embodiments disclosed as the best mode contemplated for carrying out the invention; the invention will include all embodiments falling within the scope of the appended claims.

Claims

1. A warning and protection method for automatic parking assistance, characterized in that, The method includes: Based on the vehicle's initial position and the target parking space information, a planned path trajectory is generated, which includes multiple planned path points; Based on the vehicle's real-time speed, a pre-aiming point farther than the current target path point is determined on the planned path trajectory; Predict whether there are any obstacle points within the vehicle's expansion model when the vehicle travels to the point between the current target path point and the pre-aiming point, and if there are obstacle points, issue a first-level warning to the vehicle driver and control the vehicle's speed to decrease to no more than a first speed; Based on the vehicle's real-time position, real-time speed, and direction of travel, the kinematic path for a predetermined time period is predicted and generated using a vehicle kinematic model. Predict whether there are obstacle points within the vehicle expansion model when the vehicle is traveling on the kinematic path, and if there are obstacle points, issue a secondary warning to the vehicle driver and control the vehicle speed to decrease to no higher than a second speed, wherein the second speed is lower than the first speed; Based on the vehicle's real-time location, speed, and direction of travel, if an obstacle exists within the vehicle's expansion model but is outside the vehicle's main model and within the current direction of travel, a level three warning is issued to the driver, and the vehicle is brought to an emergency stop.

2. The early warning and protection method for automatic parking assistance according to claim 1, characterized in that, The method further includes: In response to the vehicle entering an emergency stop state, the planned path trajectory is regenerated.

3. The early warning and protection method for automatic parking assistance according to claim 2, characterized in that, The method further includes: The emergency stop status of the vehicle is lifted when the driver takes over the vehicle or receives a regenerated planned route trajectory.

4. The early warning and protection method for automatic parking assistance according to claim 1, characterized in that, After controlling the vehicle to enter an emergency stop state, the method further includes: Based on the vehicle's real-time position, real-time speed, and direction of travel, a re-predicted kinematic path is generated within a predetermined future time period using a vehicle kinematics model. Predict whether there are obstacle points within the vehicle body model when the vehicle is traveling on the re-predicted kinematic path; Based on the vehicle's real-time location, detect whether the distance between the vehicle and the obstacle point has increased; If there are no obstacles within the vehicle's model and the distance between the vehicle and the obstacle increases, the vehicle's emergency stop state is lifted.

5. The early warning and protection method for automatic parking assistance according to any one of claims 1-4, characterized in that, The warning sensitivity can be adjusted based on one or more of the following: The boundary expansion dimensions of the vehicle expansion model compared to the vehicle body model; The number of path points between the pre-aiming point and the current target path point; The length of the predetermined time period.

6. The early warning and protection method for automatic parking assistance according to any one of claims 1-4, characterized in that, The method further includes: Predict whether there are obstacle points within the vehicle expansion model when the vehicle passes through the multiple planned path points, and send a prompt message to the vehicle driver if there are obstacle points.

7. The early warning and protection method for automatic parking assistance according to any one of claims 1-4, characterized in that, The execution frequency of generating kinematic paths for a predetermined time period based on vehicle kinematics models is greater than or equal to 30Hz and less than or equal to 100Hz.

8. The early warning and protection method for automatic parking assistance according to any one of claims 1-4, characterized in that, The vehicle's real-time speed is calculated based on the pulse values ​​measured by wheel speed pulse meters installed on the rear wheels of the vehicle.

9. The early warning and protection method for automatic parking assistance according to any one of claims 1-4, characterized in that, The vehicle's initial position is determined based on the vehicle's position, speed, and direction of travel when the automatic parking assist function is activated.

10. A warning and protection device for automatic parking assistance, characterized in that, The device includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the warning and protection method for automatic parking assistance as described in any one of claims 1 to 9.

Images