CN114684111A

CN114684111A - Parking method, device and system with vehicle head entering first

Info

Publication number: CN114684111A
Application number: CN202110641541.2A
Authority: CN
Inventors: 袁峻; 沈玉杰
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2020-12-31
Filing date: 2021-06-09
Publication date: 2022-07-01
Also published as: WO2022142592A1

Abstract

The application discloses a parking method, device and system with a vehicle head entering first, which are used for efficiently and accurately completing parking. The method comprises the following steps: collecting parking data, wherein the parking data comprises part or all of vehicle pose information, obstacle position information, target parking space information and passable area position information; estimating a driving direction based on the parking data, and determining at least one parking unit; determining the parking track of each parking unit in sequence by adopting a stepping algorithm to obtain at least one initial parking track; determining an evaluation value of each initial parking track based on the pose of the vehicle at the end point of the initial parking track, and determining an optimal parking track according to the evaluation values; and parking according to the optimal parking track. According to the method, the stepping algorithm is adopted for parking track planning, the track searching time can be effectively shortened, the parking track with high reliability can be generated efficiently and quickly, the planning time consumption is short, and the real-time requirement is met.

Description

Parking method, device and system with vehicle head entering first

The present application claims priority from the chinese patent application entitled "a method, apparatus, and system for parking with a vehicle front in" filed by the chinese patent office at 31/12/2020, application number 202011633813.6, which is incorporated herein by reference in its entirety.

Technical Field

The invention relates to the technical field of automobiles, in particular to a parking method, a parking device and a parking system with a vehicle head entering first.

Background

In the case of a limited parking space, it has been a problem for the driver how to park the vehicle quickly and easily. Particularly, when the vehicle is parked in the parking space in a mode that the vehicle head is first put in, due to factors such as large vehicle body yaw, limited driver vision and the like in the process of forward turning of the vehicle, the vehicle can be smoothly parked in the parking space by frequently adjusting and planning for many times, and even in the parking process, the vehicle can be scratched by other vehicles due to improper parking.

In conclusion, the parking difficulty coefficient is higher by means of the mode that the vehicle head enters first at present, the time consumption of the parking process is longer, and the success rate is lower.

Disclosure of Invention

The application provides a parking method, device and system with a vehicle head entering first, which are used for efficiently and accurately completing vehicle head entering first parking.

It should be understood that the parking method with the vehicle head entering first provided in the embodiment of the present application may be a parking device with the vehicle head entering first.

The parking system with the vehicle head entering first comprises a collecting device, a processing device and an executing device.

The processing device may be a server with a processing function, for example, a central processing unit, or may be a processing chip in the server, and the embodiment of the present application is not limited in particular.

It should be understood that the collecting device provided in the embodiments of the present application is various, and may be a single device or a combination of at least two devices. May include camera devices, radar devices, sensing devices, etc.

In a possible implementation manner, the acquisition device in the embodiment of the present application may be integrated in the vehicle, or may be a device capable of communicating with the vehicle. For example, the collection device is a Road Side Unit (RSU).

In a first aspect, an embodiment of the present application provides a parking method with a vehicle head entering first, including:

collecting parking data, wherein the parking data comprises part or all of vehicle pose information, obstacle position information, target parking space information and passable area position information; estimating a driving direction based on the vehicle pose information and the target parking space information, and determining at least one parking unit; determining the parking track of each parking unit in sequence by adopting a stepping algorithm to obtain at least one initial parking track; determining an evaluation value of each initial parking track in the parking unit based on the pose of the vehicle at the end point of the initial parking track, and determining an optimal parking track from the at least one initial parking track according to the evaluation value; and carrying out vehicle head entering type parking according to the optimal parking track.

Based on the method, the parking track is planned by adopting a stepping algorithm, so that the track searching time can be effectively reduced, the parking track with high reliability can be generated efficiently and quickly, the planning time consumption is short, and the real-time requirement is met. In addition, the optimal parking track is selected from the obtained at least one parking track for parking, so that the success rate of parking and warehousing can be effectively improved.

In one possible implementation manner, based on the parking data and the initial pose of the parking unit, a stepping algorithm is adopted to sequentially determine the parking trajectory of each parking unit, so as to obtain at least one initial parking trajectory.

In a possible implementation manner, determining the sum of the transverse deviation of the center of the vehicle head and the center of the rear axle of the vehicle and the angle deviation value of the central axis of the vehicle body and the parking space according to the pose of the vehicle at the end point of the initial parking track; and determining an evaluation value corresponding to the initial parking track according to the sum of the transverse deviation of the vehicle head center and the rear axle center and the angle deviation value of the vehicle body and the parking space central axis.

Based on the method, the embodiment of the application provides a method for determining an optimal parking trajectory, namely, according to the sum of the transverse deviations of the vehicle head center and the rear axle center and the angle deviation value of the vehicle body and the central axis of the parking space, an evaluation value corresponding to the initial parking trajectory is determined, and then the initial parking trajectory with the minimum evaluation value is determined as the optimal initial parking trajectory.

In a possible implementation manner, in the process of performing the vehicle-head-first-entry parking according to the optimal parking trajectory, after determining that the vehicle has a risk of colliding with the obstacle and can replan the parking route for obstacle avoidance, replan the parking route, and performing the vehicle-head-first-entry parking according to the newly planned parking route.

Based on the method, the embodiment of the application provides a processing scheme for meeting obstacles in the actual parking process.

In a possible implementation manner, after the vehicle runs to the end point of the optimal parking track, a target turning angle of a front wheel of the vehicle is determined; and after the front wheels of the vehicle are adjusted to the target turning angle, the vehicle is parked with the head entering.

In a possible implementation manner, whether the vehicle can drive into the parking space by adjusting the angle of the front wheel is determined according to the vehicle pose of the current position and the position of the target parking space.

In a possible implementation manner, determining an actual pose of a vehicle at a current position and a target pose corresponding to the current position in the optimal parking track; determining a parking error according to the actual pose and the target pose; and adjusting the pose of the vehicle according to the parking error.

Based on the method, when the parking and warehousing are carried out, the error adjustment is carried out, the success rate of the parking and warehousing can be higher, and the parking position of the vehicle is more standard after the parking and warehousing.

In a possible implementation manner, a first rotation angle of a front wheel of the vehicle and a safe rotation angle of the front wheel are determined according to the pose of the current position of the vehicle and the position of the target parking space; and determining the intersection of the first corner and the front wheel safety corner as a target corner for front wheel adjustment of the vehicle.

Based on the method, when the front wheel steering angle is determined, safety protection is conducted, and the process of parking and warehousing is safer.

In a second aspect, embodiments of the present application further provide a parking device with a front-end entry, which may be used to perform the operations in the first aspect. For example, the apparatus may comprise means or elements for performing the respective operations in the first aspect or any possible implementation manner of the first aspect. Including for example an acquisition module and a processing module.

In a third aspect, an embodiment of the present application provides a chip system, including a processor, and optionally a memory; the memory is configured to store a computer program, and the processor is configured to call and run the computer program from the memory, so that the parking device with the chip system installed therein with the vehicle head first enters executes any one of the methods of the first aspect or any possible implementation manner of the first aspect.

In a fourth aspect, embodiments of the present application provide a vehicle, at least one camera, at least one memory, at least one transceiver, and at least one processor;

the camera is used for collecting parking data, and the parking data comprises part or all of data information of vehicle poses, data information of obstacle positions, data information of target parking spaces and data information of positions of passable areas;

the memory is used for storing one or more programs and data information; wherein the one or more programs include instructions;

the processor is used for determining an initial parking track according to the parking data; step-by-step searching is carried out on the initial parking track, and a target parking track is determined; and driving into the target parking space according to the target parking track.

In one possible implementation manner, the vehicle further comprises a display screen and a voice broadcasting device;

the display screen is used for displaying the target parking track;

and the voice broadcasting device is used for broadcasting the target parking track.

The camera in this embodiment of the present application may be a camera of a driver monitoring system, a cabin-type camera, an infrared camera, a driving recorder (i.e., a video recording terminal), a back-up image camera, and the like, and this embodiment of the present application is not limited in particular.

The photographing region of the camera may be an external environment of the vehicle. For example, when the vehicle moves forward, the shooting area is the area in front of the vehicle head; when the vehicle backs, the shooting area is the area behind the tail of the vehicle; when the camera is a 360-degree multi-angle camera, the shooting area may be a 360-degree area around the vehicle, or the like.

The sensor described in the embodiment of the present application may be one or more of a photoelectric/photosensitive sensor, an ultrasonic/acoustic sensor, a distance measurement/distance sensor, a vision/image sensor, and the like.

In a fifth aspect, an embodiment of the present application provides a parking system with a vehicle head entering first, where the system includes a collecting device, a processing device, and an executing device;

the acquisition device is mainly used for acquiring vehicle data, obstacle data, parking space data, passable area data and the like, and mainly comprises an ultrasonic radar and a fisheye camera;

and the processing device is used for processing the data acquired by the acquisition device to obtain the target parking track.

And the execution device is used for parking the vehicle according to the parking instruction issued by the processing device.

In a sixth aspect, an embodiment of the present application provides a computer program product, where the computer program product includes: computer program code for causing said processing means for reporting information to perform any of the methods of the first aspect or any possible implementation manner of the first aspect when said computer program code is run by a computer.

In a seventh aspect, an embodiment of the present application provides a computer-readable storage medium, where a program is stored in the computer-readable storage medium, and the program enables a computer to execute any one of the above-mentioned methods of the first aspect or any possible implementation manner of the first aspect.

Drawings

Fig. 1 is a schematic view of a parking system with a vehicle head entering first according to an embodiment of the present disclosure;

FIG. 2 is a diagram illustrating a first system architecture according to an embodiment of the present application;

FIG. 3 is a diagram illustrating a second system architecture according to an embodiment of the present application;

fig. 4 is a track segmentation schematic diagram of a parking method with a vehicle head entering first according to an embodiment of the present application;

fig. 5 is a schematic flow chart of a parking method with a vehicle head entering first according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a first partial parking trajectory provided by the embodiment of the present application;

fig. 7 is a schematic view of a pose of a target vehicle and an angle of a median line of a target parking space according to an embodiment of the present application;

fig. 8 is a schematic view of a first application scenario provided in the embodiment of the present application;

fig. 9 is a schematic diagram illustrating a parking unit partition according to an embodiment of the present application;

FIG. 10 is a schematic diagram of a connection point between parking units according to an embodiment of the present application;

fig. 11 is a schematic diagram of a first parking unit generating a track according to an embodiment of the present application;

fig. 12 is a schematic flow chart of step-by-step determination of an optimal pose provided in an embodiment of the present application;

fig. 13 is a schematic view of a second application scenario provided in the embodiment of the present application;

fig. 14 is a schematic view of a first vehicle head-in parking device provided in the present application;

fig. 15 is a schematic view of a second vehicle parking device with a front-in vehicle provided by the present application.

Detailed Description

In the case of a limited parking space, it has been a problem for the driver how to park the vehicle quickly and easily. Especially when the vehicle is parked in the parking space in a mode that the vehicle head enters first, due to factors such as large vehicle body yaw, limited driver vision and the like in the process of forward turning of the vehicle, the vehicle can be parked in the parking space smoothly only by frequently adjusting and planning for many times, the parking time is long, and the success rate is low. Even in the parking process, scratch and rub with other vehicles due to improper parking, so that economic loss and the like are caused.

In order to solve the problem, the embodiment of the application provides a parking method and device with a vehicle head entering first, so as to provide an efficient, convenient and accurate parking scheme with the vehicle head entering first.

The technical scheme of the embodiment of the application can be applied to various vehicle-mounted systems, wherein in the embodiment of the application, a track with simple planning action and optimal pose adjustment is found by adopting a stepping searching method according to the collected vehicle information, the surrounding environment information and the parking space information in the process of parking the vehicle head first. In addition, in the embodiment of the application, when the vehicle drives into the parking space, the position and the size of the parking space are continuously detected, the parking space information is fed back in real time, the reasonable and safe front wheel steering angle is output, the error is corrected, and the parking precision is improved.

In order to facilitate understanding of the embodiments of the present application, the embodiments of the present application provide a parking system for vehicle head-in, and as shown in fig. 1, the hardware devices of the parking system include an ultrasonic radar 100 (e.g., a 12-way ultrasonic radar), a camera 110 (e.g., a four-way fisheye camera), an image processor 120, a CPU130, and a controller 140.

The ultrasonic radar 100 is mainly responsible for collecting distance information between obstacles around a vehicle body and the vehicle.

The camera 110 is mainly responsible for acquiring images of the environment around the vehicle body.

The image processor 120 is mainly responsible for completing parking space recognition, obstacle recognition, passable area recognition and the like from the image data.

The CPU130 is mainly responsible for module scheduling, receiving of ultrasonic radar data, image processing data, completion of data information fusion, determination of a planning scheme, generation and output of a planning instruction, and the like.

According to an optional solution of the embodiment of the present application, when the vehicle is driven artificially, the CPU130 may send a planning instruction to a vehicle display screen to prompt a driver how to operate the vehicle.

In another optional aspect of the embodiment of the present application, when the vehicle is automatically driven, the CPU130 may send a planning instruction to the controller, so that the controller controls the vehicle to move, and the vehicle is automatically parked.

And the controller 140 is used for controlling the vehicle to move according to the planning instruction of the CPU, so that the vehicle can be automatically parked.

Further, a system architecture formed by the hardware devices according to the embodiment of the present application may be specifically divided into an acquisition system, a processing system, and an execution system, as shown in fig. 2.

The acquisition system in the embodiment of the application mainly comprises an ultrasonic radar and a fisheye camera and is used for acquiring vehicle data, obstacle data, parking space data, passable area data and the like.

The processing system described in the embodiment of the present application, as shown in fig. 3, may be further divided into an identification monitoring layer and a decision planning layer.

In an optional mode of the embodiment of the application, the recognition monitoring layer mainly performs vehicle/pedestrian recognition on an image acquired by the fisheye camera through the image processor, and performs passable region recognition; monitoring the distance of the obstacle according to the data acquired by the ultrasonic radar; and the parking space recognition is carried out by combining a fisheye camera and an ultrasonic radar.

In an optional mode of the embodiment of the application, the decision planning layer mainly processes the information obtained by the identification and monitoring layer through a CPU to obtain the parking path plan.

The execution system in the embodiment of the application mainly comprises a controller, and is used for parking the vehicle according to the parking instruction issued by the processing system.

Further, the parking indication according to the embodiment of the present application includes, but is not limited to, the following: a vehicle longitudinal control indication and a vehicle transverse control indication.

The vehicle control may be divided into a vehicle longitudinal control, for example, a vehicle speed control, and a vehicle lateral control, for example, a vehicle steering wheel rotation angle control, a gear, and the like.

The system architecture and the service scenario described in the embodiment of the present application are for more clearly illustrating the technical solution of the embodiment of the present application, and do not limit the technical solution provided in the embodiment of the present application. Further, as can be known by those skilled in the art, with the evolution of vehicle architecture and the emergence of new service scenarios, the technical solution provided in the embodiments of the present application is also applicable to similar technical problems. It should be understood that fig. 1 to 3 are simplified schematic diagrams that are merely illustrated for ease of understanding, and that other devices or other unit modules may also be included in the system architecture.

In the embodiment of the present application, the parking process by means of the manner of entering the vehicle head first can be divided into two parts, that is, the parking trajectory that the vehicle head enters first can be understood as being divided into two sections.

Illustratively, as shown in fig. 4, the first partial trajectory is the AB segment trajectory shown in fig. 4, and the second partial trajectory is the BC segment trajectory shown in fig. 4. The point A is a starting point position of parking of a target vehicle in a manner that a vehicle head enters first; the point B is the position of the target vehicle after the head of the target vehicle is adjusted to deviate from the target parking space by a threshold angle, and at the moment, the head of the target vehicle is between the tail of the target vehicle and the target parking space; the point C is a parking position of the target vehicle after being parked in the parking space in the embodiment of the application, that is, an end point of the whole parking track.

Next, as shown in fig. 5, based on the two parking trajectories described above, the flow of the parking method with the vehicle head first entering described in the embodiment of the present application is described.

A first part: the first partial trajectory (i.e., the AB segment trajectory) of parking is performed by head-first entry.

And S500, collecting parking data by a collecting device in the vehicle.

In the embodiment of the present application, the parking data includes part or all of the following:

data information of vehicle position, data information of obstacle position, data information of parking space, data information of passable area position and the like.

For example, the parking data includes a location of a target vehicle (i.e., a vehicle that needs to be parked), a size and a position of a target parking space, a position and a size of a passable area around the target vehicle, a position of an obstacle around the target vehicle, a distance from the target vehicle, and the like.

The acquisition device includes, but is not limited to, a camera device, a sensing device, ultrasonic waves, radar, and the like.

S501, the collecting device in the vehicle sends the parking data to a processing device in the vehicle.

S502, a processing device in the vehicle obtains at least one first partial track through a step algorithm according to the parking data.

For example, it is assumed that the processing device in the embodiment of the present application obtains 3 first partial trajectories, i.e., 3 AB segment trajectories, shown in fig. 6 by a step-by-step algorithm according to the parking data.

S503, the processing device in the vehicle determines the evaluation value of each first partial track.

In an alternative manner, the evaluation value of the first partial track may be determined in the following manner.

Firstly, selecting one AB section track from at least one obtained AB section track, simulating the running of a target vehicle along the AB section track, and acquiring the simulated pose of the target vehicle at a point B after the target vehicle runs to the point B.

Then, according to the simulated pose of the target vehicle at the point B of the AB track, as shown in fig. 7, the sum of the lateral deviations of the front center and the rear axle center of the target vehicle at the point B (i.e., angle 1+ angle 2 in fig. 7) and the angular deviation of the body of the target vehicle from the central axis of the parking space (i.e., angle 2 in fig. 7) are determined.

And finally, determining the evaluation value of the AB track according to the sum of the transverse deviation of the head center and the rear axle center of the target vehicle at the point B and the angular deviation of the body of the target vehicle and the central axis of the parking space.

And S504, determining the first partial track with the minimum evaluation value as the target parking track by the processing device in the vehicle.

And S505, the vehicle runs according to the target parking track.

Optionally, the processing device in the vehicle determines a parking planning scheme according to the target parking trajectory, and generates a parking instruction. And the processing device in the vehicle sends the parking instruction to the vehicle execution device. The parking instruction comprises a target speed, a gear, a steering wheel rotation angle and the like. And the execution device in the vehicle runs according to the parking instruction.

And S506, judging whether the vehicle has the risk of collision with the obstacle or not in the parking process according to the target parking track, if so, executing S507, and if not, executing S508.

In an optional mode of the embodiment of the application, during the parking process according to the parking instruction, the execution module continues to acquire data of the surrounding environment of the target vehicle by using the acquisition device in the vehicle and uploads the data to the processing device in the vehicle; and the processing device in the vehicle analyzes and judges whether the target vehicle has the risk of colliding with the obstacle according to the received surrounding environment data from the acquisition device.

And S507, judging whether obstacle avoidance can be realized through re-planning by the processing device in the vehicle according to the pose of the current target vehicle, if so, executing S502, and if not, executing S509.

And S508, the control module in the vehicle reaches the end point of the target parking track according to the target parking track, and continues to execute S512.

And S509, the target vehicle stops to wait for the obstacle to leave, and the step continues to be executed to S508.

S510, determining whether the vehicle is overtime or not by a processing device in the vehicle, and if yes, executing S511; if not, go to S509.

And S511, stopping parking.

A second part: and carrying out a second part of parking tracks in a mode that the vehicle head enters first.

And S512, judging whether the head of the vehicle can drive into the parking space by the processing device in the vehicle, if so, executing S513, and if not, executing S514.

In an optional mode in the embodiment of the application, the acquisition device in the vehicle acquires the current position information of the vehicle, the distance information between the vehicle and the target parking space and the like, and uploads the acquired information to the processing device of the vehicle. And the processing device in the vehicle determines whether the vehicle can drive into the parking space by adjusting the angle of the front wheel according to the information uploaded by the acquisition device.

And S513, driving the vehicle into a parking space after error adjustment is carried out by the control device in the vehicle, and finishing parking.

In an optional manner of this embodiment of the application, after determining that the target vehicle can enter the parking space, the control device may further control the execution device to perform closed-loop error dynamic trajectory forward/backward adjustment, in order to effectively ensure that the vehicle can enter the parking space safely and accurately.

And S514, enabling a control device in the vehicle to enter a parking space by reversing back and forth to adjust the pose.

In order to show the technical solutions provided by the present application more clearly, the parking method with a vehicle head entering first provided by the present application is described below by embodiments.

It should be noted that the following description is only an exemplification of the technical solutions provided in the present application, and does not limit the technical solutions provided in the present application, and any means for solving the technical problems of the present application obtained by combining and modifying the following embodiments is included in the scope of protection of the present application.

The scheme of the embodiment of the present application is described in stages with reference to the scenario shown in fig. 8.

For example, assume that the target vehicle is a vehicle a in a current parking scene, and there is an obstacle 1 (e.g., a pedestrian) 5 meters ahead of the target vehicle a. And a target parking space A is arranged below the target vehicle A, wherein the target parking space A is between the parking space 1 and the parking space 2, the vehicle 1 is parked in the parking space 1, and the vehicle 2 is parked in the parking space 2.

Phase one, parking data acquisition

The module is specifically used for receiving parking data from cameras, ultrasonic radars, sensors and other acquisition devices.

Illustratively, in the scene, the stage mainly identifies parking spaces existing in the environment, namely a target parking space A, through the camera and the ultrasonic radar data; recognizing objects and positions of vehicles/pedestrians and the like existing in the environment, namely an obstacle 1, through camera data; passable areas in the environment, i.e. diagonal areas in fig. 8, are identified by the camera and the ultrasonic radar data.

For example, in the parking data acquisition phase of the vehicle, the acquired parking data information is as follows:

(1) parking space information:

equation 1: slot ═ P₁,P₂,P₃,P₄}

Where Slot denotes the target vehicle, P₁Represents the coordinates of the upper left corner of the parking space P₂Represents the coordinate of the upper right corner of the parking space, P₃Represents the coordinates of the lower left corner of the parking space, P₄And the coordinates of the lower right corner of the parking space are represented.

(2) Pedestrian/vehicle targets:

equation 2: object is { Object }₁,Object₂,...,Object_n}；Object＝{P₁,P₂,P₃,P₄}

Wherein Objects represents a pedestrian, Object₁Representing the coordinates of the upper left corner of the pedestrian, Object₂Representing the coordinates of the upper right corner of the pedestrian, Object₃Representing the coordinates of the lower left corner of the pedestrian, Object₄Representing the pedestrian's lower right corner coordinates.

Wherein Object represents other vehicle, P₁Represents the coordinates of the upper left corner of the parking space P₂Represents the coordinate of the upper right corner of the parking space, P₃Represents the coordinates of the lower left corner of the parking space, P₄And the coordinates of the lower right corner of the parking space are represented.

(3) Passable area:

equation 3: freespace ═ P₁,P₂,P₃,...,P_n}

Wherein Freespace represents the passable area, P₁,P₂,P₃,...,P_nRepresenting the passable area coordinates.

Stage two, aiming at generation and tracking of first part of track in parking process

And obtaining an optimal track according to the parking data information.

In an optional manner of this embodiment of the application, after the parking data information is sent to a processing device in a vehicle, a processing process executed in the processing device may be as follows:

after the acquisition device in the target vehicle acquires parking data, the processing device in the target vehicle can determine the general trend of the vehicle in the parking process and the parking area according to the parking data.

Furthermore, the target vehicle according to the embodiment of the present application may divide the parking process into at least one parking unit according to the approximate vehicle heading and the parking area during the parking process.

For example, assuming that the target vehicle is parked with the target slot on the right side of the host vehicle, the general direction of the vehicle is as shown in fig. 9 (a). Then, the parking process may be divided into 4 parking units, for example, the first parking unit of the parking process is shown as (b) in fig. 9, the second parking unit of the parking process is shown as (c) in fig. 9, the third parking unit of the parking process is shown as (d) in fig. 9, and the fourth parking unit of the parking process is shown as (e) in fig. 9. The planned trajectory of the first parking unit to the third parking unit is the AB section trajectory, and the planned trajectory of the fourth parking unit is the BC section trajectory.

In the embodiments of the present application, there are various ways for determining the approximate direction of the vehicle during parking and for dividing the parking units during parking, and the embodiments of the present application are not limited thereto. For example, the present embodiment may determine the approximate direction of the parking process and the parking unit during the parking process according to the prior trajectory model during the previous parking process. Wherein the prior trajectory model is derived from geometric analysis and a plurality of experimental proofs.

Further, the processing means in the vehicle may perform parking trajectory planning on a per parking unit basis. That is, the entire parking trajectory during parking is composed of several parking unit trajectories.

In an optional manner of the embodiment of the present application, the processing device in the vehicle generates the trajectory in each parking unit by using a step-by-step algorithm.

It is understood that a section of track of the vehicle may include a straight track and a circular track during the driving process, and therefore, the track in the parking unit in the embodiment of the present application may be understood as being composed of a plurality of straight tracks and/or a plurality of circular tracks.

Wherein both the circular arc and the straight line play an important role in the parking unit trajectory. For example, the circular arc has the function of flexibly adjusting the direction of the bicycle; the straight line is used for adjusting the position of the vehicle on one hand and smoothly connecting two sections of circular arcs on the other hand, so that the system can track the generated track more easily.

It should be noted that, in the embodiment of the present application, only a straight-line trajectory or only an arc trajectory may exist in the minimum parking unit, and the sequence of the arc trajectory and the straight-line trajectory is not limited in the embodiment of the present application, and any manner capable of combining the arc trajectory and the straight-line trajectory is applicable to the embodiment of the present application.

In the embodiment of the present application, when determining the trajectory of the parking unit, as shown in fig. 10, the first parking unit uses point a as a calculation starting point, and then determines the parking trajectory in the first parking unit according to a step-by-step algorithm, and obtains a trajectory end point in the first parking unit, for example, point Q1 is the end point of the trajectory of the first parking unit.

Further, the second parking unit uses the end point of the parking trajectory planned in the first parking unit (i.e., Q1) as the starting point of the parking trajectory planning in the second parking unit, then determines the parking trajectory in the second parking unit according to the step-by-step algorithm, and obtains the end point of the trajectory in the second parking unit, for example, point Q2 is the end point of the trajectory of the second parking unit. And the like until the whole parking trajectory is planned.

That is, when the stepwise route determination is performed, each time the starting point of the stepwise route is the route end point obtained in the last stepwise route.

For convenience of understanding, the present embodiment of the application assumes that each parking unit trajectory is composed of a straight line trajectory and an arc trajectory, and the straight line trajectory precedes the arc trajectory, and introduces the content of determining the parking unit trajectory in a stepwise manner:

assuming that the pose information of the starting pose after each stepping algorithm is performed is as follows:

equation 4: position_{Vehicle with wheels}＝{x_{Vehicle with a detachable front cover}，y_{Vehicle with wheels}，θ_{Vehicle with wheels}}。

For a straight track, the step length of each step is d_{step_line}Then the step sizes in the x and y directions are:

equation 5:

in the process of searching the linear track, the end position and pose after each stepping algorithm is updated as follows:

equation 6:

further, after the vehicle completes the linear threshold number of steps, a linear trajectory is generated as shown in fig. 11 (a).

For the circular arc track, in order to simplify calculation and meet the requirement of finishing the adjustment of the direction of the vehicle by the simplest track, the minimum turning radius of the vehicle is taken as the fixed turning radius r of the circular arc track, and then the position of the center of the circular arc track can be calculated according to the current position of the vehicle:

equation 7:

wherein, equation 8:

in the process of track searching, the step length of the circular arc is d_{step_arc}Then the step length of the corner is:

equation 9: theta_{step_arc}＝d_{step_arc}/r。

Therefore, in the arc track searching process, the end point pose after each stepping algorithm is updated as follows:

equation 10:

wherein, equation 11:

further, after the vehicle completes the straight-line threshold number of steps, an arc trajectory is generated as shown in fig. 11 (b).

The angle in the formula in the embodiment of the application is variable, and when the linear track is generated, a plurality of linear tracks can be generated by adjusting the angle. When generating the arc trajectory, a plurality of arc trajectories may be generated by adjusting the angle, and thus, at least one parking unit trajectory may be obtained in each parking unit.

It should be noted that, in the embodiment of the present application, the value range of the angle may be determined according to the existing manner, and the embodiment of the present application is not limited.

By adding the stepping search algorithm into the parking track model, the track search time can be greatly reduced on the premise of ensuring high-quality and simple search results, the tolerance to the sensing error at a far position is high, and when the vehicle approaches an obstacle, the vehicle can make a rapid and reasonable re-planning strategy according to sensing detection with higher precision.

Further, as shown in fig. 12, an embodiment of the present application provides a flowchart for determining an optimal pose step by step for each parking unit, as follows:

it is assumed that the parking trajectory in the parking unit is determined by a straight trajectory and an arc trajectory, and the straight trajectory is executed first.

S1200, determining a linear stepping step length for generating a linear track.

S1201, selecting a first angle for linear track stepping, and generating a linear track according to the first angle and the linear stepping step length.

S1202, whether the generated linear track has the risk of collision with an obstacle or not is determined, if yes, S1203 is executed, and if not, S1204 is executed.

And S1203, returning to the parking unit trajectory planning starting point, replacing the first angle, stepping the straight trajectory again, and continuing to execute S1202.

And S1204, determining whether the linear stepping times for stepping the linear track is reached, if so, executing S1205, and if not, executing S1201.

And S1205, determining the arc stepping step length for generating the arc track.

And S1206, selecting a second angle for arc track stepping, and generating a section of arc track according to the second angle and the arc stepping step length.

S1207, determining whether the generated arc track has the risk of collision with an obstacle or not, if so, executing S1208, and if not, executing S1209.

And S1208, retreating to the starting point of the previous step circular arc track, replacing the second angle, repeating the circular arc track stepping, and continuing to execute S1207.

S1209, determining whether the arc track is reached and the number of arc stepping times for stepping is reached, if yes, executing S1210, and if not, executing S1206.

S1210, finishing the track generation of the unit.

Further, in the embodiment of the present application, the obtained first parking unit trajectory, the second parking unit trajectory, and the third parking unit trajectory are connected by the step-by-step algorithm, and then the first partial parking trajectory is obtained.

Stage three, pose evaluation

In the embodiment of the application, after the second-stage trajectory generation and tracking are completed, at least one first partial parking trajectory is obtained. Then, at this stage, the trajectory evaluation is performed on the obtained at least one first partial parking trajectory, so as to obtain an evaluation (cost) value corresponding to each first partial trajectory, and the quality of each first partial trajectory is judged according to the size of the cost.

The embodiment of the application provides an optional mode, and when pose evaluation is performed, evaluation can be performed by combining the following two aspects:

in the first judgment aspect: sum of transverse deviations (e) of the center of the head and the center of the rear axle_{rear_distance}+e_{front_distance})；

In the first evaluation aspect, the vehicle head center and the rear axle center are the vehicle head center and the rear axle center corresponding to the target vehicle when the target vehicle is simulated at the route end point planned by the third parking unit.

And a second evaluation aspect: and the angle deviation between the vehicle body and the central axis of the parking space.

And the central axis of the vehicle body and the parking space in the second evaluation aspect is the central axis of the vehicle body and the parking space corresponding to the target vehicle when the target vehicle is simulated at the route end point planned by the third parking unit.

Illustratively, the specific formula for determining the evaluation value (cost) is as follows:

equation 12: cost ═ 1.0+ k₁×(e_θ)²)×(1.0+k₂×(e_{rear_distance}+e_{front_distance})²)

Wherein k is₁And k₂The angular deviation and the lateral deviation, respectively, account for the weight of the loss function.

Further, in the embodiment of the present application, after determining the evaluation value for at least one first partial parking trajectory generated in the second phase, the first partial parking trajectory with the smallest evaluation value is determined as the optimal parking trajectory. Namely, the trajectory whose evaluation value is the smallest is determined as the target parking trajectory employed in the process of parking the vehicle.

Stage four, dynamically fine-tuning the trajectory

In the fourth stage of the embodiment of the application, it is mainly determined whether the target vehicle can drive into the parking space at the pose of the end point (i.e., point B) of the target parking trajectory after the target vehicle drives according to the target parking trajectory obtained in the third stage.

When the processing device in the vehicle determines that the head of the vehicle can not be detected into the target parking space according to the data information acquired by the acquisition device, the pose can be adjusted through a plurality of arc curves. And when the processing device in the vehicle determines that the head of the vehicle can be inserted into the parking space according to the data information acquired by the acquisition device, starting dynamic fine tuning planning.

Furthermore, due to various error factors such as parking space detection errors, positioning errors, planning errors and control errors, when a vehicle enters a parking space, a large error still exists between the vehicle and a target position, and therefore dynamic adjustment type planning needs to be performed according to the position of the vehicle, and the parking position of the vehicle in the parking space is more standard.

Therefore, in an optional mode of the embodiment of the invention, a closed-loop error planning mode is adopted, and the front wheel rotation angle is determined directly according to the error existing between the pose of the self-vehicle and the pose of the target.

According to the embodiment of the application, the pose error is determined by the pose of the self-vehicle and the pose of the target through the dynamic fine adjustment, the control instruction is directly generated according to the determined pose error, the closed loop effect is the fastest, and the problem that the closed loop response is not timely in the process from the intention of error elimination to the track generation to the track tracking is solved.

In an optional mode of the embodiment of the application, in the dynamic fine tuning stage, the dimension selected when the pose of the host vehicle and the pose of the target parking space are determined to have errors is the same as the dimension considered in the pose evaluation in the stage three.

Namely, the sum (e) of the transverse deviation of the center of the head of the vehicle and the center of the rear axle is adopted_{rear_distance}+e_{front_distance}) And determining the error between the vehicle and the target parking space by the angular deviation of the central axis of the vehicle body and the parking space. For example, the model adopted by the closed-loop error planning performed in the embodiment of the present application is assumed to be the following closed-loop control PID model.

Equation 13:

and taking the sum of the transverse deviation of the center of the head and the center of the rear axle and the angular deviation of the central axis of the vehicle body and the parking space as e (t), and substituting the e (t) into the formula 13 to obtain an error value y between the vehicle and the target parking space.

Further, if safety protection is not considered in planning due to a narrow parking space, only closed-loop error control is used, and the risk of scraping obstacles beside the parking space exists.

Therefore, according to an optional mode of the embodiment of the application, when the front wheel steering angle is determined according to the error existing between the parking position and the target position, the safety protection constraint can be carried out on the output front wheel steering angle.

Specifically, according to the embodiment of the application, before a control command is generated according to the determined front wheel steering angle, safety protection constraint is performed on the front wheel steering angle. Thus, the trajectory indicated by the obtained control command can be made safer.

An optional mode of the embodiment of the present application provides a method for calculating safety protection constraints on front wheel steering angles, where:

illustratively, when the self-vehicle drives into the parking space, in order to avoid collision between the self-vehicle and obstacles on two sides of the parking space, the adjustment range of the front wheel steering angle needs to be restricted.

Assuming that the maximum front wheel steering angle of the self-vehicle is max _ front _ wheel _ angle, the front wheel steering angle ranges from [ -max _ front _ wheel _ angle, max _ front _ wheel _ angle ], turning left positive and turning right negative.

As shown in fig. 13, line segment V₀V₁And a line segment S₂S₃Is distance of₁Line segment V₂V₃And a line segment S₀S₁Is distance of₂。

To ensure the line segment V₂V₃And a line segment S₀S₁Keeping a minimum distance larger than min _ obstacle _ distance limits the amplitude of the right turn of the bicycle, i.e. limits the minimum value of the rotation angle of the output front wheel. The following equation 14 is given:

min_angle＝-max_front_wheel_angle×min(max(distance₂-min_obstacle_distance,0)×k,1.0)

the larger k is, the faster steering speed of the vehicle is needed, and the space can be used more flexibly to correct the position of the vehicle.

Furthermore, as can be seen from the formula, when distance₂The smaller, the larger min _ angle, when distance₂When the distance is less than or equal to min _ obstacle _ distance, min _ angle can only take 0, namely the self-vehicle can only move forwards along a straight line, thereby avoiding the line segment V₂V₃And a line segment S₀S₁A collision may occur.

To ensure the line segment V₀V₁And a line segment S₂S₃Maintaining a minimum distance greater than min _ obstacle _ distance limits the amplitude of the turn to the left of the vehicle, i.e., limits the maximum value of the output front wheel turning angle.

Considering the limit when distance₂When min _ obstacle _ distance is defined, the distance is guaranteed at the next time₂When the max _ angle is the maximum value, the turning radius OV is ensured₁Perpendicular to S₂S₃。

Wherein, because of S₂S₃The angle of orientation is known, and thus OV is obtained₁Angle of direction, again according to V₁Coordinates, OV can be calculated₁The equation of the straight line of (c).

The line segment OC is the direction that the turning radius of the bicycle is vertical to the posture of the bicycle, so the direction angle of the OC is known, the linear equation of the OC can be calculated according to the coordinate of the C point, namely the position of the bicycle, and the OV is used₁And the OC linear equation is simultaneous, the position of the turning circle center O is calculated, and the radius of the turning circle is as follows:

equation 15:

the front wheel turning angle can be calculated according to the Ackerman steering model as follows:

equation 16:

the maximum value of the front wheel steering angle is the following equation 17:

where k is the distance constraint coefficient.

Furthermore, as can be seen from the formula, when distance₁The smaller the max _ angle, when distance₂When min _ obstacle _ distance is less than or equal to min _ obstacle _ distance, max _ angle is taken as boundary _ angle, namely, the driving guarantee distance of the self vehicle₁Is increased so as to avoid line segment V₀V₁And a line segment S₂S₃A collision may occur.

In conclusion, according to geometric calculation constraints, the horizontal control instruction is safely and efficiently output in the movable space by dynamic fine adjustment.

According to the parking method with the vehicle head entering first, the route is searched step by step in the parking process, the planning track is simplified and effective, the effect of adjusting the vehicle to the optimal entering pose is achieved under the condition that fewer gear switching times and less driving distance are guaranteed, the planning time consumption is short, and the real-time requirement is met.

On the other hand, the invention provides that when the self-vehicle drives into the parking space, further safe and quick fine adjustment is carried out according to more accurate sensing information, the error is quickly converged, and the parking precision is improved.

In the embodiments of the present application, the term "at least one" means one or more, "and the" plurality "means two or more. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone, wherein, A and B can be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. At least one of the following items or the like, refers to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or multiple.

Unless stated to the contrary, the embodiments of the present application refer to the ordinal numbers "first", "second", etc., for distinguishing between a plurality of objects, and do not limit the sequence, timing, priority, or importance of the plurality of objects. Furthermore, the terms "comprising" and "having" in the description of the embodiments and claims of the present application and the drawings are not intended to be exclusive. For example, a process, method, system, article, or apparatus that comprises a list of steps or modules is not limited to only those steps or modules listed, but may include other steps or modules not listed.

Through the above description of the present application, it can be understood that, in order to implement the above functions, the above-described devices include hardware structures and/or software units for performing the respective functions. Those of skill in the art will readily appreciate that the present invention can be implemented in hardware or a combination of hardware and computer software, with the exemplary elements and algorithm steps described in connection with the embodiments disclosed herein. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

As shown in fig. 14, a parking apparatus with a vehicle head first in an embodiment of the present invention includes a processor 1400, a memory 1401, and a transceiver 1402;

the processor 1400 is responsible for managing the bus architecture and general processing, and the memory 1401 may store data used by the processor 1400 in performing operations. The transceiver 1402 is used to receive and transmit data in data communication with the memory 1401 under the control of the processor 1400.

The bus architecture may include any number of interconnected buses and bridges, with one or more processors, represented by processor 1400, and various circuits of memory, represented by memory 1401, linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The processor 1400 is responsible for managing the bus architecture and general processing, and the memory 1401 may store data used by the processor 1400 in performing operations.

The processes disclosed in the embodiments of the present invention may be applied to the processor 1400, or implemented by the processor 1400. In the implementation process, the steps of the parking procedure that the vehicle head enters first may be completed by processing instructions in the form of hardware integrated logic circuits or software in 1400. The processor 1400 may be a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like that implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like.

The steps of a method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 1401, and the processor 1400 reads the information in the memory 1401, and completes the steps of the signal processing flow in combination with the hardware thereof.

In an alternative manner of the present application, the processor 1400 is configured to read a program in the memory 1401 and execute the method flows in S500-S514 shown in fig. 5; or perform the method flows in S1200-S1210 as shown in fig. 12.

As shown in fig. 15, the present invention provides a device for parking with a vehicle head entering first, which includes an acquisition module 1500 and a processing module 1501.

The acquisition module 1500 is configured to acquire parking data, where the parking data includes part or all of vehicle pose information, obstacle position information, target parking space information, and passable area position information;

the processing module 1501 is configured to determine at least one initial parking trajectory by using a step-by-step algorithm according to the parking data; evaluating each initial parking track to determine an optimal initial parking track; determining the optimal initial parking track as a target parking track; and carrying out vehicle head early parking according to the target parking track.

In one implementation, the processing module 1501 is specifically configured to:

dividing the parking process into at least one parking unit; determining the parking tracks of each parking unit in sequence by adopting a stepping algorithm to obtain at least one initial parking track; wherein the track end point in the previous parking unit is the track start point of the next parking unit.

determining the pose of the vehicle at the end point of each initial parking track;

and evaluating the initial parking track according to the pose to determine an optimal initial parking track.

determining the sum of the transverse deviation of the center of the head of the vehicle and the center of a rear axle of the vehicle and the angle deviation value of the central axis of the body of the vehicle and the parking space according to the position and posture of the vehicle at the end point of the initial parking track;

determining an evaluation value corresponding to an initial parking track according to the sum of the transverse deviation of the center of the vehicle head and the center of the rear axle and the angular deviation value of the central axis of the vehicle body and the parking space;

and determining the initial parking track with the minimum evaluation value as an optimal initial parking track.

In one implementation, the processing module 1501 is further configured to:

when the vehicle parks according to the target parking track, judging whether a parking route can be re-planned for avoiding the obstacle after determining that the risk of collision with the obstacle exists;

if so, replanning the parking route, and parking according to the newly planned parking route; if not, within the threshold duration, after waiting for the obstacle to leave, continuing to park according to the target parking track.

In one implementation, the processing module 1501 is further configured to:

after the vehicle runs to the end point of the target parking track, determining whether the vehicle can drive into a parking space at the current position;

if yes, determining a target turning angle of a front wheel of the vehicle, and driving the vehicle into a parking space; if not, the parking route is planned again.

and determining whether the vehicle can drive into the parking space by adjusting the angle of the front wheel according to the vehicle pose of the current position and the position of the target parking space.

In one implementation, the processing module 1501 is further configured to:

determining the actual pose of the vehicle at the current position and the target pose corresponding to the current position in the target parking track;

determining a parking error according to the actual pose and the target pose;

and adjusting the pose of the vehicle according to the parking error.

determining a first turning angle of a front wheel of the vehicle and a safe turning angle of the front wheel according to the pose of the current position of the vehicle and the position of the target parking space;

and determining the intersection of the first corner and the front wheel safety corner as a target corner for front wheel adjustment of the vehicle.

In some possible embodiments, the aspects of the parking method with vehicle headway according to the embodiments of the present invention may also be implemented in the form of a program product including program code for causing a computer device to perform the steps of the parking method with vehicle headway according to the various exemplary embodiments of the present invention described in this specification when the program code is run on the computer device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

A parking program product for head-in according to an embodiment of the present invention may employ a portable compact disk read only memory (CD-ROM) and include program code, and may be run on a server device. However, the program product of the present invention is not limited in this regard and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with a communications transport, apparatus, or device.

A readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the periodic network action system, apparatus, or device.

Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device.

The embodiment of the application also provides a storage medium readable by the computing device aiming at the parking method with the vehicle head entering first, namely, the content is not lost after the power is cut off. The storage medium stores therein a software program comprising program code which, when executed on a computing device, when read and executed by one or more processors, implements any of the above vehicle-ahead parking solutions of the embodiments of the present application.

The present application is described above with reference to block diagrams and/or flowchart illustrations of methods, apparatus (systems) and/or computer program products according to embodiments of the application. It will be understood that one block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, and/or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer and/or other programmable data processing apparatus, create means for implementing the functions/acts specified in the block diagrams and/or flowchart block or blocks.

Accordingly, the subject application may also be embodied in hardware and/or in software (including firmware, resident software, micro-code, etc.). Furthermore, the application may take the form of a computer program product on a computer-usable or computer-readable storage medium having computer-usable or computer-readable program code embodied in the medium for use by or in connection with an instruction execution system. In the context of this application, a computer-usable or computer-readable medium may be any medium that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

Various embodiments are described in detail herein with reference to various flow diagrams, but it should be understood that the description of these flow diagrams and their corresponding embodiments is merely exemplary for ease of understanding and is not intended to limit the present application in any way. It is not necessary that each step in the flowcharts be performed, and some steps may be skipped, for example. In addition, the execution sequence of each step is not fixed or limited to that shown in the figures, and the execution sequence of each step should be determined by the function and the inherent logic of each step.

The multiple embodiments described in this application can be executed in any combination or in an intersection of steps, the execution order of each embodiment and the execution order of the steps of each embodiment are not fixed and are not limited to the order shown in the drawings, and the execution order of each embodiment and the intersection of the execution order of each step of each embodiment should be determined by their functions and inherent logic.

Although the present application has been described in conjunction with specific features and embodiments thereof, it will be evident that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and figures are merely exemplary of the present application as defined in the appended claims and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include such modifications and variations.

Claims

1. A parking method with a vehicle head entering first is characterized by comprising the following steps:

collecting parking data, wherein the parking data comprises part or all of vehicle pose information, obstacle position information, target parking space information and passable area position information;

estimating a driving direction based on the vehicle pose information and the target parking space information, and determining at least one parking unit;

determining the parking track of each parking unit in sequence by adopting a stepping algorithm to obtain at least one initial parking track;

determining an evaluation value of each initial parking track in the parking unit based on the pose of the vehicle at the end point of the initial parking track, and determining an optimal parking track from the at least one initial parking track according to the evaluation value;

and parking in a vehicle head-entering mode according to the optimal parking track.

2. The method of claim 1, wherein determining the parking trajectory for each parking unit in turn using a step-wise algorithm to obtain at least one initial parking trajectory comprises:

and sequentially determining the parking track of each parking unit by adopting a stepping algorithm based on the parking data and the initial pose of the parking unit to obtain at least one initial parking track.

3. The method according to claim 1 or 2, wherein determining the evaluation value of each initial parking trajectory in the parking unit based on the pose of the vehicle at the end point of the initial parking trajectory comprises:

determining the sum of the transverse deviation of the center of the vehicle head and the center of a rear axle of the vehicle and the angle deviation value of the vehicle body and the central axis of the parking space according to the position and posture of the vehicle at the end point of the initial parking track;

and determining an evaluation value corresponding to the initial parking track according to the sum of the transverse deviation of the vehicle head center and the rear axle center and the angle deviation value of the vehicle body and the parking space central axis.

4. The method according to any one of claims 1 to 3, wherein vehicle-head-ahead parking is performed according to the optimal parking trajectory, further comprising:

and in the process of carrying out the vehicle-head-first-entering parking according to the optimal parking track, after determining that the vehicle has the risk of collision with the obstacle and can replan the parking route to avoid the obstacle, replan the parking route, and carrying out the vehicle-head-first-entering parking according to the newly-planned parking route.

5. The method according to any one of claims 1 to 4, wherein after the vehicle-head-entering parking according to the optimal parking trajectory, the method further comprises:

determining a target corner of a front wheel of the vehicle after the vehicle runs to the end point of the optimal parking track;

and after the front wheels of the vehicle are adjusted to the target turning angle, the vehicle is parked with the head entering.

6. The method of claim 5, wherein determining the target steering angle for the front wheels of the vehicle before entering the space further comprises:

determining the actual pose of the vehicle at the current position and the target pose corresponding to the current position in the optimal parking track;

determining a parking error according to the actual pose and the target pose;

and adjusting the pose of the vehicle according to the parking error.

7. The method of claim 5 or 6, wherein determining a target steering angle for a front wheel of the vehicle comprises:

8. A parking device with a vehicle head entering first is characterized by comprising:

the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring parking data, and the parking data comprises part or all of vehicle pose information, obstacle position information, target parking space information and passable area position information;

the processing module is used for predicting a driving direction based on the vehicle pose information and the target parking space information and determining at least one parking unit; determining the parking track of each parking unit in sequence by adopting a stepping algorithm to obtain at least one initial parking track; determining an evaluation value of each initial parking track in the parking unit based on the pose of the vehicle at the end point of the initial parking track, and determining an optimal parking track from the at least one initial parking track according to the evaluation value; and carrying out vehicle head entering type parking according to the optimal parking track.

9. The vehicle parking device according to claim 8, wherein the processing module is specifically configured to:

10. The parking device according to claim 8 or 9, wherein the processing module is specifically configured to:

11. The vehicle parking device according to any one of claims 8 to 10, wherein the processing module is further configured to:

12. The vehicle parking device according to any one of claims 8 to 11, wherein the processing module is further configured to:

13. The vehicle of claim 12, wherein the processing module is further configured to:

determining a parking error according to the actual pose and the target pose;

and adjusting the pose of the vehicle according to the parking error.

14. The parking device according to claim 12 or 13, wherein the processing module is specifically configured to:

15. A parking device with a vehicle head entering first is characterized by comprising: one or more processors; a memory; a transceiver;

the processor configured to perform the method of any one of claims 1-7 according to at least one or more programs in the memory.

16. A vehicle, characterized by comprising: at least one camera and/or sensor, at least one memory, and at least one processor;

the camera and/or the sensor are used for collecting parking data, and the parking data comprises part or all of vehicle pose information, obstacle position information, target parking space information and passable area position information;

the processor is used for estimating a driving direction based on the vehicle pose information and the target parking space information and determining at least one parking unit; determining the parking track of each parking unit in sequence by adopting a stepping algorithm to obtain at least one initial parking track; determining an evaluation value of each initial parking track in the parking unit based on the pose of the vehicle at the end point of the initial parking track, and determining an optimal parking track from the at least one initial parking track according to the evaluation value; and parking in a vehicle head-entering mode according to the optimal parking track.

17. A computer-readable storage medium, comprising computer instructions that, when executed on a vehicle front-entry parking device, cause the vehicle front-entry parking device to perform the method according to any one of claims 1 to 7.