WO2022142592A1 - Procédé, dispositif et système de stationnement avant-premier - Google Patents

Procédé, dispositif et système de stationnement avant-premier Download PDF

Info

Publication number
WO2022142592A1
WO2022142592A1 PCT/CN2021/123788 CN2021123788W WO2022142592A1 WO 2022142592 A1 WO2022142592 A1 WO 2022142592A1 CN 2021123788 W CN2021123788 W CN 2021123788W WO 2022142592 A1 WO2022142592 A1 WO 2022142592A1
Authority
WO
WIPO (PCT)
Prior art keywords
parking
vehicle
trajectory
target
initial
Prior art date
Application number
PCT/CN2021/123788
Other languages
English (en)
Chinese (zh)
Inventor
袁峻
沈玉杰
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2022142592A1 publication Critical patent/WO2022142592A1/fr

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/06—Automatic manoeuvring for parking
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles

Definitions

  • the present invention relates to the technical field of automobiles, and in particular, to a method, a device and a system for first-in parking.
  • the difficulty coefficient of parking by the first-in method is relatively high, the parking process takes a long time, and the success rate is low.
  • the present application provides a first-in parking method, device and system for efficiently and accurately completing the first-in parking.
  • the head-first-in parking method provided in the embodiments of the present application may be a head-first-in parking device.
  • the first-in parking system includes a collection device, a processing device, and an execution device.
  • the processing device may be a server with a processing function, for example, a central processing unit, or a processing chip in the server, which is not limited in the specific embodiment of the present application.
  • the collection device provided in the embodiment of the present application has various situations, which may be a single device or a combination of at least two devices. Cameras, radars, sensing devices, etc. may be included.
  • the collection device in this embodiment of the present application may be integrated in the vehicle, or may be a device capable of communicating with the vehicle.
  • the collection device is a roadside unit (RSU).
  • RSU roadside unit
  • an embodiment of the present application provides a first-in parking method, including:
  • the parking data includes vehicle pose information, obstacle position information, target parking space information, and some or all of the passable area position information; based on the vehicle pose information and the target parking space information estimate the driving direction, and determine at least one parking unit; use a step-by-step algorithm to sequentially determine the parking trajectory of each parking unit to obtain at least one initial parking trajectory; based on the vehicle at the end point of the initial parking trajectory determine the evaluation value of each initial parking trajectory in the parking unit, and determine the optimal parking trajectory from the at least one initial parking trajectory according to the evaluation value; according to the optimal parking trajectory Parking trajectory, front-end parking.
  • the step-by-step algorithm is used for parking trajectory planning, which can effectively reduce the trajectory search time, efficiently and quickly generate a highly reliable parking trajectory, with short planning time and meeting real-time requirements.
  • the optimal parking trajectory is selected from the obtained at least one parking trajectory for parking, which can effectively improve the success rate of parking and storage.
  • a step-by-step algorithm is used to sequentially determine the parking trajectory of each parking unit, and at least one initial parking track is obtained. car track.
  • the sum of the lateral deviation between the center of the front of the vehicle and the center of the rear axle, and the angle between the vehicle body and the central axis of the parking space are determined according to the posture of the vehicle at the end point of the initial parking trajectory Deviation value: According to the sum of the lateral deviation between the center of the vehicle front and the center of the rear axle, and the angle deviation between the vehicle body and the center axis of the parking space, the evaluation value corresponding to the initial parking trajectory is determined.
  • an embodiment of the present application provides a method for determining an optimal parking trajectory, that is, according to the sum of the lateral deviations between the center of the vehicle front and the center of the rear axle, and the angle deviation between 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 smallest evaluation value is determined as the optimal initial parking trajectory.
  • the vehicle when it performs the front-end parking according to the optimal parking trajectory, when it is determined that there is a risk of collision with an obstacle, the vehicle can re-plan the parking route for the obstacle. After evading, re-plan the parking route and perform front-end parking according to the newly planned parking route.
  • the embodiments of the present application provide a solution for dealing with obstacles encountered during an actual parking process.
  • the target turning angle of the front wheels of the vehicle is determined; after the vehicle adjusts the target turning angle of the front wheels, the front-end parking is performed. car.
  • the actual pose of the vehicle at the current position and the target pose corresponding to the current position in the optimal parking trajectory are determined; according to the actual pose and the target pose, the parking vehicle error; adjust the pose of the vehicle according to the parking error.
  • the embodiment of the present application performs error adjustment when parking into the garage, which can make the success rate of the parking into the garage higher and the parking position of the vehicle more standardized after the parking into the garage.
  • the first turning angle of the front wheel of the vehicle and the safe turning angle of the front wheel are determined;
  • the intersection of the safe corners is determined as the target corner for the vehicle to perform front wheel adjustment.
  • the embodiment of the present application performs safety protection when determining the turning angle of the front wheel, so that the process of parking and entering the warehouse is safer.
  • an embodiment of the present application further provides a front-end parking device, which can be used to perform the operations in the first aspect.
  • the apparatus may include modules or units for performing various operations in the first aspect or any possible implementation of the first aspect described above.
  • it includes acquisition module and processing module.
  • an embodiment of the present application provides a chip system, including a processor, and optionally a memory; wherein, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the installed The first-in parking device of the chip system performs any method in the first aspect or any possible implementation manner of the first 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 to collect parking data, and the parking data includes data information of vehicle posture, data information of obstacle positions, data information of target parking spaces, and data information of passable area positions. Part or all of the data information ;
  • the memory for storing one or more programs and data information; wherein the one or more programs include instructions;
  • the processor is configured to determine an initial parking trajectory according to the parking data; perform a step-by-step search on the initial parking trajectory to determine a target parking trajectory; drive into the target according to the target parking trajectory parking space.
  • the vehicle further includes a display screen and a voice broadcasting device
  • the display screen for displaying the target parking track
  • the voice broadcasting device is used for broadcasting the target parking track.
  • the camera described in the embodiment of the present application may be a camera of a driver monitoring system, a cockpit camera, an infrared camera, a driving recorder (ie a video recording terminal), a reversing image camera, etc., which are not limited in the specific embodiment of the present application. .
  • the shooting area of the camera may be the external environment of the vehicle.
  • the photographing area is the area in front of the vehicle; when the vehicle is reversing, the photographing area is the area behind the rear of the vehicle; when the camera is a 360-degree multi-angle camera, the photographing area is It can be a 360-degree area around the vehicle, or the like.
  • the sensors described in the embodiments of the present application may be one or more of photoelectric/photosensitive sensors, ultrasonic/acoustic sensors, ranging/distance sensors, vision/image sensors, and the like.
  • an embodiment of the present application provides a front-end parking system, the system includes a collection device, a processing device, and an execution device;
  • the acquisition device mainly includes ultrasonic radar and fisheye camera, and is used to acquire vehicle data, obstacle data, parking space data, and passable area data, etc.;
  • the processing device is used for processing the data collected by the collecting device to obtain the target parking track.
  • the execution device is used for parking the vehicle according to the parking instruction issued by the processing device.
  • an embodiment of the present application provides a computer program product, the computer program product includes: computer program code, when the computer program code is run by a computer, the processing device for reporting information executes the first aspect or the first Any method of any possible implementation of an aspect.
  • an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a program, and the program enables a computer to execute any method in the first aspect or any possible implementation manner of the first aspect .
  • FIG. 1 is a schematic diagram of a front-first-in parking system according to an embodiment of the present application.
  • FIG. 2 is a schematic diagram of a first system architecture provided by an embodiment of the present application.
  • FIG. 3 is a schematic diagram of a second system architecture provided by an embodiment of the present application.
  • FIG. 4 is a schematic diagram of trajectory segmentation of a front-first-in parking method provided by an embodiment of the present application.
  • FIG. 5 is a schematic flowchart of a front-first-in parking method according to an embodiment of the present application.
  • FIG. 6 is a schematic diagram of a first part of a parking trajectory according to an embodiment of the present application.
  • FIG. 7 is a schematic diagram of the position and attitude of the target vehicle and the angle of the median line of the target parking space according to an embodiment of the present application;
  • FIG. 8 is a schematic diagram of a first application scenario provided by an embodiment of the present application.
  • FIG. 9 is a schematic diagram of the division of a parking unit 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 trajectory generated by a first parking unit according to an embodiment of the present application.
  • FIG. 12 is a schematic flowchart of a step-by-step determination of an optimal pose provided by an embodiment of the present application
  • FIG. 13 is a schematic diagram of a second application scenario provided by an embodiment of the present application.
  • FIG. 14 is a schematic diagram of the first front-first-in parking device provided by the application.
  • FIG. 15 is a schematic diagram of a second type of front-first-in parking device provided by the application.
  • the difficulty coefficient of parking by the first-in method is relatively high, the parking process takes a long time, and the success rate is low.
  • the embodiments of the present application provide a front-first-in parking method and device, so as to provide an efficient, convenient and accurate front-in-parking solution.
  • the step-by-step search is mainly used according to the collected vehicle information, surrounding environment information and parking space information during the first-in parking process. method, to find a trajectory with simplified planning actions and optimal pose adjustment.
  • the parking space information is fed back in real time, a reasonable and safe front wheel angle is output, errors are corrected, and the parking accuracy is improved.
  • the embodiments of the present application provide a parking system for front-end entry.
  • the hardware device of the parking system includes an ultrasonic radar 100 (for example, a 12-channel ultrasonic radar) , a camera 110 (for example, a four-way fisheye camera), an image processor 120, a CPU 130, a controller 140, and the like.
  • the ultrasonic radar 100 is mainly responsible for collecting the distance information between the obstacles around the vehicle and the vehicle.
  • the camera 110 is mainly responsible for collecting images of the surrounding environment of the vehicle body.
  • the image processor 120 is mainly responsible for completing parking space identification, obstacle identification, passable area identification, etc. from the image data.
  • the CPU 130 is mainly responsible for module scheduling, receiving ultrasonic radar data, image processing data, completing data information fusion, determining a planning scheme, generating and outputting planning instructions, and the like.
  • the CPU 130 may send a planning instruction to the display screen of the vehicle to prompt the driver how to operate the vehicle.
  • the CPU 130 may send a planning instruction to the controller, so that the controller controls the movement of the vehicle and realizes the automatic parking of the vehicle.
  • the controller 140 is configured to control the vehicle to move according to the planning instruction of the CPU, so as to realize the automatic parking of the vehicle.
  • system architecture constituted by the above-mentioned hardware device according to the embodiment of the present application may be as shown in FIG. 2 , and may be specifically divided into a collection system, a processing system, and an execution system.
  • the acquisition system described in the embodiments of the present application mainly includes ultrasonic radar and fisheye camera, which are used to acquire vehicle data, obstacle data, parking space data, and passable area data.
  • the processing system described in the embodiment of the present application may be further divided into an identification monitoring layer and a decision planning layer.
  • the identification and monitoring layer mainly uses an image processor to perform vehicle/pedestrian identification and passable area identification on the images collected by the fisheye camera;
  • the data is used for distance monitoring of obstacles; combined with fisheye camera and ultrasonic radar for parking space recognition, etc.
  • the decision planning layer mainly processes the information obtained by the identification monitoring layer through the CPU to obtain the parking path plan.
  • the execution system described in the embodiment of the present application mainly includes a controller, which is used for parking the vehicle according to the parking instruction issued by the processing system.
  • parking instructions described in the embodiments of the present application include but are not limited to the following types: vehicle longitudinal control instructions and vehicle lateral control instructions.
  • the vehicle control can be divided into vehicle longitudinal control, such as vehicle speed control, and vehicle lateral control, such as vehicle steering wheel rotation angle control, gear position, and the like.
  • FIG. 1 to FIG. 3 are only simplified schematic diagrams for easy understanding, and the system architecture may further include other devices or may also include other unit modules.
  • the parking process by the first-in approach in the embodiment of the present application can be divided into two parts, that is, it can be understood that the parking trajectory of the first-in approach is divided into two sections.
  • the first partial trajectory is the AB segment trajectory shown in FIG. 4
  • the second partial trajectory is the BC segment trajectory shown in FIG. 4
  • point A described in the embodiment of the present application is the starting position of the target vehicle for parking by means of front-end first-in
  • point B is the position where the target vehicle adjusts the front of the vehicle to deviate from the threshold angle of the target parking space.
  • the target vehicle The front of the vehicle is between the rear of the target vehicle and the target parking space
  • point C is the parking position after the target vehicle is parked in the parking space in the embodiment of the application, that is, the end point of the entire parking trajectory.
  • the first part the first part of the trajectory (ie, the AB segment trajectory) for parking in the first-in method.
  • the collection device in the vehicle collects parking data.
  • the parking data includes the location of the target vehicle (that is, the vehicle that needs to be parked), the size and location of the target parking space, the location and size of the passable area around the target vehicle, the location and distance of obstacles around the target vehicle distance to the target vehicle, etc.
  • the collection device includes but is not limited to a camera device, a sensor device, an ultrasonic wave, a radar, and the like.
  • the collection device in the vehicle sends the parking data to the processing device in the vehicle.
  • the processing device in the vehicle obtains at least one first partial trajectory through a step-by-step algorithm according to the parking data.
  • the processing device in the embodiment of the present application obtains three first partial trajectories as shown in FIG. 6 , that is, three AB segment trajectories through a step-by-step algorithm according to the parking data.
  • the processing device in the vehicle determines the evaluation value of each first partial trajectory.
  • the evaluation value of the first partial trajectory may be determined in the following manner.
  • the target vehicle travels to point B obtain the simulated pose of the target vehicle at point B.
  • the evaluation value of the AB trajectory is determined according to the sum of the lateral deviation of the center of the front of the target vehicle and the center of the rear axle when the target vehicle is at point B, and the angle deviation between the body of the target vehicle and the central axis of the parking space.
  • the processing device in the vehicle determines the first partial trajectory with the smallest evaluation value as the target parking trajectory.
  • the processing device in the vehicle determines a parking planning scheme according to the target parking trajectory, and generates a parking instruction.
  • the processing device in the vehicle sends the parking instruction to the vehicle execution device.
  • the parking instruction includes target speed, gear position and steering wheel rotation angle.
  • the execution device in the vehicle travels according to the parking instruction.
  • S506 during the parking process of the vehicle according to the target parking trajectory, determine whether there is a risk of collision with an obstacle, if yes, go to S507 , if not, go to S508 .
  • the collection device in the vehicle continues to collect data on the surrounding environment of the target vehicle, and upload the data to The processing device in the vehicle; the processing device in the vehicle analyzes and determines whether the target vehicle has a risk of colliding with an obstacle according to the surrounding environment data received from the collecting device.
  • the processing device in the vehicle determines whether the obstacle avoidance can be realized by re-planning according to the pose of the current target vehicle, if so, execute S502 , if not, execute S509 .
  • control device in the vehicle reaches the end point of the target parking trajectory according to the target parking trajectory, and continues to execute S512 .
  • the processing device in the vehicle determines whether to wait for a timeout, if so, execute S511; if not, execute S509.
  • the second part the second part of the trajectory of parking by the way of front first.
  • the processing device in the vehicle determines whether the front of the vehicle can drive into the parking space, and if so, executes S513, and if not, executes S514.
  • the collection device in the vehicle collects the current position information of the vehicle, the distance information between the vehicle and the target parking space, etc., and uploads the collected information to The processing device of the vehicle.
  • the processing device in the vehicle determines whether the vehicle can drive into the parking space by adjusting the angle of the front wheels according to the information uploaded by the collecting device.
  • the processing device in the vehicle may also control the The execution device performs forward/backward adjustment of the closed-loop error dynamic trajectory.
  • the control device in the vehicle adjusts the posture and posture by reversing back and forth, and enters the parking space.
  • the target vehicle is vehicle A, and there is an obstacle 1 (eg, a pedestrian) at a distance of 5 meters in front of the target vehicle A.
  • an obstacle 1 eg, a pedestrian
  • This module is specifically used to receive parking data from acquisition devices such as cameras, ultrasonic radars, and sensors.
  • the camera and ultrasonic radar data are used to identify the parking spaces in the environment at this stage, that is, the target parking space A; the camera data is used to identify targets and positions such as vehicles/pedestrians in the environment, that is, obstacle 1. ; Identify the passable area in the environment through camera and ultrasonic radar data, that is, the twill area in Figure 8.
  • the acquired parking data information is as follows:
  • Slot represents the target vehicle
  • P1 represents the coordinates of the upper left corner of the parking space
  • P2 represents the coordinates of the upper right corner of the parking space
  • P3 represents the coordinates of the lower left corner of the parking space
  • P4 represents the coordinates of the lower right corner of the parking space .
  • Objects represents pedestrians
  • Object 1 represents the coordinates of the upper left corner of the pedestrian
  • Object 2 represents the coordinates of the upper right corner of the pedestrian
  • Object 3 represents the coordinates of the lower left corner of the pedestrian
  • Object 4 represents the coordinates of the lower right corner of the pedestrian.
  • Object represents other vehicles
  • P1 represents the coordinates of the upper left corner of the parking space
  • P2 represents the coordinates of the upper right corner of the parking space
  • P3 represents the coordinates of the lower left corner of the parking space
  • P4 represents the coordinates of the lower right corner of the parking space .
  • Freespace represents the passable area
  • P 1 , P 2 , P 3 , ..., P n represent the coordinates of the passable area.
  • Stage 2 Generation and tracking of the first part of the trajectory during the parking process
  • the optimal trajectory is obtained.
  • the processing process performed in the processing device may be as follows:
  • the processing device in the target vehicle can determine the approximate direction of the vehicle during the parking process and the parking area according to the parking data .
  • the target vehicle described in this embodiment of the present application may divide the parking process into at least one parking unit according to the approximate direction of the vehicle and the parking area during the parking process.
  • the target vehicle is in the process of parking and when the target parking space is on the right side of the own vehicle, the approximate direction of the vehicle is as shown in (a) of FIG. 9 .
  • the parking process can be divided into 4 parking units.
  • the first parking unit in the parking process is shown in (b) of FIG. 9
  • the second parking unit in the parking process is shown in FIG. 9 .
  • the third unit of the parking process is shown in (d) of FIG. 9
  • the fourth unit of the parking process is shown as (e) of FIG. 9 .
  • the planned trajectory of the first parking unit to the third parking unit is the above-mentioned AB segment trajectory
  • the planned trajectory of the fourth parking unit is the above-mentioned BC segment trajectory.
  • the embodiment of the present application can determine the general direction of the parking process and the parking units in the parking process according to the prior trajectory model in the previous parking process.
  • the prior trajectory model is obtained according to geometric analysis and a large number of experimental proofs.
  • the processing device in the vehicle may perform parking trajectory planning based on each parking unit. That is to say, the entire parking trajectory during the parking process is composed of several segments of parking unit trajectories.
  • the processing device in the vehicle uses a step-by-step algorithm to generate the trajectory in each parking unit.
  • a segment of trajectory may include a straight trajectory and a circular arc trajectory. Therefore, the trajectory in the parking unit in the embodiment of the present application can be understood as consisting of several straight trajectories and/or several circular arcs. composed of tracks.
  • both arcs and straight lines play an important role.
  • the function of the arc is to flexibly adjust the direction of the ego vehicle;
  • the function of the straight line is to adjust the position of the ego car on the one hand, and on the other hand, it can smoothly connect the two arcs, making it easier for the system to track the generated trajectory.
  • the minimum parking unit described in the embodiments of the present application there may be only straight trajectories or only circular arc trajectories, and the order of the circular arc trajectories and the straight trajectories is not limited in the embodiments of the present application. , any method that can be combined into a minimum unit parking trajectory is applicable to the embodiments of the present application.
  • the first parking unit when determining the trajectory of the parking unit, as shown in FIG. 10 , the first parking unit takes point A as the starting point of calculation, and then determines the trajectory of the first parking unit according to the step-by-step algorithm.
  • the parking trajectory is obtained, and the end point of the trajectory in the first parking unit is obtained, for example, point Q1 is the end point of the trajectory of the first parking unit.
  • the second parking unit takes the planned parking trajectory end point (ie Q1) in the first parking unit as the starting point of the parking trajectory planning in the second parking unit, and then determines the second parking trajectory according to the step-by-step algorithm.
  • the parking trajectory in the car unit is obtained, and the end point of the trajectory in the second parking unit is obtained, for example, point Q2 is the end point of the trajectory of the second parking unit. And so on, until the entire parking trajectory planning is completed.
  • the starting point of each step-by-step route is the route end point obtained in the previous step-by-step route.
  • each parking unit trajectory is composed of a linear trajectory and a circular arc trajectory, and the linear trajectory is before the circular arc trajectory, and the step-by-step determination of the parking unit trajectory is performed.
  • the content is introduced:
  • step_line the step length of each step is d step_line , then the step lengths in the x and y directions are:
  • the minimum turning radius of the ego vehicle is used as the fixed turning radius r of the arc trajectory, and the arc trajectory can be calculated according to the current ego vehicle position.
  • Center position the minimum turning radius of the ego vehicle is used as the fixed turning radius r of the arc trajectory, and the arc trajectory can be calculated according to the current ego vehicle position.
  • the arc step size is d step_arc
  • the corner step size is:
  • the angle in the formula in the embodiment of the present application is a variable value, and when generating a linear trajectory, by adjusting the angle, multiple linear trajectories can be generated.
  • generating a circular arc trajectory by adjusting the angle, multiple circular arc trajectories can be generated. Therefore, at least one parking unit trajectory can be obtained in each parking unit.
  • the value range of the angle in the embodiment of the present application may be determined according to the existing manner, which is not limited in the embodiment of the present application.
  • the trajectory search time can be greatly reduced on the premise of ensuring high-quality and simplified search results, and the tolerance for sensing errors in farther distances can be high. Perceptual detection with higher accuracy, making a fast and reasonable re-planning strategy.
  • an embodiment of the present application provides a flowchart of step-by-step determination of the optimal pose for each parking unit, as follows:
  • the parking trajectory in the parking unit is determined by a straight line trajectory and a circular arc trajectory, and the straight line trajectory is executed first.
  • S1202. Determine whether the generated linear trajectory has a risk of colliding with an obstacle, if so, execute S1203, and if not, execute S1204.
  • S1204 Determine whether the number of linear steps to be performed on the linear track is reached, if so, execute S1205, and if not, execute S1201.
  • S1206 Select a second angle for performing circular arc trajectory step, and generate a segment of circular arc trajectory according to the second angle and the circular arc step length.
  • S1209 Determine whether the number of arc stepping times for stepping on the arc track is reached, if so, execute S1210, and if not, execute S1206.
  • the first part of the parking trajectory is obtained.
  • At least one first partial parking trajectory will be obtained. Then, in this stage, the obtained at least one first part of the parking trajectory is respectively evaluated for the trajectory, and the evaluation (cost) value corresponding to each first part of the trajectory is obtained, and the pros and cons of each first part of the trajectory are judged according to the size of the cost.
  • Judgment aspect one the sum of the lateral deviation between the center of the front and the center of the rear axle (e rear_distance +e front_distance );
  • the front center and the rear axle center mentioned in the first aspect of the evaluation are the corresponding front center and rear axle center when the target vehicle simulates the end point of the route planned by the third parking unit.
  • Judgment aspect 2 The angle deviation between the body and the central axis of the parking space.
  • the central axis of the body and the parking space described in the judgment aspect 2 is the central axis of the body and the parking space corresponding to when the target vehicle simulates the end point of the route planned by the third parking unit.
  • k 1 and k 2 are the proportions of angular deviation and lateral deviation in the loss function, respectively.
  • the first partial parking trajectory with the smallest evaluation value is determined as the optimal parking trajectory. That is, the trajectory with the smallest evaluation value is determined as the target parking trajectory used in the parking process of the vehicle.
  • the position of the target vehicle at the end point (ie point B) of the target parking trajectory is mainly determined. Whether the posture can drive into the parking space.
  • the pose can be adjusted through several arc curves.
  • the processing device in the vehicle determines according to the data information collected by the collecting device that the front of the vehicle can penetrate into the parking space.
  • an optional method in the embodiment of the present invention uses a closed-loop error planning method to directly determine the front wheel rotation angle according to the error existing between the self-vehicle posture and the target posture.
  • the pose error is determined from the self-vehicle pose and the target pose, and the control command is directly generated according to the determined pose error, and the closed-loop effect is the fastest, eliminating the need for error elimination From the trajectory to the tracking trajectory, the closed-loop response is not timely.
  • the dimension selected for determining the position and attitude error between the ego vehicle and the target vehicle is the same as the dimension considered in the above-mentioned third stage for pose evaluation.
  • the model used for closed-loop error planning in this embodiment of the present application is the following closed-loop control PID model.
  • the sum of the lateral deviation between the center of the vehicle head and the center of the rear axle and the angle deviation between the center axis of the vehicle body and the parking space are taken as e(t), and are substituted into the above formula 13 to obtain the error value y between the own vehicle and the target parking space.
  • safety protection constraints can be performed on the output front wheel rotation angle.
  • a safety protection constraint is performed on the front wheel rotation angle. Therefore, the trajectory indicated by the obtained control instruction can be made safer.
  • the adjustment range of the front wheel rotation angle needs to be restricted.
  • the maximum front wheel angle of the vehicle is max_front_wheel_angle
  • the range of the front wheel angle is [-max_front_wheel_angle, max_front_wheel_angle] turning left is positive, and turning right is negative.
  • the distance between the line segment V 0 V 1 and the line segment S 2 S 3 is distance 1
  • the distance between the line segment V 2 V 3 and the line segment S 0 S 1 is distance 2 .
  • k is the distance constraint coefficient. The larger the k is, the faster the turning speed of the ego car is required, and the position and posture of the ego car can be corrected more flexibly by using the space.
  • the min_angle can only take 0, that is, the self-vehicle can only go forward in a straight line, thus avoiding the line segment V 2 V 3 and The line segment S 0 S 1 may collide.
  • the direction angle of S 2 S 3 is known, the direction angle of OV 1 can be obtained, and then according to the coordinates of V 1 , the straight line equation of OV 1 can be calculated.
  • the line segment OC is the self-vehicle turning radius perpendicular to the self-vehicle posture direction, so the OC direction angle is known, and then according to the C point coordinate, that is, the self-vehicle position, the straight line equation of OC can be calculated.
  • the radius of the turning circle is:
  • the front wheel steering angle can be calculated as:
  • the max_angle when the distance 1 is smaller, the max_angle is smaller.
  • the max_angle takes the boundary_angle, that is, the distance 1 is guaranteed to increase when the vehicle travels, so as to avoid the line segment V 0 V 1 and the line segment S 2 S 3 collision is possible.
  • the dynamic fine-tuning can ensure the safe and efficient output of lateral control commands in the movable space.
  • the step-by-step search path planning is performed during the parking process, the planning trajectory is simplified and effective, and the automatic adjustment can be achieved while ensuring fewer gear switching times and driving distances.
  • the effect of the car to the best entry pose, and the planning time is short, which meets the real-time requirements.
  • the present invention proposes to make further safe and rapid fine-tuning according to more accurate perception information when the self-vehicle enters the parking space, so as to quickly converge the error and improve the parking accuracy.
  • the term "at least one" in the embodiments of the present application refers to one or more, and "a plurality” refers to two or more.
  • "And/or" which describes the relationship of the associated objects, means that there can be three kinds of relationships, for example, A and/or B, which can mean that A exists alone, A and B exist at the same time, and B exists alone, where A , B can be singular or plural.
  • the character “/” generally indicates that the associated objects are an "or” relationship.
  • the following at least one item(s) or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items(s).
  • At least one (a) of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c may be single or multiple .
  • ordinal numbers such as “first” and “second” mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, sequence, priority, or importance of multiple objects .
  • the terms “comprising” and “having” in the embodiments and claims of the present application and the drawings are not exclusive.
  • a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, and may also include unlisted steps or modules.
  • the above implementing devices include hardware structures and/or software units corresponding to executing the functions.
  • the present invention can be implemented in hardware or a combination of hardware and computer software in conjunction with the units and algorithm steps of each example described in the embodiments disclosed herein. Whether a function is performed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.
  • an embodiment of the present invention is a front-end parking device, the device 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 when performing operations.
  • the transceiver 1402 is used to receive and transmit data under the control of the processor 1400 for data communication with the memory 1401 .
  • the bus architecture may include any number of interconnected buses and bridges, in particular 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, and power management circuits, which are well known in the art and, therefore, will not be described further herein.
  • the bus interface provides the 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 when 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 .
  • each step of the first-in parking process can be completed through the hardware integrated logic circuit in the processing 1400 or the instructions in the form of software.
  • 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, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the embodiments of the present invention.
  • a general purpose processor may be a microprocessor or any conventional processor or the like.
  • the steps of the method disclosed in conjunction with the embodiments of the present invention may be directly embodied as executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature 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 its hardware.
  • the processor 1400 is configured to read the program in the memory 1401 and execute the method flow in S500-S514 shown in FIG. 5; or execute the S1200-S514 shown in FIG. The method flow in S1210.
  • the present invention provides a head-first parking device, the device includes a collection module 1500 and a processing module 1501 .
  • the collection module 1500 is used to collect parking data, and the parking data includes part or all of vehicle posture information, obstacle position information, target parking space information, and passable area position information;
  • the processing module 1501 is used to determine at least one initial parking trajectory by using a step-by-step algorithm according to the parking data; evaluate each initial parking trajectory to determine the optimal initial parking trajectory; The optimal initial parking trajectory is determined as the target parking trajectory; the front-end parking is performed according to the target parking trajectory.
  • processing module 1501 is specifically used for:
  • the parking process is divided into at least one parking unit; the step-by-step algorithm is used to determine the parking trajectory of each parking unit in turn, and at least one initial parking trajectory is obtained; wherein, the end point of the trajectory in the previous parking unit is the next one.
  • the starting point of the trajectory of a parking unit is the first point of the trajectory of a parking unit.
  • processing module 1501 is specifically used for:
  • the initial parking trajectory is evaluated according to the pose to determine the optimal initial parking trajectory.
  • processing module 1501 is specifically used for:
  • the initial parking trajectory with the smallest evaluation value is determined as the optimal initial parking trajectory.
  • processing module 1501 is further configured to:
  • processing module 1501 is further configured to:
  • processing module 1501 is specifically used for:
  • the vehicle posture at the current position and the position of the target parking space it is determined whether the vehicle can enter the parking space by adjusting the angle of the front wheels.
  • processing module 1501 is further configured to:
  • the pose of the vehicle is adjusted according to the parking error.
  • processing module 1501 is specifically used for:
  • intersection of the first turning angle and the front wheel safe turning angle is determined as the target turning angle for the vehicle to perform front wheel adjustment.
  • various aspects of the first-in parking method provided by the embodiments of the present invention may also be implemented in the form of a program product, which includes program code, and when the program code runs on a computer device , the program code is used to cause the computer device to execute the steps in the first-in parking method according to various exemplary embodiments of the present invention described in this specification.
  • 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.
  • the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • the parking program product for first entry may employ a portable compact disk read only memory (CD-ROM) and include program codes, and may run on a server device.
  • CD-ROM portable compact disk read only memory
  • the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium that contains or stores a program that can be communicated, used by an apparatus or device, or used in conjunction therewith.
  • a readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, carrying readable program code therein. Such propagated data signals may take a variety of forms including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a readable signal medium can also be any readable medium, other than a readable storage medium, that can transmit, propagate, or transport a program for use by or in connection with a periodic network action system, apparatus, or device.
  • Program code embodied on a readable medium may be transmitted using any suitable 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 of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural Programming Language - such as the "C" language or similar programming language.
  • the program code may execute entirely on the user computing device, partly on the user device, as a stand-alone software package, partly on the user computing device and partly on a remote computing device, or entirely on the remote computing device or server execute on.
  • 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.
  • LAN local area network
  • WAN wide area network
  • the embodiments of the present application further provide a storage medium readable by a computing device for the first-in parking method, that is, the content is not lost after the power is turned off.
  • Software programs are stored in the storage medium, including program codes. When the program codes are run on a computing device, the software programs can implement any of the above-mentioned embodiments of the present application when the software program is read and executed by one or more processors. parking plan.
  • the present application may also be implemented in hardware and/or software (including firmware, resident software, microcode, etc.). Still further, the present 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 an instruction execution system or Used in conjunction with an instruction execution system.
  • a computer-usable or computer-readable medium can be any medium that can contain, store, communicate, transmit, or transmit a program for use by, or in connection with, an instruction execution system, apparatus, or device. device or equipment use.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)

Abstract

La présente demande concerne un procédé, un dispositif et un système de stationnement avant-premier, qui sont utilisés pour effectuer efficacement et avec précision un stationnement. Le procédé consiste à : collecter des données de stationnement, les données de stationnement comprenant une partie ou la totalité des informations de position d'un véhicule, des informations d'emplacement d'obstacle, des informations d'espace de stationnement cible et des informations d'emplacement d'une zone de passage ; estimer la direction de conduite sur la base des données de stationnement, et déterminer au moins une unité de stationnement ; déterminer séquentiellement la trajectoire de stationnement de chaque unité de stationnement à l'aide d'un algorithme pas à pas, de façon à obtenir au moins une trajectoire de stationnement initiale ; déterminer une valeur d'évaluation de chaque trajectoire de stationnement initiale sur la base de la position du véhicule à un point d'extrémité de la trajectoire de stationnement initiale, et déterminer la trajectoire de stationnement optimale en fonction de la valeur d'évaluation ; et stationner selon la trajectoire de stationnement optimale. Dans le procédé, un algorithme pas à pas est utilisé pour planifier une trajectoire de stationnement, la durée de recherche de trajectoire peut être efficacement réduite, une trajectoire de stationnement hautement fiable est efficacement et rapidement générée, la durée de planification est courte, et des exigences en temps réel sont satisfaites.
PCT/CN2021/123788 2020-12-31 2021-10-14 Procédé, dispositif et système de stationnement avant-premier WO2022142592A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202011633813 2020-12-31
CN202011633813.6 2020-12-31
CN202110641541.2A CN114684111A (zh) 2020-12-31 2021-06-09 一种车头先入的泊车方法、装置和***
CN202110641541.2 2021-06-09

Publications (1)

Publication Number Publication Date
WO2022142592A1 true WO2022142592A1 (fr) 2022-07-07

Family

ID=82135879

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/123788 WO2022142592A1 (fr) 2020-12-31 2021-10-14 Procédé, dispositif et système de stationnement avant-premier

Country Status (2)

Country Link
CN (1) CN114684111A (fr)
WO (1) WO2022142592A1 (fr)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115376358A (zh) * 2022-07-18 2022-11-22 英博超算(南京)科技有限公司 基于有限状态机的超声波车位探测
CN115465266A (zh) * 2022-11-10 2022-12-13 集度科技有限公司 泊车路径规划方法、装置、设备及存储介质
CN115775062A (zh) * 2023-02-10 2023-03-10 深圳市永泰光电有限公司 基于物联网的汽车摄像头与雷达数据采集***及方法
CN116461499A (zh) * 2023-03-02 2023-07-21 合众新能源汽车股份有限公司 一种泊车控制方法及装置
CN117002490A (zh) * 2023-08-23 2023-11-07 镁佳(北京)科技有限公司 辅助泊车方法、装置、计算机设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106143609A (zh) * 2016-07-15 2016-11-23 江苏大学 一种泊车***及其垂直方向泊车方法
CN109131317A (zh) * 2018-07-23 2019-01-04 同济大学 基于多段式规划与机器学习的自动垂直泊车***及方法
CN111178295A (zh) * 2019-12-31 2020-05-19 华为技术有限公司 车位检测和模型训练方法、装置、车辆、设备及存储介质
CN111307152A (zh) * 2020-02-18 2020-06-19 中国科学院合肥物质科学研究院 一种自主泊车路径反向生成规划方法

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102011122421B4 (de) * 2011-12-24 2022-05-19 Volkswagen Aktiengesellschaft Verfahren und Vorrichtung zum Einparken eines Kraftfahrzeugs
DE102012201112A1 (de) * 2012-01-26 2013-08-01 Robert Bosch Gmbh Verfahren zur Unterstützung eines Fahrers beim Vorwärtseinparken
KR101906952B1 (ko) * 2013-11-08 2018-10-11 한화지상방산 주식회사 무인 주행 차량의 최적 주차 경로를 생성하는 방법, 및 이 방법을 채용한 무인 주행 차량
KR102625258B1 (ko) * 2016-10-24 2024-01-16 주식회사 에이치엘클레무브 주차지원장치 및 주차지원방법
JP6759143B2 (ja) * 2017-04-07 2020-09-23 クラリオン株式会社 駐車支援装置
US10281921B2 (en) * 2017-10-02 2019-05-07 Ford Global Technologies, Llc Autonomous parking of vehicles in perpendicular parking spots
DE102018204994A1 (de) * 2018-04-04 2019-10-10 Bayerische Motoren Werke Aktiengesellschaft Parkassistenzsystem und Verfahren zur Unterstützung eines Fahrers beim Einparken in eine Querparklücke
CN110471412A (zh) * 2019-08-01 2019-11-19 广州小鹏汽车科技有限公司 一种评估路径跟踪算法性能的方法及评估***

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106143609A (zh) * 2016-07-15 2016-11-23 江苏大学 一种泊车***及其垂直方向泊车方法
CN109131317A (zh) * 2018-07-23 2019-01-04 同济大学 基于多段式规划与机器学习的自动垂直泊车***及方法
CN111178295A (zh) * 2019-12-31 2020-05-19 华为技术有限公司 车位检测和模型训练方法、装置、车辆、设备及存储介质
CN111307152A (zh) * 2020-02-18 2020-06-19 中国科学院合肥物质科学研究院 一种自主泊车路径反向生成规划方法

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115376358A (zh) * 2022-07-18 2022-11-22 英博超算(南京)科技有限公司 基于有限状态机的超声波车位探测
CN115376358B (zh) * 2022-07-18 2023-12-05 英博超算(南京)科技有限公司 基于有限状态机的超声波车位探测
CN115465266A (zh) * 2022-11-10 2022-12-13 集度科技有限公司 泊车路径规划方法、装置、设备及存储介质
CN115775062A (zh) * 2023-02-10 2023-03-10 深圳市永泰光电有限公司 基于物联网的汽车摄像头与雷达数据采集***及方法
CN115775062B (zh) * 2023-02-10 2023-05-02 深圳市永泰光电有限公司 基于物联网的汽车摄像头与雷达数据采集***及方法
CN116461499A (zh) * 2023-03-02 2023-07-21 合众新能源汽车股份有限公司 一种泊车控制方法及装置
CN116461499B (zh) * 2023-03-02 2024-01-02 合众新能源汽车股份有限公司 一种泊车控制方法及装置
CN117002490A (zh) * 2023-08-23 2023-11-07 镁佳(北京)科技有限公司 辅助泊车方法、装置、计算机设备及存储介质
CN117002490B (zh) * 2023-08-23 2024-02-20 镁佳(北京)科技有限公司 辅助泊车方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
CN114684111A (zh) 2022-07-01

Similar Documents

Publication Publication Date Title
WO2022142592A1 (fr) Procédé, dispositif et système de stationnement avant-premier
US11631200B2 (en) Prediction on top-down scenes based on action data
US11042157B2 (en) Lane/object detection and tracking perception system for autonomous vehicles
US10582137B1 (en) Multi-sensor data capture synchronizaiton
WO2021217420A1 (fr) Procédé et appareil de suivi de voie
US11332132B2 (en) Method of handling occlusions at intersections in operation of autonomous vehicle
US20220394156A1 (en) Image scan line timestamping
US10849543B2 (en) Focus-based tagging of sensor data
EP4089369A1 (fr) Procédé de sélection de trajet et dispositif de sélection de trajet
US11550324B2 (en) Parking zone detection for vehicles
CN110390240B (zh) 自动驾驶车辆中的车道后处理
WO2023034321A1 (fr) Étalonnage de multiples unités de mesure inertielle
WO2021017504A1 (fr) Procédé et appareil de prédiction de trajectoire de mouvement
EP3841525A1 (fr) Gestion opérationnelle de véhicule autonome avec commande de perception de saillance visuelle
CN112534483A (zh) 预测车辆驶出口的方法和装置
JP2023547988A (ja) 衝突回避計画システム
JP2022502919A (ja) 画像スキャンラインのタイムスタンプ
WO2023009794A1 (fr) Détection d'objets tridimensionnels sur la base de données d'image
WO2021027966A1 (fr) Procédé de déplacement, dispositif de déplacement, et support d'informations
CN116189150B (zh) 基于融合输出的单目3d目标检测方法、装置、设备和介质
CN116225026A (zh) 自动驾驶车辆操作方法、电子设备以及计算机可读介质
CN114511834A (zh) 一种确定提示信息的方法、装置、电子设备及存储介质
US20230347880A1 (en) Systems and methods for determining buffer regions
US20240166239A1 (en) Trajectory planning for navigating small objects on road
US20240140432A1 (en) Long-distance autonomous lane change

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21913337

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21913337

Country of ref document: EP

Kind code of ref document: A1