Parking control methods, devices, equipment and storage media

By predicting the trajectory of dynamic objects and integrating the areas to be avoided when a vehicle approaches a target parking space, unified path planning is achieved for both the driving and parking phases. This solves the problem of pauses when the vehicle switches from cruise mode to parking mode, improving parking efficiency and driving experience.

CN123104632APending Publication Date: 2026-11-17DONGFENG MOTOR CO LTD DONGFENG NISSAN PASSENGER VEHICLE CO
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611540153.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-09-30
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

In existing technologies, there is a noticeable pause when a vehicle switches from cruise mode to parking mode, resulting in a long overall switching time and low efficiency.

Method used

When a vehicle approaches a target parking space, the system predicts the trajectory of dynamic objects to determine the area to be avoided. This prediction is then fused with the current perception point cloud to perform an integrated search for both the cruising and parking paths. This process determines whether an available path exists and enables unified path planning for both the driving and parking phases.

Benefits of technology

It improves the continuity of the transition from driving to parking, shortens the total time required to complete parking, and enhances the smoothness of the driving experience and the success rate of path search.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123104632A_ABST
    Figure CN123104632A_ABST
Patent Text Reader

Abstract

This invention belongs to the field of autonomous driving control technology and discloses a parking control method, device, equipment, and storage medium. The method includes: predicting the trajectory of a dynamic target object based on its type, motion parameters, and area when the distance between the current vehicle's cruising position and the target parking space is less than or equal to a preset distance; determining a avoidance area based on the dynamic target object's trajectory; determining whether an available path exists based on the avoidance area and the current perception point cloud, wherein the available path includes a cruising path and a parking path; and, if an available path exists and the vehicle reaches the end of the cruising path, switching from cruising mode to parking mode, and controlling the vehicle to drive to the target parking space based on the parking path to complete the parking control. This method improves the continuity of the transition from driving to parking, thereby reducing parking transition time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of autonomous driving control technology, and in particular to parking control methods, devices, equipment and storage media. Background Technology

[0002] Currently, control schemes for switching between cruise control and parking often involve the vehicle first cruiseing to the vicinity of the target parking space, then braking to a stop, and finally switching to the parking state machine for path planning. This process involves significant pauses, resulting in a long overall switching time and low efficiency. Therefore, improving the continuity of the driving-to-parking transition to reduce parking switching time has become an unresolved issue.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The main objective of this invention is to provide a parking control method, apparatus, device, and storage medium, aiming to solve the technical problem of how to improve the continuity of driving-to-parking transition in the prior art, so as to reduce parking transition time.

[0005] To achieve the above objectives, the present invention proposes a parking control method, the parking control method comprising: When the distance between the current vehicle's cruising position and the target parking space is less than or equal to a preset distance, the trajectory of the dynamic target object is predicted based on the type, motion parameters, and area occupied by the dynamic target object. The area to be avoided is determined based on the trajectory of the dynamic target object; The availability of a path is determined based on the area to be avoided and the current perception point cloud, wherein the available path includes a cruise path and a parking path; If an available path exists and the vehicle reaches the end of the cruise path, switch from cruise mode to parking mode, and control the vehicle to drive to the target parking space based on the parking path to complete parking control.

[0006] It should be noted that by actively predicting the trajectory of dynamic objects as the vehicle approaches the target parking space and determining the avoidance area based on the trajectory, the system achieves proactive utilization of environmental information. By fusing the avoidance area with the current perception point cloud and performing an integrated search of the cruise path and parking path to determine whether an available path exists, the system achieves unified path planning for the driving and parking phases. This avoids the waiting time in traditional solutions where the vehicle first cruises to the vicinity of the parking space and then switches to the parking state machine for path planning. This improves the continuity of the transition from driving to parking, shortens the total time required to complete parking, and enhances the smoothness of the driving experience.

[0007] Optionally, the step of determining the area to be avoided based on the trajectory of the dynamic target object includes: Obtain the target type, target speed, and target heading angle corresponding to the dynamic target trajectory; The lateral safety factor and the longitudinal safety factor are determined based on the target type, the target speed, and the target heading angle. The area to be avoided is determined based on the lateral safety factor, the longitudinal safety factor, and the trajectory of the dynamic target.

[0008] It should be noted that by determining the longitudinal and lateral safety factors based on the target type, target speed, and target heading angle, different types of targets can obtain differentiated safety redundancy allocation in the longitudinal and lateral directions, thereby improving the success rate of path search and overall traffic efficiency while ensuring safety.

[0009] Optionally, the step of determining the lateral safety factor and the longitudinal safety factor based on the target type, the target speed, and the target heading angle includes: The longitudinal safety factor is determined based on the type and velocity of the target object. The lateral safety factor is determined based on the target type and the target heading angle.

[0010] It should be noted that by linking the determination of the longitudinal safety factor to the target type and target speed, the speed, a key factor that directly affects braking distance and longitudinal collision risk, can be adjusted in real time to adjust the magnitude of the longitudinal safety redundancy. By linking the determination of the lateral safety factor to the target type and target heading angle, the heading angle, a key factor that directly reflects the lateral intrusion trend, can be adjusted in real time to adjust the magnitude of the lateral safety redundancy. Based on this, the obtained safety factor value can fit the actual risk changes in each dimension, ensuring safety while minimizing the ineffective occupation of path planning space due to excessive redundancy.

[0011] Optionally, the step of determining whether an available path exists based on the area to be avoided and the current perceived point cloud includes: Obtain the obstacle height of static obstacles; The obstacle to be avoided is determined from the static obstacles based on the obstacle height. Based on the area to be avoided and the obstacle to be avoided, determine the available range point cloud from the current perceived point cloud; Determine whether an available path exists based on the available range point cloud.

[0012] It should be noted that by obtaining the height of static obstacles and comparing it with the height of the vehicle's lower edge, low-attribute obstacles such as low curbs and steps are excluded from the avoidance range. This avoids excessive avoidance of low objects that do not affect passage by path planning, thereby reducing unnecessary path detours and parking maneuvers. At the same time, by using the avoidance area and the avoidance obstacle as constraints to remove them from the current perception point cloud to generate a usable range point cloud, the unified integration of static obstacle constraints and dynamic target constraints is achieved. This allows path planning to process information from both static and dynamic environments on a single spatial representation, improving the accuracy and efficiency of path search.

[0013] Optionally, the step of determining the obstacle to be avoided from the static obstacles based on the obstacle height includes: Obtain the height of the lower edge of the vehicle body; If the height of the obstacle is greater than or equal to the height of the lower edge of the vehicle body, the static obstacle is determined to be an obstacle that needs to be avoided.

[0014] It should be noted that by comparing the height of each static obstacle with the height of the vehicle's lower edge, only obstacles with a height greater than or equal to the vehicle's lower edge are identified as obstacles to be avoided. This excludes low-lying objects below the vehicle's lower edge, such as protruding bricks, low curbs, low steps, the edges of parking spaces in scenic areas, or the edges of drainage ditches, from the avoidance range. This effectively reduces the number of invalid constraints in the path planning process and minimizes the need for excessive path detours and increased number of road maneuvers caused by excessive avoidance of low obstacles. Thus, while ensuring collision safety, this improves the efficiency of path planning and the smoothness of the generated path.

[0015] Optionally, after the step of determining whether an available path exists based on the area to be avoided and the current perceived point cloud, the method further includes: If no available path exists, the vehicle will be stopped and wait based on a preset safe distance. If the vehicle stops and waits for a longer period than the preset waiting time, a driver takeover message will be sent.

[0016] It should be noted that by controlling the vehicle to stop and wait at a preset safe distance when no available path exists, the vehicle is given the opportunity to regain an available path after dynamic environmental changes. This avoids the interruption of the driving experience caused by immediately disengaging the function once no feasible path is available. At the same time, it also avoids the collision risk that may be caused by the vehicle continuing to drive blindly when no path is available. By setting a preset waiting time and pushing a driver takeover message after the timeout, the system stagnation and road occupation problems caused by the vehicle waiting indefinitely are reduced, ensuring that the driver can take over in time when the automatic control cannot complete the parking.

[0017] Optionally, before the step of determining whether an available path exists based on the area to be avoided and the current perceived point cloud, the method further includes: Acquire obstacle perception data, parking space perception data, and lane perception data: The current perception point cloud is generated based on the obstacle perception data, parking space perception data, and lane perception data.

[0018] It should be noted that by acquiring obstacle perception data, parking space perception data, and lane perception data separately, the three types of perception data are fused and discretized into the current perception point cloud. This transforms continuous and heterogeneous environmental information into structured spatial data in a unified format, providing a computational foundation for subsequent path planning that can be directly used for collision detection and spatial search, thereby improving the accuracy and execution efficiency of path planning.

[0019] Furthermore, to achieve the above objectives, the present invention also proposes a parking control device, the parking control device comprising: The data prediction module is used to predict the trajectory of a dynamic target object based on its type, motion parameters, and area when the distance between the current vehicle's cruising position and the target parking space is less than or equal to a preset distance. The data processing module is used to determine the area to be avoided based on the trajectory of the dynamic target object; The path determination module is used to determine whether there is an available path based on the area to be avoided and the current perception point cloud, wherein the available path includes a cruising path and a parking path; The driving control module is used to switch from cruise mode to parking mode when an available path exists and the vehicle reaches the end of the cruise path, and to control the vehicle to drive to the target parking space based on the parking path to complete the parking control.

[0020] Furthermore, to achieve the above objectives, the present invention also proposes a parking control device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the parking control method as described above.

[0021] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the parking control method described above. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating an embodiment of the parking control method of the present invention. Figure 2 This is a schematic diagram of the available paths provided in Embodiment 1 of the parking control method of the present invention; Figure 3 This is a flowchart illustrating a second embodiment of the parking control method of the present invention. Figure 4 This is a schematic diagram of cruise control provided in Embodiment 2 of the parking control method of the present invention; Figure 5 This is a schematic diagram of cruise control provided in Embodiment 2 of the parking control method of the present invention; Figure 6 This is a schematic diagram of the path planning module provided in Embodiment 1 of the parking control method of the present invention; Figure 7 This is a simplified flowchart illustrating a second embodiment of the parking control method of the present invention. Figure 8 This is a schematic diagram of the module structure of the parking control device according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the hardware operating environment involved in the parking control method in this embodiment of the invention.

[0025] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0026] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0027] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0028] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or intelligent driving controller capable of performing the above functions. The following description uses an intelligent driving controller as an example to illustrate this embodiment and the subsequent embodiments.

[0029] Based on this, the embodiments of this application provide a parking control method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the parking control method of this application.

[0030] In this embodiment, the parking control method includes steps S10 to S40: Step S10: When the distance between the current vehicle's cruising position and the target parking space is less than or equal to a preset distance, predict the trajectory of the dynamic target object based on its type, motion parameters, and area.

[0031] It should be noted that when the Door-to-Door (D2D) function is activated, the intelligent driving controller will learn the map information stored in the cloud in advance, control the vehicle to cruise, and finally drive to the target parking space and complete the parking. Specifically, after the driver sets the target parking space, this function controls the vehicle to automatically drive out of the starting parking space and drive along the preset cruise route recorded in the map information in the parking lot or park roads. When the vehicle approaches the target parking space, it automatically switches from cruise mode to parking mode and controls the vehicle to park in the target parking space.

[0032] Additionally, the preset distance is a pre-defined threshold indicating the distance at which the cruising position approaches the target parking space. Dynamic targets refer to other traffic participants in the vehicle's surrounding environment that are in motion and may affect the vehicle's driving path.

[0033] In addition, the types of dynamic targets can include different categories such as pedestrians, four-wheeled vehicles, two-wheeled vehicles, and large trucks. Motion parameters are a set of data characterizing the current motion state of the dynamic target, including at least its velocity and heading angle. The footprint is a parameter characterizing the physical space occupied by the dynamic target on the horizontal plane, reflecting its actual outline dimensions.

[0034] It should be understood that during the vehicle's parking space transfer function, when the vehicle is in cruise mode and receives a user's parking instruction, it continuously monitors the real-time distance between the current vehicle's cruise position and the target parking space. When this distance is less than or equal to a preset distance, it is determined that the vehicle has approached the target parking space. At this point, it is necessary to predict the trajectory of surrounding dynamic objects. This can be achieved by collecting surrounding environmental data through onboard sensors, identifying all dynamic objects, and obtaining information on the type of each object, such as pedestrians, four-wheeled vehicles, two-wheeled vehicles, or large trucks, along with their corresponding speed, heading angle, and area of ​​occupation. Then, based on the dynamic object's type Odi, speed v, heading angle θ, and area of ​​occupation A, combined with the object's kinematic characteristics, the most likely path curve for the object in the near future is calculated, resulting in the dynamic object's trajectory (Odi, v, θ, A).

[0035] Step S20: Determine the area to be avoided based on the trajectory of the dynamic target object.

[0036] It should be noted that the avoidance zone is the spatial range that a vehicle needs to avoid entering during its journey, defined by the trajectory of a dynamic target. This zone is formed by extending the predicted trajectory of the dynamic target through both horizontal and vertical safety procedures.

[0037] It should be understood that after obtaining the trajectory of a dynamic target, it is necessary to perform safety redundancy processing on the trajectory of the dynamic target to generate the area to be avoided.

[0038] In some embodiments, step S20 may include steps S21 to S23: Step S21: Obtain the target type, target speed, and target heading angle corresponding to the dynamic target trajectory.

[0039] It should be noted that the target object type is the category attribute to which a dynamic target object belongs, used to distinguish different types of traffic participants. Target object types include pedestrians, four-wheeled vehicles, two-wheeled vehicles, and large trucks, etc. Target object speed is used to characterize how fast a dynamic target object moves in its direction of motion. Target object heading angle is the angle of deflection of the dynamic target object's direction of motion relative to a reference direction, used to characterize the target object's orientation.

[0040] It should be understood that the sensing data collected by the sensing sensors can be used to extract the target object type, target object speed, and target object heading angle corresponding to the trajectory of the dynamic target object. Specifically, the pre-identified and classified target object type labels can be read from the dynamic target object information output by the sensing module, and the corresponding speed and heading angle measurements can be read to obtain the target object type, target object speed, and target object heading angle. If multiple dynamic target objects exist simultaneously at a certain moment, their corresponding type, speed, and heading angle can be extracted for each dynamic target object separately.

[0041] Step S22: Determine the lateral safety factor and the longitudinal safety factor based on the target type, the target speed, and the target heading angle.

[0042] It should be noted that the longitudinal safety factor is a weighted parameter used to determine the extent of the avoidance zone along the direction of the target's movement. A larger factor results in a wider longitudinal extension of the avoidance zone, allowing the vehicle to maintain a longer longitudinal safety distance from the dynamic target. The lateral safety factor is a weighted parameter used to determine the extent of the avoidance zone along the normal direction of the target's movement. A larger factor results in a wider lateral extension of the avoidance zone, requiring the vehicle to deviate a greater lateral distance away from the dynamic target. The lateral and longitudinal safety factors can be obtained through a pre-defined mapping relationship.

[0043] It should be understood that after obtaining the target type, target speed, and target heading angle, the longitudinal safety factor and the lateral safety factor can be determined separately.

[0044] In some embodiments, step S22 may include steps S221 to S222: Step S221: Determine the longitudinal safety factor based on the target object type and the target object speed.

[0045] It should be understood that the longitudinal safety coefficient can be determined by using the target object type and speed as input variables through a pre-defined longitudinal safety mapping relationship. The target object type determines the basic level of longitudinal safety; different types of targets have different basic weights due to differences in mass, braking capacity, and the randomness of their movement intentions. For example, when the target object types include trucks, pedestrians, two-wheeled vehicles, and four-wheeled vehicles, trucks have the highest longitudinal collision risk due to their extremely large mass and significantly longer braking distance compared to other types of targets, resulting in the highest basic level of longitudinal safety and a correspondingly higher longitudinal safety coefficient. Pedestrians have extremely high randomness in their movement intentions and can stop or turn back at any time, making their longitudinal uncertainty second only to trucks, and their basic level of longitudinal safety is the second highest. Two-wheeled vehicles have better longitudinal motion continuity than pedestrians but poorer stability, while four-wheeled vehicles have smooth acceleration and deceleration and predictable trajectories, resulting in relatively lower basic levels of longitudinal safety for both. That is, in the pre-defined longitudinal safety mapping relationship, at the same target object speed, the longitudinal safety coefficient values ​​for trucks, pedestrians, two-wheeled vehicles, and four-wheeled vehicles can decrease sequentially.

[0046] The target object's speed, as a regulating variable, has a gain effect on the longitudinal safety factor. The higher the speed, the greater the longitudinal displacement change of the target object, the longer the safety distance required for emergency braking of the vehicle, and the higher the longitudinal safety factor. The preset longitudinal safety mapping relationship can be stored in the planning module using a pre-calibrated lookup table method or an empirical fitting method. After obtaining the target object type and speed at the current moment, the planning module directly retrieves the mapping relationship and outputs the corresponding longitudinal safety factor value.

[0047] Step S222: Determine the lateral safety factor based on the target type and the target heading angle.

[0048] It should be understood that the lateral safety factor is determined by using the target object type and its heading angle as input variables through a pre-defined lateral safety mapping relationship. The target object type determines the basic level of lateral safety; different types of targets have different basic weights due to differences in their lateral motion degrees of freedom and physical stability. For example, when the target object type includes trucks, pedestrians, two-wheeled vehicles, and four-wheeled vehicles, two-wheeled vehicles have the highest basic lateral safety level because their physical instability causes significant lateral swaying at low speeds or when stationary, and they have strong agility in weaving. Pedestrians, although having high lateral movement degrees of freedom, typically have a smaller lateral swaying amplitude than two-wheeled vehicles, resulting in a lower basic lateral safety level. Four-wheeled vehicles, constrained by Ackermann steering, have continuous and predictable lateral displacement. Trucks, due to their long wheelbase and extremely slow heading angle changes, have relatively low basic lateral safety levels. That is, within the pre-defined lateral safety mapping relationship, under the same target object heading angle, the lateral safety factor values ​​for two-wheeled vehicles, pedestrians, four-wheeled vehicles, and trucks can decrease sequentially.

[0049] The target object's heading angle acts as a moderating variable, increasing the lateral safety factor. A larger heading angle increases the risk of lateral intrusion of the target object relative to the vehicle, and the lateral safety factor increases accordingly to accommodate the lateral positional uncertainty caused by changes in the heading angle. This preset lateral safety mapping relationship is stored in the planning module using a pre-calibrated lookup table method or empirical fitting method. After obtaining the target object type and heading angle at the current moment, the planning module directly retrieves this mapping relationship and outputs the corresponding lateral safety factor value.

[0050] In this embodiment, by correlating the determination of the longitudinal safety factor with the target type and target speed, the speed, a key factor that directly affects braking distance and longitudinal collision risk, can be adjusted in real time to adjust the magnitude of the longitudinal safety redundancy. By correlating the determination of the lateral safety factor with the target type and target heading angle, the heading angle, a key factor that directly reflects the lateral intrusion trend, can be adjusted in real time to adjust the magnitude of the lateral safety redundancy. Based on this, the obtained safety factor value can fit the actual risk changes in each dimension, ensuring safety while minimizing the ineffective occupation of path planning space due to excessive redundancy.

[0051] Step S23: Determine the area to be avoided based on the lateral safety factor, the longitudinal safety factor, and the trajectory of the dynamic target.

[0052] It should be understood that the longitudinal length and lateral width of the footprint of a dynamic target can be obtained. Multiplying the longitudinal safety factor by the corresponding longitudinal length yields the longitudinal length of the area to be avoided. Similarly, multiplying the lateral safety factor by the corresponding lateral width of the dynamic target's footprint yields the lateral width of the area to be avoided. Using each path point in the dynamic target's trajectory as the center, the area to be avoided is generated based on its longitudinal length and lateral width.

[0053] In this embodiment, by determining the longitudinal and lateral safety factors based on the target type, target speed, and target heading angle, different types of targets can obtain differentiated safety redundancy allocation in the longitudinal and lateral directions, thereby improving the success rate of path search and overall traffic efficiency while ensuring safety.

[0054] Step S30: Determine whether there is an available path based on the area to be avoided and the current perception point cloud, wherein the available path includes a cruise path and a parking path.

[0055] It should be noted that the current perception point cloud is a spatial occupancy status dataset obtained by the vehicle through the perception module to detect and discretize the environment at the current moment. This point cloud divides the environment around the vehicle into multiple regular spatial cubes and marks the occupied or vacant status information of each cube, reflecting the spatial layout of the static environment at the current moment.

[0056] Additionally, the available path is a safe passage route from the current vehicle position to the target parking space within the free space defined by the available point cloud. This route includes both the driving phase from the current position to the switching start point and the parking phase from the switching start point into the target parking space, and it does not overlap with any avoidable areas or obstacles at any time. The cruise path is the driving phase from the current vehicle position to the switching start point within the available paths in cruise mode, during which the vehicle maintains a relatively high speed along the road. The parking path is the parking phase from the switching start point into the target parking space within the available paths in parking mode, during which the vehicle is precisely adjusted to the target position using a low-speed maneuver.

[0057] It should be understood that after obtaining the area to be avoided, this area is superimposed on the current sensing point cloud. All spatial cubes covered by the area to be avoided are then removed from the current sensing point cloud, resulting in an updated available range point cloud. This available range point cloud represents the free space that simultaneously satisfies both static spatial constraints and dynamic safety constraints at the current moment. Subsequently, starting from the current vehicle position and ending at the target parking space, an integrated search for driving and parking paths is performed within the free space defined by the available range point cloud.

[0058] Furthermore, all candidate parking trajectory schemes are traversed, and each candidate trajectory is broken down into multiple single-step parking maneuvering routes from the switching start point to the parking end point. A corresponding estimated travel time is assigned to each single-step route. Then, each single-step route is verified to ensure that it falls completely within the free space defined by the available point cloud at the corresponding time and does not overlap with the area to be avoided in time and space. If at least one candidate trajectory has all its single-step parking maneuvering routes pass the above spatial and temporal verifications, then a usable path is determined to exist, and this candidate trajectory is divided into a cruising path and a parking path.

[0059] Please refer to Figure 2 , Figure 2 This is a schematic diagram of the available paths provided in Embodiment 1 of the parking control method of the present invention. Figure 2 As shown, ① represents the cruise path, and ② represents the parking path. The cruise path and the parking path together constitute the available paths.

[0060] In some embodiments, steps A10 to A20 may be included before step S30: Step A10: Acquire obstacle perception data, parking space perception data, and lane perception data.

[0061] It should be noted that obstacle perception data is a collection of information about various obstacles obtained by the perception module after sensing the environment around the vehicle. This includes the spatial location information of the obstacles, the category attribute information of the obstacles, and the motion state information of the obstacles.

[0062] Parking space perception data is a set of spatial attribute information about a target parking space obtained by the perception module after sensing the target parking area. This data is used to describe the geometric features and occupancy status of the target parking space. Lane perception data is a set of information about the lane layout obtained by the perception module after sensing the road environment in which the vehicle is currently traveling. This data is used to describe the structural features and traffic attributes of the road surrounding the vehicle.

[0063] It should be understood that before the vehicle approaches the target parking space and executes path planning, it comprehensively perceives the environment through onboard sensors. Specifically, the perception module collects raw environmental signals through various sensors such as LiDAR, millimeter-wave radar, ultrasonic radar, and cameras, and processes and identifies these signals to extract obstacle perception data, including the position and height information of all static obstacles around the vehicle, as well as the type, speed, heading angle, and area occupied by dynamic objects; it also extracts parking space perception data, including the type of target parking space, such as marked parking space or open space parking space, perpendicular, parallel, or angled parking space, the opening direction of the parking space, the size of the parking space, and the occupancy status of the parking space; and it also extracts lane perception data, including the number of lanes on the current road, such as single lane, double lane, or multi-lane, lane width, lane direction (same direction or opposite direction), and traffic density information of the area where the lane is located.

[0064] Furthermore, before acquiring obstacle perception data, parking space perception data, and lane perception data, the perception system undergoes range tuning to determine an appropriate environmental perception range. This ensures that the system's detection area covers the maximum safe distance and lateral width required for vehicle parking. Simultaneously, perception model training is performed, training and defining recognition models for different types of perceived targets such as pedestrians, four-wheeled vehicles, two-wheeled vehicles, large trucks, parking spaces, and lane lines. This enables the perception system to accurately distinguish different categories of targets and output corresponding classification labels. Through this tuning and training, the perception system can stably output accurate obstacle type labels, speed measurements, heading angle measurements, and spatial attribute information for parking spaces and lanes.

[0065] Furthermore, when the vehicle's cruising position approaches the target parking space, the perception system classifies the environmental information perceived through pre-tuned and defined perception strategies. The classification results include at least three categories: obstacles, parking spaces, and lanes. Obstacle perception includes the identification of the environmental boundaries around the vehicle and road traffic participants. According to the type of obstacle, it is further divided into static obstacles and dynamic obstacles. Static obstacles are further divided into low-attribute obstacles and high-attribute obstacles based on their relationship with the height of the vehicle's lower edge. Low-attribute obstacles are low-lying objects that are lower than the lower edge of the vehicle and do not affect vehicle passage, such as protruding bricks, low curbs, low steps, the edges of parking spaces in scenic areas, and the edges of drainage ditches. High-attribute obstacles are taller objects that are higher than the lower edge of the vehicle and pose a collision risk, such as walls, pillars, and guardrails. Dynamic obstacles are classified by type as pedestrians, four-wheeled vehicles, two-wheeled vehicles, and large trucks. Parking space perception includes information on the target parking space, such as parking space type, parking space opening direction, parking space size, and parking space occupancy status. Parking space types include marked parking spaces and open spaces, as well as perpendicular, parallel, and angled parking spaces. Lane perception includes information on the number of lanes, lane width, lane direction, and traffic density of the lane. The number of lanes includes single lanes, two lanes, and multiple lanes, and the lane direction includes same-direction and opposite-direction.

[0066] Step A20: Generate the current perception point cloud based on the obstacle perception data, parking space perception data, and lane perception data.

[0067] It should be understood that after acquiring obstacle perception data, parking space perception data, and lane perception data, these three types of data are fused to generate the current perception point cloud. First, based on preset spatial division dimensions, the environmental space within a certain range around the vehicle is divided into multiple uniformly sized spatial cubes in a three-dimensional coordinate system, each cube corresponding to a specific spatial position coordinate. Then, the spatial position and outline dimensions of each obstacle in the obstacle perception data are mapped onto the corresponding spatial cube. Cubes occupied by obstacles whose height is greater than or equal to the lower edge of the vehicle body are marked as occupied. Cubes occupied by dynamic targets at the current moment are also marked as occupied. Simultaneously, the outline position of the target parking space in the parking space perception data is mapped onto the corresponding spatial cube, and the cubes of the parking space area are marked as having a special parking space attribute state. Finally, the position of the lane boundary in the lane perception data is mapped onto the corresponding spatial cube, and the cubes within the lane are marked as passable. After the above mapping and marking process, the state information of all spatial cubes together constitutes the current perception point cloud.

[0068] In this embodiment, obstacle perception data, parking space perception data, and lane perception data are acquired separately, and the three types of perception data are fused and discretized into the current perception point cloud. This transforms continuous and heterogeneous environmental information into structured spatial data in a unified format, providing a computational basis for subsequent path planning that can be directly used for collision detection and spatial search, thereby improving the accuracy and execution efficiency of path planning.

[0069] In some embodiments, after step S30, steps B10 to B20 may be included: Step B10: If no available path exists, control the vehicle to stop and wait based on a preset safe distance.

[0070] It should be noted that the preset safety distance is a pre-set threshold value used to determine the minimum distance between the vehicle's braking position and surrounding obstacles or areas to be avoided. This distance ensures that the vehicle will not collide with any obstacles while braking, and its value is pre-calibrated based on the vehicle's braking performance and the safety requirements of the surrounding environment. Vehicle braking and waiting refers to the process where, after determining that there is no feasible path, the vehicle performs a braking operation to bring it to a complete stop and remains stationary while waiting for changes in the environment. During this process, the vehicle is in a stationary, standby state.

[0071] It should be understood that when no available path is determined, the vehicle cannot safely continue to the target parking space at the current moment, triggering a braking and waiting process. First, a preset safe distance is obtained. Then, the vehicle is controlled to perform deceleration and braking operations, gradually slowing down along the current trajectory until it comes to a complete stop. This ensures that the final stopping position maintains a distance of at least the preset safe distance between itself and the outlines of all surrounding static obstacles and the outer edges of the avoidable areas of dynamic objects. This distance serves as a safety buffer to prevent accidental collisions caused by braking errors or sudden environmental changes. Once the vehicle comes to a complete stop, it enters a braking and waiting state. In this state, the vehicle remains stationary while continuously monitoring changes in the surrounding environment, including updates to the positions of static obstacles and the trajectories of dynamic objects, so that the path search process can be restarted promptly once environmental conditions improve.

[0072] Step B20: If the vehicle has been stopped for a longer period than the preset waiting time, push a driver takeover message.

[0073] It should be noted that the preset waiting time is a pre-set upper limit for the duration a vehicle can remain in a stopped waiting state. This time is used to determine whether the waiting replanning process has exceeded the acceptable time range, preventing vehicles from waiting indefinitely and causing delays in the overall parking task or road occupancy. Driver takeover information is a notification used to prompt the driver to regain control of the vehicle. This information is presented to the driver through the human-machine interface using visual or auditory prompts.

[0074] It should be understood that after the vehicle enters the braking and waiting state, a timer is started and continuously records the cumulative duration of the braking and waiting. Within each control cycle, this cumulative duration is compared with a preset waiting time. When the braking and waiting time exceeds the preset waiting time, it indicates that no available time window has appeared within the allowed waiting time range, and the vehicle cannot automatically complete path planning and continue the parking task within a reasonable time. In this case, a driver takeover message is pushed to the driver through a human-machine interface such as a head-up display, instrument panel, or central display screen. This message includes at least a text description prompting the driver to regain control of the vehicle and a corresponding graphic symbol. After receiving this takeover message, the driver can manually take over the vehicle and complete the subsequent parking operation. If the driver successfully takes over, the automatic parking control process exits, and vehicle control is completely transferred to the driver.

[0075] Additionally, if no available path exists, when the braking wait time is less than or equal to the preset planned waiting limit, the system returns to the path planning step and continues to determine if an available parking path exists. That is, during the braking wait, the system repeatedly performs path search to detect if an available path appears. When the braking wait time exceeds the preset waiting time, the system pushes a driver takeover message and exits the function.

[0076] In this embodiment, by controlling the vehicle to stop and wait at a preset safe distance when no available path exists, the vehicle is given the opportunity to regain an available path after dynamic environmental changes. This avoids the interruption of the driving experience caused by immediately disengaging the function once no feasible path is available. At the same time, it also avoids the collision risk that may be caused by the vehicle continuing to drive blindly when no path is available. By setting a preset waiting time and pushing a driver takeover information after the timeout, the system stagnation state and road occupation problems caused by the vehicle waiting indefinitely are reduced, ensuring that the driver can take over in time when the automatic control cannot complete the parking.

[0077] Step S40: If an available path exists and the vehicle reaches the end of the cruise path, switch from cruise mode to parking mode, and control the vehicle to drive to the target parking space based on the parking path to complete parking control.

[0078] It should be noted that the end of the cruise path is the dividing point between the driving cruise phase and the parking phase within the available path. It is the starting position point where the vehicle ends cruise driving and begins parking operations. This point marks the end of the driving phase and the beginning of the parking phase. Cruise mode refers to a driving mode where the navigation system controls the vehicle to maintain a relatively high speed along a preset route. This mode emphasizes long-distance travel efficiency and lane keeping. Parking mode refers to a driving mode where the navigation system controls the vehicle to perform precise positional adjustments at extremely low speeds. This mode emphasizes accurately parking the vehicle into the target parking space in tight spaces through multiple forward and reverse maneuvers.

[0079] It should be understood that, after determining the existence of an available path and dividing it into a cruise path and a parking path, the cruise path will be used as the control target for the current driving phase, and the real-time position of the vehicle while traveling along the cruise path will be continuously monitored. When the vehicle reaches the end of the cruise path, which is also the switching start point, there is no need to stop and wait; instead, the switching operation from cruise mode to parking mode will be executed immediately. After the switch is completed, the previously planned parking path will be used as the control target, and longitudinal control information and lateral control information will be decomposed based on the parking path.

[0080] Furthermore, the longitudinal control information includes at least parking speed control commands and travel distance control commands, while the lateral control information includes at least steering wheel angle control commands. Following these control commands, the vehicle is driven to perform forward and reverse movements, gradually adjusting its position along the parking path and ultimately entering the designated position of the target parking space, thus completing the parking control.

[0081] Furthermore, during the lateral and longitudinal control of the vehicle according to the planned path, the planned control results and the vehicle's actual execution status are transmitted to the planning correction module. This module combines driving prerequisite information, spatial environment update information, available time interval update information, and actual execution status information to dynamically fine-tune the overall route planning. Driving prerequisite information includes basic state parameters affecting vehicle handling response, such as the vehicle's current load and power mode. Spatial environment update information refers to real-time updates of static obstacle positions and dynamic target trajectories over time. Available time interval update information refers to updates of the passable spacetime window due to changes in the motion state of dynamic targets. Actual execution status information refers to the deviation data between the vehicle's actual driving trajectory and the planned trajectory. Through correction, the vehicle can adjust its subsequent path in real time when the environment changes or deviations occur, avoiding pauses caused by the accumulation of small deviations requiring a re-search of the global path, thus ensuring the continuity and smoothness of the entire driving to parking process.

[0082] This embodiment proactively predicts the trajectory of dynamic objects as the vehicle approaches the target parking space and determines the avoidance area based on the trajectory. This enables the active use of environmental information. By fusing the avoidance area with the current perception point cloud and performing an integrated search of the cruise path and parking path, it determines whether an available path exists. This achieves unified path planning for the driving and parking phases, avoiding the waiting time in traditional solutions where the vehicle first cruises to the vicinity of the parking space and then switches to the parking state machine for path planning. This improves the continuity of the transition from driving to parking, shortens the total time required to complete parking, and enhances the smoothness of the driving experience.

[0083] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S30 may include steps S31 to S34: Step S31: Obtain the obstacle height of the static obstacle.

[0084] It should be noted that static obstacles are objects in the environment surrounding a vehicle that are stationary and do not move on their own. The position and shape of such obstacles do not change in a short period of time, such as walls, pillars, guardrails, curbs, and steps. Obstacle height is a measure of the vertical distance of a static obstacle from the ground to its highest point. This value is used to determine whether the obstacle will have a substantial impact on vehicle passage.

[0085] It should be understood that vehicle-mounted sensors, such as lidar or millimeter-wave radar, detect the environment and acquire three-dimensional spatial data of all static obstacles around the vehicle. The height information of each static obstacle is then extracted from this data. Specifically, the sensors emit detection signals and receive reflected signals. The distance between each point on the obstacle surface and the sensor is calculated based on the round-trip time of the signals. Combined with the sensor's installation location and orientation, the three-dimensional coordinates of each point on the obstacle surface in space can be calculated, thus obtaining the highest point height value of the obstacle. This height value is recorded as the obstacle height and used for subsequent obstacle screening.

[0086] Step S32: Determine the obstacle to be avoided from the static obstacles based on the obstacle height.

[0087] It should be noted that obstacles to be avoided are a set of obstacles selected from all static obstacles that may pose a collision risk to vehicle passage in terms of spatial height. These obstacles need to be actively avoided on the vehicle's travel path.

[0088] It should be understood that after obtaining the height of each static obstacle, the obstacle height can be compared with the height of the lower edge of the vehicle body to determine whether the corresponding static obstacle is an obstacle that needs to be avoided.

[0089] In some embodiments, step S32 may include steps S321 to S322: Step S321: Obtain the height of the lower edge of the vehicle body.

[0090] It should be noted that the vehicle's lower edge height is the vertical distance from the lowest point of the vehicle's bottom to the ground. This value represents the maximum height of obstacles the vehicle can safely cross. The lower edge height can be pre-stored as an inherent parameter in the vehicle's configuration information. Its value is determined by the minimum ground clearance of the vehicle's chassis design, and different vehicle models have different lower edge heights.

[0091] It should be understood that when performing static obstacle screening, the lower edge height information of the vehicle body is first read from the vehicle's overall parameter storage module. This information can be obtained from the vehicle's electronic control unit via the controller area network bus when the vehicle starts, or it can be read from a pre-configured vehicle parameter file when the parking control function is activated.

[0092] Step S322: If the height of the obstacle is greater than or equal to the height of the lower edge of the vehicle body, the static obstacle is determined to be an obstacle that needs to be avoided.

[0093] It should be understood that after obtaining the height of the vehicle's lower edge and the heights of various static obstacles, the height of each static obstacle is compared with the height of the vehicle's lower edge. If the height of a static obstacle is greater than or equal to the height of the vehicle's lower edge, it means that the highest point of the obstacle is higher than or equal to the lowest point of the vehicle's chassis. When the vehicle approaches the obstacle, the obstacle will contact or collide with the vehicle's chassis. Therefore, the obstacle poses a substantial collision risk to the vehicle's passage, and this static obstacle is identified as an obstacle to be avoided. If the height of a static obstacle is less than the height of the vehicle's lower edge, it means that the highest point of the obstacle is lower than the lowest point of the vehicle's chassis. The vehicle can safely pass over the obstacle without any contact. Therefore, this static obstacle is not identified as an obstacle to be avoided, and no active avoidance is required in subsequent path planning.

[0094] In this embodiment, by comparing the height of each static obstacle with the height of the vehicle's lower edge, only obstacles with a height greater than or equal to the vehicle's lower edge are identified as obstacles to be avoided. This excludes low-lying objects below the vehicle's lower edge, such as protruding bricks, low curbs, low steps, the edges of parking spaces in scenic areas, or the edges of drainage ditches, from the avoidance range. This effectively reduces the number of invalid constraints in the path planning process and minimizes the excessive detours and increased number of road maneuvers caused by excessive avoidance of low obstacles. Thus, while ensuring collision safety, this improves the efficiency of path planning and the smoothness of the generated path.

[0095] Step S33: Determine the available range point cloud from the current perceived point cloud based on the area to be avoided and the obstacle to be avoided.

[0096] It should be noted that the available range point cloud is the free space dataset remaining after removing all impassable areas from the current perceived point cloud. This point cloud represents the entire spatial range that vehicles can safely pass through at the current moment, excluding both the areas occupied by static obstacles and the areas that dynamic objects may occupy in the future.

[0097] It should be understood that after determining the avoidable area and the obstacle to be avoided, two elimination operations are performed based on the current perception point cloud as the base data. The first elimination operation marks all spatial cubes in the current perception point cloud that are covered by the avoidable area as unusable. This avoidable area is a tubular spatial region formed by the safe horizontal and vertical extension of the predicted trajectory of the dynamic target, representing the space that the dynamic target may occupy in the future. The second elimination operation marks all spatial cubes in the current perception point cloud that are occupied by the obstacle to be avoided. This obstacle is a static obstacle with a height higher than the lower edge of the vehicle body, representing an impassable physical obstacle in a static environment. After these two elimination operations, all the remaining spatial cubes in the current perception point cloud that were not marked as unusable together constitute the usable area point cloud.

[0098] Step S34: Determine whether there is an available path based on the available range point cloud.

[0099] It should be noted that the available path is a safe passage route from the current vehicle position to the target parking space within the free space defined by the available point cloud. This route includes both the driving stage route from the current position to the switching start point and the parking stage route from the switching start point to the target parking space. Moreover, this route does not overlap with any avoidable areas or obstacles at any time.

[0100] It should be understood that after obtaining the available range point cloud, this point cloud is used as the spatial constraint for path search, performing an integrated search for driving and parking paths. The search process starts from the current vehicle position and ends at the target parking space, traversing all possible candidate trajectories within the free space defined by the available range point cloud. Each candidate trajectory is broken down into multiple consecutive single-step driving segments according to the vehicle's gear shifting point. A corresponding estimated driving time is assigned to each single-step driving segment, and the spatial pose of each single-step driving segment at the corresponding time is verified to ensure that it completely falls within the free space marked by the available range point cloud. If at least one candidate trajectory has all single-step driving segments that pass the above spatial and temporal dimension verification, then a usable path is determined to exist; if all candidate trajectories have at least one single-step driving segment that overlaps with an unusable area in the available range point cloud, then a usable path is determined not to exist.

[0101] Please refer to Figure 4 , Figure 4 This is a schematic diagram of cruise control provided in Embodiment 2 of the parking control method of the present invention. Figure 4 As shown, the vehicle is in the cruise phase. The blue area represents the available point cloud, area 10 represents the area to be avoided, and ① represents the cruise path in the available path.

[0102] Please refer to Figure 5 , Figure 5 This is a schematic diagram of cruise control provided in Embodiment 2 of the parking control method of the present invention. Figure 4 As shown, the vehicle is currently at the cruise mode switching point. The blue area represents the available range point cloud, area 10 represents the area to be avoided, and ② represents the parking path in the available path.

[0103] In the specific implementation, during the process of determining whether there is an available path based on the available range point cloud, the system acquires information such as traversing parking lines, vehicle size information, overall switching start point information, overall parking end point information, information on each individual parking line, and the individual parking time information corresponding to each individual parking line. The traversing parking line information is a set of all candidate trajectories that can theoretically reach the target parking space from the switching start point, enumerated by the planning module in order to find feasible paths.

[0104] Among them, the vehicle size information is the physical outline geometric parameters of the vehicle itself, including the vehicle length, width and wheelbase; the overall switching start point information is the starting pose point corresponding to the end of the cruise phase and the start of parking planning; the overall parking end point information is the target pose expected to be reached when the vehicle finally parks in the target parking space; the single-step parking traverse information is the set of single-step driving paths formed by decomposing the complete parking trajectory into multiple independent forward or reverse action segments according to the vehicle gear shift point; and the single-step parking traverse time information corresponding to each single-step parking traverse is the estimated driving time required to complete each single-step parking traverse.

[0105] Starting from the current vehicle position and ending at the target parking space, all candidate trajectories are traversed within the free space defined by the available point cloud. Each candidate trajectory is decomposed into multiple single-step parking maneuvering routes from the overall switching start point to the overall parking end point. A corresponding estimated travel time is assigned to each single-step route. Then, the vehicle contour pose of each single-step route at the corresponding time is checked to see if it completely falls within the free space defined by the available point cloud and does not overlap with the area to be avoided in time and space. If all single-step parking maneuvering routes of at least one candidate trajectory pass the above checks, then it is determined that there is a usable path.

[0106] Please refer to Figure 6 , Figure 6 This is a schematic diagram of the path planning module provided in Embodiment 1 of the parking control method of the present invention. Figure 6 As shown, the planning module includes a perception-prediction fusion submodule, a driving-parking path planning submodule, and a planning correction submodule. The perception-prediction fusion submodule first obtains the dynamic target object Odi at time i. The dynamic target object carries velocity v information, heading angle θ information, and land area A information. Based on the above information, the predicted path Pi(Odi,v,θ,A) of the dynamic target object is generated. Subsequently, the longitudinal safety factor α = f(v, K) is determined based on the target object type K and velocity v, and the lateral safety factor β = f(θ, K) is determined based on the target object type K and heading angle θ. Then, the predicted path Pi is subjected to safety expansion processing using the longitudinal and lateral safety factors α and β to generate a non-collision path Pin(Odi, v, θ, A, α, β). This non-collision path Pin contains comprehensive information on the velocity v, heading angle θ, occupied area A, longitudinal safety factor α, and lateral safety factor β of the dynamic target object Odi. The non-collision path Pin is then fused with the current sensing point cloud Bi, and the entire spatial region covered by the non-collision path Pin is removed from the sensing point cloud Bi(Xi, Yi, Zi). Finally, the usable range point cloud Ti(Xi, Yi, Zi, Pin) is generated. This usable range point cloud Ti contains spatial coordinates Xi, Yi, Zi, and the constraint information of the non-collision path Pin.

[0107] Upon receiving the available range point cloud Ti, the driving-parking path planning submodule acquires the traversal parking route J information, vehicle size Sz information, overall switching start point St information, overall parking end point Ds information, each single-step parking maneuver route Li information, and the corresponding single-step parking maneuver time ti information. Based on the above information, it performs overall route planning to determine whether an available path Piy(J,Sz,St,Ds,Li,ti,Ai) exists. If an available path exists, vehicle control planning is executed. Vehicle control planning is further decomposed into longitudinal control and lateral control, and the actual execution status is passed to the execution correction module to generate execution correction information. At the same time, the planning result is passed to the planning correction module to output comprehensive correction information Ai for subsequent path rolling optimization. If no available path exists, it further checks whether the braking waiting time Tw is greater than the preset planning waiting upper limit Tw0. If the braking waiting time Tw is greater than the preset planning waiting upper limit Tw0, the planning process is exited. If the braking waiting time Tw is less than or equal to the preset planning waiting upper limit Tw0, the overall route planning step is returned and the existence of an available path is continuously checked. The comprehensive correction information Ai output by the planning correction module includes forward-looking correction information, idle correction information, time correction information, and execution correction information. Forward-looking correction information is used to make forward-looking adjustments to the path that has not yet been executed based on changes in the environment ahead. Idle correction information is used to optimize the subsequent path while the vehicle is stationary. Time correction information is used to dynamically correct the time allocation of the subsequent single-step traverse route based on the deviation between the actual travel time and the estimated time. Execution correction information is used to correct the subsequent control commands in real time based on the deviation between the actual posture of the vehicle and the planned posture.

[0108] Please refer to Figure 7 , Figure 7 This is a simplified flowchart illustrating a second embodiment of the parking control method of the present invention. Figure 7 As shown, the system first loads mapping information, navigation information, and real-time environmental information and completes parameter initialization. Then, it activates the parking space-to-parking space function and controls the vehicle to start cruising along a preset route. During the vehicle's cruising, it continuously judges whether the current cruising path is close to the target parking space. If the cruising path is not close to the target parking space, it controls the vehicle to continue cruising. If the cruising path is close to the target parking space, it triggers the perception module to collect and classify environmental information and transmits the perception results to the planning module to perform integrated search of driving and parking paths and determination of available paths. After determining that there is an available path, it controls the vehicle to switch from cruising mode to parking mode and drive to the target parking space according to the planned path. Finally, it completes the parking operation and ends the current function flow.

[0109] This embodiment obtains the height of static obstacles and compares it with the height of the vehicle's lower edge. Low-attribute obstacles such as low curbs and steps are excluded from the avoidance range. This avoids excessive avoidance of low objects that do not affect passage by the path planning, thereby reducing unnecessary path detours and parking maneuvers. At the same time, by using the avoidance area and the avoidance obstacle as constraints to remove them from the current perception point cloud to generate an usable range point cloud, the unified integration of static obstacle constraints and dynamic target constraints is achieved. This allows the path planning to process information from both static and dynamic environments on a single spatial representation, improving the accuracy and efficiency of path search.

[0110] Furthermore, embodiments of the present invention also propose a storage medium storing a parking control program, which, when executed by a processor, implements the steps of the parking control method described above.

[0111] Reference Figure 8 , Figure 8 This is a structural block diagram of the first embodiment of the parking control device of the present invention.

[0112] like Figure 8 As shown, the parking control device proposed in this embodiment of the invention includes: The data prediction module 10 is used to predict the trajectory of a dynamic target object based on its type, motion parameters, and area when the distance between the current vehicle's cruising position and the target parking space is less than or equal to a preset distance. Data processing module 20 is used to determine the area to be avoided based on the trajectory of the dynamic target object; The path determination module 30 is used to determine whether there is an available path based on the area to be avoided and the current perception point cloud, wherein the available path includes a cruise path and a parking path; The driving control module 40 is used to switch from cruise mode to parking mode when there is an available path and the vehicle reaches the end of the cruise path, and to control the vehicle to drive to the target parking space based on the parking path to complete the parking control.

[0113] The parking control device provided in this application, employing the parking control method in the above embodiments, can solve the technical problem of how to improve the continuity of the transition from driving to parking, thereby reducing parking transition time. Compared with the prior art, the beneficial effects of the parking control device provided in this application are the same as those of the parking control method provided in the above embodiments, and other technical features in the parking control device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0114] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0115] This embodiment proactively predicts the trajectory of dynamic objects as the vehicle approaches the target parking space and determines the avoidance area based on the trajectory. This enables the active use of environmental information. By fusing the avoidance area with the current perception point cloud and performing an integrated search of the cruise path and parking path, it determines whether an available path exists. This achieves unified path planning for the driving and parking phases, avoiding the waiting time in traditional solutions where the vehicle first cruises to the vicinity of the parking space and then switches to the parking state machine for path planning. This improves the continuity of the transition from driving to parking, shortens the total time required to complete parking, and enhances the smoothness of the driving experience.

[0116] This application provides a parking control device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the parking control method in Embodiment 1 above.

[0117] The following is for reference. Figure 9 The diagram illustrates a structural schematic of a parking control device suitable for implementing embodiments of this application. The parking control device in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 9 The parking control device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0118] like Figure 9As shown, the parking control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in ROM (Read Only Memory) 1002 or a program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the parking control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. Input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touch screens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, LCDs (Liquid Crystal Displays), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the parking control device to communicate wirelessly or wiredly with other devices to exchange data. Although the figures show parking control devices with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented alternatively.

[0119] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0120] The parking control device provided in this application, employing the parking control method described in the above embodiments, can solve the technical problem of how to improve the continuity of the transition from driving to parking, thereby reducing parking transition time. Compared with the prior art, the beneficial effects of the parking control device provided in this application are the same as those of the parking control method provided in the above embodiments, and other technical features of this parking control device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0121] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0122] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0123] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the parking control method in the above embodiments.

[0124] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory), or flash memory, optical fiber, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0125] The aforementioned computer-readable storage medium may be included in the parking control device; or it may exist independently and not be assembled into the parking control device.

[0126] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the parking control device, the parking control device: when the distance between the current vehicle's cruising position and the target parking space is less than or equal to a preset distance, predicts the trajectory of the dynamic target object based on its type, motion parameters, and area; determines a avoidance zone based on the dynamic target object's trajectory; determines whether an available path exists based on the avoidance zone and the current perception point cloud, wherein the available path includes a cruising path and a parking path; and, if an available path exists and the vehicle reaches the end of the cruising path, switches from cruising mode to parking mode and controls the vehicle to drive to the target parking space based on the parking path, thus completing the parking control.

[0127] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0129] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0130] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described parking control method. This solves the technical problem of how to improve the continuity of the transition from driving to parking, thereby reducing parking transition time. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the parking control method provided in the above embodiments, and will not be repeated here.

[0131] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the parking control method described above.

[0132] The computer program product provided in this application solves the technical problem of how to improve the continuity of the driving-to-parking transition to reduce parking transition time. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the parking control method provided in the above embodiments, and will not be repeated here.

[0133] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A parking control method, characterized in that, The parking control method includes: When the distance between the current vehicle's cruising position and the target parking space is less than or equal to a preset distance, the trajectory of the dynamic target object is predicted based on the type, motion parameters, and area occupied by the dynamic target object. The area to be avoided is determined based on the trajectory of the dynamic target object; The availability of a path is determined based on the area to be avoided and the current perception point cloud, wherein the available path includes a cruise path and a parking path; If an available path exists and the vehicle reaches the end of the cruise path, switch from cruise mode to parking mode, and control the vehicle to drive to the target parking space based on the parking path to complete parking control.

2. The method as described in claim 1, characterized in that, The step of determining the area to be avoided based on the trajectory of the dynamic target object includes: Obtain the target type, target speed, and target heading angle corresponding to the dynamic target trajectory; The lateral safety factor and the longitudinal safety factor are determined based on the target type, the target speed, and the target heading angle. The area to be avoided is determined based on the lateral safety factor, the longitudinal safety factor, and the trajectory of the dynamic target.

3. The method as described in claim 2, characterized in that, The step of determining the lateral safety factor and the longitudinal safety factor based on the target type, the target speed, and the target heading angle includes: The longitudinal safety factor is determined based on the type and velocity of the target object. The lateral safety factor is determined based on the target type and the target heading angle.

4. The method as described in claim 1, characterized in that, The step of determining whether a usable path exists based on the area to be avoided and the current perceived point cloud includes: Obtain the obstacle height of static obstacles; The obstacle to be avoided is determined from the static obstacles based on the obstacle height. Based on the area to be avoided and the obstacle to be avoided, determine the available range point cloud from the current perceived point cloud; Determine whether an available path exists based on the available range point cloud.

5. The method as described in claim 4, characterized in that, The step of determining the obstacle to be avoided from the static obstacles based on the obstacle height includes: Obtain the height of the lower edge of the vehicle body; If the height of the obstacle is greater than or equal to the height of the lower edge of the vehicle body, the static obstacle is determined to be an obstacle that needs to be avoided.

6. The method according to any one of claims 1 to 5, characterized in that, After the step of determining whether an available path exists based on the area to be avoided and the current perceived point cloud, the method further includes: If no available path exists, the vehicle will be stopped and wait based on a preset safe distance. If the vehicle stops and waits for a longer period than the preset waiting time, a driver takeover message will be sent.

7. The method according to any one of claims 1 to 5, characterized in that, Before the step of determining whether an available path exists based on the area to be avoided and the current perceived point cloud, the method further includes: Acquire obstacle perception data, parking space perception data, and lane perception data; The current perception point cloud is generated based on the obstacle perception data, parking space perception data, and lane perception data.

8. A parking control device, characterized in that, The device includes: The data prediction module is used to predict the trajectory of a dynamic target object based on its type, motion parameters, and area when the distance between the current vehicle's cruising position and the target parking space is less than or equal to a preset distance. The data processing module is used to determine the area to be avoided based on the trajectory of the dynamic target object; The path determination module is used to determine whether there is an available path based on the area to be avoided and the current perception point cloud, wherein the available path includes a cruising path and a parking path; The driving control module is used to switch from cruise mode to parking mode when an available path exists and the vehicle reaches the end of the cruise path, and to control the vehicle to drive to the target parking space based on the parking path to complete the parking control.

9. A parking control device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the parking control method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the parking control method as described in any one of claims 1 to 7.