Automatic parking method and system for stereo garage

Abstract

The invention provides an automatic parking method and system for a stereo garage, and the method comprises the steps: recognizing a baffle plate for limiting a target parking space under the condition that the type of the target parking space is determined to be a stereo garage, and determining the width of the target parking space based on the baffle plate; at least partially based on the parking space width of the target parking space, determining a parking starting position capable of realizing one-time reversing parking under the condition that wheels of the vehicle do not collide with a baffle; calculating a driving route for parking the vehicle into the target parking space at least partially based on the current position of the vehicle and the determined parking starting position, the driving route at least comprising a first section of driving route from the current position of the vehicle to the parking starting position, the second section of driving route is from the parking starting position to the target parking space; and controlling the vehicle to be automatically parked in the target parking space according to the determined driving route.

Description

Technical Field

[0001] The present invention relates to a driving assistance technology, and more particularly, to an automatic parking method and system for a stereo garage. Background Art

[0002] Automated parking refers to the process of automatically identifying parking spaces and parking the car without human intervention through the coordination of onboard sensors, processors and control systems. The automatic parking system can greatly simplify the parking process, especially for novice drivers, and can bring an intelligent and convenient user experience. As a driving assistance function, more and more car models have been equipped with automatic parking function.

[0003] However, there are many limitations and problems with current automatic parking, the most important of which is that the automatic parking function is not applicable in all scenarios. Typically, automatic parking mostly only supports two types of parking: perpendicular parking (also known as "reverse parking") and parallel parking (also known as "side parking"), and for each type, specific spatial conditions need to be met, that is, there needs to be enough distance in front, behind, left and right of the parking space to avoid vehicle collisions. Limited by the detection range and accuracy of the sensor, the spatial distance required by the automatic parking function of various manufacturers is relatively high, usually much higher than the space requirements for experienced human drivers to manually park the vehicle into the parking space. This results in the automatic parking function being unable to be used in situations where users need and hope that the vehicle can provide driving assistance, such as situations where the space is small and parking is more difficult.

[0004] For example, current automatic parking is generally not applicable to parking spaces with three-dimensional parking equipment (hereinafter referred to as "three-dimensional parking garages"), and the factors that restrict the realization of automatic parking functions for three-dimensional parking garages mainly include:

[0005] (1) The places where stereo garages are installed (such as office buildings and shopping malls) need to park as many vehicles as possible in a limited area, so the space is generally small;

[0006] (2) Conventional automatic parking requires identifying parking spaces by identifying white lines on the ground, but parking spaces in a multi-story parking garage do not have white lines for identification;

[0007] (3) Stereoscopic parking garages are usually installed underground or indoors, where the ambient light is dim, which places high demands on the sensor's capabilities and accuracy, increasing the possibility of collision;

[0008] (4) The width of parking spaces in a three-dimensional garage is generally much narrower than that of conventional parking spaces, and it is impossible to squeeze into the line, which further increases the difficulty of parking;

[0009] (5) Unlike conventional parking spaces that are on a flat surface, a multi-story parking garage requires the vehicle to be driven onto a parking plate, which usually requires additional control of the accelerator and brakes. It cannot be achieved by simply controlling the vehicle at a slow and constant speed like conventional automatic parking.

[0010] Therefore, the current automatic parking does not support stereo garage parking spaces, which reduces the attractiveness of the automatic parking function for users. In addition, for high-level automatic driving or even driverless cars, the lack of this function is unacceptable. Summary of the invention

[0011] This Summary is provided to introduce some concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0012] Based on the above problems, the purpose of the present invention is to provide an automatic parking solution suitable for a multi-story parking garage, which can achieve safe and precise vehicle control in a small and dim space through the coordination of a sensor system and optimization of parking logic and parking routes.

[0013] According to a first aspect of the present invention, there is provided an automatic parking method for a stereoscopic parking garage, comprising: in response to receiving an instruction to start an automatic parking function, determining the type of parking spaces around a vehicle; in response to determining that the parking space type is a stereoscopic parking garage, searching for and determining a target parking space; identifying a baffle defining the target parking space, and determining the parking space width of the target parking space based on the baffle; determining, at least in part based on the parking space width of the target parking space, a parking starting position that enables a single reverse parking into the garage while keeping the wheels of the vehicle from colliding with the baffle; calculating, at least in part based on the current position of the vehicle and the determined parking starting position, a driving route for parking the vehicle into the target parking space, wherein the driving route includes at least a first driving route from the current position of the vehicle to the parking starting position, and a second driving route from the parking starting position to the target parking space; and controlling the vehicle to automatically park into the target parking space according to the determined driving route.

[0014] According to a further embodiment of the present invention, determining a parking starting position that can realize a reverse parking into a garage while keeping the vehicle's wheels from colliding with the fender further includes: detecting the environment in front of the target parking space to determine the parking range; calculating a possible driving route that can realize a reverse parking into a garage while keeping the vehicle's wheels from colliding with the fender based on the vehicle's wheel trajectory characteristics and the parking space width; and selecting a parking starting position within the parking range based on the determined parking range and the possible driving routes.

[0015] According to a further embodiment of the present invention, calculating a driving route for parking a vehicle in a target parking space further includes: determining at least one intermediate position based on a current position of the vehicle and a determined parking starting position, so that a first driving route includes first driving from the current position of the vehicle to at least one intermediate position, and then driving from the at least one intermediate position to the parking starting position.

[0016] According to a further embodiment of the present invention, controlling the vehicle to automatically park in the target parking space further includes: controlling the vehicle to travel along the second driving route at a predetermined speed; in response to detecting that the rear wheels of the vehicle drive onto the ramp of the target parking space, increasing the driving force output of the vehicle; and in response to detecting that the rear wheels of the vehicle drive onto the flat plate of the target parking space, reducing the driving force output of the vehicle to restore the speed of the vehicle to the predetermined speed.

[0017] According to a further embodiment of the present invention, controlling the vehicle to automatically park in a target parking space further includes: in response to detecting that the front wheels of the vehicle have driven onto a ramp of the target parking space, increasing the driving force output of the vehicle; and in response to detecting that the front wheels of the vehicle have driven onto a flat plate of the target parking space, reducing the driving force output of the vehicle to restore the speed of the vehicle to a predetermined speed.

[0018] According to a further embodiment of the present invention, controlling the vehicle to automatically park in a target parking space further includes: after the front wheels and rear wheels of the vehicle have driven onto the flatbed of the target parking space, detecting whether the rear wheels of the vehicle contact the wheel stopper of the target parking space; and in response to detecting that the rear wheels of the vehicle contact the wheel stopper of the target parking space, controlling the vehicle to enter a parking mode.

[0019] According to a further embodiment of the present invention, the automatic parking method further includes: in the process of controlling the vehicle to travel along the second driving route, detecting whether there is an obstacle that may collide with the body or chassis of the vehicle; and in response to detecting the obstacle that may collide with the body or chassis of the vehicle, adjusting the second driving route.

[0020] According to a further embodiment of the present invention, the automatic parking method further comprises: in response to detecting an obstacle that may collide with one or more rearview mirrors of the vehicle, automatically folding the corresponding rearview mirror.

[0021] According to a further embodiment of the present invention, determining the parking space type around the vehicle further includes: capturing an image of the vehicle's surroundings through a camera of the vehicle; inputting the captured environmental image into a pre-trained parking space type recognition model; and determining the parking space type based on an output result of the parking space type recognition model, the parking space type including at least a multi-story parking garage and a non-multi-story parking garage.

[0022] According to a further embodiment of the present invention, it further includes: after determining the target parking space, judging whether the image of the vehicle's surrounding environment currently captured by the vehicle is sufficient to identify the parking space width of the target parking space; and if the image of the vehicle's surrounding environment currently captured by the vehicle is insufficient to identify the parking space width of the target parking space, controlling the vehicle to pass in front of the target parking space so that the vehicle's camera can capture an image sufficient to identify the parking space width of the target parking space.

[0023] According to a second aspect of the present invention, there is provided an automatic parking system, comprising: a sensing unit, the sensing unit being configured to sense an environment around a vehicle and generate sensing data; a processing unit, the processing unit being configured to perform the following automatic parking process according to the sensing data generated by the sensing unit: in response to receiving an instruction to start an automatic parking function, determining the type of parking spaces around the vehicle; in response to determining that the type of the parking space is a three-dimensional parking garage, searching for and determining a target parking space; identifying a baffle defining the target parking space, and determining a parking space width of the target parking space based on the baffle; determining a parking starting position that enables a single reverse parking operation without colliding the wheels of the vehicle with the baffle based at least in part on the parking space width of the target parking space; calculating a driving route for parking the vehicle into the target parking space based at least in part on a current position of the vehicle and the determined parking starting position, wherein the driving route at least includes a first driving route from the current position of the vehicle to the parking starting position, and a second driving route from the parking starting position to the target parking space; and a vehicle control unit, the vehicle control unit being configured to control the vehicle to automatically park into the target parking space according to the driving route calculated by the processing unit.

[0024] According to a further embodiment of the present invention, the sensing unit is configured to: capture an image of the environment around the vehicle; sense the distance between the vehicle and objects in the environment; sense the posture of the vehicle; and sense a collision of the vehicle wheels.

[0025] According to a further embodiment of the present invention, the processing unit is further configured to perform the method as described in the first aspect of the present invention according to the sensing data generated by the sensing unit.

[0026] According to a further embodiment of the present invention, the vehicle control unit is further configured to perform the method as described in the first aspect of the present invention according to the sensing data generated by the sensing unit.

[0027] According to a third aspect of the present invention, a vehicle is provided, comprising the automatic parking system as described in the second aspect of the present invention.

[0028] These and other features and advantages will become apparent by reading the following detailed description and by reference to the associated drawings.It is to be understood that the foregoing general description and the following detailed description are illustrative only and are not restrictive of the aspects of what is claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to understand in detail the manner in which the above-stated features of the present invention are used, a more particular description of the above briefly summarized contents may be made with reference to various aspects, some of which are illustrated in the accompanying drawings. It should be noted, however, that the accompanying drawings illustrate only certain typical aspects of the present invention and are not to be considered as limiting its scope, as the description may admit to other equally effective aspects.

[0030] Figure 1 is an example flow chart of an automatic parking method for a stereo garage according to an embodiment of the present invention

[0031] Figure 2 It is a schematic structural diagram of a parking space in a three-dimensional garage.

[0032] Figure 3 It is a schematic diagram explaining the driving route and vehicle position during a conventional automatic parking process.

[0033] Figure 4 2 is a schematic diagram illustrating a parking starting position in an automatic parking process according to an embodiment of the present invention.

[0034] Figure 5 FIG. 4 is a schematic diagram illustrating a driving route and a vehicle position during an automatic parking process according to an embodiment of the present invention.

[0035] Figure 6 Schematic diagram of the logical structure of an automatic parking system according to an embodiment of the present invention.

[0036] Figure 7 4 is a schematic diagram of a logical structure of a vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The detailed description set forth below in conjunction with the accompanying drawings is intended as a description of various configurations, and is not intended to represent the only configuration in which the concepts described herein can be practiced. This detailed description includes specific details to provide a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts can be practiced without these specific details. In some instances, well-known components are shown in block diagram form in order to avoid diluting such concepts. The term "A or B" used in the specification refers to "A and B" and "A or B", rather than meaning that A and B are exclusive, unless otherwise stated. It should be understood that other embodiments will be apparent based on the present disclosure, and system, structural, process or mechanical changes may be made without departing from the scope of the present disclosure.

[0038] In addition, the terms "component", "module", "unit" used herein may be one of the parts that make up the system, may be hardware or software or some combination thereof, and may be divided into other components. Although the operations described below are presented in a particular order and / or as performed by example components, it should be understood that the order of these actions and the components that perform the actions may vary depending on the implementation. In addition, it should be understood that the following actions or functions may be performed by a specially programmed processor, a processor that executes specially programmed software or a computer-readable medium, or by any other combination of hardware components and / or software components that are capable of performing the described actions or functions.

[0039] Figure 1 FIG. 1 is an example flow chart of an automatic parking method for a stereo garage according to an embodiment of the present invention. Figure 1 As shown in , method 100 starts at step 102, in response to receiving an instruction to start the automatic parking function, determining the parking space type around the vehicle. The instruction to start the automatic parking function can be manually triggered by the user, for example, when the user drives the car into a parking lot or near an area to be parked, the automatic parking function equipped by the vehicle can be started by an interactive method such as pressing / touching / voice. Alternatively, the instruction to start the automatic parking function can also be automatically triggered by the vehicle, such as a vehicle in an unmanned or automatic driving process, which can be trained to automatically recognize the entry into the parking scene according to the driving state of the vehicle, thereby activating the automatic parking process.

[0040] According to one embodiment of the present invention, the parking space type may include at least "stereoscopic garage" and "non-stereoscopic garage", wherein the parking space type of "stereoscopic garage" refers to a parking space where the position of the vehicle to be parked is in a stereoscopic parking device. This type of device requires the vehicle to be parked on multiple parking plates of the stereoscopic parking device, and then the parking plates are moved by mechanical transmission to achieve the movement and stacking of the vehicle to save space. In contrast, the parking space type of "non-stereoscopic garage" refers to parking the vehicle directly on the flat ground. Optionally, more types of parking space types can be set, for example, "non-stereoscopic garage" can be subdivided into vertical parking, parallel parking, etc.

[0041] According to a further embodiment of the present invention, determining the parking space type may further include: capturing an image of the vehicle's surrounding environment through a vehicle's camera, then inputting the captured environment image into a pre-trained parking space type recognition model, and determining the parking space type according to the output result of the parking space type recognition model. In one example, the parking space type recognition model may be an image classification model based on machine learning. In the training stage, an image library may be established by collecting images related to the parking space collected by the vehicle's camera, and a sample data set may be established by marking and classifying the images. The labeled sample data set may be trained by a convolutional neural network (CNN). Since the features of a stereo garage are very obvious, such as a garage steel frame, a transmission chain, a parking board, etc., the training process of the model for distinguishing the two types of parking spaces, a stereo garage and a non-stereo garage, will be easy based on the existing image recognition technology. When the training is completed, this parking space type recognition model may be configured locally in a vehicle with an automatic parking function, so that after the automatic parking function is started, it can quickly determine which type of automatic parking is currently required to be performed based on the surrounding environment image currently captured by the vehicle camera, and more specifically, in the example of the present invention, whether to perform "stereo garage" parking.

[0042] In step 104, in response to determining that the parking space type is a stereo garage, the target parking space is searched and determined. If it is determined that the automatic parking of a non-stereo garage type, i.e., conventional ground parking, is currently to be performed, the automatic parking system performs a process similar to the existing automatic parking process to attempt automatic parking. If it is determined that the automatic parking of a stereo garage type is currently to be performed, the automatic parking system may further search whether there is an empty parking space, and preferably, in the case of searching for multiple empty parking spaces, determine which empty parking space to park in, i.e., the target parking space. This can be comprehensively selected by combining multiple factors such as the location of the empty parking space, the current location of the vehicle, surrounding obstacles and space, which is conducive to shortening the time of the automatic parking process, improving the success rate of automatic parking, and reducing the risk of collision during the automatic parking process.

[0043] In step 106, the baffle defining the target parking space is identified, and the width of the target parking space is determined based on the baffle. After determining the target parking space to be parked, the specific size of the target parking space, especially the width of the parking space, needs to be determined first, because the widths of parking spaces in different multi-story garages may not be consistent. Since multi-story garage parking spaces usually do not have ground lines used as parking space outlines, they are defined by baffles around each parking space. Figure 2 As shown, a parking space in a three-dimensional parking garage is usually composed of a parking plate 201 for parking the main body of the vehicle, baffles 202 surrounding the left, right and rear sides of the parking plate, a ramp 203 in front of the parking plate for the vehicle to drive onto, and a wheel blocking rod 204 installed on the parking plate 201. Therefore, according to one embodiment of the present invention, the baffles of the target parking space, especially the baffles on the left and right sides, can be identified by the vehicle's sensors, and then the parking space width of the target parking space can be measured. The principle of identifying parking space baffles is basically the same as the recognition of objects such as vehicles, pedestrians, and buildings commonly used in current driving assistance systems. It only needs to add specific classification and training for three-dimensional parking space baffles on the basis of the existing object recognition model. The width of the parking space can be determined by determining the distance between the baffles on the left and right sides of the parking space through ranging technology based on the baffle recognition.

[0044] In step 108, a parking start position that can achieve a reverse parking without the vehicle's wheels colliding with the fender is determined based at least in part on the parking width of the target parking space. After determining the parking width of the target parking space in the previous step, the automatic parking system begins to calculate the route to park the vehicle in the parking space. As mentioned above, the environment in which the multi-story parking garage is located is usually relatively small. Figure 3 As shown in the figure, if the vehicle reverses according to the conventional vertical parking route, for example, reverses into the garage along position ABCD, there is a great possibility that the wheel will hit the baffle at position C in the figure, which may cause the tire to be scratched. At the same time, there is also a risk that the vehicle body will scratch the steel frame, transmission chain and other components of the three-dimensional parking equipment. In addition, even if the vehicle is stopped before the actual collision or scratch occurs through collision sensing, it will inevitably lead to the failure of automatic parking or extend the time of the automatic parking process. To overcome this problem, it is crucial to determine a parking starting position that can safely perform reverse parking. More specifically, this parking starting position should be a position that can be parked "in one go" while ensuring that the wheels do not hit the baffle during the process. For example, Figure 4 As shown in Figure 3 Compared with position A in Figure 4 The angle between the position A' and the parking space is small, so the vehicle can be reversed into the parking space in one go from the position A' and the wheels will not collide with the baffles on both sides.

[0045] As an example, in order to determine a suitable "parking start position", the environment in front of the target parking space can be first detected to determine the parking range, which can also be known by the vehicle's sensing unit sensing the environment around the vehicle. For example, by sensing objects around the vehicle, it can be determined how much available space is in front of and on both sides of the target parking space. In a non-limiting example, the local environment of the vehicle can be converted into a planar bird's-eye view, which at least identifies the vehicle's current position, the parking space, and the surrounding safe available space, and subsequent route planning can be performed based on the planar view.

[0046] Subsequently, based on the wheel track characteristics of the vehicle and the width of the parking space, a possible driving route that can achieve a reverse parking in one time under the condition that the wheels of the vehicle do not collide with the baffle is calculated. In the existing automatic parking process, the method often used is to roughly determine a range, then align the reference object (such as the center point of the entrance edge of the parking space) with the sensor of the vehicle, and reverse, turn, and adjust, which is an important reason for the large surplus space currently required. In order to overcome this defect, the present invention adopts a "backward" method to plan the route, that is, starting from the result, assuming that you want to reverse into the garage safely in one go, then according to the wheel track characteristics of the vehicle (including wheelbase, wheelbase, turning radius, etc.) and the width of the parking space, multiple possible driving routes can be calculated, more precisely, reverse routes. These possible routes constitute a range, which looks similar to a sector on a plane. In this sector area, no matter from which position the vehicle starts, the vehicle can reverse into the garage in one go according to the requirements.

[0047] On this basis, a suitable parking start position can be selected within the parking range based on the determined parking range and possible driving routes. By comparing the parking range determined in the first two steps and the selectable range suitable as the parking start position on the plan view, the selectable range can be first screened out. Preferably, within these selectable ranges, a relatively more suitable position can be further selected, such as a position that is convenient for moving the vehicle from the current position.

[0048] In step 110, a driving route for parking the vehicle in the target parking space is calculated based at least in part on the current position of the vehicle and the determined parking start position, wherein the driving route includes at least a first driving route from the current position of the vehicle to the parking start position, and a second driving route from the parking start position to the target parking space. It can be understood that, since in step 108, a parking start position that can achieve a reverse parking without colliding with the vehicle's wheels and the fender has been determined, the driving route of the complete automatic parking process can actually be divided into two sections, the first section is from the current position to the parking start position, and the second section is from the parking start position to the target parking space. The route planning for reverse parking from the parking start position is similar to conventional vertical parking type automatic parking, so only the first section of the route from the current position to the parking start position needs to be additionally planned. This section of the route depends on the actual situation in the parking scene, so it cannot be preset, and needs to be planned in real time by the vehicle according to the current environmental sensing results.

[0049] As a non-limiting example, Figure 5 A schematic diagram of a driving route planning suitable for a narrow space is shown. Figure 5 In the example, it is assumed that the current position of the vehicle (i.e., the position where the automatic parking process is started) is position A. Through the previous steps, the vehicle has determined parking space P as the target parking space, and further determined the appropriate parking starting position as position C. On this basis, combined with the available space in the scene, the automatic parking system can determine the following driving route: the vehicle is reversed from the current position A to the middle position B, and then driven forward from the middle position B to the parking starting position C, and finally reversed from the parking starting position C into the target parking space P. It can be understood that this driving route is only exemplary, and other driving routes can be planned according to actual needs. In addition, the determination of the middle position B can be similarly determined by reference factors such as the environment of the scene, the characteristics of the wheel track, and whether it is convenient to drive from the current position A to the position and from the position to the position C. In an optional example, in order to adapt to the extremely narrow space scene, the possibility of setting multiple intermediate positions can be further considered, that is, there is no route that can reach position B in one step and then from position B to position C in one step on the scene. In this case, multiple intermediate positions can be set, and the purpose of finally moving the vehicle to the parking starting position C can be achieved through multiple maneuvers.

[0050] Optionally, the selection and determination of the parking starting position C and the intermediate position B, as well as the short-distance route planning between the positions, can be trained through targeted limited space scenarios. For example, the driving routes of human drivers in such scenarios can be used as training samples for learning. This is conducive to improving the speed of formulating driving route plans on site and improving the availability and success probability of the automatic parking function.

[0051] In step 112, the vehicle is controlled to automatically park in the target parking space according to the determined driving route. After determining the automatic parking driving route for parking the vehicle in the parking space, the automatic parking system can control the vehicle to park in the parking space along the driving route similar to the conventional automatic parking process. Preferably, for a three-dimensional garage type parking space, additional sensing steps and control strategies can be configured to ensure that the vehicle is parked smoothly in the parking space. As an example, for a three-dimensional garage parking space, as described above, the driving route may include a first route from the current position to the parking start position, and a second route from the parking start position to the target parking space. In these two routes, the first route can use a conventional vehicle control method to control the vehicle, and for the second route, firstly, the sensing and monitoring of wheel collisions and vehicle body postures can be increased and enhanced, and then the corresponding precise control different from the vehicle control on the ground can be performed according to the characteristics of the three-dimensional parking equipment. For example, some parking spaces in stereo garages require a certain speed or driving force when the vehicle is driven onto the parking space, similar to the ramp that makes the vehicle "rush" onto the parking board. However, once the vehicle is driven onto the ramp, it is necessary to decelerate immediately to avoid the vehicle speed being too fast and violently hitting the wheel blocking rod behind the parking board, which is more demanding for users with little driving experience. In response to such vehicle control requirements, the automatic parking system disclosed in the present invention can be configured to additionally detect whether the rear wheels of the vehicle are driven onto the ramp of the target parking space. If the vehicle is driven onto the ramp, the driving force output of the vehicle can be increased at this time so that the vehicle can be driven onto the parking board. In a non-limiting example, this can be achieved by the body posture detection of the vehicle gyroscope. Alternatively or additionally, it is also possible to determine whether the rear wheels of the vehicle are driven onto the ramp of the target parking space by a sensor for rear wheel collision detection. Subsequently, within a relatively short period of time, the rear wheels of the vehicle should pass the ramp and drive onto the flat plate of the parking space. At this time, the vehicle can be quickly decelerated by relaxing the throttle and / or increasing the brakes to restore to a predetermined speed. For example, when the second route is set to a vehicle driving at a constant speed of, for example, 5 km / h, the driving force of the vehicle can be increased when the rear wheels drive up the ramp, and the vehicle may exceed 5 km / h for a short time. When the rear wheels pass the ramp and drive onto the flat plate, the previously increased driving force of the vehicle can be removed, and the vehicle speed can be returned to the predetermined 5 km / h by braking. Then, the vehicle maintains reverse driving until the front wheels of the vehicle also drive up the ramp. Similarly, the vehicle can increase the driving force output at this time, and when the front wheels drive onto the flat plate, the increased driving force is immediately removed, and the vehicle speed is restored to the predetermined speed by braking.

[0052] After the front wheels of the vehicle also drive onto the flat part of the parking board, the vehicle should enter the stage of preparing to park and parking. Unlike the conventional automatic parking method in which the white lines around the parking space are used as a reference to center the vehicle in the parking space, in the three-dimensional garage type automatic parking, there are no white lines as a reference, and the parking position is not completely centered, so the parking position cannot be determined according to the parking space baffle. In practice, such parking spaces usually require the rear wheels of the vehicle to support the wheel block rod before parking. To this end, it is necessary to increase the rear wheel collision detection sensor, or increase the sensitivity of the rear wheel collision detection to detect whether the rear wheel contacts the wheel block rod. If the rear wheel contacts the wheel block rod, the vehicle can be controlled to enter the parking mode, including activating the handbrake, closing the open windows, air conditioning, lights or other equipment, and turning off the vehicle.

[0053] Through the above-mentioned vehicle control method, the vehicle can be automatically parked in the parking space of the three-dimensional garage smoothly and safely. As an additional implementation, during the parking process, especially during the driving process of the second driving route, the detection of the collision of the vehicle body or chassis can be increased or enhanced. For example, there are usually many obstacles such as steel frames, transmission chains, and columns in the three-dimensional parking equipment and garage. Although such obstacles can be taken into account and avoided in advance when planning the route, they may not necessarily be accurately sensed in the route planning stage due to the accuracy of the sensor. All obstacles and their positions and sizes. Therefore, in the actual reversing process, accurate sensing can be performed by a higher-precision sensor. For example, in one embodiment, the vehicle can mainly perform parking space type recognition, free parking space recognition, environmental object recognition, etc. based on the image captured by the camera, and when automatically parking, radar, laser radar, millimeter-wave radar, etc. can be further turned on to accurately identify the objects involved in the driving route. This is conducive to saving resources and improving the efficiency of the automatic parking process.

[0054] According to a further embodiment of the present disclosure, during the automatic parking process, especially during the driving process of the second driving route, if it is detected that the vehicle body or chassis will collide with an obstacle, necessary measures can be taken to avoid the collision. As some non-limiting examples, if it is detected that there is a possibility of collision with a passing pedestrian or vehicle, the driving can be continued after the pedestrian or vehicle has passed; if the possibility of collision with a fixed object such as a pillar or steel frame is detected, the second driving route can be adjusted, for example, the parking starting position C can be recalculated; if it is detected that one or more rearview mirrors may collide with an obstacle such as a steel frame or a transmission chain, the corresponding rearview mirror can be automatically folded to avoid the collision.

[0055] It should be understood that the specific order or hierarchy of steps in the disclosed methods is an illustration of an exemplary process. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the methods or methodologies described herein may be rearranged. The attached method claims present elements of the various steps in a sample order and are not meant to be limited to the specific order or hierarchy presented unless specifically stated herein.

[0056] Figure 6 FIG. 6 is a schematic diagram of the logical structure of an automatic parking system 600 according to an embodiment of the present invention. Figure 6 As shown in FIG. 6 , the automatic parking system 600 may include a sensing unit 602, a processing unit 604, and a vehicle control unit 606. The sensing unit 602 may be configured to sense the environment around the vehicle and generate sensing data. The sensing data may include the above-mentioned Figure 1-5 The various types of environmental sensing data that may be used in the described automatic parking process include, but are not limited to: environmental images around the vehicle, the distance between the vehicle and objects in the environment, the posture of the vehicle, the collision of the vehicle wheels, etc. Accordingly, the sensing unit 602 may adopt various types of vehicle-mounted sensors commonly configured on current vehicles, or add corresponding sensors to the vehicle, which may include, but are not limited to: cameras, radars, laser radars, millimeter-wave radars, gyroscopes, collision sensors, etc.

[0057] The processing unit 604 may be configured to perform the above-mentioned processing according to the sensing data generated by the sensing unit 602. Figure 1-5 The automatic parking process described. It can be understood that when the automatic parking system is integrated into the vehicle's onboard system, the processing unit 604 can be a control unit of the vehicle's onboard system. Alternatively, when the automatic parking system is independent of the onboard system, for example, it is installed on an existing vehicle as an independent system, the processing unit is an independent processor or computing unit. The processing process and operation logic of the automatic parking process can be implemented in the form of computer software and stored in the storage unit of the vehicle in the form of executable instructions. Examples of processing units may include, but are not limited to: microprocessors, microcontrollers, digital signal processors (DSPs), field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gated logic, discrete hardware circuits, and other suitable hardware configured to perform various functionalities described throughout the present disclosure.

[0058] Software should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, etc., whether it is described in software, firmware, middleware, microcode, hardware description language, or other terms. The software may reside on a computer-readable medium. The computer-readable medium may be a non-transient computer-readable medium. As an example, a non-transient computer-readable medium includes: a magnetic storage device (e.g., a hard disk, a floppy disk, a magnetic stripe), an optical disk (e.g., a compact disk (CD), a digital versatile disk (DVD)), a smart card, a flash memory device (e.g., a memory card, a memory stick, a key drive), a random access memory (RAM), a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a register, a removable disk, and any other suitable medium for storing software and / or instructions that can be accessed and read by a computer. As an example, computer readable media may also include carrier waves, transmission lines, and any other suitable media for transmitting software and / or instructions that can be accessed and read by a computer. Computer readable media may reside in a processing system, outside a processing system, or across multiple entities including the processing system. Computer readable media may be implemented in a computer program product. As an example, a computer program product may include a computer readable medium in a packaging material. Those skilled in the art will recognize how to best implement the described functionality provided throughout this disclosure depending on specific applications and the overall design constraints imposed on the overall system.

[0059] The vehicle control unit 606 can be configured to control the vehicle to automatically park in the target parking space according to the driving route calculated by the processing unit 604. Similar to the existing automatic parking system, the vehicle control unit 606 can control the vehicle's driving, braking, steering and other systems according to the instructions to perform corresponding driving operations, so that the vehicle can automatically park in the target location according to the calculated route and speed. Optionally, in the case where the vehicle itself has an automatic driving function, the vehicle control unit 606 can be integrated with the vehicle's automatic driving unit.

[0060] Figure 7 FIG. 7 is a schematic diagram of the logical structure of a vehicle 700 according to an embodiment of the present invention. Figure 7 As shown in FIG. , a vehicle 700 may include Figure 6As mentioned above, the automatic parking system 600 can be integrated with the vehicle system of the vehicle 700 or can be independent. In the case of integration, the sensing unit and the vehicle control unit of the automatic parking system 600 can be implemented as part of the sensor system and the vehicle control unit of the vehicle 600 itself, and the processing unit can also be part of the vehicle central processing unit of the vehicle 700. In the case of both being independent, the automatic parking system 600 can partially utilize the sensors of the vehicle 700 itself and add additional sensors as needed.

[0061] What has been described above includes examples of various aspects of the claimed subject matter. Of course, it is not possible to describe every conceivable combination of components or methods for the purpose of describing the claimed subject matter, but one of ordinary skill in the art will recognize that many further combinations and permutations of the claimed subject matter are possible. Thus, the disclosed subject matter is intended to encompass all such alterations, modifications, and variations that fall within the spirit and scope of the appended claims.

Claims

1. An automatic parking method for a stereo garage, comprising: In response to receiving a command to initiate an automatic parking function, determining a parking space type around the vehicle; In response to determining that the parking space type is a three-dimensional parking garage, searching for and determining a target parking space; identifying a baffle defining the target parking space, and determining a parking space width of the target parking space based on the baffle; Determining a parking start position capable of implementing a reverse parking operation without colliding the wheels of the vehicle with the baffle based at least in part on the parking space width of the target parking space; Calculating a driving route for parking the vehicle in the target parking space based at least in part on the current position of the vehicle and the determined parking start position, wherein the driving route includes at least a first driving route from the current position of the vehicle to the parking start position and a second driving route from the parking start position to the target parking space; as well as According to the determined driving route, the vehicle is controlled to automatically park in the target parking space.

2. The automatic parking method according to claim 1, characterized in that: Determining a parking start position capable of implementing a reverse parking operation without colliding the wheels of the vehicle with the baffle further includes: Detecting the environment in front of the target parking space to determine a parking range; Calculating a possible driving route for reversing into a parking space without colliding the wheels of the vehicle with the baffle based on the wheel track characteristics of the vehicle and the width of the parking space; and The parking start position is selected within the parking range based on the determined parking range and the possible driving route.

3. The automatic parking method according to claim 2, characterized in that: Calculating a driving route for parking the vehicle in the target parking space further includes: At least one intermediate position is determined based on the current position of the vehicle and the determined parking start position, so that the first driving route includes driving from the current position of the vehicle to the at least one intermediate position first, and then driving from the at least one intermediate position to the parking start position.

4. The automatic parking method according to claim 1, characterized in that: Controlling the vehicle to automatically park in the target parking space further includes: Controlling the vehicle to travel along the second driving route at a predetermined speed; In response to detecting that the rear wheels of the vehicle have driven onto the ramp of the target parking space, increasing the driving force output of the vehicle; and In response to detecting that the rear wheels of the vehicle have driven onto a flatbed of the target parking space, the driving force output of the vehicle is reduced to restore the speed of the vehicle to the predetermined speed.

5. The automatic parking method according to claim 4, characterized in that: Controlling the vehicle to automatically park in the target parking space further includes: In response to detecting that the front wheels of the vehicle have driven onto the ramp of the target parking space, increasing the driving force output of the vehicle; and In response to detecting that the front wheels of the vehicle have driven onto a flatbed of the target parking space, the driving force output of the vehicle is reduced to restore the speed of the vehicle to the predetermined speed.

6. The automatic parking method according to claim 5, characterized in that: Controlling the vehicle to automatically park in the target parking space further includes: After the front wheels and the rear wheels of the vehicle have both driven onto the flatbed of the target parking space, detecting whether the rear wheels of the vehicle are in contact with the wheel blocking rod of the target parking space; and In response to detecting that a rear wheel of the vehicle contacts a wheel stopper of the target parking space, the vehicle is controlled to enter a parking mode.

7. The automatic parking method according to claim 1, characterized in that: The automatic parking method further comprises: In the process of controlling the vehicle to travel along the second driving route, detecting whether there is an obstacle that may collide with the body or chassis of the vehicle; and In response to detecting an obstacle that may collide with a body or chassis of the vehicle, adjusting the second driving route.

8. The automatic parking method according to claim 7, characterized in that: The automatic parking method further comprises: In response to detecting an obstacle that would collide with one or more rearview mirrors of the vehicle, the corresponding rearview mirrors are automatically folded.

9. The automatic parking method according to claim 1, characterized in that: Determining the type of parking space around the vehicle further includes: capturing an image of the vehicle's surroundings by a camera of the vehicle; Inputting the captured environment image into a pre-trained parking space type recognition model; and The parking space type is determined according to an output result of the parking space type recognition model, and the parking space type at least includes a three-dimensional parking garage and a non-three-dimensional parking garage.

10. The automatic parking method according to claim 1, characterized in that: Further including: After determining the target parking space, determining whether the image of the vehicle surrounding environment currently captured by the vehicle is sufficient to identify the parking space width of the target parking space; as well as If the image of the vehicle's surrounding environment currently captured by the vehicle is insufficient to identify the parking space width of the target parking space, the vehicle is controlled to pass in front of the target parking space so that the camera of the vehicle can capture an image sufficient to identify the parking space width of the target parking space.

11. An automatic parking system, comprising: a sensing unit configured to sense an environment around the vehicle and generate sensing data; A processing unit, wherein the processing unit is configured to perform the following automatic parking process according to the sensing data generated by the sensing unit: In response to receiving a command to initiate an automatic parking function, determining a parking space type around the vehicle; In response to determining that the parking space type is a three-dimensional parking garage, searching for and determining a target parking space; identifying a baffle defining the target parking space, and determining a parking space width of the target parking space based on the baffle; Determining a parking start position capable of implementing a reverse parking operation without colliding the wheels of the vehicle with the baffle based at least in part on the parking space width of the target parking space; as well as Calculating a driving route for parking the vehicle in the target parking space based at least in part on the current position of the vehicle and the determined parking start position, wherein the driving route includes at least a first driving route from the current position of the vehicle to the parking start position and a second driving route from the parking start position to the target parking space; and a vehicle control unit configured to control the vehicle to automatically park in the target parking space according to the driving route calculated by the processing unit.

12. The automatic parking system according to claim 11, characterized in that: The sensing unit is configured to: capturing an image of the environment around the vehicle; Sense the distance between the vehicle and objects in the environment; sensing the posture of the vehicle; and Senses collision of vehicle wheels.

13. The automatic parking system according to claim 12, characterized in that: The processing unit is further configured to execute the method of any one of claims 2-4, 7 and 9-10 according to the sensing data generated by the sensing unit.

14. The automatic parking system according to claim 12, characterized in that: The vehicle control unit is further configured to execute the method according to any one of claims 5 to 6 and 8 according to the sensing data generated by the sensing unit.

15. A vehicle comprising the automatic parking system according to any one of claims 11 to 14.

Images