Methods, equipment, media and products for parking vehicles
By installing multiple sensors on autonomous vehicles to detect ground hazards, constructing local ground models, and adjusting parking trajectories, the problem of autonomous vehicles not considering passenger safety when selecting parking locations has been solved, resulting in a safer and more comfortable parking experience.
Patent Information
- Application Number
- CN202510642628.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-16
- Publication Date
- 2026-11-17
AI Technical Summary
Current autonomous driving and driver assistance systems fail to effectively consider the actual ground conditions during passenger boarding and alighting when selecting parking locations, resulting in potentially dangerous areas that affect passenger safety and comfort.
By using multiple sensors around the vehicle (such as cameras, lidar, thermal imaging, polarization sensors, etc.) to detect ground hazards, a local ground model is constructed to assess the safety and comfort of the parking location, and the parking trajectory is dynamically adjusted to avoid dangerous areas.
This effectively avoids parking vehicles in high-risk ground areas, reducing the possibility of passengers slipping or tripping, and improving the safety and comfort of passengers getting on and off the vehicle.
Smart Images

Figure CN123104628A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of vehicles, and more specifically to methods, electronic devices, media, and program products for parking vehicles. Background Technology
[0002] With the continuous advancement of intelligent driving technology, autonomous driving and driver assistance systems have become a key research focus in the industry. Autonomous driving systems can analyze and make decisions based on perceived information about the surrounding environment and automatically execute corresponding driving operations, enabling vehicles to drive autonomously without human intervention. Autonomous driving technology can improve road traffic safety, increase overall traffic efficiency, and alleviate road congestion.
[0003] With the widespread application of autonomous vehicles in daily travel, in order to ensure passenger safety and comfort, autonomous vehicles need to consider the feasibility of parking and the safety and convenience of the environment in which passengers enter and exit the vehicle during automatic parking and boarding operations, so that passengers can enter and exit the vehicle safely and conveniently. Summary of the Invention
[0004] Embodiments of this disclosure provide a method, electronic device, medium, and program product for parking a vehicle.
[0005] According to a first aspect of this disclosure, a method for parking a vehicle is provided. The method includes detecting ground hazard information associated with the ground using multiple sensors at different locations of the vehicle. The method further includes determining a parking position for the vehicle in a target parking area based on the detected ground hazard information.
[0006] According to a second aspect of this disclosure, an electronic device for parking a vehicle is provided, including a processor and a memory coupled to the processor and storing instructions that, when executed by the processor, cause the device to perform the steps of a method for parking a vehicle according to embodiments of this disclosure.
[0007] In a third aspect of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions that, when executed, cause a computer to perform the steps of a method for parking a vehicle according to embodiments of this disclosure.
[0008] According to a fourth aspect of this disclosure, a computer program product is provided. The computer program product is tangibly stored on a non-volatile computer-readable medium and includes machine-executable instructions that, when executed, cause a machine to perform the steps of a method for parking a vehicle according to embodiments of this disclosure.
[0009] Please note that this summary is provided to introduce some concepts in a simplified form, which will be further described in the detailed embodiments below. The summary is not intended to identify key or essential features of this disclosure, nor is it intended to limit the scope of this disclosure. Attached Figure Description
[0010] The above and other objects, features, and advantages of this disclosure will become clearer through a more detailed description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, in which:
[0011] Figure 1 A schematic diagram of an example environment in which several embodiments of the present disclosure may be implemented is shown;
[0012] Figure 2 A flowchart of a method for parking a vehicle according to an embodiment of the present disclosure is shown;
[0013] Figure 3 A schematic diagram illustrating a process for parking a vehicle according to some embodiments of the present disclosure is shown;
[0014] Figure 4 A schematic diagram of another process for parking a vehicle according to some embodiments of the present disclosure is shown;
[0015] Figure 5 A flowchart of a process for parking a vehicle according to some embodiments of the present disclosure is shown; and
[0016] Figure 6 A schematic block of an apparatus that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation
[0017] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that this application will be thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.
[0018] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.
[0019] In the description of embodiments of this disclosure, the term "comprising" and its variations should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "an embodiment" or "the embodiment" should be understood as "at least one embodiment". Although the terms first, second, third, etc., may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Therefore, the first component discussed below may be referred to as the second component without departing from the teachings of this application. As used herein, the terms "and / or" and similar terms include all combinations of any, multiple, and all of the associated listed items.
[0020] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.
[0021] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily need to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.
[0022] As mentioned above, current autonomous driving and driver assistance systems still have some areas for improvement in terms of driver and passenger experience. Current automated parking systems, when selecting parking locations, only consider factors such as vehicle parking availability and distance control from road boundaries, without taking into account the actual ground conditions on which passengers are situated during boarding and alighting. After a current autonomous vehicle has parked, there may be dangerous or uncomfortable areas along the passenger boarding and alighting path. These ground conditions affect passenger comfort and may also cause passengers to slip, trip, or fall.
[0023] Therefore, embodiments of this disclosure propose a scheme for vehicle parking. In embodiments of this disclosure, multiple sensors located at different positions on the vehicle can first detect ground hazard information associated with the ground. These sensors can be installed around the vehicle, such as in front, on the left and right sides, and behind. Furthermore, these sensors can be of different types, such as camera sensors, lidar sensors, thermal imaging sensors, or polarization sensors, etc. Ground hazard information may include, but is not limited to, puddles, ice surfaces, garbage dumps, sunken areas, and excessively high curbs.
[0024] According to some embodiments of this disclosure, the parking location of the vehicle in the target parking area can also be determined based on detected ground hazard information. For example, when the vehicle determines that the driver's or passenger's current parking spot is an unsuitable location such as a puddle, ice, a sunken surface, or an excessively high curb, the vehicle can choose another suitable parking location. The method implemented by this disclosure can avoid parking in high-risk or unsuitable ground areas, reduce the risk of passengers slipping or tripping, improve passenger safety, and enhance the user experience for passengers getting on and off the vehicle.
[0025] Figure 1 A schematic diagram of an example environment 100 in which various embodiments of the present disclosure may be implemented is shown. It should be understood that these exemplary embodiments are given only to enable those skilled in the art to better understand and implement embodiments of the present disclosure, and are not intended to limit the scope of the present disclosure in any way.
[0026] like Figure 1 As shown, the example environment 100 may include an example autonomous vehicle 110 and elements such as a first target parking location 112, a second target parking location 114, and a danger zone 116. As an example, the autonomous vehicle 110 may approach the target parking area at a low speed and perform an automatic parking operation. According to embodiments of this disclosure, the autonomous vehicle 110 may have various sensing devices, including but not limited to a front-facing camera, a region view camera, a lidar sensor, and thermal imaging sensors or polarization sensors. These sensors can be configured to collect state information about the ground in front of and around the vehicle.
[0027] According to some embodiments of this disclosure, the initial preset parking point for the autonomous vehicle 110 can be a first target parking location 112. For example, the first target parking location 112 can be a default stopping location planned based on the previous vehicle navigation route or the user-input destination. In some embodiments of this disclosure, the first target parking location 112 can be near the edge of the lane and can meet the space, safety distance, and other factors required for vehicle parking.
[0028] According to some embodiments of this disclosure, when the autonomous vehicle 110 approaches a target parking area including a first target parking position 112, the autonomous vehicle 110 can activate a near-field environmental perception mode to collect more precise ground information about the area in front of and to the sides of the autonomous vehicle 110. For example, according to some embodiments of this disclosure, the autonomous vehicle 110 can activate sensor devices including components such as a front-facing camera, a region view camera, and a lidar sensor. In some embodiments, the lidar sensor may include radar applications such as frequency-modulated continuous wave (FMCW) lidar and / or optical cross-section-based lidar. In some embodiments of this disclosure, as an example, the area collected may be 5 to 10 meters around the autonomous vehicle 110, thereby covering the potential path area where the autonomous vehicle 110 is about to park.
[0029] According to some embodiments of this disclosure, the front-facing camera and area view camera of the autonomous vehicle 110 can acquire ground images or videos of the surrounding area. According to some embodiments of this disclosure, the lidar sensor of the autonomous vehicle 110 can acquire three-dimensional structure or 3D information and height changes of the surrounding area and construct a corresponding point cloud model. Additionally or alternatively, in some embodiments of this disclosure, the thermal imaging sensor of the autonomous vehicle 110 can detect the thermal radiation characteristics of the ground temperature gradient, thereby enhancing the identification of ground conditions at night or under low-contrast conditions.
[0030] Additionally or alternatively, according to some embodiments of this disclosure, the polarization sensor of the autonomous vehicle 110 can also identify different ground materials, such as water accumulation, snow, ice, oil stains, etc., by determining the reflectivity information or polarization characteristics of the ground. According to some embodiments of this disclosure, the vehicle controller of the autonomous vehicle 110 can also model the ground information collected from multiple different sensors to construct a local ground model around the vehicle, and classify the state of each ground unit in the local ground model.
[0031] According to some embodiments of this disclosure, the vehicle controller of the autonomous vehicle 110 can determine whether the first target parking location 112 is suitable for parking based on the constructed local ground model. For example, in some embodiments, the vehicle controller of the autonomous vehicle 110 can determine whether there are water stains, dirt, snow, etc., at the first target parking location 112 based on the collected image information. For example, in some embodiments of this disclosure, the vehicle controller of the autonomous vehicle 110 can determine whether there are terrain anomalies such as potholes, raised curbs, and steep slopes at the first target parking location 112 based on the constructed point cloud model. Additionally or alternatively, in some embodiments of this disclosure, the vehicle controller of the autonomous vehicle 110 can determine whether there is water accumulation or ice at the first target parking location 112 based on the determined ground reflectivity; for example, these areas may be shallow but have high reflectivity.
[0032] According to some embodiments of this disclosure, the vehicle controller of the autonomous vehicle 110 can also determine whether the detected or identified hazardous area coincides with the area corresponding to the driver's or passenger's alighting / getting-out door. In some embodiments, if the detected or identified hazardous area is located within a predetermined threshold distance directly below or near the door opening area of the autonomous vehicle 110, the location can be identified as a non-recommended parking location.
[0033] As an example, in an embodiment of this disclosure, the vehicle controller of the autonomous vehicle 110 can identify the first target parking position 112 as an unrecommended parking position by detecting a dangerous area 116, such as a puddle, on the right side of the first target parking position 112, and the dangerous area 116 is located in the passenger door opening area of the right-side door of the first target parking position 112.
[0034] Subsequently, the vehicle controller of the autonomous vehicle 110 can replan the trajectory. For example, in some embodiments of this disclosure, the vehicle controller of the autonomous vehicle 110 can assign a hazard level score to each of the identified ground hazard areas. The score can be set based on manufacturer pre-determined criteria or user preferences. For example, in some embodiments of this disclosure, the score may include, but is not limited to, one or more of the following factors: ground safety (whether there are no obstacles or hazard areas), ground comfort (whether the ground is clean, free of water stains or debris), parking accessibility (whether there are obstacles in front or to the side, such as other vehicles or utility poles), compliance (i.e., the selected parking location does not cross the lines or is located in a no-parking zone), and the minimum distance from the user to the destination.
[0035] As an example, the vehicle controller of the autonomous vehicle 110 can determine a path from a first target parking location 112 to one or more other candidate parking locations and select an area with the lowest hazard level score as the new parking location, such as a second target parking location 114. According to embodiments of this disclosure, for example, relative to the first target parking location 112, the second target parking location 114 avoids the hazard area 116 and simultaneously meets requirements such as dockability, safety, and passenger comfort.
[0036] According to some embodiments of this disclosure, the vehicle controller of the autonomous vehicle 110 can redetermine the driving trajectory between the current location and the second target parking location 114, and adjust the front and rear wheel directional angles based on the determined driving trajectory while driving at a low speed. According to some embodiments of this disclosure, upon reaching the second target parking location 114, one or more sensors of the autonomous vehicle 110 can re-identify and confirm whether the area where the passenger door was previously opened is still clean and / or safe. Additionally or alternatively, in some embodiments of this disclosure, data associated with this path change and ground detection can be recorded by the vehicle controller of the autonomous vehicle 110 for further automatic road trajectory planning optimization and service improvement.
[0037] It should be understood that the above examples are not intended to be limiting, but are merely illustrative for the purpose of aiding understanding, and the embodiments of this disclosure are not limited to the above examples.
[0038] The above combination Figure 1 A schematic diagram of an example environment 100 in which methods and / or processes according to embodiments of the present disclosure may be implemented is described. The following is in conjunction with... Figure 2 A flowchart is provided to describe a method 200 for parking a vehicle 110 according to an embodiment of the present disclosure.
[0039] like Figure 2 As shown in box 202, multiple sensors at different locations on the vehicle detect ground hazard information associated with the ground. According to some embodiments of this disclosure, the multiple sensors may include one or more front-facing cameras mounted in front of the vehicle, and one or more area view cameras, radar sensors, lidar sensors, thermal imaging sensors, polarization sensors, and ultrasonic sensors positioned around the vehicle. In some embodiments, high-resolution radar sensors are capable of detecting small protruding obstacles such as curbs. According to some embodiments of this disclosure, these sensors can be used to scan and identify one or more hazardous areas around the parking location of the target parking area where the vehicle is currently to park, such as potholes, puddles, debris piles, snow, road bumps, ice, etc.
[0040] At box 204, the parking location of the vehicle in the target parking area is determined based on the detected ground hazard information. According to some embodiments of this disclosure, the most suitable parking location for passenger access can be determined based on the determined ground hazard information. For example, one or more candidate parking locations can be selected in the current target parking area, and then the selected one or more candidate parking locations can be scored for hazard level based on parking conditions. Parking conditions may include whether hazardous areas can be avoided, the comfort of the parking location, etc. Thus, the area with the lowest hazard level score can be selected as the suitable parking location for the user.
[0041] The method implemented through this disclosure can effectively avoid parking the vehicle in high-risk ground areas, thereby reducing the possibility of passengers falling, improving safety during boarding and alighting, and enhancing the comfort and user experience of the ride.
[0042] Figure 3 A schematic diagram of a vehicle parking process 300 according to some embodiments of the present disclosure is shown. When the vehicle 310 enters a target area for parking, the vehicle 310 can use multiple sensors mounted around the vehicle to detect the ground area, such as a front-facing camera sensor 320 and a region-view camera sensor 330. In some embodiments of the present disclosure, the front-facing camera sensor 320 and the region-view camera sensor 330 can provide images with resolutions such as 720p or higher. In some embodiments of the present disclosure, the front-facing camera sensor 320 and the region-view camera sensor 330 can provide a video stream at a frame rate of 30 frames per second or higher. According to some embodiments of the present disclosure, the front-facing camera sensor 320 can be used to acquire road surface conditions in the road area 350 in front of the vehicle 310.
[0043] According to some embodiments of this disclosure, the vehicle's area view camera sensor 330 can be used to collect information on the road surface conditions of the road area 360 to the side of the vehicle and the footholds of the driver or passengers entering or exiting the door 370 as the vehicle decelerates or approaches a target parking area. In some embodiments, the door 370 may include the front door and / or the rear door of the vehicle, etc., and this disclosure does not impose any limitations thereon.
[0044] According to some embodiments of this disclosure, images or videos provided by the front-facing camera sensor 320 and the area view camera sensor 330 can be transmitted to an image recognition model of the vehicle 310 to identify potential ground hazard features in the ground image information related to the path a passenger takes to enter or leave the vehicle. In some embodiments, the image recognition model can be a machine learning model based on an architecture such as a transformer or a region convolutional neural network model, and this disclosure does not impose any limitations on this. In some embodiments, the image recognition model can be trained to identify specific ground hazard features. For example, in some embodiments of this disclosure, the image recognition model can identify water accumulation areas by learning the brightness characteristics and edge perturbations of the water surface. In some embodiments of this disclosure, the image recognition model can also identify depressions or potholes with a depth exceeding a predetermined threshold, roadside obstacles, etc., by learning changes in image brightness, shadow projection, and geometric structure. In some embodiments, ground hazard features may also include features such as ice areas, garbage areas, and snow accumulation areas.
[0045] Additionally or alternatively, in some embodiments, the image recognition model can score the confidence level of the acquired images, for example, the confidence level for identifying a puddle area may be 89%, or the confidence level for identifying a garbage area may be 75%. In some embodiments, when the confidence level of the identified area exceeds a predetermined threshold (e.g., 60%), a potential ground hazard area may be identified as a confirmed ground hazard area.
[0046] As an example, when the front-facing camera sensor 320 of vehicle 310 acquires a suspected puddle-filled danger zone 340 in front of the vehicle, the front-facing camera sensor 320 can transmit the acquired image to the image recognition model of the vehicle's infotainment controller. According to some embodiments of this disclosure, the image recognition model can then identify and analyze the acquired image data. When the probability of confirming that the danger zone 340 is a puddle exceeds a predetermined threshold (e.g., 60%), the image recognition model can notify the infotainment controller. The infotainment controller can then generate a parking trajectory based on the identified danger zone 340 and the target parking area, allowing the vehicle to drive along the generated parking trajectory, avoid the danger zone 340, and ultimately park in a safe and comfortable location.
[0047] Additionally or alternatively, in some embodiments of this disclosure, the sensors of vehicle 310 may also include lidar sensors, which may be mounted in front of, to the side of, or on top of the vehicle. In some embodiments, the lidar sensor can construct a three-dimensional point cloud model of the ground by projecting a laser beam onto the ground and measuring the round-trip time of the laser beam, thereby determining, for example, changes in point cloud height or depth around door 370.
[0048] In some embodiments of this disclosure, the lidar sensor can detect depth differences caused by ground depressions, ground bulges, or ground variations to determine ground hazard features. For example, when the depth difference exceeds a predetermined threshold (e.g., 5 cm), it can be determined that there is a deep pit or a high curb protrusion around the vehicle door 370. As an example, the vehicle controller can then generate a parking trajectory based on the identified ground hazard features, allowing the vehicle to travel along the generated parking trajectory and avoid the ground hazard area 340, eventually parking in a safe area.
[0049] Additionally or alternatively, in some embodiments of this disclosure, the sensors of vehicle 310 may also include thermal imaging sensors that can identify ground hazard features by detecting thermal radiation characteristics in changes in ground temperature gradients. For example, as an example, the thermal imaging sensor of vehicle 310 may analyze the ground temperature distribution with a local sliding window and calculate the temperature gradient of the adjacent area.
[0050] In some embodiments, if an area experiences significantly low temperatures, such as more than 3°C below the surrounding ground level, that area can be identified as an ice surface. In some embodiments, if some areas have low thermal radiation characteristics, those areas can be identified as puddles or wet mud. According to some embodiments of this disclosure, thermal imaging sensors can be used in scenarios where camera sensors cannot be used, such as in low light or at night. The vehicle controller can then generate a corresponding parking trajectory based on thermal radiation characteristics to avoid the area and eventually park in a safe area. In some embodiments, thermal imaging sensors can distinguish between scenarios such as frozen hazardous roads, wet road surfaces, and dry road surfaces based on temperature differences.
[0051] Additionally or alternatively, in some embodiments of this disclosure, the sensors of vehicle 310 may also include polarization sensors, which can identify ground hazard features by detecting changes in the polarization of ground reflections and based on polarization characteristics. For example, the polarization sensor can determine the polarization rate of collected image pixels; a higher polarization rate may indicate a highly reflective surface, such as puddles, water surfaces, ice surfaces, oil stains, etc. In some embodiments, if the determined polarization rate is higher than a predetermined threshold, the area can be determined as a hazard area.
[0052] In some embodiments, the polarization sensor can also determine the road type based on the texture variations of the collected image pixels. For example, if the texture variations are consistent in direction and the polarization rate is high, it indicates significant specular reflection in the area, suggesting that the area may be ice or water. In some embodiments, if the texture variations are inconsistent in direction and the polarization rate is low, it indicates low specular reflection in the area, suggesting that the area may be dry and rough.
[0053] In some embodiments, the vehicle's infotainment controller may further include a multimodal model that can synthesize different types of data from multiple different sensors to comprehensively evaluate or score ground information. For example, in some embodiments, the multimodal model can increase the confidence level of data from camera sensors during the day and increase the confidence level of data from lidar sensors or thermal imaging sensors at night.
[0054] In some embodiments, the vehicle's infotainment controller can also generate a set of candidate parking locations within the target parking area based on different types of data collected from multiple different sensors, such as a first candidate parking location, a second candidate parking location, and so on up to the Nth candidate parking location. The infotainment controller can also calculate a hazard level score for each candidate parking location in the set based on previous safe parking conditions, and select the area with the lowest hazard level score as the final parking location. In this way, ground detail environment recognition and response control can be achieved using current vehicle hardware without increasing the cost of additional sensors, ultimately improving the user's parking experience.
[0055] According to embodiments of this disclosure, the vehicle's infotainment controller 310 can be deployed with an artificial intelligence (AI) application specifically trained for an automated parking task. The parking process can be handled by the AI application. This AI application can be trained to automatically detect potential ground hazards and adaptively plan and update the vehicle's driving or parking trajectory based on the detected real-time decision results, enabling the vehicle to drive at a low, smooth speed towards the location determined by the AI application as the most suitable for passenger parking and complete the parking process. The AI application can continuously learn online and receive over-the-air (OTA) updates to adapt to different vehicle models and changing road environments.
[0056] Figure 4 A schematic diagram of another process 400 for parking a vehicle according to some embodiments of the present disclosure is shown. It should be understood that... Figure 4 The vehicle 410 shown may include or have the same as Figure 3 The vehicle 310 shown may contain one or more device elements or components that are the same as or corresponding to the vehicle 310 shown, and process 400 may include more or fewer steps or processes that are the same as or corresponding to process 300, without any limitation in this disclosure.
[0057] For example, according to some embodiments of this disclosure, vehicle 410 may include sensor components such as a front-facing camera sensor 420, a region view camera sensor 430, a lidar sensor, a thermal imaging sensor, and a polarization sensor. In some embodiments of this disclosure, the front-facing camera sensor 420 and one or more other sensors of vehicle 410 may be used to detect the road surface area 450 of the road surface in front of vehicle 410.
[0058] In some embodiments of this disclosure, the area view camera sensor 430 and one or more other sensors can be used to detect road surface areas 460, etc., on the side of the vehicle 410. According to some embodiments of this disclosure, the area view camera sensor 430 can also be a surround-view camera with wide-angle imaging capabilities to cover a larger imaging range. According to embodiments of this disclosure, sensor data such as image data and laser point cloud data captured by the area view camera sensor 430 and one or more other sensors can be transmitted to a trained image recognition model or multimodal model in the vehicle's infotainment controller for identification and analysis to determine hazardous ground areas such as puddles, snowdrifts, mud pits, and garbage, and their corresponding confidence levels.
[0059] As an example, when the vehicle detects that the road surface area 460 detected by the area view camera sensor 430 includes surfaces such as puddles 440 that could cause passengers to slip, trip, or experience discomfort after opening the door 470, the vehicle's infotainment controller can perform parking trajectory replanning and adjust the current path along the driving direction to determine a parking point that meets the ground conditions for disembarking, for example, selecting a suitable location from multiple candidate locations within the target parking area. The method implemented in this disclosure can optimize hazard detection and parking in the driver's or passenger's entry / exit area, enabling intelligent identification and dynamic response to the ground conditions at the driver's or passenger's entrance / exit, ensuring that the area corresponding to the door 470 is clean and free of danger.
[0060] Figure 5 A flowchart of a vehicle parking process 500 according to some embodiments of the present disclosure is shown. For example... Figure 5 As shown, the entire process can begin at box 502. At box 504, when a decrease in vehicle speed is detected and the vehicle approaches the target parking area, the parking method implemented according to this disclosure can be executed. At box 506, multiple sensors can be activated for data acquisition.
[0061] For example, according to some embodiments of this disclosure, image data can be acquired using a camera sensor that includes a front-facing camera and a surrounding area view camera. In some embodiments of this disclosure, 3D point cloud scanning can be performed using a LiDAR sensor. In some embodiments, ground thermal radiation gradient detection can also be performed using a thermal imaging sensor, and ground polarization feature detection can be performed using a polarization sensor.
[0062] At box 508, this data can be processed to determine ground hazard information. For example, in some embodiments, the collected data can be fused and then identified using methods such as image recognition models, 3D point cloud height difference detection, thermal radiation gradient, and polarization feature analysis. This can distinguish areas such as water accumulation, depressions exceeding a depth threshold, ice or snow accumulation, litter areas, and curb areas higher than vehicle thresholds.
[0063] At box 510, the marked areas can be scored for hazard level, for example, based on factors such as prior knowledge, user predefined conditions, and preferred behavioral habits. At box 512, it can be determined whether one or more of these scored areas contain at least one area with a hazard level score below a threshold. At box 514, if it is determined that at least one area contains an area with a hazard level score below the threshold, that area can be located as the desired safe parking area, and a parking trajectory can be generated to perform automatic parking.
[0064] At box 516, if it is determined that there are no areas below the hazard level score threshold, the vehicle's own ground hazard treatment components or devices can be used to treat the ground accordingly. For example, in some embodiments, ground drying components such as hot air or infrared drying at the bottom of the vehicle can be used to locally dry areas of water or snow. In some embodiments, ground debris or snow areas can also be locally cleared using ground mechanical obstacle clearing devices at the bottom of the vehicle. Additionally or alternatively, in some embodiments, the vehicle door opening strategy, such as door angle and door opening sequence, can be adjusted to avoid ground obstacles.
[0065] Figure 6 A schematic block diagram of a device 600 that can be used to implement embodiments of the present disclosure is shown. Device 600 can be the device or apparatus described in the embodiments of the present disclosure. Figure 6As shown, device 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) 602 or loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. CPU 601, ROM 602, and RAM 603 are interconnected via bus 605. Input / output (I / O) interface 605 is also connected to bus 604.
[0066] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0067] The various methods or processes described above can be executed by processing unit 601. For example, in some embodiments, the methods can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by CPU 601, one or more steps or actions in the methods or processes described above can be performed.
[0068] In some embodiments, the methods and processes described above can be implemented as a computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of this disclosure.
[0069] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example, but not limited to, electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.
[0070] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper cables, fiber optic cables, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to computer-readable storage media within the respective computing / processing device.
[0071] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages and conventional procedural programming languages. The computer-readable program instructions may execute entirely on a user's computer, partially on a user's computer, as a standalone software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.
[0072] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, these instructions create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.
[0073] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more blocks of a flowchart and / or block diagram.
[0074] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive 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 action, or using a combination of dedicated hardware and computer instructions.
[0075] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.
Claims
1. A method for parking a vehicle, comprising: By utilizing multiple sensors at different locations on the vehicle, ground hazard information associated with the ground is detected; as well as The parking location of the vehicle in the target parking area is determined based on the detected ground hazard information.
2. The method of claim 1, wherein the plurality of sensors of the vehicle comprises one or more of the following: Camera sensors, radar sensors, lidar sensors, thermal imaging sensors, or polarization sensors.
3. The method of claim 2, wherein the camera sensor comprises at least one front-facing camera and one or more area view cameras disposed around the vehicle; and The camera sensor is configured to acquire ground image information corresponding to the vehicle as the vehicle decelerates or approaches the target parking area.
4. The method of claim 3, wherein determining the ground hazard information comprises: Based on the ground image information acquired by the camera sensor, at least one image recognition model is used to identify ground hazard features in the ground image information related to the path a passenger takes to enter or leave the vehicle. The aforementioned ground hazards include at least: waterlogged areas, ground depressions with a depth exceeding a predetermined threshold, ice areas, garbage areas, snow-covered areas, and curbs higher than the vehicle door sill height.
5. The method of claim 4, wherein identifying the ground hazard features in the ground image information related to the path by which the passenger enters or leaves the vehicle further comprises: The acquired ground hazard features are inferred and matched using the at least one image recognition model to determine potential ground hazard areas and associated confidence scores; as well as In response to the confidence score being higher than a predetermined threshold, the potential ground hazard area is identified as a ground hazard area.
6. The method of claim 2, wherein the lidar sensor is configured to construct a three-dimensional point cloud model of the ground by projecting a laser beam and measuring the round-trip time of the laser beam; Ground hazard features are identified based on elevation changes in the aforementioned 3D point cloud model; and The lidar sensor mentioned above includes a lidar based on frequency modulated continuous wave (FMCW) and / or a lidar based on optical cross section.
7. The method of claim 6, wherein identifying the ground hazard features based on the height changes in the three-dimensional point cloud model comprises: Detect depth differences caused by ground depressions, ground uplifts, or ground changes.
8. The method of claim 2, wherein the thermal imaging sensor is configured to detect thermal radiation characteristics of a temperature gradient change on the ground; and Ground hazard features are identified based on the aforementioned thermal radiation characteristics.
9. The method of claim 2, wherein the polarization sensor is configured to detect changes in polarization reflected from the ground; and Ground hazard features are identified based on polarization characteristics in the polarization changes, wherein the polarization characteristics include changes in ground reflectivity or ground texture.
10. The method according to any one of claims 1-9, wherein determining the parking location of the vehicle in the target parking area based on the ground hazard information comprises: A parking trajectory is generated based on the identified ground hazard area and the target parking area; as well as The vehicle is made to drive and stop based on the generated parking trajectory.
11. The method of claim 10, wherein generating the parking trajectory based on the identified ground hazard area and the target parking area comprises: A hazard level score is assigned to each of the identified ground hazard zones; as well as The area with the lowest hazard level score is selected as the parking location.
12. The method of claim 11, further comprising: In response to each of the ground hazard zones exceeding the hazard level score threshold, The ground drying assembly at the bottom of the vehicle can be used to locally dry areas of water or snow; or The ground clearing component at the bottom of the vehicle is used to locally clear debris or snow from the ground.
13. An electronic device for parking a vehicle, comprising: processor, and A memory, coupled to the processor, stores instructions that, when executed by the processor, cause the device to perform the method according to any one of claims 1 to 12.
14. A computer-readable storage medium storing computer-executable instructions that, when executed, cause a computer to perform the method according to any one of claims 1 to 12.
15. A computer program product tangibly stored on a non-volatile computer-readable medium and comprising machine-executable instructions that, when executed, cause a machine to perform the method according to any one of claims 1 to 12.
