SYSTEM AND METHOD FOR INFRASTRUCTURE-BASED PARKING

Abstract

This disclosure introduces an innovative infrastructure-based software solution for autonomous parking garages that manages the simultaneous parking of multiple vehicles. The system is equipped with bird's-eye view cameras with night vision capabilities and radar devices covering a large ground area. It also features a central computer with extensive graphical and parallel computing capabilities for planning and controlling maneuvers for multiple vehicles simultaneously. The system establishes two-way V2I (vehicle-to-infrastructure) communication with the vehicles, manages their control, and calculates a suitable parking space based on various factors such as space availability, vehicle model, parking duration, and garage congestion.The system offers several advantages, including minimizing the overall time and energy expenditure for parking, reducing the need for expensive sensors and software for autonomous parking in each vehicle, optimizing overall parking behavior in a parking garage, and ensuring fair and efficient use of parking space.

Description

BACKGROUND

[0001] In modern urban environments, parking has become an increasingly complex problem for drivers and passengers. Growing traffic density and the limited availability of parking spaces have made finding a suitable place to park a difficult task. This problem is particularly acute near popular destinations where the demand for parking is high.

[0002] Besides the difficulty of finding available parking spaces, drivers also struggle to stay informed about their immediate availability. Current systems don't provide real-time information on vacant spaces, causing drivers to waste time and fuel searching for them. Another major problem is the high cost of parking, especially in city centers and popular destinations, which discourages people from using their vehicles.

[0003] Furthermore, remembering the exact location where a vehicle was parked can be difficult, especially in large structures. The lack of a reliable system to guide drivers back to their parked vehicles often leads to unnecessary stress and wasted time. This problem is exacerbated in multi-story parking garages, where navigating the different levels can be confusing for drivers.

[0004] Several attempts have been made to solve these problems, but with limited success. Some solutions focused on providing real-time information about parking availability, but these systems often fail to deliver accurate and reliable data. Other solutions have tried to reduce parking costs by offering discounted rates outside of peak hours, but these initiatives have not significantly reduced the overall cost burden of parking on motorists.

[0005] Furthermore, existing parking management systems have not adequately addressed the problem of storing vehicle location data. While some systems offer a basic function for marking the parked vehicle's location, they are unable to provide precise navigation back to the vehicle, especially in large and complex parking structures.

[0006] Therefore, there is a need to solve the aforementioned problems by introducing an autonomous parking management system. SUMMARY

[0007] The primary objective of this disclosure is to provide an infrastructure-based autonomous parking garage software solution capable of controlling incoming vehicles and planning and directing their parking maneuvers. This is achieved through the deployment of advanced sensors such as RGB bird's-eye view cameras (e.g., with night vision capabilities and radar) and a central computer with extensive graphics and parallel computing capabilities.

[0008] Another objective of this disclosure is to optimize the overall time and energy consumption for all vehicles parked by reducing traffic, planning vehicle paths more effectively, and eliminating the need for drivers to search for parking spaces by driving around. This is achieved by planning all parking maneuvers and the sequence for each vehicle in the garage as a whole, for example, based on a ranking system, a graph sorting algorithm, or deep learning.

[0009] Another objective of this disclosure is to save significant resources and money by eliminating the need to equip every car with expensive sensors and software for autonomous parking. This is achieved, for example, through a centralized planning and control system for perception, where each vehicle does not need to trigger its own automatic parking assist (APA) software or camera / lidar sensors for parking.

[0010] Another objective of this disclosure is to optimize the overall macro-parking behavior / maneuvers in a parking garage. This is achieved, for example, by monitoring the situation of all vehicles in the parking garage, receiving data from each vehicle, performing path or movement planning for all vehicles in the parking garage as a whole, and controlling each vehicle.

[0011] According to one aspect of the present disclosure, the autonomous parking management system comprises a communication system (e.g., a WiFi communication interface) configured to establish communication with multiple cameras and radar sensors when deployed in a parking garage with multiple cameras and radar sensors, and to communicate with multiple vehicles entering or leaving the parking garage. The system also comprises one or more computing devices communicatively coupled to the communication system and configured to receive camera sensor information from the multiple cameras and radar sensor information from the multiple radar sensors; receive multiple respective parking request messages from the multiple vehicles, the multiple respective parking request messages being used to request parking within the parking garage;Perform a planning operation that identifies multiple parking spaces in the parking garage to be assigned to multiple vehicles; determine multiple paths for each vehicle to follow to reach the identified parking spaces; generate multiple sets of vehicle control commands based on camera and radar sensor information, each set controlling the acceleration, steering, and braking of a vehicle to maneuver to its assigned parking space; and instruct the communication system to communicate or transmit the multiple sets of vehicle control commands to the vehicles.

[0012] According to another aspect of the present disclosure, the one or more computing devices are configured to identify the multiple spaces assigned to the multiple vehicles based on their respective vehicle types (e.g., sedan versus SUV), vehicle models, or vehicle sizes. The one or more computing devices are also configured to determine the respective vehicle sizes of the multiple vehicles based on radar sensor information.The one or more computing devices are further configured to determine, for at least one of the several respective parking request messages, a predicted parking duration for which a respective vehicle associated with the at least one parking request message is expected to park in the parking garage, and wherein a respective space assigned to the respective vehicle is identified by the one or more computing devices on the basis of the predicted parking duration.

[0013] According to a further aspect of the present disclosure, the one or more computing devices are configured to determine a parking priority level for each of the multiple vehicles relative to the other multiple vehicles, and wherein the one or more computing devices are configured to identify, if the parking garage includes a first set of parking spaces that is closer to a parking garage exit relative to a second set of parking spaces, the multiple parking spaces based on a planning algorithm which increases the probability for each of the multiple vehicles of being assigned to the first set of parking spaces instead of the second set of parking spaces as the parking priority level of the vehicle relative to the other multiple vehicles increases.

[0014] According to another aspect of the present disclosure, the one or more computing devices are configured to track the respective positions of the multiple vehicles in the parking garage based on camera sensor information and / or radar sensor information; to track the respective positions of obstacles (e.g., pillars in the parking garage) between the multiple vehicles and their assigned parking spaces based on camera sensor information and / or radar information; and to generate the multiple sets of vehicle control commands based on the respective positions of the multiple vehicles and on the respective positions of the obstacles.

[0015] The proposed system offers several advantages over conventional parking solutions. It minimizes the overall time and energy expenditure for all vehicles during parking by generating less traffic and better planning vehicle paths. It also saves significant resources and money, as it eliminates the need to equip every car with expensive sensors and autonomous parking software. Furthermore, it optimizes the overall macro-parking behavior within a parking garage by monitoring the situation of all vehicles, receiving data from each vehicle, planning as a whole, and controlling each vehicle individually. The preceding sections serve as a general introduction and are not intended to limit the scope of the following claims. The described embodiments and further advantages are best understood by referring to the detailed description below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1: In Fig. Figure 1 shows a parking management system, a parking garage, cameras and radar sensors in the parking garage, and vehicles in the parking garage, as described here. Fig. 2: Fig. Figure 2 is a block diagram of a parking management system as described in this document. Fig. 3: Fig. Figure 3 shows a flowchart illustrating a procedure carried out by a parking management system as described in this document. DETAILED DESCRIPTION

[0016] Aspects of the present revelation are best understood by reference to the description contained herein. All aspects described herein will be better appreciated and understood when considered in conjunction with the descriptions that follow. However, it should be understood that the following descriptions, although they indicate favored aspects and numerous specific details thereof, are for illustrative purposes only and should not be considered limitations. Changes and modifications may be made within the scope described herein without deviating from the spirit and scope, and the present revelation includes all such modifications.

[0017] The proposed system described in this disclosure is an innovative, infrastructure-based, autonomous parking garage software solution that can control vehicles entering the garage and command them to park. In one embodiment, the parking garage is equipped with RGB bird's-eye view cameras with night vision capabilities and radars, all mounted vertically downwards on the structure and each covering a large area (e.g., 10 m x 10 m). The camera captures video and images during the day, while the night vision radar detects vehicles, pedestrians, and obstacles such as pillars in the parking space.

[0018] In one embodiment, radar devices installed on the ceiling of the parking garage provide depth information that assists the central computer in determining the height of vehicles and objects, as well as ground information for improved planning. This allows the system, for example, to park low vehicles under low ceilings. The system also includes devices for communication with the vehicles, such as radio or Bluetooth. Furthermore, the system features a central computer with extensive graphical and parallel computing capabilities to calculate planning and control maneuvers for multiple vehicles simultaneously.

[0019] When a vehicle enters or exits the parking garage's maneuvering area, two-way communication (vehicle-to-infrastructure, V2I) is established between the vehicle and the parking garage. The parking garage's system takes over the vehicle's control (steering, pedals, and brakes) via radio, wireless internet, or Bluetooth. Based on the current availability of space, the vehicle model, the parking duration, and the parking garage's status (e.g., congestion and traffic flow), the central computer calculates a suitable parking space for the vehicle. Once a suitable space has been identified and a feasible path for the vehicle to enter and exit the parking garage has been planned, the control unit sends the appropriate control commands to guide the vehicle into the designated space.

[0020] This parking garage can monitor the situation of all vehicles within the garage, receive data from each vehicle, plan the overall parking situation, and control each vehicle individually. In this case, the parking garage can monitor the entire parking situation, control all vehicles, and plan the movements of each individual vehicle. This type of management has many advantages compared to autonomous onboard parking solutions.

[0021] The system can minimize the overall time and energy required for parking for all vehicles by reducing traffic congestion, better planning car paths, and eliminating the need for drivers to search for parking spaces themselves. In contrast, conventional autonomous parking is performed by each individual vehicle, meaning each vehicle is responsible for its own optimal maneuver and parking positions, resulting in a lack of overarching planning intelligence. Using the camera and radar on the ceiling, for example, we can detect the size and type of each vehicle and park it in appropriate spaces, such as compact or larger ones, to minimize wasted space and achieve optimal parking capacity.

[0022] With a central planning and control system for perception, not every vehicle needs to trigger its own APA (automatic parking assist) software or camera / LiDAR sensors for parking, meaning not every car needs to be equipped with expensive sensors and software for autonomous parking. Therefore, cars don't have to carry all these heavy payloads, saving a lot of resources and money.

[0023] The entire macro-parking behavior / maneuver within a parking garage can be optimized. We can guarantee the parking behavior for all vehicles, ensuring that the space is used efficiently and that no driver parks incorrectly or takes up too much space. We can guarantee the parking behavior of the vehicles without having to worry about some OEMs having better parking software than others.

[0024] The proposed system is novel in that it does not focus on parking a single vehicle, but rather on planning the overall behavior of all vehicles, taking into account that the parking maneuvers of some vehicles influence the behavior and decisions of others, especially neighboring vehicles. Furthermore, this system does not require sensor installations or heavy computing equipment on the vehicles, as the sensors and computers are integrated into the infrastructure. Only communication modules between each vehicle and the central control unit of the infrastructure are needed. In this case, the garage infrastructure acts as an "edge computing device," where the calculations take place near the vehicle's periphery, but not on the vehicle itself.

[0025] The planning algorithm not only plans and controls the parking of a single vehicle, but, more importantly, it plans all parking maneuvers and the sequence for all vehicles in the garage overall, based on a ranking, a graph sorting algorithm, or deep learning. This large-scale planning ensures that vehicles wanting to park in the garage at a specific time can be accommodated based on their arrival time and their respective positions relative to other vehicles. This would be particularly useful during peak hours.

[0026] Existing systems focus on methods for a vehicle that uses its own sensors to perceive and plan its parking maneuvers in a parking garage where the GNSS signal is unreliable or lost. Meanwhile, the system according to the invention focuses on enabling perception and planning using only infrared signals. In summary, the described system not only meets the immediate need for detailed monitoring and management of parking spaces but also provides a scalable and flexible solution that can evolve with technological advancements and changing user requirements. The embodiment of the disclosure described here is intended to provide a thorough understanding of the capabilities of the disclosure and should not be considered a limitation of its scope.

[0027] Fig. Figure 1 shows an illustrative representation of an autonomous system 1000 for managing parking spaces in a parking garage 2000, equipped with several cameras 2210 / 2220 / 2230 / 2240 (also in Fig. (2 shown) and radar sensors 2110 / 2120 / 2130. In one embodiment, the system 1000 comprises a communication system 1100 and one or more computing devices 1200. The cameras and radar sensors can be strategically positioned throughout the parking garage to acquire comprehensive data about the vehicles 3100 / 3200 / 3300 and their surroundings. The communication system 1100 establishes and maintains two-way vehicle-to-infrastructure (V2I) communication with the vehicles entering or already present in the parking garage, enabling the system 1000 to control the movement of the vehicles within the parking garage.

[0028] In one embodiment, the cameras 2210 / 2220 / 2230 / 2240 in parking garage 2000 are equipped with RGB bird's-eye view and night vision capabilities to capture video and image data day and night. These cameras can be particularly useful for detecting the presence and movement of vehicles, pedestrians, and obstacles within the space. The radar sensors 2110 / 2120 / 2130 can be particularly useful for obtaining depth information that assists a central computer or other computing device 1200 in determining the height of vehicles and objects, as well as ground information, for optimal parking planning. For example, low-profile vehicles can be parked under low ceilings to make the best use of the available space.

[0029] In one embodiment, the communication system 1100 of the parking management system 1000 is configured to communicate with the cameras 2210 / 2220 / 2230 / 2240 and the radar sensors 2110 / 2120 / 2130, and with the vehicles 3100 / 3200 / 3300 entering or located in the parking garage 2000. This system can communicate, for example, via wireless internet, WiFi, or Bluetooth®, thus ensuring seamless communication between the vehicles and the computer 1200. The computer 1200 is configured to receive camera sensor information from the cameras and radar sensor information from the radar sensors via the communication system 1100.

[0030] In one embodiment, vehicles entering or already present in the parking garage can request that the parking management system 1000 direct them to the appropriate parking spaces. More precisely, the vehicles can transmit parking requests to the parking management system 1000 or communicate in some other way. Upon receiving a request from a vehicle, the system 1200 calculates a suitable parking space for the vehicle, based, for example, on the current availability of spaces, the vehicle model, the parking duration, and the traffic situation and flow within the garage. It can then perform path planning to determine a route for the vehicle to reach the parking space and subsequently generate a set of vehicle control commands to guide the vehicle to its designated parking space.

[0031] In one embodiment, the computing device 1200 of the parking management system 1000 is also capable of determining multiple parking spaces for several vehicles parked simultaneously in the parking garage and controlling the multiple vehicles at the same time, thereby ensuring efficient use of space and a smooth flow of traffic in the parking garage. In another embodiment, it can automatically guide a vehicle to the exit area of ​​the parking garage so that the customer can easily pick it up, thus eliminating the need for the customer to enter the parking garage or search for their vehicle.

[0032] In one embodiment, the Autonomous Parking Management System 1000 provides a centralized perception, planning, and control system, eliminating the need for each vehicle to have its own set of sensors or automatic parking assistance (APA) software. This can lead to significant cost savings, as the system reduces the need for expensive sensors and software in each vehicle for autonomous parking. Furthermore, the System 1000 helps minimize the overall time and energy spent on parking by better planning vehicle paths and reducing traffic within the parking garage.

[0033] The detailed description above provides an understanding of the general structure and operation of the autonomous parking management system 1000, as it is implemented in Fig. Figure 1 is shown. However, it should be noted that the system can be modified or improved without exceeding the scope of the disclosure. For example, the system can be configured to work with different types of sensors or communication protocols, or it can be integrated with other systems or services to offer additional functions or capabilities.

[0034] In Fig. Figure 2 shows a block diagram of an autonomous parking management system, commonly referred to as system 1000. System 1000 is designed to automate the process of parking vehicles in a parking garage by utilizing sensor data from a series of cameras 2210, 2220, 2230, and 2240, as well as radar sensors (in Fig. 2 (not shown) for perception. The System 1000 can include a series of computing devices 1200 for planning and control, as well as a communication module 1100 that enables two-way communication between the System 1000 and the vehicles 3100, 3200, and 3300. The computing devices 1200 are responsible for processing the data from the cameras and radar sensors, planning parking maneuvers, and generating control commands for the vehicle. As shown in Fig. As shown in Figure 2, the parking management system 1000 can include a non-volatile, computer-readable medium 1300, such as computer memory, in which various modules can be stored that can be executed by the computing devices 1200. For example, the memory or other non-volatile, computer-readable medium can contain a camera fusion module 1310, a higher-level planning and scheduling module 1320, an individual control module 1330, and a vehicle movement control module 1340, which are explained in more detail below.

[0035] In one embodiment, cameras 2210, 2220, 2230, and 2240 can be strategically positioned throughout the parking garage to provide a comprehensive overview of the parking area. Thanks to their night vision capabilities, these cameras can capture video and still images both day and night. The cameras can detect vehicles, pedestrians, and obstacles such as pillars within the parking area. The radar sensors can provide depth information, which helps the System 1000 determine the heights of vehicles and objects, as well as ground information for planning purposes. The System 1000 parking management system can receive image information from the cameras (e.g., via the Communication System / Module 1100) and process this image information using the Camera Fusion Module 1310 to detect the presence of other vehicles, pedestrians, and obstacles in the parking garage.

[0036] In one embodiment, the communication module 1100 establishes bidirectional vehicle-to-infrastructure (V2I) communication with vehicles 3100, 3200, and 3300 entering or exiting the parking garage. This communication is established via radio, wireless internet, or Bluetooth and enables the exchange of information and control commands.

[0037] In one embodiment, the computing devices 1200 have extensive graphical and parallel computing capabilities that enable them to identify vehicles and / or obstacles in the parking garage and to perform path and motion planning calculations to control maneuvers for multiple vehicles parking simultaneously. When a vehicle enters the parking garage and requests parking assistance from the parking management system 1000, the computing devices 1200 can calculate a suitable parking space for the vehicle based on the current availability of spaces, the vehicle model, the parking time, and other factors such as the traffic situation and flow in the parking garage. In one embodiment, the suitable parking space can be calculated based on sensor data from the cameras and radar sensors. The computing devices 1200 can execute the general planning and scheduling module 1320 to, for example,to determine which vehicle(s) have priority over other vehicles in terms of access to parking spaces or right-of-way when moving in the parking garage, and they can run the individual path planning module 1330 to determine individual paths that the respective vehicles must follow to reach their assigned parking spaces.

[0038] Once the computing devices 1200 have identified a valid parking space and planned a suitable path for the vehicle, they generate the corresponding control commands (e.g., generated by the control module 1340) that the vehicle can execute to follow the path and reach the parking space. These commands, which control, for example, the vehicle's steering, acceleration, and braking, are then transmitted to the vehicle via the communication module 1100. In this way, the parking management system 1000 can automatically park the vehicle in the designated space. Similarly, when a vehicle needs to leave the parking garage, the system 1000 can automatically transport the vehicle to a specific pick-up area, such as the exit area of ​​the parking garage.

[0039] The System 1000 parking management system does more than just manage individual vehicles. It also monitors the overall situation in the parking garage by receiving data from each vehicle and planning as a whole. This holistic approach allows System 1000 to comprehensively manage the parking situation, control all vehicles, and plan the movements of individual vehicles. This is a significant advantage over conventional autonomous parking solutions, which focus on parking individual vehicles without considering the overall parking situation.

[0040] The System 1000 parking management system can plan and control parking maneuvers and the sequence for each vehicle in the garage, for example, based on a ranking system, a graph sorting algorithm, or deep learning. This large-scale planning ensures that all vehicles wishing to park at a particular point in the garage can be accommodated efficiently, especially during peak hours. Furthermore, System 1000 eliminates the need for sensors or heavy computing devices on the vehicles. All necessary sensors and computers are integrated into the parking garage infrastructure, and only communication modules are required between each vehicle and System 1000's computing devices. The parking garage infrastructure thus acts as an "edge computing device," where the calculations take place near the vehicle's periphery, but not on the vehicle itself.

[0041] Fig. Figure 3 shows a flowchart illustrating the process carried out by the computer system 1200 of the autonomous parking management system 1000 according to the embodiments of the present disclosure. The process begins with step 4100, in which the autonomous parking management system (1000) establishes communication with several vehicles entering or already located in the parking garage (2000). The communication is established via a communication system (1100) that is also connected to various cameras (2210 / 2220 / 2230 / 2240) and radar sensors (2110 / 2120 / 2130) installed in the parking garage. These cameras and radar sensors are responsible for acquiring real-time data about the vehicles and their surroundings, including vehicle dimensions, positions, and the availability of parking spaces.

[0042] In step 4200, the system receives several message requests from the vehicles. These messages are requests from the vehicles for a space in the parking garage. Each request message contains specific information about the vehicle, such as its size, model, and expected parking duration. This information is used by the system to make informed decisions in the following steps.

[0043] In step 4300, the system performs a planning operation. This planning operation is carried out by one or more computing devices (1200) that are communicatively coupled to the communication system (1100). The task of these computing devices is to process the data received from the cameras and radar sensors and, based on this information, to identify suitable spaces for the vehicles. The identification of parking spaces is based on various factors, including the availability of spaces, the dimensions of the vehicles, and the expected parking duration.

[0044] In step 4400, the system determines several paths for the vehicles to reach their assigned spaces. For each vehicle, the optimal route to its assigned space is calculated, taking into account the current positions of the vehicles, the locations of the parking spaces, and the presence of obstacles in the parking garage.

[0045] Step 4500 involves generating several sets of vehicle control commands. These commands are generated based on sensor information received from the cameras and radar sensors. Each set of vehicle control commands is designed to control the acceleration, steering, and braking of the respective vehicle, enabling it to maneuver within its assigned space. The control commands are designed to ensure safe and efficient vehicle navigation within the parking garage.

[0046] Finally, in step 4600, the system transmits the commands for controlling the vehicles to the vehicles themselves. This is done via the communication system (1100), which transmits the commands to the vehicles via radio, wireless internet, or Bluetooth. Once the vehicles have received the commands, they can autonomously navigate to their assigned spaces, guided by the control units.

[0047] This procedure, which is in Fig. As shown in Figure 3, this enables effective parking management in a parking garage. By using an infrastructure-based autonomous system to manage parking spaces, the parking process is simplified and made more efficient. The system saves drivers the manual search for a space, thus reducing the time and energy spent parking. Furthermore, by planning vehicle paths and controlling their movements, the system can minimize traffic within the parking garage, further improving the efficiency of the parking process.

[0048] This disclosure presents an infrastructure-based system for the autonomous management of parking spaces. This advanced system is designed to control the movement of multiple vehicles entering a parking garage and to plan and direct them to parking. The parking garage is equipped with RGB bird's-eye view cameras with night vision capability and radar sensors mounted on the vertically downward-facing cell. Each sensor covers a large area, for example, an area of ​​10 m x 10 m.

[0049] The cameras serve a dual purpose. During the day, they function as devices for capturing videos and images. At night, their night vision capabilities come into play. These cameras are used to detect vehicles, pedestrians, and obstacles such as pillars in the room. The radar sensors provide depth information that assists the central computer in determining vehicle and object heights, as well as ground information, for improved planning. This allows the system, for example, to park low vehicles under low ceilings.

[0050] The system also includes devices for communication with the vehicles, such as radio or Bluetooth. Furthermore, the system is equipped with a central computer that possesses extensive graphical and parallel computing capabilities. This computer is used to calculate planning and control maneuvers for multiple vehicles simultaneously.

[0051] When a vehicle enters the maneuvering area of ​​the parking garage or attempts to exit, two-way communication (V2I) is established between the vehicle and the parking garage system. The parking garage system takes control of the vehicle, either via radio, wireless internet, or Bluetooth. Based on factors such as the current availability of spaces, the vehicle model, the parking duration, and other conditions within the parking garage, like the traffic situation and flow, the central computer calculates a suitable parking space for the vehicle.

[0052] Once it has located a suitable parking space and planned a feasible path for the vehicle to enter and exit, it sends the corresponding control commands to guide the vehicle into the designated space. Using the same control and planning function, the parking garage can also automatically move the container to the exit area. This allows customers to conveniently retrieve their vehicles without having to enter the garage or search for them.

[0053] This container can monitor the situation of all vehicles in the parking garage, receive data from each vehicle, plan as a whole, and control each vehicle individually. This holistic approach to parking management has several advantages compared to onboard autonomous parking solutions. It can minimize the overall time and energy spent parking all vehicles by reducing traffic, better planning vehicle paths, and eliminating the need for drivers to search for a parking space by driving around.

[0054] With a centralized planning and control system for perception, each vehicle no longer needs to trigger its own APA (automatic parking assist) software or camera / LiDAR sensors for parking. This eliminates the need for vehicles to carry around all these heavy payloads, saving significant resources and money. The overall macro-parking behavior and maneuvers within a parking garage can also be optimized. The proposed system allows for efficient use of space, preventing drivers from parking incorrectly and taking up excessive room.

[0055] The parking management system is novel in that it doesn't focus on parking a single vehicle, but rather on the global behavioral planning of all vehicles. It takes into account that the parking maneuvers of some vehicles influence the behavior and decisions of others, especially neighboring vehicles. Furthermore, this system requires no sensor installation or heavy computing equipment on the vehicle, as the sensors and computers are integrated into the infrastructure. Only communication modules between each vehicle and the central control unit of the infrastructure are needed.

[0056] More precisely, the planning algorithm not only plans and controls the parking of a single vehicle, but, more importantly, it plans all parking maneuvers and the sequence for every vehicle in the garage overall, based on a ranking, a graph sorting algorithm, or deep learning. This large-scale planning ensures that vehicles wanting to park in the garage at a specific time can be accommodated based on their arrival time and their respective positions relative to other vehicles. This would be particularly useful during peak hours.

[0057] The innovative approach of this parking management system offers several advantages over conventional methods. It provides a centralized perception, planning, and control system, eliminating the need for each vehicle to have its own sensors or automatic parking assist (APA) control unit. This results in cost savings, as the system reduces the need for expensive sensors and autonomous parking software in every vehicle. Furthermore, the system helps minimize the overall time and energy spent on parking by better planning vehicle paths and reducing traffic within the parking garage.

[0058] Furthermore, the system can monitor the overall situation in the parking garage by receiving data from each vehicle and planning as a whole. This holistic approach allows the system to comprehensively manage the parking situation, control all vehicles, and plan the movements of individual vehicles. This is a significant advantage over conventional autonomous parking solutions, which focus on parking individual vehicles without considering the overall parking situation.

[0059] These embodiments serve only to illustrate the inventive concepts contained herein. Other embodiments and modifications may be made to the compositions and processes without departing from the spirit and scope of the disclosure. Therefore, the scope of this disclosure should not be limited to the embodiments described herein, but should be defined by the appended claims and their equivalents.

Claims

[1] Autonomous parking management system (1000) comprising the following: a communication system (1100) configured to establish communication with the multiple cameras (2210 / 2220 / 2230 / 2240) and the multiple radar sensors (2110 / 2120 / 2130) when deployed in a parking garage (2000) equipped with multiple cameras (2210 / 2220 / 2230 / 2240) and multiple radar sensors (2110 / 2120 / 2130) and to establish communication with multiple vehicles (3100 / 3200 / 3300) entering or located in the parking garage (2000). one or more computing devices (1200) that are communicatively coupled to the communication system 1100 and configured to: (i) receive camera sensor information from the multiple cameras and radar sensor information from the multiple radar sensors via the communication system (4100); (ii) receive multiple respective parking request messages from the multiple vehicles (3100 / 3200 / 3300) via the communication system (4200), the multiple respective parking request messages being used to request parking within the parking garage; (iii) perform a planning operation (4300) that identifies multiple spaces in the parking garage in order to assign them to the multiple vehicles (3100 / 3200 / 3300); (iv) determine (4400) multiple respective paths for the multiple vehicles to follow in order to reach the multiple parking spaces identified in step (4300);(v) Generating (4500) respective sets of vehicle control commands based on the camera sensor information and the radar sensor information, each set of vehicle control commands being used to control the acceleration, steering, and braking of a respective vehicle in order to maneuver to a respective space assigned to that vehicle; (vi) Causing (4600) the communication system (1100) to communicate or transmit the respective sets of vehicle control commands to the multiple vehicles (3100 / 3200 / 3300). [2] Autonomous parking management system according to claim 1, wherein the one or more computing devices are configured to identify the multiple spaces to be allocated to the multiple vehicles based on their respective vehicle types, vehicle models or vehicle sizes. [3] Autonomous parking management system according to claim 2, wherein the one or more computing devices are configured to determine the respective vehicle sizes of the multiple vehicles on the basis of the radar sensor information. [4] Autonomous parking management system according to claim 1, wherein the one or more computing devices are configured to determine, for at least one of the several respective parking request messages, a predicted parking duration for which a respective vehicle associated with the at least one parking request message is expected to park in the parking garage, and wherein a respective space assigned to the respective vehicle is identified by the one or more computing devices on the basis of the predicted parking duration. [5] Autonomous parking management system according to claim 4, wherein the one or more computing devices are configured to identify, if the parking garage has multiple parking levels, the multiple parking spaces to be assigned to the multiple vehicles, based on a determination for each of the multiple vehicles as to which parking level is to be assigned to the respective vehicle, wherein the parking level for the vehicle is determined on the basis of the predicted parking duration of the respective vehicle. [6] Autonomous parking management system according to claim 1, wherein the one or more computing devices are configured to determine a parking priority level for each of the multiple vehicles relative to the other multiple vehicles, and wherein the one or more computing devices are configured to identify, if the parking garage comprises a first set of parking spaces that is closer to a parking garage exit relative to a second set of parking spaces, the multiple parking spaces based on a planning algorithm which increases the probability for each of the multiple vehicles of being assigned to the first set of parking spaces instead of the second set of parking spaces as the parking priority level of the vehicle relative to the other multiple vehicles increases. [7] Autonomous parking management system according to claim 6, wherein the one or more computing devices are configured to determine the respective parking priority levels for the multiple vehicles on the basis of their respective garage entry times. [8] Autonomous parking management system according to claim 1, wherein the one or more computing devices are configured to track the respective positions of the multiple vehicles in the parking garage based on camera sensor information and / or radar sensor information, to track the respective positions of obstacles between the multiple vehicles and their assigned parking spaces based on camera sensor information and / or radar information, and wherein the multiple sets of vehicle control commands are generated based on the respective positions of the multiple vehicles and on the basis of the respective positions of the obstacles. [9] Autonomous parking management system according to claim 1, wherein the one or more computing devices are configured to determine the respective vehicle heights of the multiple vehicles based on the radar sensor information, and wherein the multiple parking spaces are identified based on the respective vehicle heights of the multiple vehicles. [10] Autonomous parking management system according to claim 1, wherein the one or more computing devices are configured to identify multiple rooms or determine the respective multiple paths for the multiple vehicles based on traffic congestion in the parking garage or the traffic flow within the parking garage. [11] Method performed by one or more computing devices (1200) of an autonomous parking management system (1000), the method comprising: (i) Receiving (4100) camera sensor information from a plurality of cameras (2210 / 2220 / 2230 / 2240) in the parking garage (2000) and radar sensor information from a plurality of radar sensors (2110 / 2120 / 2130) in the parking garage (2000) via the communication system; (ii) Receiving (4200), via a communication system (1100) of the autonomous parking management system (1000), several respective parking request messages from several vehicles entering a parking garage (2000) or the parking garage (2000); (iii) Identifying (4300) several spaces in the parking garage (2000) in order to assign them to the several vehicles; (iv) Determining (4400) of respective multiple paths for the multiple vehicles to follow in order to reach the multiple spaces, each of the multiple sets of vehicle control commands being used to control the acceleration, steering and braking of a respective vehicle in order to maneuver to a respective parking space assigned to that vehicle; (v) Generating (4500) respective multiple sets of vehicle control commands based on the camera sensor information and the radar sensor information; (vi) Causing (4600) the communication system (1100) to communicate or transmit the respective multiple sets of vehicle control commands to the multiple vehicles. [12] Method according to claim 11, wherein the multiple parking spaces are identified on the basis of their respective vehicle types, vehicle models or vehicle sizes. [13] Method according to claim 12, wherein the respective vehicle sizes of the multiple vehicles are determined on the basis of the radar sensor information. [14] Method according to claim 11, further comprising determining an expected parking duration for at least one of the several respective parking request messages for which a respective vehicle associated with the at least one parking request message is expected to park in the parking garage, wherein respective parking spaces for the respective vehicle are identified on the basis of the expected parking duration. [15] Method according to claim 14, wherein the multiple spaces are identified on the basis of a determination for each of the multiple vehicles which parking level is to be assigned to the respective vehicle, wherein the parking level for the vehicle is determined on the basis of the predicted parking duration of the respective vehicle. [16] Method according to claim 11, wherein a parking priority level of each of the multiple vehicles is determined relative to the other multiple vehicles and wherein the multiple parking spaces are identified on the basis of a planning algorithm which, for each of the multiple vehicles, increases the probability of the vehicle being assigned to a first set of parking spaces closer to a parking garage exit relative to a second set of parking spaces as the parking priority level of the vehicle increases relative to the other multiple vehicles. [17] Method according to claim 16, wherein the respective parking priority levels for the multiple vehicles are determined on the basis of their respective garage entry times. [18] Method according to claim 11, wherein the multiple sets of vehicle control commands are generated on the basis of the respective positions of the multiple vehicles in the parking garage and on the basis of the respective positions of obstacles between the multiple vehicles and their assigned spaces. [19] Method according to claim 11, wherein the multiple parking spaces are identified on the basis of the respective vehicle heights of the multiple vehicles, which are determined on the basis of the radar sensor information. [20] Method according to claim 11, wherein the multiple parking spaces or the respective multiple paths for the multiple vehicles are determined on the basis of the traffic congestion in the parking garage or the traffic flow within the parking garage.

Images