A parking lot is designed for parking motor vehicles in a non-organized manner. A method for managing the parking lot includes steps of determining an area P of the parking lot that is able to be occupied by parked motor vehicles, of determining an area K of the parking lot that is currently occupied by parked motor vehicles, and of determining a number Z of motor vehicles that may be parked additionally in the parking lot, on the basis of the relationship Z=(1−K/P)*M, where M comprises a maximum number of motor vehicles that may be parked in the parking lot.

System, methods, and other embodiments described herein relate to improving the identification of available parking spaces by inferring when a vehicle is likely to depart. In one embodiment, a method includes, responsive to acquiring sensor data about a surrounding environment including at least one parked vehicle, extracting a feature from the sensor data about a context of the parked vehicle. The method includes analyzing the feature to determine a status of the vehicle in relation to whether the vehicle is remaining parked. The method includes providing the status to inform additional vehicles about an availability of a parking spot of the parked vehicle.

Methods, systems, and computing platforms for mobile data communication are disclosed. The processor(s) may be configured to receive a plurality of user mobile parking beacon data and storing the user mobile parking beacon data in a computer readable database for a mobile device. The processor(s) may be configured to process the user mobile parking beacon data with a machine learning processor as to output at least one most probable lane location vector associated with the mobile device. The processor(s) may be configured to electronically output the at least one most probable lane location vector to a parking processing module.

A processor coupled to memory is configured to receive an identification of a geographical location associated with a target specified by a user remote from a vehicle. A machine learning model is utilized to generate a representation of at least a portion of an environment surrounding the vehicle using sensor data from one or more sensors of the vehicle. At least a portion of a path to a target location corresponding to the received geographical location is calculated using the generated representation of the at least portion of the environment surrounding the vehicle. At least one command is provided to automatically navigate the vehicle based on the determined path and updated sensor data from at least a portion of the one or more sensors of the vehicle.

A method of communication in an Intelligent Transport System, ITS, comprising, at an originating ITS station reporting in a collective perception message an element describing a space representing a specific area of a road topology.

Systems, methods, and apparatuses for locating parking spaces are disclosed. According to one method, a request is received from a user of a vehicle to locate a space; the location of the user is determined; a database comprising spaces within a geographic region is accessed; from the database, a subset of spaces within the geographic region is identified, the subset comprising user-specific spaces; a determination is made regarding the availability of the user-specific spaces; and if a user-specific space is available, a transmission is initiated, intended for the user, providing the location of at least one available space. The systems, methods, and apparatus may be used to locate free spaces, may allow users to indicate when they are vacating a space to enable other users to access the space via a “park it forward” approach, and may assign available spaces to users based on an equitable prioritization protocol.

A vehicle flow monitoring system for detecting both a car count and direction of movement of vehicles passing a point of interest. The vehicle flow monitoring system generally includes a car counter which may include a microcontroller and a pair of distance sensors. Each of the distance sensors is oriented toward a unique point of interest. Each of the distance sensors includes a threshold distance reading which is used to detect whether a vehicle has passed underneath the car counter. The system may determine direction of travel of the vehicle based on which of the distance sensors is passed by the vehicle first. The microcontroller may assign an Event ID to each time a vehicle passes each of the sensors, with the Event ID being used to identify when and if the vehicle should be counted, or whether a non-vehicle object has passed the car counter.

Generating parking area statistics for identifying parking areas within a geographic region. Navigation support for reaching a top-ranked parking area according to collected parking area data, user preferences, parking feedback, and real-time traffic conditions. Selection of a top-ranked parking area and monitoring progress during a parking event improve future identification and ranking of parking areas.

A method for calibrating an internal sensor in a vehicle with an external sensor which is designed to detect external positional data dependent on a position of the vehicle. The method includes: detecting the external positional data using the external sensor; sending the external positional data to the vehicle and filtering the internal positional data based on the external positional data and dependent on the position of the vehicle and by an internal sensor.

A method for managing charging resources of a charging system for plug-in electric vehicles (PEVs), the charging system including a central recording center including a tracking database. The method including initiating a charging session to a first PEV based on detecting that the first PEV has been plugged into a charging station. The first PEV is associated with the charging session in the tracking database. The first PEV is associated, in the tracking database, to a first user and a first PEV profile. The first PEV is charged in accordance with information from the first PEV profile. Charging session data is monitored and stored in the tracking database during the charging session. A machine learning model is generated based on collective charging data. Charge completion time of the first PEV is predicted based on the machine learning model.