Abstract: A system and method are provided for automatically alerting drivers to potential tread ware problems to enable them to avoid the danger hazards associated with worn treads. A tread-evaluation station is placed at a location where images of tires may be captured. Images of tires are recorded when a vehicle is at or near the tread-evaluation station. An automated analysis is performed on the images. Based on the automated analysis, tires depicted in the captured images are classified into categories of wear. The automated analysis may include a detection component trained to detect tires in images, and a classification model trained to assign a classification to the wear status of the tires identified by the detection component. The tread-evaluation station may further be trained to predict when tires that do not currently need replacing will need replacing.

Abstract: Techniques are provided for dividing control of energy flow at multiple Electric Vehicle (EV) stations using the combination of a centralized controller and a plurality of decentralized controllers. The centralized controller is configured to perform: executing algorithms to generate centralized predictions for a first period of time, wherein the centralized predictions relate to energy usage at a plurality of stations, and generating one or more centralized baseline signals based on the centralized predictions. Each decentralized controller is configured to perform: receiving the one or more centralized baseline signals, monitoring interactions at a subset of the plurality of stations during the first period of time, and updating the one or more centralized baseline signals in real-time based on the interactions to produce one or more locally-updated baseline signal.

Abstract: An approach is provided for dynamically controlling power distribution amongst a plurality of charging station ports based on one or more objectives. A method includes obtaining input data, wherein the input data includes at least one of: user data associated with one or more current charging station users, or non-user data that is not associated with the current charging station users. The method includes processing the input data through one or more machine learning engines, wherein the one or more machine learning engines are trained to determine a particular power distribution, among the plurality of charging station ports, that achieves one or more objectives. The method includes configuring the plurality of charging station ports according to the particular power distribution. The particular power distribution specifies a maximum charging rate or a percentage of a power budget for each of the plurality of charging station ports.

Abstract: The disclosed embodiments include a charging station for an electric vehicle. The charging station includes a plurality of light sources, one or more processors, and memory storing instructions for performing a set of operations. The set of operations includes determining a state of the charging station, the state indicating a status of an electric vehicle at the charging station. In accordance with a determination that the state is a first state, the charging station provides a first visual indication of the first state using a first light source of the plurality of light sources. In accordance with a determination that the state is a second state, the charging station provides a second visual indication of the second state.

Abstract: The disclosed implementations provide systems and methods for tracking a user device. The method includes receiving, from a respective application running on a first electronic device associated with a user, a request initiated by the user to affiliate with a second electronic device. In response to the request by the user to affiliate with the second electronic device, the method includes determining a wireless identifier of the first electronic device. After determining the wireless identifier of the first electronic device, the method includes receiving an indication that a second wireless access point, distinct from the first wireless access point, is in communication with the first electronic device of the user based on the second wireless access point detecting the wireless identifier of the first electronic device. The method further includes determining that the first electronic device of the user is proximal to the second wireless access point.

Abstract: The disclosed embodiments provide systems and methods for retracting a charging cable at an electric vehicle charging station (EVCS). The EVCS includes a housing, a charging cable configured to provide an electric current to charge a battery of an electric vehicle, a sensor for detecting whether external objects are within a predefined region proximal to the housing, a motor configured to retract at least a portion of the charging cable, and a controller electrically coupled to both the sensor and the motor. The method includes energizing the motor, via the controller, to retract at least a portion of the charging cable when retraction criteria are met. The retraction criteria include criteria that are met when the charging cable is not coupled to a vehicle and the one or more sensors do not detect an external object in the predefined region proximal to the housing.

Abstract: The disclosed embodiments provide a method performed at a computer system that is in communication with an electric vehicle charging station (EVCS). The EVCS includes a camera for obtaining images in a region proximal to the EVCS. The method includes capturing, using the camera, a plurality of images of electric vehicles, each image in the plurality of images being an image of a respective electric vehicle. The method further includes, for each respective image of the plurality of images of electric vehicles: determining, without user intervention, a characteristic of the respective electric vehicle; and tagging, without user intervention, the respective image with the characteristic of the respective electric vehicle. The method further includes training a first machine learning algorithm to identify the characteristic of other electric vehicles using the tagged plurality of images.

Abstract: Techniques are described herein for fleet electrification management. A method includes determining a composition of electric vehicles (EVs) to replace at least a portion of non-electric vehicles in a vehicle fleet while satisfying travel requirements of the vehicle fleet. The method includes estimating an energy demand of the composition of EVs. The method includes determining an electric vehicle supply equipment (EVSE) charging infrastructure to meet the estimated energy demand. The method includes providing one or more recommendations including at least one of: a fleet electrification recommendation for transitioning the vehicle fleet into the composition of EVs, or a charging infrastructure recommendation for implementing the EVSE charging infrastructure.

Abstract: A method is performed at an electronic device with a display. The method includes receiving a request from a user to display information about electric vehicle charging stations near a geographic location. The method further includes, in response to the request to display information about electric vehicle charging stations near the geographic location, for a respective charging station near the geographic location: identifying a commercial enterprise co-located with the respective electric vehicle charging station, and displaying, on the display, an indication of the respective electric vehicle charging station. The indication of the respective electric vehicle charging station includes a representation of the co-located commercial enterprise.

Abstract: Techniques are described herein for predicting popularity metrics and/or visitation metrics that are used in the selection of a point of interest (POI) for placement of an electric vehicle charging station (EVCS). The techniques involve training a machine learning model based on information obtained about POIs at which EVCSs are already installed. The information used to train the machine learning model includes, for each existing installation location: (a) visitation data that describes visitation features, and (b) popularity metrics and/or visitation metrics that have been generated for the location. When the machine learning model has been trained, the trained machine learning model predicts popularity metrics and/or visitation metrics for a POI location at which no EVCS has been installed based on the visitation data of that POI.