Abstract: A system for deploying user supplied algorithms that inserts the user supplied algorithms and creates application program interfaces within client or server devices. The user supplied algorithm is analyzed and software dependencies are determined along with computation that influences the systems decision to deploy the algorithm for inference on the device or in a cloud server device. Server type selection is determined based on analyst of the user supplied algorithm by the system and the user supplied algorithm is deployed in a selectable efficient manner. Using the user supplied algorithm, a sample a sample set of software is generated from analyst and deployment through an application program interface. The sample set of software can be used by the user to demonstrate the algorithm function in technologies like TOT devices, Smartphone apps or websites.

Abstract: Techniques described herein may be used to provide a driver of a vehicle with an accurate assessment of the remaining life of the vehicle battery. An on-board device may collect information from one or more sensors or devices within the vehicle. The information may be processed to generate a data set that accurately describes the current status and operating conditions of the battery. The data set may be used to evaluate the health of the battery and make predictions regarding the future performance of the battery, which may be communicated to the driver of the vehicle. Machine-learning techniques may be implemented to improve upon methodologies to evaluate the health of the battery and make predictions regarding battery performance.

Abstract: A device may receive a request for imaging of a particular location. The device may identify one or more sensors associated with imaging the particular location. The device may select a sensor, of the one or more sensors, for imaging the particular location. The sensor may be associated with an autonomous vehicle. The device may cause the autonomous vehicle to move the sensor to the particular location. The device may receive imaging of the particular location based on causing the autonomous vehicle to move the sensor to the particular location. The device may selectively combine the imaging of the particular location with archived other imaging of the particular location. The device may provide imaging of the particular location to fulfill the request for imaging of the particular location based on selectively combining the imaging of the particular location with archived imaging of the particular location.

Abstract: A controller/application synchronizes a camera's image capture rate with a LIDAR light burst rate. The controller instructs LIDAR to direct bursts within a field of view of the camera. When reflection of energy of a given burst is detected, the controller/application instructs an image recognition/analysis application to determine object characteristics by evaluating pixels of an image corresponding to the given burst within an evaluation range that corresponds to the location to which the burst was directed during an aperture open period when the camera captured the image. The controller may also instruct the LIDAR to determine a distance to an object that reflected the energy of the given burst. Based on the determined distance to the object and object characteristics, the controller may generate a take-action message. The take-action message may include instruction for controlling an autonomous vehicle to avoid interaction with the object that reflected energy of the burst.

Abstract: A controller/application synchronizes a camera's image capture rate with a LIDAR light burst rate and direction. A user may identify and manually bound an object-of-interest in an image captured with the camera with a user interface. Image and LIDAR point cloud data corresponding to the object-of-interest are applied to a machine learning model to train the model to automatically identify and bound objects-of-interest in future images based on point cloud data corresponding to the future images without human intervention. The LIDAR point cloud data and corresponding image data from the automatically identifying and bounding of objects are applied to the trained model to result in a refined trained machine learning model. The refined machine learning model may be used to determine the nature, location, distance, motion, and heading of an object of interest in an image by evaluation of the image without using corresponding LIDAR point cloud data.

Abstract: A method may perform assisted position determination based on pressure measurements which includes ascertaining a pressure value, and determining whether the ascertained pressure value is within a first threshold of a stored pressure value of the set of stored position and pressure values. The method may also include obtaining a stored position value, from the set of stored position and pressure values, which corresponds to the stored pressure value, in response to determining that the ascertained pressure value is within the first threshold of the stored pressure value, and providing the stored position value as a current location along the route.

Abstract: Aerial images, such as images from satellites or other aerial imaging devices, may be used to assist in responding to the occurrence of events (such as vehicle accidents or other emergency events) or conditions. In one implementation, an alert may be received indicating a condition or event associated with a user device. In response, an aerial image associated with the location of the user device may be requested. The alert may be responded to based on the received image. Aerial imaging may also provide views of the road ahead of a driver that terrain, topography, or darkness may otherwise impede. Image recognition may provide analysis of a hazard, condition, or occurrence at a scene that the aerial imaging system has captured and transmitted in response to a request.

Abstract: Vehicle data may be analyzed to predict potential component failures, diagnostic trouble codes (DTCs), or other mechanical failures relating to the vehicle. In one implementation the vehicle data may be received from a number of vehicles, the vehicle data including DTCs generated by on-board diagnostic (OBD) systems of the vehicles. The vehicle data may be evaluated using a predictive model to output predictions of DTCs that are likely to occur for a particular vehicle.

Abstract: A computer device may include logic configured to detect a wake up event that wakes the computer device from an idle mode, wherein the wake up event indicates that a user is getting ready to use a vehicle; obtain accelerometer data from an accelerometer, associated with the vehicle, during a time period that includes the wake up event; determine a number of door slam events during the time period based on the obtained accelerometer data; and determine a number of people in the vehicle based on the determined number of door slam events.

Abstract: Information identifying one or more conditions associated with a vehicle is collected. This information may include first data associated with the vehicle, second data associated with a driver of the vehicle, and third data associated with an environment around the vehicle. The information may be collected from a vehicle sensor, a telematics unit, a user device associated with the driver or a passenger, or a remote server. A likelihood of a collision involving the vehicle, a likelihood of avoiding the collision, and a risk associated with the collision may be determined based on the collected data. An appropriate response may be selected based on the likelihood of the collision, the likelihood of avoiding the collision, and the risk associated with the collision.

Abstract: Information identifying one or more conditions associated with a vehicle is collected. This information may include first data associated with the vehicle, second data associated with a driver of the vehicle, and third data associated with an environment around the vehicle. The information may be collected from a vehicle sensor, a telematics unit, a user device associated with the driver or a passenger, or a remote server. A likelihood of a collision involving the vehicle, a likelihood of avoiding the collision, and a risk associated with the collision may be determined based on the collected data. An appropriate response may be selected based on the likelihood of the collision, the likelihood of avoiding the collision, and the risk associated with the collision.

Abstract: Techniques described herein relate to the classification of fall events for PER (personal emergency response) devices. In one implementation, data relating to acceleration events that occurred at the PER devices may be received. The data relating to the acceleration events may be associated with indications of whether the acceleration events correspond to fall events of users of the PER devices. A classification model may be trained based on the data relating to the acceleration events and the indications of whether the data relating to the acceleration events corresponds to the fall events. The classification model may be transmitted to at least some of the PER devices to update a previous version of the classification model at the at least some of the PER devices.

Abstract: Techniques described herein may be used to provide a driver of a vehicle with an accurate assessment of the remaining life of the vehicle battery. An on-board device may collect information from one or more sensors or devices within the vehicle. The information may be processed to generate a data set that accurately describes the current status and operating conditions of the battery. The data set may be used to evaluate the health of the battery and make predictions regarding the future performance of the battery, which may be communicated to the driver of the vehicle. Machine-learning techniques may be implemented to improve upon methodologies to evaluate the health of the battery and make predictions regarding battery performance.

Abstract: A system comprise a server configured to communicate vehicle information with a vehicle transceiver of a vehicle moving along a vehicle route and communicate drone information with a drone transceiver of a drone moving along a drone route. A computing device with a memory and a processor may be configured to communicatively connect with the server, process the vehicle information and the drone information, identify a plurality of pickup locations based in part on the vehicle information and drone information, select at least one of the plurality of pickup locations based in part on a priority score associated with a travel time to or wait time for each of the plurality of pickup locations, and update the drone route based in part on the selected pickup location.

Abstract: A computer device may include logic configured to detect a wake up event that wakes the computer device from an idle mode, wherein the wake up event indicates that a user is getting ready to use a vehicle; obtain accelerometer data from an accelerometer, associated with the vehicle, during a time period that includes the wake up event; determine a number of door slam events during the time period based on the obtained accelerometer data; and determine a number of people in the vehicle based on the determined number of door slam events.

Abstract: A device may receive a request for imaging of a particular location. The device may identify one or more sensors associated with imaging the particular location. The device may select a sensor, of the one or more sensors, for imaging the particular location. The sensor may be associated with an autonomous vehicle. The device may cause the autonomous vehicle to move the sensor to the particular location. The device may receive imaging of the particular location based on causing the autonomous vehicle to move the sensor to the particular location. The device may selectively combine the imaging of the particular location with archived other imaging of the particular location. The device may provide imaging of the particular location to fulfill the request for imaging of the particular location based on selectively combining the imaging of the particular location with archived imaging of the particular location.

Abstract: An approach is provided for causing an extension of secure emergency network resources via one or more trusted point of presence. The approach involves determining a networking context, wherein the networking context initiates a request to join an extension mesh network to a currently trusted network. The approach also involves determining a target network trust level associated with the networking context, the currently trusted network, or a combination thereof. The approach further involves selecting the extension mesh network based on the target network trust level. The approach also involves initiating a joining of the extension mesh network to the currently trusted network.

Abstract: A personal emergency response (PER) device may include an audio sensor that is used to enhance the operation of the PER device. The audio sensor may obtain audio data that can be used to verify whether a fall event that is detected by the PER device is a false positive signal and/or enhance the reliability of a detected fall event. In some implementations, the audio data may be used in the detection of vehicle crashes in which a user of the PER device is involved.

Abstract: Vehicle collisions may be automatically detected and reported based to a call center. The collisions may be automatically detected based on a collision detection model that receives sensor data, or other data, as input, and outputs an indication of whether there is a collision. The collision detection model may be trained on historical sensor data associated with potential vehicle collisions, where the historical sensor data is labeled to indicate whether the data corresponds to an actual collision.

Abstract: Aerial images, such as images from satellites or other aerial imaging devices, may be used to assist in responding to the occurrence of events (such as vehicle accidents or other emergency events) or conditions. In one implementation, an alert may be received indicating a condition or event associated with a user device. In response, an aerial image associated with the location of the user device may be requested. The alert may be responded to based on the received image. Aerial imaging may also provide views of the road ahead of a driver that terrain, topography, or darkness may otherwise impede. Image recognition may provide analysis of a hazard, condition, or occurrence at a scene that the aerial imaging system has captured and transmitted in response to a request.