Abstract: Aspects of the disclosed technology encompass solutions for automatically requesting a backup vehicle for passengers of an autonomous vehicle provisioned ride-hailing service. In some aspects, a process of the disclosed technology includes steps for collecting diagnostic data relating to at least one AV operation, and analyzing the diagnostic data to determine if the AV needs maintenance. Moreover, in response to a determination that the AV needs maintenance, the process can include steps for automatically requesting a backup service for a passenger of the AV. Systems and machine-readable media are also provided.

Abstract: Disclosed are systems and methods for autonomous vehicles and vehicles with automatic driver-assistance systems (ADAS) to automatically detect an imminent collision, determine whether the collision is avoidable or unavoidable, and plot a course minimizing the hazard using an artificial intelligence (AI) model. For example, a collision is avoidable if the vehicle can avoid it by steering, braking, and/or accelerating in a particular sequence. The AI model finds the best sequence for collision avoidance, and if that is not possible, it finds the best sequence for minimizing the harm. The harm is based on an estimated number of fatalities, injuries, and property damage predicted to be caused in the collision. The AI-based situation analysis and sequence selection are directly applicable to human-driven vehicles with an emergency-intervention ADAS system, as well as fully autonomous vehicles. With fast electronic reflexes and multi-sensor situation awareness, the AI model can save lives on the highway.

Abstract: A system that may include a first route circuit that may be configured to be coupled with a first route section and may be configured to generate a first location coded signal that is unique to the first route section responsive to a vehicle being located on or within the first route section. A second route circuit may be configured to be coupled with a second route section and configured to generate a second location coded signal that is unique to the second route section and that is different from the first location coded signal, the second route circuit configured to generate the second location coded signal responsive to the vehicle being located on or within the second route section. A controller may be configured to receive the first location coded signal and the second location coded signal and determine a location of the vehicle based on the first location coded signal or the second location coded signal.

Abstract: Embodiments provide techniques, including systems and methods, for determining matches of requestors and providers based on a dynamic provider eligibility model. For example, a request matching model uses an estimated arrival time for a requestor and estimated travel times for available providers to a pickup location to determine eligible providers for matching to a ride request. The matching model determines those providers that are far enough away from the request location to allow the requestor time to arrive at the pickup location without matching providers that are too far away, causing delay for the requestor and lowering the efficiency of the system by taking provider system resources from other service areas and increasing provider downtime upon matching. Additionally, embodiments provide more efficient matching processing leading to fewer canceled matched requests, fewer requests for a successful match, and fewer system resources necessary to meet requestor demand.

Abstract: Described is a computer-implemented method which comprises receiving a plurality of images captured by at least one user device, wherein each image is associated with one of a corresponding plurality of geographic locations; determining a path between the plurality of geographic locations; determining a confidence indicator representative of whether the determined path corresponds to a demarked path, wherein determining the confidence indicator comprises determining a time of capture of each of the plurality of images; identifying the path as corresponding to a demarked route, based on the confidence indicator; and marking the plurality of images for display as a demarked route.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for allowing vehicles access or egress from a dedicated roadway. In some implementations, a system includes a server, an interface, and sensors. The interface receives data from a railroad system that manages a railroad running parallel to a first roadway. The sensors are positioned in a location relative to the first and second roadway. Each sensor can detect vehicles on the second roadway. For each detected vehicle, each sensor can generate first sensor data based on the detected vehicle and the data received at the interface. Second sensor data can be generated based on activities on the first roadway. Observational data can be generated based on the first and second sensor data. An instruction can be determined to allow the detected vehicle access to the first roadway. The instruction can be transmitted to the detected vehicle.

Abstract: This application provides a data processing method and apparatus and a storage medium. The data processing method includes: obtaining K idle calculation blocks in real time, where K is greater than or equal to 1; invoking first K pieces of detected data from a cache stack in a preset priority sequence of detected data, and inputting the detected data into the K idle calculation blocks; sequentially processing K pieces of detected data on the K idle calculation blocks in the preset priority sequence; and integrating sensing calculation results of the K pieces of detected data in real time based on a boundary relationship between detection ranges of the K pieces of detected data, and outputting a sensing result.

Abstract: The present invention relates to method and system for controlling speed of vehicle by using GPS location, real-time traffic light status and machine learning techniques to recommend cruising speed to vehicle without stopping at the traffic lights. The method includes determining status of traffic lights located on route of traffic junctions and associated time period for status of traffic lights based on data received from sensors. The method includes broadcasting status of traffic lights and associated time period. The method includes calculating in real-time a recommended cruising speed of the vehicle based on GPS location associated with vehicle, status of traffic lights and associated time period, and a time period required by vehicle to arrive at the traffic lights using machine learning techniques. The method includes providing in real-time the recommended cruising speed to vehicle. The method includes adaptively controlling in real-time speed of vehicle to recommended cruising speed.

Abstract: Physical and logical components of a long line loiter control system address control of a long line loiter maneuver conducted beneath a carrier, such as a fixed-wing aircraft. Control may comprise identifying, predicting, and reacting to estimated states and predicted states of the carrier, a suspended load control system, and a long line. Identifying, predicting, and reacting to estimated states and predicted states may comprise determining characteristics of state conditions over time as well as response time between state conditions. Reacting may comprise controlling a hoist of the carrier, controlling thrusters of the suspended load control system, and or controlling or issuing flight control instructions to the carrier so as not to increase the response time and or to avoid a hazard.

Abstract: Technologies and techniques for vehicle perception. A first contour of a current image a dna second contour of a next image are determined relative to an optical center. The current image is scaled to the next image relative to the optical center, wherein the scaling includes applying a scale vector to the first contour. A frame offset vector is determined, and the second contour is translated, based on the frame offset vector and the scale vector, to align the translated second contour to a focus of expansion. An image velocity is determined, based on the first contour and the translated second contour, wherein the image velocity is used to determine object movement from the image data.

Abstract: A transportation system is provided. The system includes: a highway vehicle, a first set of highway points located along a path of the vehicle, a second set of highway points located along a traffic signal section, at least one RFID tag located at each of the first set and the second set of highway points, and at least one RFID tag reader located on the highway vehicle connected to a network. The at least one RFID tag located at the first set of highway points is configured to store dynamic and static characteristics of the highway vehicle as it passes the first set of highway points and the at least one RFID tag located at the second set of highway points is configured to store dynamic and static characteristics of the vehicle as it passes the second set of highway points.

Abstract: A method, apparatus and computer program product are provided to define a strand upstream of a direction based traffic (DBT) link. In a method, a strand is defined upstream of a DBT link. The method includes extending the strand so as to include one or more links upstream of the DBT link. The strand is extended by determining whether a link is to be added to the strand based upon evaluation of a termination criteria. The termination criteria is at least partially based upon a relationship of a function class of the link to the function class of one or more other links. In an instance in which the termination criteria is satisfied, the method ceases further extension of the strand.

Abstract: A computer vision processor of a camera generates hyperzooms for persons or vehicles from image frames captured by the camera. The hyperzooms include a first hyperzoom associated with the persons or vehicles. The computer vision processor tracks traffic patterns of the persons or vehicles while obviating network usage by the camera by predicting positions of the persons or vehicles using a Kalman Filter from the first hyperzoom. The persons or vehicles are detected in the second hyperzoom. The positions of the persons or vehicles are updated based on detecting the persons or vehicles in the second hyperzoom. The first hyperzoom is removed from the camera. Tracks of the persons or vehicles are generated based on the updated positions. The second hyperzoom is removed from the camera. Track metadata is generated from the tracks for storing in a key-value database located on a non-transitory computer-readable storage medium of the camera.

Abstract: Systems and methods are disclosed for supporting and executing automated control of adjustable components of a vehicle based on occupant classification in a group identity database. Methods and systems for generating and employing the group identity database are also disclosed. Occupancy information may be utilized to determine how the group identity database is employed.

Abstract: A framework for modeling traffic speed in a transportation network analyzes both the spatial and temporal dependencies in probe-based traffic speeds, historical weather data, and forecasted weather data, using multiple machine learning models. A decentralized partial least squares (PLS) regression model predicts short-term speed using localized, historical probe-based traffic data, and a deep learning model applies the predicted short-term speed to further estimate traffic speed at specified times and at specific locations in the transportation network for predicting traffic bottlenecks and other future traffic states.

Abstract: The hydraulic excavator 1 includes a work implement 7, a detection device that detects an obstacle around the hydraulic excavator 1, and a controller 27 that controls the operation of the work implement 7. The controller 27 has a driving assistance function and a work assistance function. The work assistance function is switchable between enabled and disabled. When the work assistance function is switched to enabled, the controller 27 suppresses, for an obstacle detected in a monitoring range but outside of a work range, the driving assistance function in comparison with when the work assistance function is switched to disabled.

Abstract: A system and method are provided for controlling movement of an implement for a self-propelled work vehicle, said implement comprising one or more components coupled to a main frame of the work vehicle. A linkage joint in defined in association with at least one implement component, wherein sensors are respectively associated with opposing sides of the linkage joint. Output signals from each sensor comprise sense elements which are fused in an independent coordinate frame associated at least in part with the respective linkage joint, wherein the independent coordinate frame is independent of a global navigation frame for the work vehicle. At least one joint characteristic (e.g., joint angle) is tracked based on at least a portion of the sense elements from the received output signals for each of the opposing sides of the respective linkage joint. Movement of implement components may optionally be controlled in view of the tracked joint characteristics.

Abstract: A vehicular driver monitoring system includes a driver status information acquisition system and an in-vehicle control system of the vehicle. The driver status information acquisition system receives data from a plurality of sensors in the vehicle and determines the driver status responsive to processing of the received data. While the driver is not driving the vehicle and the in-vehicle control system is autonomously driving the vehicle, and responsive to determination that the driver of the vehicle should take over driving the vehicle from the in-vehicle control system, the in-vehicle control system alerts the driver to indicate that the driver should take over driving the vehicle. Responsive to the status of the driver while the driver is not driving the vehicle being indicative of the driver not being able to take over driving the vehicle, the in-vehicle control system continues driving the vehicle and initiates an emergency action.

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.

Abstract: A method of operating a traffic management system comprises receiving data from a vehicle indicating a traffic state, estimating a future time at which the vehicle will receive driving instructions transmitted by the traffic management system, predicting a future traffic state at the estimated future time, determining the driving instructions for the vehicle based on the predicted future traffic state, and transmitting the driving instructions to the vehicle.