Abstract: One or more techniques and/or systems are provided for parking space routing. For example, parking data for a parking region, such as a parking lot, may be obtained from one or more data sources (e.g., vehicle sensor data, a parking lot camera, parking meter transaction data, etc.). Routes from a current location of a vehicle to available parking spaces within the parking region may be computed. The routes may be ranked based upon various criteria, such as convenience, congestion, travel time, travel distance, a parking space fill order, etc. A route, having a rank above a threshold (e.g., a highest ranked route), may be provided to a driver of the vehicle, such as through a vehicle navigation unit, a mobile device, a wearable device, etc. The route may be provided to autonomous driving functionality of the vehicle for automatic routing and navigation of the vehicle to the parking space.

Abstract: One or more techniques and/or systems are provided for notifying drivers to assume manual vehicle control of vehicles. For example, sensor data is acquired from on-board vehicles sensors (e.g., radar, sonar, and/or camera imagery of a crosswalk) of a vehicle that is in an autonomous driving mode. In an example, the sensor data is augmented with driving condition data aggregated from vehicle sensor data of other vehicles (e.g., a cloud service collects and aggregates vehicle sensor data from vehicles within the crosswalk to identify and provide the driving condition data to the vehicle). The sensor data (e.g., augmented sensor data) is evaluated to identify a driving condition of a road segment, such as the crosswalk (e.g., pedestrians protesting within the crosswalk). Responsive to the driving condition exceeding a complexity threshold for autonomous driving decision making functionality, a driver alert to assume manual vehicle control may be provided to a driver.

Abstract: One or more techniques and/or systems are provided for slowdown detection. Location data received from vehicles traveling a road is evaluated to identify a road segment associated with vehicle speeds below a threshold. A space-time diagram is generated, and location data associated with vehicles traveling the road segment are plotted within the space-time diagram. The space-time diagram is processed using a convolutional neural network to determine a probability that the space-time diagram illustrates a slowdown. If the probability that the space-time diagram illustrates the slowdown is greater than a threshold, then a notification of the slowdown is transmitted to one or more computing devices associated with vehicles that may encounter the slowdown.

Abstract: Among other things, one or more techniques and/or systems are provided for providing users with access to a route for travelling. A user, of a client device, may send a request for access to the route to a route planning service. The route may correspond to a starting location and an ending location. The route planning service may query a route database to identify an entry indicating that a restricted access road segment (e.g., a high occupancy vehicle lane, a shoulder lane, a bus lane, etc.) and/or a road segment (e.g., comprising a traffic light alteration capability) exists between the starting location and the ending location. Responsive to successfully authorizing the user for travelling the restricted access road segment and/or the road segment, the route, comprising the restricted access road segment and/or the road segment, may be provided to the client device.

Abstract: One or more techniques and/or systems are provided for facilitating simulation of an application used to access features of a vehicle. For example, an application developer may use an application development environment to develop an application that is used to display information through a vehicle display, obtain telemetry data from the vehicle, and/or modify vehicle features of the vehicle. However, the application development environment may not have real-time access to a vehicle (e.g., while the vehicle is being driven), which significantly reduces the ability to test the application. Accordingly, vehicle parameter signals may be simulated and provided to application code of the application (e.g., the application developer may specify a fan speed as “high”, preprogrammed vehicle speed data may be supplied to the application code, etc.). In this way, the application can be tested as though the application had access to an operational vehicle.

Abstract: Vehicles feature various forms of automated driving control, such as speed control and braking distance monitoring. However, the parameters of automated control may conflict with the user driving behaviors of the user; e.g., braking distance maintained with respect to a leading vehicle may seem overcautious to users who prefer shorter braking distances, and unsafe to users who prefer longer braking distances. Presented herein are techniques for controlling vehicles according to the user driving behaviors of users. While a user operates a vehicle in a driving context, a device monitors various driving features (e.g., acceleration or braking) to determine various user driving behaviors. When requested to control a driving feature of the vehicle, a controller may identify the user driving behaviors of the user in the driving context, and control the driving features according to the user driving behaviors, thus personalizing automated driving to the preferences of the user.

Abstract: One or more techniques and/or systems are provided for slowdown detection. Location data received from vehicles traveling a road is evaluated to identify a road segment associated with vehicle speeds below a threshold. A space-time diagram is generated, and location data associated with vehicles traveling the road segment are plotted within the space-time diagram. The space-time diagram is processed using a convolutional neural network to determine a probability that the space-time diagram illustrates a slowdown. If the probability that the space-time diagram illustrates the slowdown is greater than a threshold, then a notification of the slowdown is transmitted to one or more computing devices associated with vehicles that may encounter the slowdown.

Abstract: Contemporary navigation systems are often tasked with routing a vehicle to a destination, but are poorly equipped to assist with finding a vacancy of a parking opportunity in which the vehicle may be parked. Static information, such as enumeration of parking garages and curbside parking meters, may be frustrating if such parking opportunities have no vacancies. The determination of vacancies with certainty may be difficult to achieve due to the characteristic volatility of parking, in which vacancies may be taken in seconds. Presented herein are navigation device configurations involving probabilistic evaluation of parking routes in a vicinity of a destination that may be generated and compared, optionally weighted by various factors, to identify a parking route with parking opportunities that collectively present a high probability of vacancy as compared with other parking routes, which may be presented to the user and/or appended to a current route of an autonomous vehicle.

Abstract: One or more techniques and/or systems are provided for parking space routing. For example, parking data for a parking region, such as a parking lot, may be obtained from one or more data sources (e.g., vehicle sensor data, a parking lot camera, parking meter transaction data, etc.). Routes from a current location of a vehicle to available parking spaces within the parking region may be computed. The routes may be ranked based upon various criteria, such as convenience, congestion, travel time, travel distance, a parking space fill order, etc. A route, having a rank above a threshold (e.g., a highest ranked route), may be provided to a driver of the vehicle, such as through a vehicle navigation unit, a mobile device, a wearable device, etc. The route may be provided to autonomous driving functionality of the vehicle for automatic routing and navigation of the vehicle to the parking space.

Abstract: One or more techniques and/or systems are provided for notifying drivers to assume manual vehicle control of vehicles. For example, sensor data is acquired from on-board vehicles sensors (e.g., radar, sonar, and/or camera imagery of a crosswalk) of a vehicle that is in an autonomous driving mode. In an example, the sensor data is augmented with driving condition data aggregated from vehicle sensor data of other vehicles (e.g., a cloud service collects and aggregates vehicle sensor data from vehicles within the crosswalk to identify and provide the driving condition data to the vehicle). The sensor data (e.g., augmented sensor data) is evaluated to identify a driving condition of a road segment, such as the crosswalk (e.g., pedestrians protesting within the crosswalk). Responsive to the driving condition exceeding a complexity threshold for autonomous driving decision making functionality, a driver alert to assume manual vehicle control may be provided to a driver.

Abstract: A method and system for modeling and processing vehicular traffic data and information, comprising: (a) transforming a spatial representation of a road network into a network of spatially interdependent and interrelated oriented road sections, for forming an oriented road section network; (b) acquiring a variety of the vehicular traffic data and information associated with the oriented road section network, from a variety of sources; (c) prioritizing, filtering, and controlling, the vehicular traffic data and information acquired from each of the variety of sources; (d) calculating a mean normalized travel time (NTT) value for each oriented road section of said oriented road section network using the prioritized, filtered, and controlled, vehicular traffic data and information associated with each source, for forming a partial current vehicular traffic situation picture associated with each source; (e) fusing the partial current traffic situation picture associated with each source, for generating a single co

Abstract: Techniques are described for using information regarding road traffic and other types of transportation-related information to determine and/or assess alternative inter-modal passenger travel options in a geographic area that supports multiple modes of transportation. For example, a particular user may have multiple alternatives for travel from a starting location to a destination location in the geographic area, including to use alternative modes of transportation (e.g., private vehicle, bus, train, walking, etc.) for some or all of the travel, and these alternatives may have different travel-related characteristics in different situations (e.g., depending on current road traffic; mass transit schedules and current actual deviations; travel-related fees for gas, parking, mass transit, etc; parking availability; etc.).

Abstract: Among other things, one or more techniques and/or systems are provided for personalized vehicle management. A current location of a vehicle may be received. A route of the vehicle may be determined based upon a trip library and/or the current location. The trip library may correspond to routes traveled by the user above a travel frequency threshold. A route segment (e.g., a portion of the route that the vehicle will travel within a threshold duration) may be identified. A route segment characteristic (e.g., a weather characteristic, a physical characteristic, a traffic characteristic, etc.) of the route segment may be determined. The route segment characteristic may be provided to a driver assistance component of the vehicle. The driver assistance component may be instructed to alter functionality of the vehicle using a vehicle operational parameter derived from the route segment characteristic.

Abstract: One or more techniques and/or systems are provided for estimating parking occupancy. For a paid parking period, parking meter transaction data may be acquired for a parking meter encompassed by a zone of one or more parking spaces. The parking meter transaction data may be evaluated to determine status data, such as an estimation of whether one or more parking spaces are available, occupied, and/or will become available. A parking occupancy, indicative of a likelihood of available parking spaces, may be estimated based upon the status data. For a free parking period, the parking occupancy may be estimated based upon vehicle flow data that is indicative of vehicles entering, parking, and/or leaving the one or more parking spaces. In this way, the parking occupancy may be provided to a driver to mitigate wasted time and/or gas otherwise spent searching for an available parking space.

Abstract: Users within transit in a vehicle may initiate location queries to fulfill a set of interests, such as stops for food, fuel, and lodging. A device may fulfill the queries according to various factors, such as the distance of nearby locations to the user or to another location specified by the user, and the popularity of various locations. However, the user may not have specified or even chosen a route, and may wish to have interests fulfilled at a later time (e.g., stopping for food in 30 minutes), and a presentation of search results near the user's current location may be unhelpful. Presented herein are techniques for fulfilling location queries that involve predicting a route of the user, and identifying a timing window for the query results (e.g., locations that are likely to be near the user's projected location when the wishes to stop for food in 30 minutes).

Abstract: One or more techniques and/or systems are provided for training and/or utilizing a traffic obstruction identification model for identifying traffic obstructions based upon vehicle location point data. For example, a training dataset, comprising sample vehicle location points (e.g., global positioning system location points of vehicles) and traffic obstruction identification labels (e.g., locations of known traffic obstructions such as stop signs, crosswalks, stop lights, etc.), may be evaluated to extract a set of training features indicative of traffic flow patterns. The set of training features and the traffic obstruction identification labels may be used to train a traffic obstruction identification model to create a trained traffic obstruction identification model. The trained traffic obstruction identification model may be used to determine whether a road segment has a traffic obstruction or not.

Abstract: One or more techniques and/or systems are provided for facilitating simulation of an application used to access features of a vehicle. For example, an application developer may use an application development environment to develop an application that is used to display information through a vehicle display, obtain telemetry data from the vehicle, and/or modify vehicle features of the vehicle. However, the application development environment may not have real-time access to a vehicle (e.g., while the vehicle is being driven), which significantly reduces the ability to test the application. Accordingly, vehicle parameter signals may be simulated and provided to application code of the application (e.g., the application developer may specify a fan speed as “high”, preprogrammed vehicle speed data may be supplied to the application code, etc.). In this way, the application can be tested as though the application had access to an operational vehicle.

Abstract: Among other things, one or more techniques and/or systems are provided for providing users with access to a route for travelling. A user, of a client device, may send a request for access to the route to a route planning service. The route may correspond to a starting location and an ending location. The route planning service may query a route database to identify an entry indicating that a restricted access road segment (e.g., a high occupancy vehicle lane, a shoulder lane, a bus lane, etc.) and/or a road segment (e.g., comprising a traffic light alteration capability) exists between the starting location and the ending location. Responsive to successfully authorizing the user for travelling the restricted access road segment and/or the road segment, the route, comprising the restricted access road segment and/or the road segment, may be provided to the client device.

Abstract: Users who are traveling on a path between a first location and a second location may be informed by navigation devices about the user's selected route. The path may also feature two or more lanes, which may present comparative advantages (e.g., a toll-restricted lane may present less traffic, and a toll-free lane may present more traffic at a reduced cost). Presented herein are techniques for enabling navigation devices to advise users about the lanes of the path. A travel service may collect information about the respective lanes, such as traffic density and the typical travel duration of users utilizing the lane during various periods, and may transmit information about the predicted travel durations of the respective lanes to the device. Such information may enable the device to advise the user to choose a selected lane, according to the predicted travel durations of the lanes of the path.

Abstract: One or more techniques and/or systems are provided for operating an autonomous vehicle based upon a driving preference. For example, a driving profile, comprising a driving preference (e.g., a speed preference, a route preference, etc.) of a user, may be provided to an automated driving component of the autonomous vehicle. An operational parameter for the autonomous vehicle may be generated based upon the driving preference of the user. The autonomous vehicle may be operated based upon the operational parameter. In an example, a condition of the user traveling in the autonomous vehicle may be determined, and the operational parameter for the autonomous vehicle may be adjusted based upon the condition of the user not corresponding to the driving preference.