Allstate Insurance Company

Here Global B.v.

Leland Stanford Junior University

Sunil Kumar Chintakindi

Howard Hayes

Timothy W Gibson

Surender Kumar

Regina Madigan

Veljko Krunic

Aleksandr Likhterman

Soton Ayodele Rosanwo

Tim Gibson

Anuradha Kodali

Mark V Slusar

Andrew Calkins

Harini Anand

Joy Hoeffler

Matei Stroila

Narayanan Alwar

Santhosh Thammi

Pedro Alvarez-Tabio Togores

Juan Carlos Aragon

Pedro Alvarez Tabio Togores

Derek Phillips

Caleb Johnson

Srinivas Nainala

Mykel Kochenderfer

Anatoly S Belkin

Juan Ortiz-Zabala

Methods, computer-readable media, software, and system may generally build and quantify mobility patterns based on user location data, both at an individual level and an aggregate level. The system may determine the origin and destination data for each trip taken by a user. The system may then define areas of mobility using a mobility graph built from the data. The graph may include nodes and edges. In some examples, the nodes are constructed from the origins and destinations of the trajectories using spatial clustering techniques. Further, the edges between nodes may be constructed based on the trips between them, such as two nodes are connected by an edge if there is at least one trip between them. The edges may be given different weights based on trip frequencies. The system may then determine a region of mobility using the generated mobility graph and data clustering techniques.

Vehicle mobility patterns based on user location data

Systems and methods are disclosed for determining that an adverse driving event is likely to occur and utilizing accident calculus algorithms to determine and cause vehicle driving actions necessary to mitigate consequences of the adverse driving event. After determining that an adverse driving event is likely to occur, a computing device my forecast consequences of the driving event. The computing device may determine potential evasive maneuvers that may be taken responsive to the adverse driving event. Additionally, the computing device may determine consequences associated with the potential evasive maneuvers and assign a weight relative to the consequence. The computing device may compare the potential driving maneuvers based on the weighted consequences to determine a driving maneuver to take.

Accident prediction and consequence mitigation calculus

Methods, computer-readable media, systems, and/or apparatuses for evaluating movement data to identify a user as a driver or non-driver passenger are provided. In some examples, movement data may be received from a mobile device of a user. The movement data may include sensor data including location data, such as global positioning system (GPS) data, accelerometer and/or gyroscope data, and the like. Additional data may be retrieved from one or more other sources. For instance, additional data such as usage of applications on the mobile device, public transportation schedules and routes, image data, vehicle operation data, and the like, may be received and analyzed with the movement data to determine whether the user of the mobile device was a driver or non-driver passenger of the vehicle. Based on the determination, the data may be deleted in some examples or may be further processed to generate one or more outputs.

Multi-computer processing system for dynamically executing response actions based on movement data

Aspects of the present disclosure describe systems, methods, and devices for automated vehicular control based on glare detected by an optical system of a vehicle. In some aspects, automated control includes controlling the operation of the vehicle itself, a vehicle subsystem, or a vehicle component based on a level of glare detected. According to some examples, controlling the operation of a vehicle includes instructing an automatically or manually operated vehicle to traverse a selected route based on levels of glare detected or expected along potentials routes to a destination. According to other examples, controlling operation of a vehicle subsystem or a vehicle component includes triggering automated responses by the subsystem or the component based on a level of glare detected or expected. In some additional aspects, glare data is shared between individual vehicles and with a remote data processing system for further analysis and action.

Glare detection systems and methods for automated vehicular control

Methods, computer-readable media, systems and apparatuses for determining a blind corner navigational score based on real-time or near real-time navigational analysis using sensor data, digital image data, and a map database are discussed. In some arrangements, detection of a blind sensor may be performing using sensor data, digital image data, and navigational data from a map database system. In at least some arrangements, a warning signal or a vehicle control signal may be transmitted to a vehicle in response to a determination that the blind corner navigational score is above a threshold. In at least some arrangements, route correction and/or route modification based on an upcoming blind corner may be performed if a blind corner navigational score is above a threshold.

Automated vehicle control and guidance based on real-time blind corner navigational analysis

Systems and methods in accordance with aspects of this disclosure may be provided to determine and calculate an overall driving risk index value corresponding to a driver and scene configuration. The overall driving risk index value may provide driving risk modeling and estimation at a personalized driving level. In some cases, the overall driving risk index value may be determined using a risk-predictive modeling system with weighting and machine learning and may include one or more of: a driver score system, a driver-contextual risk score system, and a conflict index system.

Personalized driving risk modeling and estimation system and methods

Apparatuses, systems, methods, and computer-readable media are provided for the preemptive logical configuration of vehicle control systems. A vehicle control computer may determine a location of a vehicle. The vehicle control computer may query a historical data source server for historical incident data corresponding to a first vicinity around the first location of the vehicle. Based on the historical incident data, the vehicle control computer may identify one or more driving danger areas in the first vicinity around the first location of the vehicle, wherein each of the one or more driving danger areas are associated with one or more driving hazards. The vehicle control computer may generate a configuration for vehicle operation in the first vicinity around the first location of the vehicle based on the one or more driving danger areas and may update driving logic of the vehicle with the configuration.

Preemptive logical configuration of vehicle control systems

Apparatuses, systems, and methods are provided for the utilization of vehicle control systems to cause a vehicle to take preventative action responsive to the detection of a near short term adverse driving scenario. A vehicle control system may receive information corresponding to vehicle operation data and ancillary data. Based on the received vehicle operation data and the received ancillary data, a multi-dimension risk score module may calculate risk scores associated with the received vehicle operation data and the received ancillary data. Subsequently, the vehicle control systems may cause the vehicle to perform at least one of a close call detection action and a close call detection alert to lessen the risk associated with the received vehicle operation data and the received ancillary data.

Vehicle control systems

Methods, systems, and apparatuses are described for engaging autonomous driving algorithms based on driver frustration levels and vehicle conditions. A frustration level of a driver of a vehicle may be determined using one or more sensors. Based on a determination that the frustration level satisfies a threshold, one or more automated driving algorithms which may be engaged by the vehicle to improve the safety of the driver may be determined. The threshold may be based on a road segment traveled by the vehicle, the user, or similar considerations. Based on a determination that the frustration level satisfies a threshold, engagement of the one or more automated driving algorithms may be caused.

Automated driving based on driver frustration

Methods, computer-readable media, systems, and/or apparatuses are provided for providing offer and insight generation functions. User input requesting an offer or insight may be received and an image of a photographic identification of a user may be requested. The image of the photographic identification may be captured and stored. A self-captured image of the user may be captured (e.g., via an image capture device of the computing device) and compared to an image of a user from the photographic identification. Responsive to determining that the images match, displaying an instruction to capture a vehicle identification number. The vehicle identification number may be captured. Data, including location data, may be extracted and an archive including the extracted data may be generated and the data may be transmitted to an entity computing system for processing. The entity computing system may evaluate the data and generate one or more insights and/or outputs.

Data processing system with machine learning engine to provide output generation functions

Systems and methods are disclosed for generating a display of a navigation map. The system may comprise a historical data source device having, for example, a historical data source computer and a database storing historical data associated with one or more of vehicle accident data, traffic data, vehicle volume data, vehicle density data, road characteristic data, or weather data. The system may comprise a map data processing device having a map data processing computer and memory storing computer-executable instructions that, when executed by the map data processing computer, cause the map data processing device to, for example, determine, based on a location determining device, a location of a vehicle. The map data processing system may determine one or more historical factors based on the location of the vehicle. The map data processing system may receive, from the historical data source device and for the location, historical data associated with the one or more historical factors. Based on the location of the vehicle, one or more real time factors and real time data associated with the one or more real time factors may be calculated. The map data processing system may calculate, using the one or more historical factors and the one or more real time factors, a navigation score for each segment of a route from the location to a destination location. The map data processing system may determine one or more colors for each navigation score and/or generate a display of a navigation map comprising the one or more colors.

Data processing system communicating with a map data processing system to generate a display of one or more segments of one or more vehicle routes

Apparatuses, systems, and methods are provided for the logical configuration of vehicle control systems based on driver profiles. A vehicle control computer may identify driving behavior of a driver of a vehicle through vehicle operation data provided by one or more of vehicle sensors, a telematics device, and a mobile device. Based on the driving behavior, the vehicle control computer may develop a first driving profile for the driver of the vehicle. The vehicle control computer transmit the first driving profile to a remote server storing driving profiles of a plurality of users. The vehicle control computer may download a second driving profile associated with a different driver from the remote server. The vehicle control computer may configure vehicle operations based off of the second driving profile associated with the different driver and may actuate vehicle operation based on the configuration.

Logical configuration of vehicle control systems based on driver profiles

Systems and methods are disclosed for determining a probability of an adverse event that will occur in a future. The system may determine a geographical location of a vehicle based on data indicating the geographical location of the vehicle received from the vehicle and sensed by a vehicle sensor of the vehicle; determine an environment of the geographical location of the vehicle; determine vehicle attributes of the vehicle; link the environment of the geographical location of the vehicle and the vehicle attributes; and based on a link between the environment of the geographical location of the vehicle and the vehicle attributes, determine a probability of an adverse event that will occur in a future.

Data processing system communicating with a map data processing system to determine or alter a navigation path based on one or more road segments

Aspects of the disclosure relate to a dynamic distance estimation output platform that utilizes improved computer vision and perspective transformation techniques to determine vehicle proximities from video footage. A computing platform may receive, from a visible light camera located in a first vehicle, a video output showing a second vehicle that is in front of the first vehicle. The computing platform may determine a longitudinal distance between the first vehicle and the second vehicle by determining an orthogonal distance between a center-of-projection corresponding to the visible light camera, and an intersection of a backside plane of the second vehicle and ground below the second vehicle. The computing platform may send, to an autonomous vehicle control system, a distance estimation output corresponding to the longitudinal distance, which may cause the autonomous vehicle control system to perform vehicle control actions.

Growing community of inventors

Chicago, IL, United States of America

Sunil Kumar Chintakindi