Allstate Insurance Company

Leland Stanford Junior University

Arity International Limited

Regina Madigan

Timothy W Gibson

Howard Hayes

Surender Kumar

Mark V Slusar

Robert H Johnson

Rothana Srey

Nicholas A Suizzo

Sean P Willett

Carolyn Parker

Chienlan Hsu-Hoffman

Juan Carlos Aragon

Sunil Kumar Chintakindi

Nan Zhang

Alicia Dornadic

Thomas McKenna

Dana Ferguson

Evan Gibbs

Julie A Jordan Peters

Bryan Keith Corder

Philip Peter Ramirez

Soton Ayodele Rosanwo

William Polisson

Maryam Zahedi

Taylor Parsell

Derek Otten

Grady Irey

Aleksandr Likhterman

Anuradha Kodali

Caleb Johnson

Srinivas Nainala

Derek Phillips

Mykel Kochenderfer

William F Polisson, Jr

Gibbs Evan

Juan Ortiz-Zabala

Mark Slusar

Systems and methods are disclosed for determining the efficacy of an autonomous vehicle driving system in exhibiting safe driving behavior during test track scenarios. Testing parameters eliciting autonomous vehicle driving system behavior may be chosen for the test track scenario. The autonomous vehicle driving system may be tested in the test track and autonomous vehicle driving system behavior may be observed in response to the presentations of testing parameters. A safe driving score may be calculated for the autonomous vehicle driving system based on measured autonomous vehicle performance and operational data generated responsive to the presentation of testing parameters in the test track. A benchmark insurance premium may be calculated for an autonomous vehicle driving system based on the calculated safe driving score.

Testing autonomous cars

Systems and methods are disclosed for monitoring or affecting movement of a vehicle using a traffic device. An event data source may have a processor and/or a transceiver. The event data source may transmit, via the transceiver and to a vehicle and infrastructure computing device, information indicative of an event affecting a portion of road. The vehicle and infrastructure computing device may comprise a vehicle and infrastructure control computer. The vehicle and infrastructure computing device may receive, from the event data source, the information indicative of the event affecting the portion of road. The computing device may determine one or more traffic devices associated with the portion of road and configured to control traffic for the portion of road. Based on the information indicative of the event affecting the portion of road, the computing device may send, to the one or more traffic devices associated with the portion of road, instructions to change one or more characteristics of the one or more traffic devices.

Electrical data processing system for monitoring or affecting movement of a vehicle using a traffic device

Methods, computer-readable media, software, and apparatuses may determine whether a human driver, or an autonomous driving system, should be in control of a vehicle in response to a detection of an unexpected event. A decision may be made to pass control from the autonomous driving system to the human driver, if it is determined that the human driver can handle the unexpected event more safely than the autonomous vehicle.

Safe hand-off between human driver and autonomous driving system

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

A system for determining a subjective risk score may include a vehicle and/or a computing device associated with a user travelling within the vehicle. The computing device may receive input from the user when the user feels a sense of unease regarding a particular road segment upon which the vehicle is traveling. The system may further include a subjective risk analysis computing system that may be communicatively coupled to the computing device. The subjective risk analysis computing system may receive subjective risk information corresponding to the user's sense of unease regarding particular road segments and may process the subjective risk information to determine a subjective risk score for each of a plurality of road segments along a route. An insurance company may use this information to determine whether to adjust a quote or premium of an insurance policy.

Subjective route risk mapping and mitigation

Aspects of the disclosure relate to enhanced processing systems for providing dynamic driving metric outputs using improved machine learning methods. A computing platform may receive sensor data from vehicle sensors. The computing platform may generate a pattern deviation output corresponding to an output of a sensor data analysis model, an actual outcome associated with a lowest TTC value, and driving actions that occurred over a prediction horizon corresponding to the pattern deviation output. The computing platform may cluster the pattern deviation outputs to maximize a ratio of inter-cluster variance to intra-cluster variance. The computing platform may train a long short term memory (LSTM) for each cluster, and may verify consistency of the pattern deviation outputs in the respective clusters. After verifying the consistency of the pattern deviation outputs in each cluster, the computing platform may modify the sensor data analysis model to reflect pattern deviation outputs associated with verified consistency.

Adaptable on-deployment learning platform for driver analysis output generation

Systems and apparatuses for receiving data from a plurality of sensors and using the data, as well as other data, to generate a parking recommendation for an autonomous vehicle and instruct the autonomous vehicle to travel to the recommended parking location are provided. Data may be received from a plurality of sensors within a first autonomous vehicle, as well as from other vehicles and/or structures. Historical parking data associated with the first autonomous vehicle may also be extracted. In some examples, an expected future trip of the first autonomous vehicle may be determined. The system may then evaluate the data to generate a parking recommendation for the first autonomous vehicle. The system may generate and transmit instructions for traveling from a current location to the recommended parking location and may cause the first autonomous vehicle to travel to the recommended parking location.

Generating and transmitting parking instructions for autonomous and non- autonomous vehicles

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

A system including a computing device may receive base map information, including attribute information associated with a plurality of road segments, and trip request information. Based on this information, a route for the user to travel may be determined. The system might further calculate a risk score for each road segment forming the route, and generate a risk map based on the risk score and the route. The risk map may then be displayed to a user. The risk map may include markers or other objects depicting potential risks along the route the driver may face. Also, the risk map may be updated based on information collected from a sensor coupled to the vehicle or located at the road segment to reflect actual, real-time risk scores calculated using an equation for providing a risk score for a particular driver driving a particular vehicle on a particular road segment.

Polynomial risk maps

A route risk mitigation system and method using real-time information to improve the safety of vehicles operating in semi-autonomous or autonomous modes. The method mitigates the risks associated with driving by assigning real-time risk values to road segments and then using those real-time risk values to select less risky travel routes, including less risky travel routes for vehicles engaged in autonomous driving over the travel routes. The route risk mitigation system may receive location information, real-time operation information, (and/or other information) and provide updated associated risk values. In an embodiment, separate risk values may be determined for vehicles engaged in autonomous driving over the road segment and vehicles engaged in manual driving over the road segment.

Real time risk assessment and operational changes with semi-autonomous vehicles

Systems, methods, apparatuses, and computer-readable media for receiving data from one or more sensors associated with one or more home devices of a user, such as appliances, home systems, etc., receiving data from one or more sensors associated with a vehicle of the user, and/or receiving data associated with a lifestyle of the user are presented. In some examples, the data may aggregated and analyzed to assess risk associated with the user in order to determine or adjust an insurance rate, premium, and/or incentive.

Device sensing

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.

Dynamic distance estimation output generation based on monocular video

Aspects of the disclosure relate to dynamic driving metric output platforms that utilize improved computer vision methods to determine vehicle metrics from video footage. A computing platform may receive video footage from a vehicle camera. The computing platform may determine that a reference marker in the video footage has reached a beginning and an end of a road marker based on brightness transitions, and may insert time stamps into the video accordingly. Based on the time stamps, the computing platform may determine an amount of time during which the reference marker covered the road marking. Based on a known length of the road marking and the amount of time during which the reference marker covered the road marking, the computing platform may determine a vehicle speed. The computing platform may generate driving metric output information, based on the vehicle speed, which may be displayed by an accident analysis platform. Based on known dimensions of pavement markings the computing platform may obtain the parameters of the camera (e.g., focal length, camera height above ground plane and camera tilt angle) used to generate the video footage and use the camera parameters to determine the distance between the camera and any object in the video footage.

Dynamic driving metric output generation using computer vision methods

Systems and methods are provided for automatically changing or updating insurance coverage using a computer device. An insurance analyzer may receive data associated with an insurance user. The insurance analyzer may determine types of insurance coverage available and coverage amounts associated with the received user data. Based on the received data the insurance analyzer may automatically activate insurance coverage based on determined types of insurance available and coverage amounts. The insurance analyzer may also deactivate insurance coverage or change insurance coverage amounts based on determined user activity.

Instant insurance

Methods, computer-readable media, systems, and/or apparatuses for providing offer and output generation functions are provided. For instance, a request for an output may be received by a device. In response, user physical trait data, pre-stored data, location data, and the like, may be extracted and received from a plurality of sources. Machine learning may be used to analyze the data to predict one or more factors associated with the user and the output or offer may be generated based on the predicted factors.

Growing community of inventors

Mountain View, CA, United States of America

Regina Madigan