Nissan North America, Inc.

Renault S.a.s.

United States of America As Represented by the Administrator of Nasa

Washington University

Ali Mortazavi

Liam Pedersen

Maarten Sierhuis

Mauro Della Penna

Atsuhide Kobashi

Christopher Ostafew

Siddharth Thakur

Vikram Krishnamurthy

Mark Allan

Eric Schafer

Armelle Guerin

John Deniston

Ben Christel

Richard Enlow

Shane Hogan

Andrea Angquist

Sannidhi Jalukar

David Lees

Dawn Wheeler

Stefan Witwicki

Richard Lui

Yue Zhao

Stephen Wu

Jen Hamon

Richard Salloum

Robert Scheepjens

Azim Eskandarian

Batch routing of autonomous vehicles is disclosed. A method may include maintaining a plurality of vehicle state data object instances that respectively correspond to a plurality of autonomous vehicles. The method includes obtaining a traffic condition location and determining a group of autonomous vehicles from the plurality of autonomous vehicles where the current route of each autonomous vehicle intersects the traffic condition location. The method also includes determining two or more subgroups of autonomous vehicles, and for each subgroup, determining a respective avoidance waypoint corresponding to the subgroup that is not on the current route of the autonomous vehicle. For each autonomous vehicle in the subgroup, the method includes determining an updated route based on the current route of the autonomous vehicle and the respective avoidance waypoint, generating a control instruction based on the updated route, and transmitting the control instruction to the autonomous vehicle.

Computing framework for batch routing of autonomous vehicles

A remote system for an autonomous vehicle, includes a receiver, a controller, and a display device. The receiver is configured to receive road information. The controller is programmed to receive input related to the road information and create a supervision zone when the road information impacts road drivability. The display device is disposed at a control center area and configured to display a visual indication on a map of the supervision zone.

Remote system for an autonomous vehicle

Methods and systems for controlling a vehicle are herein disclosed. A method includes receiving vehicle data and external data from a vehicle control system of a vehicle and generating an environment representation of an area of the transportation network proximate to the vehicle location. The method includes displaying the environment representation in a GUI and receiving a solution path via the graphical user interface, the solution path indicating a route and one or more stop points. The method includes transmitting the route to the vehicle including a respective geolocation of each of the one or more stop points. The vehicle receives the route and begins traversing the transportation network based on the solution path. The method includes receiving updated vehicle data and/or updated external data from the vehicle and updating the environment representation based thereon. The method includes displaying, the updated environment representation via the graphical user interface.

Solution path overlay interfaces for autonomous vehicles

An autonomous vehicle service system having a display device, a receiver, and a controller. The receiver is configured to receive transmitted data from an autonomous vehicle related to status of the autonomous vehicle and information from a third party related to road conditions. The controller is programmed to monitor the transmitted data related to the status of the autonomous vehicle and the road conditions, determine when the autonomous vehicle requires assistance based on the transmitted data, and, when the autonomous vehicle requires assistance, cause information related to the autonomous vehicle to be displayed on the display device.

Autonomous vehicle service system

A method for world objects tracking and prediction by an autonomous vehicle includes receiving, from sensors of the AV, a first observation data; associating the first observation data with a first world object; determining hypotheses for the first world object; determining a respective hypothesis likelihood of each of the hypotheses indicating a likelihood that the first world object follows the intention; determining, for at least one hypothesis of the hypotheses, a respective state; and in response to a query, providing a hypothesis of the hypotheses based on the respective hypothesis likelihood of each of the hypotheses. A hypothesis corresponds to an intention of the first world object and the respective state includes predicted positions of the first world object.

Probabilistic object tracking and prediction framework

Exception handing, such as of obstruction situations, by an autonomous vehicle (AV) is disclosed. A method includes identifying an exception situation; identifying a risk associated with autonomously resolving the exception situation; and in response to the risk exceeding a risk threshold, initiating a request for assistance from a tele-operator, and halting for the tele-operator to respond to the request; and receiving a response from the tele-operator.

Teleoperation for exception handling

According to some implementations of the present disclosure, a method for controlling an autonomous vehicle is disclosed. The method includes traversing the transportation network in accordance with a route and receiving vehicle sensor data from one or more vehicle sensors of the autonomous vehicle. The method also includes determining that the autonomous vehicle has encountered an occlusion scenario based on the vehicle sensor data. In response to determining that the autonomous vehicle has encountered the occlusion scenario, the method includes transmitting a request for infrastructure data to an external resource via a communication network, receiving infrastructure data from the external resource, determining a control action for the autonomous vehicle to perform based on the infrastructure data and the vehicle sensor data, and controlling the autonomous vehicle based on the control action.

Transportation network infrastructure for autonomous vehicle decision making

A host vehicle receives remote vehicle spatial state information for a remote vehicle and identifies vehicle transportation network information representing a portion of a transportation network based on that information. At least one initial probability value is generated based on comparing the spatial state information and the transportation network information at an initial time point, each initial probability value indicating a likelihood that the remote vehicle is following a lane within the transportation network. A deviation between adjacent values for the spatial state information relative to the transportation network information is generated for a plurality of time points. For each single lane and deviation, the likelihood that the remote vehicle is following the lane using a new probability value based on the deviation is updated, a trajectory using the updated likelihood is generated, and the host vehicle traverses the transportation network using the transportation network information and trajectory.

Host vehicle operation using remote vehicle intention prediction

A method and apparatus for traffic signal timing estimation are disclosed. Traffic signal timing estimation may include a vehicle identifying transportation network information representing a vehicle transportation network including an intersection. The transportation network information may include expected traffic control device state information corresponding to the intersection, such as an artificial neural network based machine learning model trained for the intersection. The vehicle may identify a route through the vehicle transportation network that includes the intersection based on the expected traffic control device state information and may control the traversal of the vehicle transportation network by the vehicle based on the expected traffic control device state information to minimize one or more operational cost metrics. Training the model may include identifying training data from input data previously generated and stored by a traffic control device controller of the intersection.

Traffic signal timing estimation using an artificial neural network model

Methods, apparatuses, and non-transitory computer readable storage media for optimizing driving time based on traffic signal states are described. The disclosed technology includes a vehicle that is able to determine, based on route data, a plurality of distances that correspond to paths between a vehicle location and a destination location for the vehicle. The route data can include a map of a predetermined area that includes the vehicle location and the destination location. The vehicle can receive traffic signal data that includes traffic signal states for a corresponding traffic signals on the paths. The vehicle can determine travel times corresponding to a predetermined portion of the paths based on the distances and the traffic signal states. The vehicle can determine an optimized path between the vehicle location and the destination location based on the path that is determined to have the shortest travel time.

Optimizing autonomous car's driving time and user experience using traffic signal information

A method and apparatus for traffic signal timing estimation are disclosed. Traffic signal timing estimation may include a vehicle identifying transportation network information representing a vehicle transportation network including an intersection. The transportation network information may include expected traffic control device state information corresponding to the intersection, such as a support vector regression based machine learning model trained for the intersection. The vehicle may identify a route through the vehicle transportation network that includes the intersection based on the expected traffic control device state information and may control the traversal of the vehicle transportation network by the vehicle based on the expected traffic control device state information to minimize one or more operational cost metrics. Training the model may include identifying training data from input data previously generated and stored by a traffic control device controller of the intersection.

Traffic signal timing estimation using a support vector regression model

A drowsiness detection system and method uses Empirical Mode Decomposition (EMD) signal processing to detect whether a vehicle driver is drowsy. The system uses a decomposed component of the steering wheel signal to extract specific features representing the steering control degradation phases. The system classifies the measured features into alert or drowsy state. The detection system is independent of the road geometry and automatically compensates steering control performance variability between drivers. The system is accurate in detecting the drowsy periods and drowsy-related lane departures. The detection system is unobtrusive and can be applied on-line.

Growing community of inventors

Walnut Creek, CA, United States of America

Ali Mortazavi