Ford Global Technolgoies, LLC

Alexander Groh

Vidya Nariyambut Murali

Ashley Elizabeth Micks

Prabhanjan Kadepurkar

Ali Hassani

John William Schmotzer

Arun Dutta

Casey Bryan Feldman

Alan Peter Norton

Pol Llado

Mohannad Hakeem

Scott Vincent Myers

Jeremy Lerner

Siddharthan Selvasekar

Taylor Hawley

Sarah Houts

Umer Khalid

Jakob Nikolaus Hoellerbauer

Ramchandra Ganesh Karandikar

Joseph Gifford

Clifton Thomas

Dylan Verster

Kay Kunes

Benjamin Vondersaar

Edgar Nunez

Matthew Dage

A vehicle can be operated in an identified map area. Output is obtained from a first classifier, based on input including the map area and one or more current environmental conditions detected in the map area, specifying a first probability that the map area is currently available for sensing to support input-free operation of the vehicle. Then, if and only if the first probability indicates that the map area is currently available for sensing to support input-free operation of the vehicle, output is obtained from a second classifier, based on input including the map area and the one or more current environmental conditions, specifying a second probability that the vehicle will traverse the map area without a minimum risk maneuver event. Then, if and only if the second probability indicates that the vehicle will traverse the map area without a minimum risk maneuver event, operating the vehicle in an input-free mode in the map area.

Location-based vehicle operation

Sensors in a vehicle detect execution of a sign language symbol. The sign language symbol invokes a vehicle interface function. In some embodiments, the sign language symbol is an ASL sign. Sensors include three-dimensional optical, ultrasonic, or other sensors. The locations of targets (fingertips, knuckles, palm, etc.) are detected in the individual outputs of the sensors. The locations of targets determined from the outputs of multiple sensors may be associated with one another and filtered, such as using an RBMCDA algorithm and Kalman filtering. The system may be calibrated to detect each symbol by measuring the target locations with the user executing the each symbol.

Sign language inputs to a vehicle user interface

A vehicle is described that includes a video camera configured to record video, a processor configured to process the recorded video from the video camera into hyperlapse video, and an input/output device to link the hyperlapse video with a social network associated with at least one of a driver of the vehicle and the vehicle. The processor may be configured to receive video data from the video camera and to create the hyperlapse video by reconstructing a video stream from the video data, planning a smooth path through the video stream, and rendering the video data along the smooth path into the hyperlapse video that has a faster speed and less jitter than the video stream. The hyperlapse video may be a non-native, sped-up video of the recorded video from the video camera.

Vehicle with hyperlapse video and social networking

Methods and systems for generating virtual sensor data for developing or testing computer vision detection algorithms are described. A system and a method may involve generating a virtual environment. The system and the method may also involve positioning a virtual sensor at a first location in the virtual environment. The system and the method may also involve recording data characterizing the virtual environment, the data corresponding to information generated by the virtual sensor sensing the virtual environment. The system and the method may further involves annotating the data with a depth map characterizing a spatial relationship between the virtual sensor and the virtual environment.

Method and system for virtual sensor data generation with depth ground truth annotation

A method for processing audible sounds using ultrasonic sensors. The method includes passively monitoring, via ultrasonic sensors, an external environment for a audible sounds. An audible sound may be detected and used to produce a sound signal. The sound signal may be filtered to determine one or more features corresponding thereto, including a class, a position, and a velocity. A priority may be assigned to the sound signal based on the sound signal to determine an appropriate response. A corresponding system and computer program product are also disclosed and claimed herein.

Passive sound source classification and localization

A computer system generates a lattice structure effective to satisfy static loading criteria, the lattice structure including surfaces, nodes, and branches interconnecting nodes. The branches are removed and various alternative configurations are tested to identify one that meets low frequency damping requirements. An outer damping layer is selected to satisfy high frequency damping requirements and is added to the lattice structure. The lattice structure may then be fabricated using an additive manufacturing device.

Manufacture of vibration damping structures

A machine learning module may generate a probability distribution from training data including labeled modeling data correlated with reflection data. Modeling data may include data from a LIDAR system, camera, and/or a GPS for a target environment/object. Reflection data may be collected from the same environment/object by a radar and/or an ultrasonic system. The probability distribution may assign reflection coefficients for radar and/or ultrasonic systems conditioned on values for modeling data. A mapping module may create a reflection model to overlay a virtual environment assembled from a second set of modeling data by applying the second set to the probability distribution to assign reflection values to surfaces within the virtual environment. Additionally, a test bench may evaluate an algorithm, for processing reflection data to generate control signals to an autonomous vehicle, with simulated reflection data from a virtual sensor engaging reflection values assigned within the virtual environment.

Physics modeling for radar and ultrasonic sensors

A vehicle includes a plurality of sensors including exterior sensors. Vehicle signals, such as those derived from sensors, are processed to detect alertable conditions and each alertable condition is represented by a created software object. A location is associated with each software object, such as corresponding to a location of an exterior feature that gave rise to the alertable condition. The software object is updated over time according to the vehicle signals, such as by updating the location according to movement of the obstacle. The software objects are processed to drive an array of speakers effective to simulate a sound originating from the location associated with the software object. The sound generated by the speakers may be repeated chimes having a volume and period determined according to the location.

Spatial auditory alerts for a vehicle

A method is disclosed for issuing audio alerts within the cabin of a vehicle. The method may include detecting a condition programmatically assigned an audio alert and a virtual source for the audio alert. The method may further include determining, by the computer system based on the virtual source, a gain value for each speaker of a plurality of speakers carried in fix positions onboard the vehicle. Once the gain value for each speaker of the plurality of speak is known, the audio alert may be projected by each speaker of the plurality of speakers according to the gain value determined therefor.

In-vehicle, multi-dimensional, audio-rendering system and method

A vehicle includes a steering wheel and a controller. The controller is configured to, in response to receiving location and speed data from other vehicles indicating an expected collision absent a trajectory change, automatically control the steering wheel to direct the vehicle along a collision avoidance path. The collision avoidance path is based on map data identifying a marking type for a traveling lane such that the path crosses the lane when the marking type is broken and does not cross the lane when the marking type is solid.

Growing community of inventors

Detroit, MI, United States of America

Alexander Groh