Ford Global Technolgoies, LLC

Bruno Sielly Jales Costa

Luke Niewiadomski

Gintaras Vincent Puskorius

Nikhil Nagraj Rao

Dimitar Petrov Filev

Vidya Nariyambut Murali

Jinesh J Jain

Douglas J Rogan

Roger Arnold Trombley

Madeline Jane Goh

Enrique Corona

Gaurav Kumar Singh

Erick Michael Lavoie

Chen Zhang

Harpreetsingh Banvait

Ashley Elizabeth Micks

Mostafa Parchami

Kyle Simmons

Marcos Paul Gerardo Castro

Pavithra Madhavan

Oleg Yurievitch Gusikhin

Hamid M Golgiri

Eric L Reed

Punarjay Chakravarty

Donald Jacob Mattern

Gaurav Pandey

Vijay K Nagasamy

Seyed Armin Raeis Hosseiny

Bo Bao

Juan Enrique Castorena Martinez

Hemanth Yadav Aradhyula

Katherine Rouen

Siyuan Ma

Saeid Nooshabadi

Binduhasini Sairamesh

Stephen Giardinelli

John Michael Celli

Subramanya Nageshrao

Frederic Christen

Smita Vinayak Bailur

Christoph Kessler

Frank Golub

Hanieh Deilamsalehy

Marcos Pau Gerardo Castro

Systems, methods, and devices for estimating a shape of an object based on sensor data and determining a presence of a fault or a failure in a perception system. A method of the disclosure includes receiving sensor data from a range sensor and calculating a current shape reconstruction of an object based on the sensor data. The method includes retrieving from memory a prior shape reconstruction of the object based on prior sensor data. The method includes calculating a quality score for the current shape reconstruction by balancing a function of resulted variances of the current shape reconstruction and a similarity between the current shape reconstruction and the prior shape reconstruction.

Simultaneous diagnosis and shape estimation from a perceptual system derived from range sensors

A hitch assist system for a vehicle comprises an imaging system that receives image data of a hitch ball and trailer coupler, and a controller. The controller estimates a distance between a point on each of the hitch ball and trailer coupler. The points are parallel to a plane defined by a surface beneath the hitch ball and trailer coupler. The controller tracks the distance with a pixel-domain comparison between each of the points responsive to the distance being less than a first threshold, and maneuvers, via steering and braking systems, the vehicle along a path such that the distance is indicative of the points being coaxial.

Prevention of trailer coupler tracking jump during hitch assist operation

A system for assisting in aligning a vehicle for hitching with a trailer includes a steering system that adjusts a steering angle of the vehicle, a braking system that adjusts a speed of the vehicle, an imaging system that receives image data of a trailer disposed in an area proximate the vehicle, and a controller. The controller detects, within a threshold distance defined from a stationary point on the vehicle and the trailer, a position of a coupler from the image data, and, responsive to the position being less than the threshold distance, a status of the trailer based on the image data being indicative of a position of a hitch ball relative to the coupler within a second threshold. The controller maneuvers, via the steering and braking systems, the vehicle based on the status.

Differentiating between near trailer and connected trailer

A computing system can receive, in a vehicle, moving object information is determined by processing lidar sensor data acquired by a stationary lidar sensor. The moving object information can be determined using typicality and eccentricity data analysis (TEDA) on the lidar sensor data. The vehicle can be operated based on the moving object information.

Vehicle path planning

The present invention extends to methods, systems, and computer program products for classifying time series image data. Aspects of the invention include encoding motion information from video frames in an eccentricity map. An eccentricity map is essentially a static image that aggregates apparent motion of objects, surfaces, and edges, from a plurality of video frames. In general, eccentricity reflects how different a data point is from the past readings of the same set of variables. Neural networks can be trained to detect and classify actions in videos from eccentricity maps. Eccentricity maps can be provided to a neural network as input. Output from the neural network can indicate if detected motion in a video is or is not classified as an action, such as, for example, a hand gesture.

Classifying time series image data

A system for assisting in aligning a vehicle for hitching with a trailer includes a vehicle steering system, a wireless communication module, a detection system outputting a signal including scene data of an area to a rear of the vehicle, and a controller. The controller receives, via the wireless communication module, an automated hitching initiation command from an external wireless device, receives the scene data and identifying the trailer within the area to the rear of the vehicle, derives a backing path to align a hitch ball mounted on the vehicle to a coupler of the trailer, and controls the vehicle steering system to maneuver the vehicle including reversing along the backing path.

System and method for remote automated vehicle alignment with a trailer for hitching

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to determine an eccentricity map based on video image data and determine vehicle motion data by processing the eccentricity map and two red, green, blue (RGB) video images with a deep neural network trained to output vehicle motion data in global coordinates. The instructions can further include instructions to operate a vehicle based on the vehicle motion data.

Vehicle visual odometry

The present disclosure describes systems and methods that include calculating, via a reinforcement learning agent (RLA) controller, a plurality of state-action values based on sensor data representing an observed state, wherein the RLA controller utilizes a deep neural network (DNN) and generating, via a fuzzy controller, a plurality of linear models mapping the plurality of state-action values to the sensor data.

Interpreting data of reinforcement learning agent controller

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to detect a moving object in video stream data based on determining an eccentricity map. The instructions can further include instructions to determine a magnitude and direction of motion of the moving object, transform the magnitude and direction to global coordinates and operate a vehicle based on the transformed magnitude and direction.

Vehicle eccentricity mapping

Example vehicle occupancy management systems and methods are described. In one implementation, a method receives a current vehicle image representing a current interior of a vehicle. An occupancy management system detects at least one passenger in the vehicle based on the current vehicle image and determines a seating location of the passenger. A seat map is generated that identifies the seating location of the passenger in the vehicle.

Vehicle occupancy management systems and methods

A system for assisting in aligning a vehicle for hitching with a trailer includes a vehicle steering system, a detection system outputting a signal including scene data of an area to a rear of the vehicle, and a controller. The controller receives the scene data and identifying a trailer and at least one ground surface within the area to the rear of the vehicle and differentiates between first and second portions of the ground surface having first and second ground surface classifications. The controller further derives a backing path to align a hitch ball mounted on the vehicle to a coupler of the trailer to maintain the vehicle within the first portion of the ground surface having the first ground surface classification and controls the vehicle steering system to maneuver the vehicle during reversing along the backing path.

Automated hitching system with variable backing paths

In one implementation, a method activates an unmanned aircraft inside a vehicle to capture images of the vehicle interior. The method accesses a flight path for the unmanned aircraft and receives data associated with the vehicle's current movement. The method adjusts the flight path of the unmanned aircraft to compensate for the vehicle's current movement.

Vehicle inspection systems and methods

A vehicle has a trailer hitch, a vehicle electrical connector configured to electrically connect to a trailer electrical connector, and an imaging system oriented to captures images proximate to the trailer hitch. The vehicle also includes a proximity sensing system arranged to sense objects proximate to the trailer hitch and generate a proximity signal, an electrical connection detection system to detect an electrical connection to the vehicle trailer connector and generate an electrical connection signal, and a controller processing the captured images, the proximity signal and the electrical connector signal and determining a connection state of a trailer to the vehicle based on the captured images, the proximity sensor and the electrical connector signal, and generating an output indicative of the determined connection state.

Vehicle system and method for detecting trailer connection

An autonomous vehicle includes a microphone sensing sounds in the interior of the vehicle. The output of the interior microphone is processed according to an unsupervised machine learning model such that anomalies are indicated by the model. In response to detection of an anomaly, a remote dispatcher is notified, who may then dismiss the anomaly or transmit an instruction to the vehicle to alter its trajectory. The output of an exterior microphone and infotainment system may be removed from the output of the interior microphone prior to processing. An anomaly may be found to occur in response to detecting speaking of a keyword in the output of the interior microphone.

Detection of anomalies in the interior of an autonomous vehicle

Growing community of inventors

Santa Clara, CA, United States of America

Bruno Sielly Jales Costa