Ford Global Technolgoies, LLC

Justin Miller, Jr

Ali Hassani

Jianbo Lu

Sanghyun Hong

John Robert Van Wiemeersch

Mahmoud Yousef Ghannam

Timothy Mark Feldkamp

Smruti Panigrahi

Kurt Michael Lundeen

Robert Schroeter

Jake S Schwartz

Pavithra Madhavan

Devesh Upadhyay

Raj Sohmshetty

Hafiz Malik

Alexandra Taylor

Medha Karkare

Kevin Hwang

Dimitar Petrov Filev

Yifan Chen

Mario Anthony Santillo

Gaurav Pandey

Meghna Menon

James McBride

Alireza Rahimpour

Matthew Cui

Zaid El Shair

Adam Wint

Mohammad Hassani

Navid Fallahinia

Anna Marie-Sophia Hoff

Jim Birley

Harshal Maske

Robert Bennett

Rafi Ud Daula Refat

A far-infrared camera mounted in a vehicle generates an image frame. When an image of a large animal is identified in the image frame, a pixel intensity of the large animal image is determined. An estimated distance to the large animal from the far-infrared camera based on the pixel intensity is determined. When the animal is classified as a tracked animal, and future trajectories of the tracked animal and the vehicle intersect, a component in the vehicle is actuated.

Large animal detection and intervention in a vehicle

Output can be provided from a selected biometric analysis task that is one of a plurality of biometric analysis tasks based on an image provided from an image sensor. The selected biometric analysis task can be performed in a deep neural network that includes a common feature extraction neural network, a plurality of biometric task-specific neural networks and a plurality of expert pooling neural networks that perform the plurality of biometric analysis tasks by inputting the image to the common feature extraction network to determine latent variables. The latent variables can be input to the plurality of biometric task-specific neural networks to determine a plurality of first outputs. Concatenated first output results can be formed and the concatenated plurality of first result outputs and the latent variables can be input to the plurality of expert pooling neural networks to determine one or more biometric analysis task outputs.

Biometric task network

A vehicle includes a window separating a compartment of the vehicle from a region external to the vehicle. The window includes an outer surface. An imaging device is in the compartment and configured to capture an image of the region external to the vehicle through the window. Control circuitry is in communication with the imaging device and configured to receive the image from the imaging device, detect an obstruction in the image data corresponding to a substance on the window, and generate an output in response to the detection of the obstruction, wherein the imaging device is disposed within 50 millimeters (mm) from the window.

Visibility obstruction detection for a vehicle

A method to prevent intoxicated operation is described. The method includes providing instructions to a vehicle user to position a vehicle user body portion posture in a predefined alignment. The method further includes obtaining the vehicle user body portion posture from a first vehicle detector, and determining whether the vehicle user body portion posture is in the predefined alignment. The method includes activating a plurality of vehicle visual indicators to illuminate in a predefined manner when the vehicle user body portion posture is in the predefined alignment. The method further includes providing instructions to the vehicle user to move vehicle user eyes to track the plurality of vehicle visual indicators, and obtaining a vehicle user eye movement from a second vehicle detector. The method further includes determining whether the vehicle user eye movement meets a predetermined condition, and actuating a control action accordingly.

Inebriation test system

A docking system is provided. The docking system includes a docking station and an autonomous mobile robot (AMR). The AMR includes a processor, a camera electrically connected to the processor, a lidar system electrically connected to the processor, and a memory. The memory may have instructions that, when executed by the processor, cause the processor to perform operations including employ the camera and the lidar system to determine an offset position and a final position of the AMR with respect to the docking station, and dock the AMR at the docking station using the offset and final positions.

Docking system and associated method

A vehicle includes a compartment having a first space having a first environmental condition and a second space having a second environmental condition. At least one camera captures a first image of a first part of a region external to the vehicle and a second image of a second part of the region. The first part of the region aligns with the first space, and the second part of the region aligns with the second space. An environmental control system of the vehicle has at least one of lighting control and climate control. Control circuitry is configured to determine brightness conditions of the region based on the first image and the second image and control the environmental control system to adjust the environmental conditions based on the brightness conditions.

Localized brightness detection for a vehicle

A facial recognition authentication system and method include obtaining a current image in response to a request for facial recognition authentication of a user. A set of current image features are generated from the input image. Live image features and spoof image features are retrieved for the user. Then a determination is output that the input image is one of live or spoofed based on a comparison of the current image features to the live image features and the spoof image features.

Spoof images for user authentication

A biometric evaluation system for a vehicle includes a vision sensor configured to detect a biometric quality of a user. The biometric evaluation system also includes an operational system for the vehicle. At least one processor is in communication with the vision sensor. The processor is configured to execute a first classification algorithm that performs a first biometric validation based on the biometric quality to estimate a state of the user. The first classification algorithm requires a first service latency. In response to an outcome of the first biometric validation, the at least one processor is further configured to execute a second classification algorithm that performs a second biometric validation to confirm the state of the user. The second classification algorithm requires a second service latency greater than the first service latency. The processor is further configured to communicate a signal to modify operation of the vehicle.

Biometric service evaluation architecture for a vehicle

Upon obtaining biometric data for a user of a structure while the user is outside the structure, user data for the user is updated based on a confidence score for the biometric data exceeding a first confidence threshold. Based on the confidence score for the biometric data not exceeding the first confidence threshold, instructions are provided to the user to provide updated biometric data. Then the user data is updated based on a confidence score for the updated biometric data exceeding a second confidence threshold. The second confidence threshold is greater than the first confidence threshold. Structure components are controlled based on the updated user data.

Enhanced biometric authorization

A vehicle includes at least one camera that captures at least one image of a region external to the vehicle. The vehicle includes an environmental control system of the vehicle having at least one of lighting control and climate control for the vehicle. The vehicle includes control circuitry configured to process a first set of images of the plurality of images at a first sampling rate, determine a brightness condition of the region external to the vehicle based on processing the first set of images, process a second set of images of the plurality of images at a second sampling rate different than the first sampling rate, detect a shift in the brightness condition based on the second set of images, and control the environmental control system in response to the shift in the brightness condition.

Vehicle environment control using brightness detection

A first computer and a second computer are each connected to a communication network. User data is generated for a user by the first computer based on receiving, from the second computer, initial enrollment biometric data for the user. The user is authorized by the first computer based on a confidence score for challenge biometric data exceeding a first confidence threshold. Then the user data is updated with updated enrollment biometric data by the first computer based on a confidence score for the updated enrollment biometric data exceeding a second confidence threshold. The second confidence threshold is greater than the first confidence threshold. The initial enrollment biometric data is deleted by the second computer after a predetermined time of receiving the initial enrollment biometric data.

A method includes obtaining state information from one or more sensors of a digital twin. The method includes determining an action at the first routing control location based on the state information, where the action includes one of a pallet merging operation and a pallet splitting operation, and determining a consequence state based on the action. The method includes calculating a transient production value based on the consequence state and a transient objective function, calculating a steady state production value based on the consequence state and a steady state objective function, and selectively adjusting one or more reinforcement parameters of the reinforcement learning system based on the transient production value and the steady state production value.

Systems and methods for training a reinforcement learning system for pallet routing in a manufacturing environment

The present disclosure is directed to multi-use mobile robots that cater to both goods delivery and people mobility. These robots allow for seamless and dynamic transition between a rideable personal transport vehicle that may be driven by a user sitting in a removable robot seat, driven by the user standing onboard the vehicle, or driven by a second individual walking behind the multi-use robot. The multi-use robot may also function as an autonomous delivery vehicle, and can provide an option to allow both people and goods to be transported simultaneously. The multi-use robots can also integrate with mobile warehouses and neighborhood storage lockers and mobile warehouses, and provide last-mile handling of goods and supplies.

Multi-use mobile robot and methods of use

This disclosure is generally directed to systems and methods for generating a last mile travel route for a delivery robot. In an example embodiment, an individual captures an image of a frontage of a property. The image may include a package drop-off spot where a package can be dropped off by the delivery robot. The individual may also insert labels and/or illustrations into the image for conveying information such as object descriptors (front door, drop-off spot, etc.), traversable areas (driveway, walkway, etc.), and non-traversable areas (lawn, flower bed, etc.). The image is converted by a computer into a travel map that the delivery robot can use to identify a travel route through the frontage area of the property. The travel map may be provided in various forms such as a semantic map of the frontage area or a bird's eye view rendering of the frontage area.

Systems and methods to generate a last mile travel route for a delivery robot

A method for controlling a robotic vehicle in a delivery environment includes causing the robotic vehicle to deploy from an autonomous vehicle (AV) at a first AV position in the delivery environment. The method further includes localizing, via a robotic vehicle controller, an initial position within a global reference map using a robot vehicle perception system, receiving, from the AV, a 3-dimensional (3D) augmented map and localizing an updated position in the delivery environment based on the 3D augmented map and the global reference map. The robot vehicle perception system senses obstacle characteristics, and generates a unified 3D augmented map with robot-sensed obstacle characteristics. The method further includes generating a dynamic path plan to a package delivery destination using the unified 3D augmented map, and actuating the robot vehicle to the package delivery destination according to the dynamic path plan.

Growing community of inventors

Berkley, MI, United States of America

Justin Miller, Jr