Ford Global Technolgoies, LLC

University of Michigan

John Moore

Sai Srikar Palukuru

Francis Obiagwu

Hafiz Malik

Soodeh Dadras

Eric L Reed

Jonathan Diedrich

James Martin Lawlis

Bradley Warren Smith

Michael Dupuis

Amit Kulkarni

Ziwei Zeng

Jiguo Song

Alan J Michaels

Uttara Thakre

Venkata Narasimha Sai Srikar Palukuru

Alekhya Karavadi

Subhadip Ghosh

Jaerock Kwon

Junho Hong

Aydin Zaboli

Kuchan Park

Sahib Singh

A computer that includes a processor and a memory, the memory including instructions executable by the processor to input an image to a first neural network to generate a first detected object and input the image to a second neural network to generate a reconstructed image which is input to a third neural network to generate a second detected object. The image can be divided into portions and the portions input to respective fourth neural networks to generate portions of a third detected object. The first detected object, the second detected object, the portions of the third detected object, and context data can be input to a partially observable Markov decision process to generate a high confidence detected object.

Machine learning and data classification for operating a device such as a vehicle

A system includes a plurality of electronic control units (ECUs) and a shared high security module (sHSM) separate from and connected to the plurality of ECUs over one or more private networks. At least one of the ECUs, over at least one of the plurality of private networks, authenticates a session with the sHSM and requests servicing during the authenticated session. The servicing includes encryption, decryption, or authentication, of a message designated to be handled by the at least one ECU and included in the request for servicing. The sHSM receives the message, performs the requested servicing of the message using capabilities onboard the sHSM, and publishes a serviced version of the message to a designated controller area network bus.

Shared hardware security module

A plurality of subimages of an image are generated based on output from a random number generator. Each subimage is input to a machine learning program trained to output an object classified in the subimage. When a number of subimages with a same classified object exceeds a threshold, an object in the image is identified as the classified object.

Enhanced object detection

An electronic control unit comprises circuitry to receive a combined signal via a vehicle bus of a vehicle, wherein the combined signal contains a combination of a data signal and a watermark signal, which can be a radio frequency (RF) signal or an analog baseband signal, wherein the data signal includes a message, circuitry to extract a watermark from the watermark signal, circuitry to verify the watermark based on a comparison of the watermark with a pre-defined watermark, circuitry to extract the data signal from the combined signal and obtain the message from the data signal, and circuitry to authenticate the message based on the verification of the watermark.

Vehicle bus message authentication using watermarking

A first connected message broadcast from a first vehicle and a second connected message broadcast from a second vehicle is received, each of the first and second connected messages including proof-of-work computed from connected vehicle data regarding a third vehicle. The first and second connected messages are authenticated, responsive to a comparison of the proof-of-work for the third vehicle included in the first connected message and the proof-of-work for the third vehicle included in the second connected message. The connected vehicle data in the first connected message broadcast or second connected message broadcast is utilized for autonomous vehicle operations or driver-assistance vehicle operations, responsive to the proof-of-work being a match.

Proof-of-work vehicle message authentication

A computing device can be programmed to, upon determining that a location of a vehicle is within a set of boundaries associated with a wireless network and that a user device is authenticated to the network, authorize the user device to control the vehicle. The computing device can be further programmed to, upon determining that the vehicle is not within the boundaries, authorize the user device to control the vehicle based on transmitting an authentication credential to a server and receiving an authorization certificate.

Multimode vehicle proximity security

A computer includes a processor and a memory, the memory storing instructions executable by the processor to collect a digital image that includes a plurality of pixels with a first sensor, input a reference data string, a key data string, and a set of collected data from a second sensor into a permutation generator that outputs a watermark data string, and embed the watermark data string in the digital image at specified pixels in the plurality of pixels.

Enhanced vehicle operation

A vehicle computer includes a watermark memory and a watermark processor programmed to execute instructions stored in the watermark memory. The instructions executed by the watermark processor include receiving an image captured by a camera, selecting a set of random pixel locations, generating a random watermark, and embedding the random watermark into the image at the set of random pixel locations. Another vehicle computer includes a validation memory and a validation processor programmed to execute instructions stored in the validation memory. The instructions executed by the validation processor include receiving a watermarked image, determining a random watermark, detecting an embedded watermark in the received watermarked image by selecting a set of random pixels and analyzing the selected set of random pixels for the random watermark, and authenticating the watermarked image as a result of determining that the watermarked image includes the random watermark at the set of random pixel locations.

Dynamic watermarking of vehicle camera images

A computer includes a processor and a memory, the memory storing instructions executable by the processor to arrange data collected by a plurality of sequentially arranged emitters in a sensor according to a nonsequential numerical order of the emitters, transmit the nonsequential numerical order to a vehicle computer according to a secure protocol, and transmit the data to the vehicle computer.

Vehicle sensor operation

A vehicle-to-vehicle communication system includes a controller programmed to digitally sign each of a plurality of basic safety messages (BSMs) using a private key and broadcast each of the BSMs via the transceiver at respective transmit power levels according to a predetermined power level sequence that is defined by one or more values generated from the private key.

Growing community of inventors

Canton, MI, United States of America

John Moore