Member Info for johnchucka

Or this below perhaps related to SEE PHD job posted today.
SYSTEMS AND METHODS FOR GAZE TRACKING FROM ARBITRARY VIEWPOINTS
A system for determining the gaze direction of a subject includes a camera, a computing device and a machine-readable instruction set. The camera is positioned in an environment to capture image data of head of a subject. The computing device is communicatively coupled to the camera and the computing device includes a processor and a non-transitory computer-readable memory. The machine-readable instruction set is stored in the non-transitory computer-readable memory and causes the computing device to: receive image data from the camera, analyze the image data using a convolutional neural network trained on an image dataset comprising images of a head of a subject captured from viewpoints distributed around up to 360-degrees of head yaw, and predict a gaze direction vector of the subject based upon a combination of head appearance and eye appearance image data from the image dataset.
https://worldwide.espacenet.com/publicationDetails/biblio?II=10&ND=3&adjacent=true&locale=en_EP&FT=D&date=20190516&CC=US&NR=2019147607A1&KC=A1#

METHODS AND APPARATUS TO ADJUST AUTONOMOUS VEHICLE DRIVING SOFTWARE USING MACHINE PROGRAMMING
Methods, apparatus, systems and articles of manufacture are disclosed that adjust autonomous vehicle driving software using machine programming. An example apparatus for adjusting autonomous driving software of a vehicle includes an input analyzer to determine a software adjustment based on an obtained driving input and a priority determiner to determine a priority level of the software adjustment. The apparatus further includes a program adjuster to, when the priority level is above a threshold, identify a parameter of the autonomous driving software of the vehicle associated with the software adjustment and adjust the parameter based on the software adjustment, the adjustment to the parameter to change driving characteristics of the vehicle.
https://worldwide.espacenet.com/publicationDetails/biblio?II=135&ND=3&adjacent=true&locale=en_EP&FT=D&date=20191024&CC=US&NR=2019324458A1&KC=A1#

REAL AND VIRTUAL COLLISION-FREE MOVEMENT OF AUTONOMOUS VEHICLES IN MIXED-REALITY ENVIRONMENTS
A mechanism is described for facilitating real and virtual collision-free movement of autonomous vehicles in mixed-reality environments. An apparatus of embodiments, as described herein, includes one or more processors including reception and selection logic to receive real environment data of a physical location associated with an application, and combined environment logic to combine the real environment data with virtual environment data associated with the application to generate a merged environment. The apparatus may further include navigation guidance logic to generate navigation guidance based on the merged environment, and communication/compatibility logic to transmit the navigation guidance to an autonomous vehicle to perform collision-free navigation within the merged environment.
https://worldwide.espacenet.com/publicationDetails/biblio?II=119&ND=3&adjacent=true&locale=en_EP&FT=D&date=20191024&CC=US&NR=2019325763A1&KC=A1#

A GM patent involving NEURAL NETWORK 2019-10-31 based learning closely followed by SEE 2019-11-4 looking to recruit a PHD student where 'The goal of the project is to implement a state-of-the-art CNN-based fully-automatic face and eye-tracking system'.

SYSTEMS AND METHODS FOR AUTONOMOUS DRIVING USING NEURAL NETWORK-BASED DRIVER LEARNING ON TOKENIZED SENSOR INPUTS
In various embodiments, methods, systems, and autonomous vehicles are provided. In one exemplary embodiment, a method is provided that includes obtaining first sensor inputs pertaining to one or more actors in proximity to an autonomous vehicle; obtaining second sensor inputs pertaining to operation of the autonomous vehicle; obtaining, via a processor, first neural network outputs via a first neural network, using the first sensor inputs; and obtaining, via the processor, second neural network outputs via a second neural network, using the first network outputs and the second sensor inputs, the second neural network outputs providing one or more recommended actions for controlling the autonomous vehicle.
https://worldwide.espacenet.com/publicationDetails/biblio?CC=US&NR=2019332109A1&KC=A1&FT=D&ND=3&date=20191031&DB=&locale=en_EP#

Semicast Research@semicast_res
What if the human factors & behavioral psychology research reveals that the optimum “user experience” comes from having a human driver, rather than being driven by a machine with all the charm of a Borg? Maybe you need to be a Brit to see the irony here.
https://consent.yahoo.com/collectConsent?brandType=nonEu&.done=https%3A%2F%2Ftechcrunch.com%2F2019%2F11%2F01%2Fwaymos-ux-challenge-getting-people-to-enjoy-the-ride%2F%3Fguccounter%3D1%26guce_referrer_us%3DaHR0cHM6Ly90LmNvL2VFdjAyUG5hV2Y%26guce_referrer_cs%3DeGc40ttelwKfG5i9OauUuA&sessionId=3_cc-session_1f7af48b-7d07-4ef8-8043-6f7f04edddb3&lang=&inline=false
https://twitter.com/semicast_res/status/1191331713508683776

ConvolutionalNeuralNetworksforEyeTrackingAlgorithm
2.3.CNNs Convolutional Neural Networks, or CNNs, are a type of neural network that have different convolution allayers used to train and build hidden levels of neurons that connect the input with output classes for classi?cation. These neurons activate depending on the input stimuli. CNNs are very popular machine learning tools for image analysis. They are
useful models with large learning capacity and are able to handle the complexity of tasks involving problems that are too large to be fully speci?ed in any data set [8]. Using CNNs for eye tracking is a newer algorithm that is now being researched [10]. Because of how little has been done in this area, our project focuses on this eye tracking algorithm in order to add knowledge to the development of CNNs for eye tracking.

http://stanford.edu/class/ee267/Spring2018/report_griffin_ramirez.pdf

Deep Learning PhD Internship
Role Description
Seeing Machines has over 15 years of research and development, commercial application and proven expertise in intelligent face and eye tracking technology that enable machines to see, understand and assist people. Our core IP brings to life a range of technology applications that make vehicles smarter, with the intelligence to protect, enable and respond. Our highly skilled team of Algorithm Scientists help evolve our research from an idea to a fully implemented and working commercial product or solution. We are looking for a PhD-level intern to work with our Algorithm Scientists on the cutting edge of driver monitoring technology challenges.
About the opportunity
We are seeking a highly motivated intern to work on deep learning. The goal of the project is to implement a state-of-the-art CNN-based fully-automatic face and eye-tracking system.
This a paid internship for a period of 3-6 months (longer the better) and the start-date is flexible, although we are looking for someone to commence soon.
Through this internship, you will gain valuable research skills, have access to our state-of-the-art datasets and algorithm scientists, and have an opportunity to potentially design an algorithm that will be used inside the cars of the future!
About you
This is a great opportunity for someone with a solid background in computer vision and deep learning. You are expected to be proficient in python and in using a deep learning library such as Tensorflow or PyTorch. Proficiency in C++ is desirable but not a requirement. A successful candidate is expected to have demonstrable ability to conduct independent research, for example, via publications in the top computer vision and machine learning conferences.
If you are a machine learning or computer vision PhD student looking for a new challenge or to take a break from your PhD to gain some practical commercial experience with an industry leader then apply now. You'll work on difficult problems, with massive real-world datasets, to develop algorithms that will be used in the cars of the future. We need the most curious minds to help us create solutions to real-world problems.
https://seeingmachines.springboard.com.au/jobtools/jncustomsearch.searchResults?in_organid=18900&in_jobDate=All

Also If we are working with Toyota and closely with Simon Stent of TRI here is a video he was involved in making.
Gaze360: Physically Unconstrained Gaze Estimation in the Wild
https://www.youtube.com/watch?v=w_tkaqfqlsM

Eye tracking mentions in Mobileye Patent
MOBILEYE VISION TECHNOLOGIES LTD 2019-10-03
SYSTEMS AND METHODS FOR NAVIGATING A VEHICLE
[0103] The memory units 140, 150 may include a database, or data organized in any other form, that indication a location of known landmarks. Sensory information (such as images, radar signal, depth information from lidar or stereo processing of two or more images) of the environment may be processed together with position information, such as a GPS coordinate, vehicle's ego motion, etc. to determine a current location of the vehicle relative to the known landmarks, and refine the vehicle location. Certain aspects of this technology are included in a localization technology known as REM™, which is being marketed by the assignee of the present application.

[0104] User interface 170 may include any device suitable for providing information to or for receiving inputs from one or more users of system 100. In some embodiments, user interface 170 may include user input devices, including, for example, a touchscreen, microphone, keyboard, pointer devices, track wheels, cameras, knobs, buttons, etc. With such input devices, a user may be able to provide information inputs or commands to system 100 by typing instructions or information, providing voice commands, selecting menu options on a screen using buttons, pointers, or eye-tracking capabilities, or through any other suitable techniques for communicating information to system 100.

[0105] User interface 170 may be equipped with one or more processing devices configured to provide and receive information to or from a user and process that information for use by, for example, applications processor 180. In some embodiments, such processing devices may execute instructions for recognizing and tracking eye movements, receiving and interpreting voice commands, recognizing and interpreting touches and/or gestures made on a touchscreen, responding to keyboard entries or menu selections, etc. In some embodiments, user interface 170 may include a display, speaker, tactile device, and/or any other devices for providing output information to a user.
https://worldwide.espacenet.com/publicationDetails/description?CC=US&NR=2019299984A1&KC=A1&FT=D&ND=3&date=20191003&DB=&locale=en_EP#

Thanks TLS,
What are your thoughts on Gill Pratt's 'Guardian for all' statement. I'm intrigued by what it actually means in practice and who will take it up.

Jazz, I think taken on it's own it could well be about building from the baseline technology but when I pull together the patents and some of the statements Gill Pratt makes, below, I wonder if these companies are collaborating to create the 'baseline'.
The other question I have is about Gill Pratts 'offering Guardian to the industry' remarks. Why with every company racing towards L2+ or L3 would they want Guardian as they would surely have spent years creating their own version. So again why would Toyota state this as a commercial objective.
My own answer is that their is far more collaboration than we are aware of around the core baseline technology and the AVCC announcement was possibly our first sighting of it's existence.
I'm likely way of track with this so happy to be shot down on all of these assumption.

Gill Pratt announces Guardian offered to the industry. @15min
https://www.youtube.com/watch?v=T4S5gHUB7_Y

'We are combining global expertise to build and deploy a cloud infrastructure and we are leveraging best practice in software, AI and cloud technology'. @1min
What does that mean?
https://www.youtube.com/watch?v=YSlg2h84ESM

APPARATUS AND METHOD FOR AUTONOMOUS DRIVING 2019-10-31
An apparatus for autonomous driving includes data collecting devices and processing circuitry. The data collecting devices collects initial data including first data related to a driving condition that includes a driving environment surrounding a vehicle and motion of the vehicle and second data related to driving the vehicle under the driving condition. The processing circuitry determines, based on the initial data, the driving environment and a vehicle driving mode including a first type of driving environment and a respective autonomous driving mode and an off-road driving environment and a respective non-autonomous driving mode. The data collecting devices collect additional data including first data related to the driving condition and second data related to driving the vehicle under the driving condition when the vehicle driving mode is the non-autonomous driving mode, and trains the vehicle to implement autonomous driving under the off-road driving environment based on the additional data.
https://worldwide.espacenet.com/publicationDetails/biblio?II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20191031&CC=US&NR=2019332111A1&KC=A1#

Time I spend trawling through the GM global Tech and Toyota TRI patents which pertain to the soft wear development of sensor alignment/ fusion within the car and objects outside the car together with the vehicle to vehicle communication systems, the more I'm persuaded that GM and Toyota and probably others work in this field is probably complimentary rather than Competitive.
That maybe obvious to those with a greater understanding of this technology. What I think I see is closely aligned technical steps and functions between these companies. The close dates at which the patents are being published also suggests to me a deeper technological partnership that predates by years the public announcement of the AVCC.

Recogni . AVCC candidates ?
AI Startup Recogni Announces $25M in First Funding Round Led by Toyota and BMW
https://www.autofutures.tv/2019/08/01/ai-startup-recogni-announces-25m-in-first-funding-round-led-by-toyota-and-bmw/
https://www.recogni.com/media-coverage

Daisy Chain;
SEE/ GM/Joyson/Osram/ Continental / Recogni

OSRAM invests in Autonomous Driving AI Start-up Recogni
https://www.osram-group.com/en/media/press-releases/pr-2019/01-08-2019

RECOGNI INC patents.
https://worldwide.espacenet.com/searchResults?ST=singleline&locale=en_EP&submitted=true&DB=&query=Recogni+
THREE-DIMENSIONAL ENVIRONMENT MODELING BASED ON A MULTI-CAMERA CONVOLVER SYSTEM
https://worldwide.espacenet.com/publicationDetails/biblio?II=0&ND=3&adjacent=true&locale=en_EP&FT=D&date=20190919&CC=US&NR=2019287297A1&KC=A1#
https://patents.justia.com/patent/20190287297

Apologies if posted previously .
Osram / Continental JV details and Driver Fatigue Patent 2019-02-14
OSRAM CONTINENTAL JOINT VENTURE COMMENCES OPERATIONS
http://www.osram-continental.com/en/news-trends/joint-venture-osram-continental-commences-operations.html

Method for operating a control device of a motor vehicle in order to determine a property of an object in an image sequence, and control device and motor vehicle.
http://translationportal.epo.org/emtp/translate/?ACTION=description-retrieval&COUNTRY=DE&ENGINE=google&FORMAT=docdb&KIND=A1&LOCALE=en_EP&NUMBER=102017118363&OPS=ops.epo.org/3.2&SRCLANG=de&TRGLANG=en

Paul McGlone
Chief Executive Officer
Any of my Australian network connections that are interested in reducing fatigue and distraction risk and the potential catastrophic consequences that follow, get in touch and I'll explain the benefits of our relationship with NTI. Similar programs coming to additional geographies soon.
https://www.linkedin.com/posts/paulamcglone_safety-bethebenchmark-activity-6595140924836327425-XfvF

Human factors related research. M Lenne / J Kuo .
Continuous monitoring of visual distraction and drowsiness in shift-workers during naturalistic driving
https://www.scopus.com/record/display.uri?eid=2-s2.0-85057020642&origin=inward&txGid=5bc4a4225a84d82ecdd2fef4d9c01e3c

Automated recognition of rear seat occupants' head position using Kinect™ 3D point cloudhttps://www.sciencedirect.com/science/article/pii/S0022437517300816

Research Scientist (Data) - Human Factors | Canberra, ACT
Role Description
The Human Factors (HF) group at Seeing Machines collaborates with customers and research partners worldwide to generate new insights that drive our technology development and validation. Our small and dynamic team is fast becoming an authority for regulation and policy in this space – leading the industry with best practice Human Factors research & development.
About the opportunity
This is a genuine career opportunity in which you will directly influence product development with our global customers - and be part of the Seeing Machines journey as we help shape the future of automotive and aviation technology.
As a Research Scientist (Data) - Human Factors, you will lead the analysis of human factors datasets and associated metrics that can be used to improve the sensing of operator state. Working with a small and dynamic applied research team, you will advise senior business leaders and play a key role in designing and executing research programs that will define and develop our future technology platform.
This will involve:
Applying human factors and analytical methods to design and statistically analyse complex datasets that foster greater understanding of and improvements in Seeing Machine's state-sensing performance.
Managing large and complex datasets, and data that is collected across a wide variety of settings
Contributing to the writing of technical reports and publications related to the analyses of Seeing Machine's human factors datasets.
Preparing peer-reviewed publications and conference papers and presenting research outcomes to internal and external customers, industry groups and conferences.
Undertaking other research-related tasks including preparation of any research documents or applications (e.g., project briefs, ethics forms, participant explanatory statements).
https://seeingmachines.springboard.com.au/jobtools/jncustomsearch.searchResults?in_organid=18900&in_jobDate=All

Looks like another close relative of the AVCC which may include Caterpillar;
https://www.autosar.org/
https://www.linkedin.com/in/sai-prakash-reddy-gaddam-6541a375/?miniProfileUrn=urn%3Ali%3Afs_miniProfile%3AACoAAA_eHeAB5mNxtc6wZPeChun1H4iCI7WEOB4

http://teamsterscanada.org/en/blog/2019/10/04/fatigue-an-issue-with-adverse-effects-on-many-workers-lives/
https://www.cbc.ca/news/politics/truck-bus-driver-fatigue-road-safety-1.5173516
https://www.canada.ca/en/transport-canada/news/2018/12/minister-of-transport-moves-to-improve-fatigue-management-for-railway-employees.html
https://www.railwayage.com/safety/risk-reduction-fatigue-management-whats-the-holdup/
http://mari-techconference.ca/wp-content/uploads/2019/05/Dittmann_Eyes_Wide_Shut_Fatigue__Marine_Industry.pdf
https://ipolitics.ca/2018/10/29/employee-fatigue-worries-transportation-safety-board/
https://electricautonomy.ca/2019/10/25/toronto-plan-sets-goal-to-be-autonomous-vehicle-ready-by-2022/