NEXYAD Presentation at SIA CESA 5.0

Posted on

The 5th and 6th december, International Conference SIA CESA 5.0 took place in Versailles (just near the Château).
The goal of the organisers is to build a bridge between traditional automotive electronics and the new developments in vehicle electrification and digitalization as well as those from the world of consumer electronics and the Internet of Things.
The event has presented a great opportunity to understand how the automotive business will evolve over the next five years, with a focus on products and services that are likely to transition from other markets into use-cases for automotive.

Gérard Yahiaoui, Nexyad CEO presented a new paper: Real Time Driving Risk Assessment for Onboard Accident Prevention :
Application to Vocal Driving Risk Assistant, ADAS, and Autonomous Driving.

Nexyad Conference at SIA CESA
Gérard Yahiaoui on the left

To read more

COMPARE YOUR AUTONOMOUS DRIVING SYSTEM TO BEST HUMAN DRIVERS IN TERMS OF DRIVING RISK TAKEN AT EVERY MOMENT

Posted on

You want to measure the efficiency of your autonomous Driving system in terms of road safety ? Not easy with the regular validation methods : observing the number of km without accident is NOT the key. Indeed, accident is very rare for human driver anyway : on OCDE countries, 1 accident every 70 000 or 100 000 km (depending on the country), and on average 3 death every billion km !
We bring a way to build a metric between YOUR system and better human drivers … using our real time Driving risk assessment module SafetyNex.
A new solution for you to imagine validation process.

Human Vs Robot

Autonomous Vehicle Test & Development : second day

Posted on

Wenesday 1st of June : Presentation this morning by Gérard YAHIAOUI President & CEO of NEXYAD, France

“BUILDING A RELEVANT VALIDATION DATABASE FOR CAMERA-BASED ADAS”
Validation of camera-based artificial vision systems applied on open world is a very complex issue. An HD colour camera may generate more than 65 000 power 2 000 000 different images (information theory), so it is not possible to test every possible message. We propose a deterministic approach for building a validation database using the AGENDA methodology that was developed and published in the 1990s for neural network database (learn & test) design.

A large audience attended to this conference that questions the way for Autonomous Vehicle ADAS validation.

Conference Stuttgart 2016
Gérard on the left, the conference’s audience on the top and the booth of Groupement ADAS from the mezzanine.

Gérard Yahiaoui, Nexyad CEO speaker at
Autonomous Vehicle – Test & Development Symposium 2016

Posted on

STUTTGART 31 may – 2 june 2016

Test and Validation Strategies for Autonomous Vehicles Room B

june 1st – 09:30 – Building a relevant validation database for camera-based ADAS

Validation of camera-based artificial vision systems applied on open world is a very complex issue. An HD colour camera may generate more than 65 000 power 2 000 000 different images (information theory), so it is not possible to test every possible message. We propose a deterministic approach for building a validation database using the AGENDA methodology that was developed and published in the 1990s for neural network database (learn and test) design.

ROBUSTNESS OF NEXYAD SOFTWARE MODULE
FOR ROAD DETECTION : RoadNex

Posted on

ROBUSTNESS OF NEXYAD SOFTWARE MODULE FOR ROAD DETECTION : RoadNex

By NEXYAD

Detection of the road, detection of the lane, in front of the vehicle is now a « must-have »
for Advanced Driver Assistance Systems (ADAS) and of course for Autonomous Cars too.
Every R&D team is able to show cases of good detection. The difference between different
modules is robustness : ability to work in many cases (almost every cases).

For instance, robustness consideration led many big Automotive firms to interger the MOBILEYE
detection system : jus because MOBILEYE is more robust than detection systems developed by
those big firms. And robustness is not a matter of deployment : you won’t get a more robust
module is you put 10 000 developers on the project. You need time, big amount of data, and
« smart ideas ».

Note : This robustness definition leads to question on ADAS validation (« almost » every case is
not that well defined … how could we put some maths on those words). NEXYAD has been
developing an applied maths-based methodology for ADAS validation and is currently
recording a validation data base that will be soon available for free worldwide on the internet.

But let’s go back to road detection modules comparison.

There is another difference between road detection systems : do they need white markings
or are they able to work even without markings ?

NEXYAD founders has been working on road detection since the beginning of the 90’s and never
stopped (*). The NEXYAD team is one of the moste experienced team in the world about road detection.
That actually makes the difference, and RoadNex is a module that would take long to develop by
other teams. RoadNex is currently available on PC (windows, Linux) in the real time framework
RT-MAPS. RoadNex will be soon available :
. on electronic device of an Automotive Tier One Company
. on smartphones (so it works in real time on a smartphone usual processor ! try to compare to other modules)
(*) publication at a scientific congress in France in 1993 :
“Texture-based Image Segmentation for Road Recognition with Neural Networks”, G. Yahiaoui, M. de Saint Blancard,
Sixth international conference on neural networks and their industrial & cognitive applications NeuroNîmes93, EC2,
Nîmes, 1993,

In order to have an idea of what robustness means, here are some case used to test RoadNex :
RoadNex01
RoadNex02
https://i2.wp.com/nexyad.net/Automotive-Transportation/wp-content/uploads/2015/11/RoadNex03.jpg?w=1170
RoadNex04
RoadNex05
RoadNex06
RoadNex08
RoadNex07
RoadNex09
RoadNex10

How many kilometers should you drive to sample those few road scenes variations ?

For more information : https://nexyad.net/Automotive-Transportation/?page_id=412