Monthly Archive: April 2016

Apr
25

Nexyad at Active Safety Europe 2016 : ADAS to Autonomous

Actice Safety Europe 2016

Come to visit Nexyad the 17th & 18th may in Munich, Germany, for the Congress & Exhibition Active Safety Europe 2016 : ADAS to Autonomous.
Nexyad will be present with Intempora firm, provider of famous real time framework RT-Maps, Don’t miss the 18th : Software “Embeddibility”, Speaker Nicolas Dulac, CEO, Intempora.
Nexyad and Intempora are members of french cluster Groupement ADAS sponsored by MOVEO.

Apr
22

Nexyad searcher Dr Grégoire Julien will make a presentation
at 20th International AMAA 2016

The abstract of Dr Grégoire Julien “Functional safety: on-board computing of risk of accident” has been accepted for the 20th International Forum on Advanced Microsystems for Automotive Applications (AMAA 2016) on September 22-23 at Brussel, Belgium, as an oral presentation as well as for publication in the AMAA conference book.

Greg Julien
Dr Grégoire Julien


Functional safety: on-board computing of risk of accident

Dr. Grégoire Julien, Pierre Da Silva Dias, Gérard Yahiaoui
Nexyad S.A.
95 Rue Pereire, F-78100 Saint-Germain-en-Laye

Safety estimation is of utmost importance for in the perspective of fully automated vehicles. In particular, recent progress on accident estimation measurement made by insurance companies have revealed that correlation-based considerations do not give satisfaction. Indeed, there is no correlation between accident data bases and data collected by accelerometers such as the so-called “severe braking” that was supposed to estimate anticipation of the driver and ten “risk of accident”. Indeed, statistical correlation cannot explain causality relationship. More recently, it has been demonstrated [1] that accidents are rare events being the consequence of the repetition of “near-misses” accidents: the larger the number of detected “near-misses” accidents, the higher the probability to generate an accident. It has also been shown that it exists causality relationships which fully explain “near-misses” accidents [2].

Based upon results discussed above, we propose a new solution, SafetyNex, taking into account the dynamics of the vehicle and inputs of different nature (visibility, grip, shape of the road, …) to estimate the risk: a dimensionless quantity r∈{0;1} is output: if r=0, the risk does not exist, if r=1, the risk is high and a “near miss” accident is detected. Hence, this solution, based on deep knowledge of causality relationships, can be used for making data-based services richer, for a more relevant estimation of safety level and a better accident anticipation. SafetyNex is then a knowledge-based system using “possibility theory” [3] and its implementation into fuzzy sets theory [4]. With more than 5 000 rules of causality, SafetyNex is the only onboard module that computes a risk that has a meaning for insurers and car manufacturers. SafetyNex has been validated by experts of accidents of French Road Safety Administration [5].

In the perspective of fully automated vehicles, the detection of “near misses” accident can act directly on the decision process for the vehicle control. Furthermore, a “risk profile” as a function of the distance forward the vehicle can be obtained with our solution. It is thus possible to fully anticipate the risk in the future considering the current behavior of the vehicle. However, the main limitation of such an approach lies in the map resolution. Finally, as a further extension of our solution, the risk estimation could be improved by adding camera in order to merge signals obtained from the road/obstacles detection in front of the vehicle with the map matching.

References

[1] Final document of the SARI program by the French research institut IFSTTAR http://sari.ifsttar.fr

[2] Final document of the SARI program by the French research institut CEREMA http://normandie-centre.cerema.fr
[3] « Théorie des possibilités », D. Dubois, H. Prade ; 2006, REE, 8, 42
[4] « Fuzzy Sets as a Basis For Theory of Possibility », A. Zadeh ; 1978, Fuzzy Sets and Systems, 1, 3-28
[5] « Evaluation du risque de sortie de route pour l’aide à la conduite ou le diagnostic d’infrastructure », J. Brunet, P. Da Silva Dias, G. Yahiaoui, Session « caractérisation du risque routier », conférence PRAC 2010, 3-4 Mai 2010.


Apr
20

RENAULT R-Link system allows SMEs to develop car applications

Renault R-Link : TomTom HD Traffic and Coyote Series

R-Link has TomTom navigation including IQ Routes technology. This calculates the ideal itinerary based on a statistical analysis of journey times during the six previous months, taking the day of the week and time of day into account.

It has LIVE services including:
•HD Traffic: the market’s best traffic information service, including an analysis of traffic flow by cross-referencing different sources of information for sections of road of just a few dozen metres in length. For any given itinerary, HD Traffic will optimise the motorist’s journey in order to avoid time loss or save fuel. It also provides precise information about the estimated arrival time as soon as the motorist sets off.
•TomTom Places: an online search facility in real time to locate a variety of features and services.
•5-day weather forecasts.
•Hazard warnings: depending on local legislation.

R-Link also has the Coyote Series (depending on market) driver aid application. This indicates hazardous zones thanks to real-time input from other users. Such zones may or may not include fixed speed checks. Coyote Series also warns of traffic incidents (accidents, items on the road, etc.) to improve everyday road safety by enabling the driver to anticipate the presence of slower-moving vehicles.

Renault R-Link Store
Renault’s aim is to make this a benchmark catalogue for automotive applications.

The strength of Renault R-Link lies in the fact that it proposes a store of applications designed for automotive use, without the functional or ergonomic- related shortcomings inherent in smartphones. R-Link Store is the first automotive application store for in-car use. The launches of New Clio and ZOE will coincide with the availability of an Introductory Pack of four pre-installed applications to enable owners to familiarise themselves with the connectivity made possible by R-Link. The free, pre-installed apps will be: e-mail, Weather, Renault Assistance and Renault R-Link Tweet, plus the LIVE services associated with the TomTom and Coyote Series functions (depending on market). The system is fully independent and there is no need to use a phone to access the available services and applications.

Instead, it is possible to consult or download a variety of services directly from the car or from a personal computer (via ‘My Renault’ where available). There are currently some 20 applications available via R-Link Store, and this choice is poised to expand very quickly as the system is extended to other vehicles of the range.

To read more : http://myrenaultzoe.com/index.php/zoe-description/r-link-multimedia-system/r-link-applications-and-app-store/

Apr
18

Many Thanks to all Nexyad booth visitors at Connected Car Insurance

Connected Car Insurance
You have been numerous to visit Nexyad Booth at Connected Car Insurance, London last week.
Our disruptive product SafetyNex benefited a lot of interest !
SafetyNex measures Risk of Accident and decreases Loss Costs. This software is available as a smartphone App and as a device.
More information about the ultimate solution for insurance companies that need onboard risk assessment : SafetyNex Position Paper
Version française

Apr
13

Speech at Connected Car Insurance, London

GY-Prez
Gérard Yahiaoui explains SafetyNex to a large audience.

Apr
12

Nexyad & Intempora at Connected Car Insurance Europe

CCI London
Philippe from Intempora and Gérard from Nexyad

The salesforce for Nexyad SafetyNex at Connected Car Insurance, London Hilton Tower Bridge, currently and till wesnesday 13th april.

Apr
11

Robustness of Road Detection by RoadNex v3.2

Nexyad compiled ten technology demos of our module software RoadNex v2.3

. 10 different roads : highway, desert track, country road, red road, et.
. 10 different conditions : fog, rain, front sunshine, overtaking, etc.
. 10 same excellent results : road on front of vehicle is detected

The 10 complete demos on “PRODUCTS” menu above

Apr
07

Nexyad at Connected Car Insurance Europe 2016

Connected Car Insurance Floorplan

Come to visit us on booth 17 and don’t miss Nexyad SafetyNex Presentation :

Wes 13th – Track 3 : Technology & Innovation
3PM : Onboard road safety assessment for insurance companies (pay how you drive) and for car manufacturers (driverless car) SafetyNex
Insurance Companies :
Move from pricing group by group (segmentation) to pricing driver by driver Then statistics of accident cannot be relevant (accidents are rare and one cannot wait for accident to modify the pricing for a driver). One need to predict … to estimate if the driver takes risks or not. And it would be great to have it in real time because it may be used to warm the driver before he/she gets in a dangerous case.
Car Manufacturers :
Measure the risk taken by the driverless function. Needed to control the driverless function, needed to know when to give back control to the driver, needed in case of accident for responsability study.

Apr
05

Nexyad RoadNex v2.3 – Road Detection for ADAS : Highway Dark Night

Nexyad RoadNex v2.3 – Road Detection for ADAS, Autonomous Vehicle & Connected Car on Highway by Dark Night.


RoadNex detects the lane and the road surface and does not depend on the level of equipment of road infrastructure. Here, low light and poor contrast don’t prevent detection.

Apr
04

Reminder : SafetyNex Presentation at Connected Car Insurance Europe

Connected Car Insurance

Connected Car Insurance Europe 2016
Tuesday 12th & Wesnesday 13th April – Hilton Tower Bridge London

Wes 13th – Track 3 : Technology & Innovation
3PM : Onboard road safety assessment for insurance companies (pay how you drive) and for car manufacturers (driverless car) SafetyNex
Insurance Companies :
Move from pricing group by group (segmentation) to pricing driver by driver Then statistics of accident cannot be relevant (accidents are rare and one cannot wait for accident to modify the pricing for a driver). One need to predict … to estimate if the driver takes risks or not. And it would be great to have it in real time because it may be used to warm the driver before he/she gets in a dangerous case.
Car Manufacturers :
Measure the risk taken by the driverless function. Needed to control the driverless function, needed to know when to give back control to the driver, needed in case of accident for responsability study.

Older posts «