NEXYAD ADAS solutions

03 décembre 2016

Special Prize "coup de coeur" (crush) of Insurers for the NEXYAD smartphone driving risk assessment App SafetyNex

Special Prize "coup de coeur" (crush) of Insurers for the NEXYAD smartphone driving risk assessment App SafetyNex

 30th Nov 2016, seven high-tech startups had to pitch in front of almost all French Insurance Companies. This was organized by the Cercle LAB (Laboratoire Assurance Banque), at ALLIANZ tower (Paris La Défense) : “colloque prospective annuel du cercle LAB”.

NEXYAD was introduced to Cercle LAB by the competitiveness cluster FINANCE & INNOVATION.
It was an interesting challenge and the jury had to pick only ONE startup from seven talented ones, to give the special prize “coup de coeur des assureurs”.


France Innovation - Cercle LAB - Nexyad SafetyNex

NEXYAD pitched on SafetyNex : a smartphone App for real time onboard driving risk assessment (with vocal alerts that warn the driver before a potential danger), that can reduce accident rate by 20%.

Winner : NEXYAD !!!

Read more :

30 novembre 2016

Return On Investment (ROI) for a car insurance company using onboard telematics

Return On Investment (ROI) for a car insurance company using onboard telematics

A lot of car insurance companies now start Proofs Of Concepts (POCs) with onboard telematics. The idea is to apply digital new capabilities to find new business models for car insurance.

We present a completely disruptive vision and telematics solution (SafetyNex) that first proposes to increase margin of car insurer, and then second, allows to use UBI (Usage Based Insurance) solutions such as Pays As You Drive and Pay How You Drive.

Read :

29 novembre 2016

NEXYAD ADAS : camera-based obstacle detection

NEXYAD ADAS : camera-based obstacle detection using the NEXYAD module ObstaNex

obstacle detection using ObstaNex


With the NEXYAD module ObstaNex it is possible to detect cars on the road, and measure interdistance and time to collision.

See :

13 novembre 2016

ADAS Morning : presentation of real time onboard risk assessment smartphone App SafetyNex by the CEO of NEXYAD

ADAS Morning : presentation of real time onboard risk assessment smartphone App SafetyNex by the CEO of NEXYAD

The CEO of NEXYAD presented at the ADAS Morning Synposium in Paris (organized by MOVEO) the smartphone App SafetyNex that reduces accident rate by 20% and that records risk profiles for Insurance companies.


This smaprtphone App is relevant both for the driver (real time alert that lets the driver slow down and keep safe in dangerous situations), and the insurance company (that gets a "real" risk assessment : risk assessment method used by SafetyNex has been PROVEN through 15 years of collaborative research).

Read more :


22 octobre 2016

NEXYAD made a presentation at the ADAS Morning in Paris : focus on Road Safety with the smartphone App SafetyNex

NEXYAD made a presentation at the ADAS Morning in Paris :

focus on Road Safety with the smartphone App SafetyNex

ADAS Morning is organized by the MOV'EO Groupement ADAS :
Check :

NEXYAD presented the smartphone App SafetyNex (real time onboard risk assessement), that warns the driver before crossing a
dangererous area (letting time to slow down and avoid accident) : SafetyNex reduces accident rate by 20%.

Screenshot_20161012-122838[1] Screenshot_20161013-170828[1]

And because risk is estimated in real time, it is possible to compute risk profiles, usage profiles, and send them on a cloud for insurance companies.

To read more :



01 octobre 2016

NEXYAD ADAS : ObstaNex new release : obstacle detection module for ADAS and driverless car

NEXYAD ADAS : ObstaNex new release :  obstacle detection module for ADAS and driverless car

Here is the new release (V3.0) of ObstaNex for obstacles detection by camera. Applications are ADAS (Advanced Driver Assistance Systems) and
Driverless Car, but also Road Safety.

ObstaNex V3
Obstacle detection with ObstaNex (by NEXYAD)


read more and watch demo video :


18 septembre 2016





Onboard telematics now can measure behavior of a driver, and therefore, car insurers

have early started this adventure of connected car, more or less successfully.


The simplest applications that have been deployed are:

. locate stolen vehicles

. measure the usage of the driver, and in particular the number of kilometers traveled in order to propose adaptive pricing (vehicle

  that always stays in a garage will never have an accident!)


But the main business of the insurer deals with the concept of risk, and then, we have seen a lot of telematics firms proposing automatic detection

of risky behaviors.

The most common is the so-called detection of "severe braking," which is based on the assumption that severe braking

reveals a lack of anticipation, and thereby a dangerous driving.

We now know that this assumption is totally false [1], but it is still in the mind of some insurers that « want to believe » there is a simple way to
classify human beings behaviours.

However, the lack of results of these deployments has led some German and US insurers to abandon Telematics [2].


The company NEXYAD has demonstrated that it is possible to « measure » in real time the risk of driving, and this stimulus now  keen interest in telematics
among insurers worldwide. This interest was even increased as NEXYAD won the BMW Tech date challenge with their onboard risk assessment App SafetyNex [3]

SafetyNex works where all other systems fail, simply because the problem was treated in a completely new way, without any « science fashion » consideration,
especially about the deep learning (or machine learning).


Indeed, the difficulties of developing  an application of efficient onboard risk estimation are :


. Science and facts : an accident is a rare event and inexplicable (definition :  "happens by chance", a driver has got one accident
  every 70 000 km, on average, most of which are harmless). Observing a driver during 5 years (to make sure an

  accident occured ) is long and ineffective (one accident does little to make individual statistics), and  variability factors of "road life situations" are extremely
  numerous, so it would take millions of drivers during decades before having relevant statistics.


. Ethics : driving behavior in itself has absolutely no direct link with the risk [1] (indeed we conceive  easily that drifting demos on an abandoned airport or just in front
  of a school at noon, corresponds to very different risks although the driving behavior is the same : it obviously needs to be "contextualize"). Contextualization (that is
  not present in the  "severe braking" experiments mentioned before) therefore demand to know, among other things, speed of  the vehicle, and where this speed is practiced.

  But as digital maps have all recoded the maximum authorized speed, then if you record the speed and geolocation in a cloud ... it potentially saves violations of speed limits.
  In many countries, ilcuding France, it is prohibited to record infringement to the law by non accredited organizations (like Insurance Companies). This totally disqualifies

  telematics boxes that record raw data in the cloud !

  However, some European insurers continue to test this kind of solution in the hope (bu in vain) that the "deep learning" and "data scientists" give their risk scores.

  But in any case in France (40 million vehicles market), the violation of the Penal Code is sanctioned and generally pursued by the CNIL [3 bis]. And insurance companies won’t
  have the opportonity to defend themselves saying ‘there is no choice » because SafetyNex estimates risk of driving without recording ANY confidential data !
  And it was shown that SafetyNex delivers every needed data to insurance companies (without any violation of driver’s privacy).


We can see with these two constraints that the solution of " big data statistics in the cloud using machine learning" can not be applied:

. statistics (or deep learning etc): accident is rare soi t won’t work at the individual level

. in the cloud: this is contrary to the laws that protect privacy of people.





The accident is a rare event (1 accident every 70 000 km on average and mostly minor).


This means that one must observe tens of thousands of km to observe ONE accident ... so to observe million accidents

(For statistics, you need millions of data), one must observe a huge number of kilometers traveled ... And in every place (because one area may be dangerous because of the presence of ravines,
another one because many roads intersect, etc’s never the same).


And as the observation of an accident is not enough, we must record all the measurable "variables" or « factors » (speed, acceleration, etc.) that describe

the behavior of the vehicle at the time of the accident (in order to "explain" the accident as say the statisticians).

Of course, nobody has millions of observations of accidents at each location of the infrastructure, then statisticians will just tell you « not enough data ».


What is the impact of unsuffissant volume of data on deep learning [4] ?  Well let’s take an example:

Let’s record for one person during 5 years (the time it taked to get an accident), the day of the week, the time slot, and driving signals (speed, acceleration, braking, ...). The result of this observation

of 5 years (it's long ? isn’t it ? ) will lead on average to 99 999 km without acident and 1 km where an accident occured.
Let’s say it was a Thursday, at 15:00, the vehicle was traveling at 100 km / h, etc.

As the vehicle drove frequently slower and faster than 100 km / h, the influence of the speed in the deep learning will be close to zero. However, the driver has never had an accident on Monday, Tuesday, Wednesday,
Friday, Saturday, Sunday.

Certainly, it has led many Thursday without accidents, but the only day he had an accident was on Thursday: the probability of having an accident on Thursday is therefore greater than that of having an accident the other days.
Here is what data analysis, statistics, or deep learning will conclude ù


Everyone can understand that this conclusion is completely wrong, and that it you observe that same driver for thirty years (the time to get several accidents), then you will see that the day is not a key factor (it can have
an influence if traffic varies with day, but obviously it os possible to have an accident any day of the week!).


As a conclusion let’s keep in mind that It's easy to make global statistics of accident on a large population (France, Europe, USA, ... hundreds of million people). But at the individual level, it is not so easy.

But the goal of onboard telematics is precisely to estimate a risk, at the local and individual level !


We know it seems obvisous when we say that it is not possible to study rare events without prior knowledge using data oriented mathematical methods (because there are few data and because those methods refer to the
« law of large numbers »). But it's better to say it because it is apparently not obvious to everybody (and it sounds always « cool » to tell your boss and your friends that you work on a deep learning application ! ^^).


SafetyNex circumvented this problem by working in a much more rational and finally "classical" way, using knowledge and risk evaluation methods already validated by experts of accident.


Note: To develop the theory of relativity, Albert Einstein did not record hundreds of billions of data to feed a deep learning system that automatically found the law E = mc2.
He used the knowledge of physicians, and inference methods of mathematics that have led to this formula. And then, in order to validate this formula, experimental physicists have performed hundreds of experiments.

It is exactly this approach that has been applied to develop SafetyNex: there are dozens of experts working on road infrastructure "risk diagnoses." NEXYAD worked in contact with these experts for 15 years (through collaborative
research programs PREDIT [5]) and developed SafetyNex which is a "knowledge-based system" [6], validated a posteriori on about 50 million km.

These experts work the same way than industrial risk experts in factories with methods like FMEA [7].


The difficulty of developing a tool like SafetyNex lies not the "technology" (gradual knowledge based system and possibility theory) because hundreds of startups in Silicon Valley (for instance) perfectly know these
techniques, but it resides in the extraction of deep knowledge of dozens of experts (that not always agree with each other, etc.). This extraction was made possible thanks to the collaborative French National Research PREDIT
projects « Arcos » and  « Sari ».

This research showed a key concept in accident: the "near accident" or "quasi accident" [8], a more regular notion than accident (And therefore a notion that can be studied mathematically).

Basically, if you put your feet in the water and strip the electric wires of the light of your ceilling, you are 100% in state of near-accident.
Note that you can do so without being electrocuted. It is the repetition of the act that eventually, randomly, will cause electric shock.


This concept is particularly interesting for the insurer because it measures the RISK THAT THE INDIVIDUAL TAKES, out of luck or bad luck consideration. It is exactly what the insurer needs to know.

And it is completely knowledge based : IF you put your feet in the water AND … THEN you are 100% in near accident case.

You do not need deep learning, you "know": SafetyNex works like this.


The advance of NEXYAD on this subject is so huge because extracting knowledge of dozens of experts in road safety in Europe, gathering experts when they disagree, etc ... is an incompressible duration,
whatever the financial strength of the company who wishes to do it.
SafetyNex applies about 5000 cause effects rules, and is usable WITHOUT DELAY: no observation period or learning period, when the driver dstarts driving with SafetyNex you know the  risk he/she takes iatevery moment.


Among these high-level expert knowledge is included the fact that 75% of accidents are due to inappropriate speed of the car to the danger of infrastructure.

Everything other factors (poor visibility, not compliant interdistances, rain, etc ...) are important, of course, but they explain 25% of the variance of the phenomenon.

When comparing SafetyNex to the work of the entire automotive industry (driver assistance systems with obstacles detection, etc ...) we can see that NEXYAD is the only partner who offers a tool that copes with main
factor of accident . All others are within remaining 25%.





Risk estimation in driving requires having contextualized synchronized data : how the driver drives, and where it takes place.


Now, as we have explained above, the recording of those data is in contravention with driver’s privacy because when you know how fast a vehicle drove
and where, you just have to read the speed limit on a regular electronic map, and then you know every infrinngement. Is it the job of the police, not of
insurance companies.


And note that, on the one hand it is forbidden to record such data in many countries, but on the other hand, it is totally unnecessary to [9] insurer. So it
shouldn’t happen !


SafetyNex bypasses this difficulty by performing all risk computing locally on the smartphone microprocessor, so that no indiscreet  data is recorded on the cloud.

Raw data are indiscreet : they may let easily know if you cross speed limits, but ot also let know who you you visited, when, etc … They are needed to compute a risk.
So the only solution is the SafetyNex solution : raw data are used locally to compute the risk, on the microprocessor of the smarphone, and those raw data are
NOT recorded in the cloud. Only risk statistics are recorded.


This technology differentiation allows SafetyNex to be the ONLY system that respects legal restriction to data recording (like in France for instance) and also the rules

of elementary ethics, and the proper respect for the privacy of drivers (even without law considerations, spying drivers does not match values of ​​NEXYAD).





Note: the time time latency can be guaranteed by NEXYAD because the computings are performed locally. Indeed, an App that would send and read data on the cloud could not guarantee latency
(it would depend on the network connection bandwith, and this is very variable). SafetyNex is then also the ONLY risk assessment App that is a real time application made to help the driver
while driving (it is not only an App for the Insurance Company).


As soon as the driver approaches an infrastructure with a speed showing that he/she did not understand the difficulty of the road, then SafetyNex warns a few seconds before danger in
order to let the driver slow down. It may save sriver’s life !


SafetyNex is not just a data collection tool for the insurer, it is also a useful tool for the driver, likely to save his/her life and at least to avoid causing accidents.


So using SafetyNex is a win win process : valuable for both insurer AND driver !


Read more :


14 septembre 2016

NEXYAD will be on the BMW booth at MONDIAL de L'AUTO (Oct 5th)

News :

NEXYAD will be on the BMW booth at MONDIAL de L'AUTO (Oct 5th): as winner of the BMW tech date challenge organized in June by BMW, NEXYAD wil demonstrate their onboard risk assessment tool SafetyNex on the booth of BMW and will meet their leads and customers in the private BMW lounge.

Feel free to visit.


10 septembre 2016

Deep changes in the business of car insurance. Contribution of smartphone App SafetyNex in this global context.

Deep changes in the business of car insurance. Contribution of smartphone App SafetyNex in this global context.


1 - Role of the insurer

The insurance idea would have appeared on the occasion of the first great journey by boat, and the appearance of "modern" insurance is generally dated from the 19th century. The principle of insurance is easy to understand : if accidents are rare (compared to the number of occurrences - travel, car trips, etc.), a simple and prudent idea then is to "put aside" a certain amount of money for each occurrence (which on average does not lead to an accident) and to use the money to repay the cost of the claim in case (rare) of accident. One could imagine that individuals manage themselves each a "pot" of this type. Of course, even if an accident is rare, you never know when it happens and it may happen at any beginning of the process so that the pot is almost empty. We could then easily make a common pot between several people, to smooth it : if three people make a common pot, it is unlikely that the three have an accident while starting hoarding. But... it is anyway possible. Although if the pot is conceived with hundreds of thousands of people there, you secure the problem of "instant" of the accident. This is the « law of large numbers », which allows a deterministic modeling of chance : the odds. It remains to define the amount of money to set aside each month for example (or each travel). To handle this (a pot shared by hundreds of thousands of contributors, the estimated sum to put aside, etc...), it is obvious that it is necessary to have qualified personnel, sufficient... and finally, it happens naturally to the idea of the Insurance Company. The insurer has hundreds of thousands or even millions of policyholders, and smooth the sinister occurrences thanks to the law of large numbers. He is responsible for ensuring that claims even exceptionally expensive will be refunded. NB: in the case of home insurance, a natural disaster on a large area can resynchronize the claims despite the large number of insured people... the insurance company then would better spread in different territories and / or to associate with other insurance companies operating on other territories to make quite impossible synchronization of claims.  The forecast of the number of potential accidents on territory and over a given period is referred to as the "Risk". In French as a first approximation we see the term "risk" roughly coincides with the idea of « probability ». If a loss is probable, the insurer takes more risk than if the disaster is unlikely. But that's not all : if one has a probability X had an accident but that the loss really cost cheap, it will be considered, always in natural language, that the risk taken by the insurer is less important than if the probability is still X (the same) but with sinister potentially costing much more ! For example, assume that the probability of burglary of an apartment is always the same (neglecting the Protections effect), then it is more risky to insure an apartment featuring original works by Picasso than apartment emblazoned with photo reproductions of works by Picasso. The probability is the same, but when the burglary applicable, the amount refunded is very different. What emerges very intuitively is an entity that is the multiplcation of likelihood by cost of the disaster.

2 - Risk management and calculation method of pricing

2.1 - Customer segmentation and risk statistics by segment

Generally, a numerous population does not lead to a homogeneous risk : someone who lives on top of a rock python have less chance to get 1m of water in his/her house than someone who lives at sea level or in the bed of a river. The insurer's interest is to achieve groups (segments) of people who have homogeneous risk. Please note, as the risk is linked to the idea of probability, it is a value which is estimated by statistics... However, claims(housing, car accidents, plane crashes, etc...) are rare (and thankfully), so the statistics are long to make and complex to interpret as for long periods, many parameters may vary (other parameters than one that interests us). This means that the well-known hypothesis statisticians "all things being equal" is rarely verified. Similarly, groups can not be based on discriminatory or racist sort variables. We saw in France the example of insurance cheaper for women than for men who have been banned. Indeed, in this case, men doing more km that women, on average, it is normal that they have more accidents. All discriminatory interpretations are only belief and fake psychology. Such segmentation may instead be reformulated by charging differently depending on the number of traveled km (which is called "pay as you drive", see following chapters). This remark felt the need to better understand the behavior and usage of policyholders, factually.

2.2 – Pricing : expected value

Once we have achieved a uniform customer segmentation in terms of risk, one must determine the amounts to be paid. The mathematical object used involves multiplying the probability by the loss of cost, and is called "the expected value". The expected value for the insurance is the amount of insurance premiums minus total costs claims multiplied by their probability of occurrence. Obviously, this expected value must be positive (the sum of premiums must be greater than the sum of costs weighted by their probability of occurrence). When the number of insured is very large, the sign of the expectation value is a predictor of the gain his, if the probability and the costs are "well estimated." If the insurer has a bad estimation of accident occurrence probabilities, and / or if the insurer poorly estimated cost of claims when they arrive, then he may realize that the sum of insurance premiums does not cover what to pay. Conversely, if the insurer is too cautious about risk by increasing insurance premiums, then the insured may be tempted to move to competitors. The scope of insurers is fairly narrow practice. Then you can list four very strong concerns of the insurer : . better estimate the probabilities of accidents . estimate at best the cost of claims likely to happen lowering claim probabilities : examples impose the installation of an alarm system, advocating responsible conduct even offer driving courses, warn in real time a driver ahead of a hazardous area (if he/she slows down, it may avoid an accident), etc... . lowering claims costs : examples : impose a degree of reparability of goods (car, ...), help a driver to detect hazardous areas (if he/she slows down, even if the accident occurs, it occurs more slowly, and the cost of claims is statistically less heavy)

3 - Contribution of embedded telematics for car insurance :

measuring factual uses and instant individual risk Technology now allows to integrate in a vehicle telematics device (communicating electronics) that may inform insurer of every events happening to the vehicle. The first telematics applications were built around geolocation, especially to retrieve stolen vehicles and then, by extension, to optimize fleet operations professional. Afterwards, applications have integrated accelerometers (processing of signals from accelerometers) to estimate exhaust of vehicles due to driving style, and next, to estimate fuel consumption (and therefore CO2 and pollutants emissions). The major pure players in the automotive telematics are mostly electronics companies, installation garages, and experts of fleets monitoring (Real-time editing performance parameters of a fleet, in the form of dashboards for the fleet manager). For insurers, vehicle telematics allows to know the usages : number of traveled kilometers, type of use (short trips, long trips, in urban, rural, highways, etc...). This kowledge is used then to develop a new offer of insurance called "pay as you drive". The interest of telematics is that factual and individual aspect can be calculated, if desired, and lead to an ad hoc fee for a driver, instead of assign him the price of the segment which he or she belongs. In practice, insurers still mostly work on segments, as individual fees are complex to communicate (depends on the country) but the segments are more accurate. The accelerometer lets you know if the driver drives in a smooth or brutal manner, and the coupling of the accelerometer with GPS allows to know the actual speeds. This gave the idea to the experts of onboard telematics to tackle the risk estimation / risk assessment (linked to customer driving behavior). But the risk of accident and its assessment is a breakthrough in terms of data processing complexity : it is strictly not possible (unfortunately) to estimate a risk of accident by using, for a given individual, statistics and / or deep learning methods, and unlike anything recount hundreds of contacts that come to appoint experts on the subject. This impossibility is due to theoretical issues, it is then futile to try to circumvent them. Some reasons : . accident is a very rare event (on average, a driver has an accident every 70 000 km): and rare events are not well observed by the use of statistics and deep learning. Of course, one can aggregate data from a large population, over a large duration, and a large territory, and do statistics, but when one try to focus on one individual in a specific location at a specific time, there is not enough data to edit robust and significant statstics. . accident is unexplainable BY DEFINITION (in the dictionary accident "happens by chance"). It takes many factors aligned for the accident to occur (hence its rarity), and even when these factors are present, the accident may not happen, it happens randomly in that rare case where it is possbile. When a factor is not present, the accident does not occur. This means that at the individual level, there is no gradualness or regularity in the data, which makes them absolutely unsuitable for any analysis (including automated methods of deep learning). It is a phenomenon that mathematicians call "parsimonious and random process". The scoring methods are inaplicables. When they seem to work (sometimes one can read that a company have built scores that show "some correlations" with risk) it is simply that one have tested these scores on 4 a small data base. Just test it longer on more data and you will find that the correlations collapse. For these reasons, estimation of individual risk of driving is a real rupture of complexity, which is why telematics experts are currently facing a wall : a lot of tests, no massive deployment (after 2 to 5 years of test). The company NEXYAD has been studying accident for 15 years through French collaborative research programs and is now able to estimate the risk taken by the driver. Those research included working in contact with experts (those who make the roads, those who study one by one serious accidents, psychologists, etc.) : mainly PREDIT national research programs. This work led to the development of the software SafetyNex, available as an App for smartphones, that gives in real time the risk taken by the driver seen as a measure of the possibility level of "near accident" (a key concept for research in road safety). This software SafetyNex, is not based on observation of a database, for the reasons explained above, but on expert knowledge. It has been validated on 50 million km. This means that the insurer have now a tool that provides the histograms (profile) of risk and every contingency tables with usages (km, kind of infrastructure, day/night, etc …). SafetyNex is a major development that can help the insurer to change its business and strategy.

3.1 - Presentation of the application SafetyNex

Read more :

08 septembre 2016

un article sur l'évolution du métier d'assureur automobile grâce au numérique

un article sur l'évolution du métier d'assureur automobile grâce au numérique

La société NEXYAD vient de proposer un article présentant sa vision de l'évolution du métier d'assureur, sous l'influence de la pénétrations du numérique, et en particulier, des objets connectés, des smartphones, des capacités avancées de télématique embarcables à bas coût dans les véhicules.

Cet article :

"Modification profonde du métier de l’assurance auto. Apport de l’App smartphone SafetyNex dans ce contexte global."

est en ligne sur le site :



Posté par NEXYAD à 08:49 - Commentaires [0] - Permalien [#]
Tags : , , , ,

05 septembre 2016

NEXYAD software modules may allow to avoid some accident like auto-pilot TESLA car recently had

NEXYAD software modules may allow to avoid some accident like auto-pilot TESLA car recently had

Passions run around the issue of autonomous vehicles, or semi-autonomous. Recently with a TESLA car there has been a fatal

accident while on autopilot mode. NEXYAD studied traffic safety for twenty years, and we give some elements of reflection on this

type of accident.


Processing circuit, informing auti-pilot systems, control, etc ... from perception, data fusion, decision-making, and automatic control of actuators,

are usually very well designed, and based on high-performance modules. But unfortunately, this is not enough to void the the risk of accidents.

Indeed, for the treatment of this risk, it lacks a parallel circuit (oarallel and independent) called "monitoring" circuit.

To understand this need for a monitoring circuit, one must first understand the level of complexity of a road scene viewed from a camera.


The variability of road scenes is actually much more than what a normal person comes to Imagine. Indeed, a color image, which has eight bits

for each color (then, 24-bit, as there are 3 colors) may encode 224 different color levels per pixel (more than 65,000 different possible values).

HD video has more than 2 million pixels.

This means that the matrix of HD 8-bit color image may encode  more than 65 000 2 000 000 images !

This huge number is simply unimaginable.


This raises the question of the validation process of driver assistance systems (ADAS) based on cameras. It really is impossible to test all possible
cases of road scenes ! Even one or ten million kilometers of testing represents a negligeable part of possible cases !

And please do not think that you can easily reduce this complexity, assuming that road scenes have a "SPECIFIC SHAPE" (the road in front of the car).

You may then be surprised ifever a spider settled in front of the camera lens ... or if the car is behind a truck or bus with an adds poster (and in such a
case, all images are possible, including the image of a straight road in the desert, while the actual road, the one on which the vehicle sets, turns !).


Completeness of validation database is impossible, however, there is a solution to use in such a case. First, build the validation database using
a methodology (NEXYAD has been publishing the « AGENDA » methodology in the field of ADAS validation, see ). And second, use in real time a parallel circuit of « monitoring » that has the role of « closing »

the open world.  In other words, it is necessary that all cases already met in the validation process are used to create  a kind of "confined space" called "known space".

Then, in real time while vehicle is driving, one check if the current case (what is seen NOW by cameras, and other sensors) is INSIDE this « known space »

so that the built-in intelligence to know if the road scene meets cases in which it can react properly, or if the road scene is very different (unknown case).

In the second case, it is obvious that embedded intelligence must take default decisions : slowdown, warns the driver, etc ...


Therefore, in parallel of the construction of the main auto-pilot chain of perception, intelligence and control , it is necessary to build a second circuit for case monitoring.
NEXYAD has been developing three software modules aimed at achieving this kind of monitoring circuit.

Read more :

Posté par NEXYAD à 07:34 - Commentaires [0] - Permalien [#]
Tags : , , , , , ,

01 septembre 2016

Onboard measurement of risk of accident with SafetyNex (real time risk assessment) : Application to prevention & auto insurance

Onboard measurement of risk of accident with SafetyNex (real time risk assessment) : Application to prevention, auto insurance pricing, respecting privacy of driver

2012 car accident blog

 1 – Introduction

Onboard telematics, smart phones, connected devices, are now in use to monitor driver’s behaviour : habits, way of driving, etc ... Many organizations are interested to collect, use and monetize those data, and one of the key questions is about the driver, privacy and choice to share data, and also his interest: What will he/she get in return (new and important) : Is it possible to offer security and safety new features that could save his life? Does it have an economic interest ? Can we guarantee not to record (in the cloud) of personal data to respect privacy? We describe the use case of automotive telematics for insurance companies.

2 – Goal of Insurance Companies with automotive telematics

Embedded telematics in vehicles could revolutionize the business of insurance companies. Indeed, insurers must price their garanty and they must take care of the accident rate for a given driver : . if costs of accidents (for a driver) is more expensive that the price he/she pays, then the insurer loses money on this driver (*) . if the price to be paid is too high, then the driver may quit and find another insurance company. (*) Insurers reduce risk by using the actuarial expectation (sum of paid prices minor sum of riskweighted by associated loss costs), thereby modulating pricestaking into account actuarial expectation (that should be positive) and not only individual risk: actuarial expectation has the effect of neutralizing the randomness of individual risk if portfolio is large enough. The scope for the insurers in terms of pricing is quite narrow. They need to estimate as accurately as possible risks, and associated loss costs, in order to offer consistent prices. Similarly, it would be interesting to act on the driving style of the driver, and thus decrease the loss cost and / or reduce the risk of accidents. In such a case, it would increase margin, or it may allow to lower price and be more competitive. 2 One can imagine many ways to achieve pricing using telematics: . production of more accurate customers segmentation, . « Pay how you drive » . a mix of both approaches. Main useful information is the risk profile of the driver and, for better understanding, usage statistics (number of kilometers, used types of infrastructure - highway road city - hourly statistics, etc. ...). In no case does the actuary need to know precisely where the driver went, how fast he was driving, and at what time. Even the driving style is not important (as we could explain in the previous white paper, see references, severe braking is no help to estimate risk of accident) : Those data are not part of the data needed for insurance companies. Risk is as we said the main needed variable for insurance companies, with statistics of uses, the there is no need to collect confidential data (like timestamped geolocation and speed, for instance). We can say then, that it is normal that insurance companies all look for devices and smartphones to collect data. For the driver, this may allow in particular reduce pricing injustices: . young drivers pay in France three times the average price (in other countries it is much more) because statistically risk profile is very high. Telematics lets the insurer know the individual actual risk of a young driver (and THIS young driver may be an excellent driver even though he/she is young !) . a driver who has three accidents because he/she is a risky driver, or a safe driver who really had bad luck (it happens) are currently seen the same way by insurers. Penalizing the safe unlucky driver is really unfair ! And it doen’t correspond to the probability of accident. Similarly, helping seniors to go on driving their individual car as long as possible is an important social issue in view of the aging of our populations: the individual vehicle is still a social connection tool, and the best suited to ensure the mobility of senior citizens (no stairs to climb, no rush hour, no long walks in the corridors, etc ...), but declining reflexes and bad eye sight can cause road safety problems. A unitary measurement of the risk profile can may lead to rapidly detect any deterioration in driving performance (increased risk), and thereby enable the insurer to propose preventive and corrective effective actions, appropriate and personalized (updated knowledge of road risks, visit the ophthalmologist, etc ...).

3 – Data needed for insurance to build its pricing

As mentioned before, relevant data for insurers are : . risk taken by the driver . kilometers . used types of infrastructure (city, road, motorway) , Dayparts . days of the week . habitual nature or not for a path 3 . geographic area of main use of the vehicle (not trips or places visited by the driver, just the regions to see how some areas are more accident-prone than others). The insurer (unlike other professions such as fleet managers), needs no accurate location data and time stamped (except for anti-theft function or post-theft). Data of interest must be gathered into histograms (aggregate) and contingency tables (aggregate data still there). Aggregation warrants the driver that there is no spying. With those data, it is absolutely not possible to reconstruct the path or know any crimes he committed (it is not known where the driver went, for how long and at what time, or how fast). So one can say that the real need of data for the insurer meets a priori requirements of every national agency for data privacy monitoring (including CNIL in France), and more generally meets the elementary rules of ethics.

4 – Data required to calculate a risk

Contrary to what we sometimes read, the risk of accident can not possibly be inferred from a measurement of the brutality of breaking (with accelerometers). Work on this subject has been published in scientific congresses, and the reader is invited to consult the chapter « 8 - references ». It is too bad, but you will never get a proper risk assessment if you use this so called « severe breaking » - based intuition. Thus, current deployments based on detecting severe braking and other seemingly logical ideas (but false) are they doomed to failure. NB: It is easy to understand that if you drifts and do severe braking on a disused airport runway is not dangerous. If you do the same thing in front of a school, it is extremely dangerous. If you do this on an open road with crossing roads, it is both dangerous for the others and for you. Similarly, if you drive with no severe braking and if you don’t stops at the stop sign … it is extremely dangerous. The context is very important (talking about contextualization of driving behavior). Then, because you must compare driving behaviour to context (infrastructure characteristics, for instance, variables to determine risk are mainly: . vehicle speed (and related data: acceleration, ...) . accurate geolocation (GPS signal) and positioning on a map (whether you are on a disused airport in front of a school, or on an open road with crosses, etc). From these data, it is possible (but not easy) to determine the risk taken by the driver. Only contextualised approaches as indicated above are scientifically credible, others are eliminated directly.

5 – Trick of « recording raw data » in the cloud

It is tempting to record all the raw data (speed, location, acceleration, ...) in the cloud and then build offline, on high capacity servers, "risk scores". This would allow the use of modern methods of deep learning, for example, and would also allow the use of very high memory capacity and computing power. NB: this off-line approach fails to warn the driver that he/she is in danger (because even if the computation in the cloud is fast and real time, data transmissions latency for upload or download is not garantied). It's a shame to estimate risk and not to warn the driver in situ! Recording of raw data in the cloud faces a major problem : from timestamped speed of the car and GPS signal, you can locate the vehicle on a map … that has many points of interest including speed limits ! Therefore, it is extremely easy, from those raw data to detect any speed limit infringement. In France the detention of violations of law by private companies is generally not legal (except special mission given by the Goverment) : it is strictly prohibited by the Penal Code (which is monitored by the CNIL): see "8-references" Art. 226-19 of the Penal Code. In other countries where data privacy protection is not as strict, we believe that the detention of law violation by insurance companies is contrary to the basic ethics. Especially since the insurer does not need this information to compute pricing, as explained above. It is very important to clearly understand this problem: an insurance company that collects raw data including speed and gps, and that records them into a cloud (on computer servers) indirectly owns offenses to the law. In France, for instance, it is likely to be prosecuted, and rightly so, by the CNIL. This solution of « recording raw data in the cloud » to estimate a rik must be avoided: it's tempting, of course, but do not.

There exist a solution to get expected data (risk and usage) without infridging the law, and in full respect of driver's privacy :

Read full paper :

See also :


06 août 2016

NEXYAD developed a scale model of car for R&D on ADAS and Autonomous Vehicle

NEXYAD developed a scale model of car for R&D on ADAS and Autonomous Vehicle


This size model car is a testing platform for NEXYAD software modules for ADAS
and driverless cars :

. RoadNex for road detection
. ObstaNex for obstacle detection
. VisiNex for visibility measurement
. SafetyNex for real time onboard risk assessment

read more :

04 juillet 2016

Télématique automobile pour assureurs et respect des libertés individuelles

Télématique automobile pour assureurs et respect des libertés individuelles

La télématique permet aujourd'hui de considérer les véhicules comme des objets connectés susceptibles de remonter des données utiles. Les assureurs,
en particulier déploient en ce moment des boîtiers et des applications sur smartphones chargés d'estimer le risque pros par le conducteur (risk assessment).

Cet article explique en quoi les applications d'estimation du risque de conduite ne sont pas compatibles avec les calcul basé sur des statistiques dans le cloud. En effet, les données enregistrées pour calculer un risque permettent de reconstituer, une fois confrontées à une carte de navigation, les infractions (de type excès de vitesse). Or, l'enregistrement d'infractions dans des fichiers informatiques, même de manière indirecte, est interdit par le code pénal et poursuivi à juste titre par la CNIL.

Nous présentons ensuite l'application SafetyNex qui permet de calculer le risque pris par le conducteur en localisant tous les calculs dans le microprocesseur du smartphone, évitant ainsi d'enregistrer les données brutes dans le cloud. Cette application fournit toutes les données nécessaires aux assureurs, sans jamais transmettre de données confidentielles (SafetyNex ne permet pas de savoitr où est le conducteur, à quel moment précis, et à quelle vitesse il roule, sachant que ces données très personnelles ne sont d'aucune utilité pour la compagnie d'assurance).

SafetyNex développé par NEXYAD est de ce fait une application disruptive autant par son mode de calcul (le calcul du risque utilise la notion de quasi-accident développée par les experts de la sécurité routière), que par son implantation informatique (calcul en local et non pas sur des serveurs informatique distant, si bien que les données confidentielle et personnelles du conducteur restent dans son propre smartphone sans que l'assureur ou NEXYAD ne puisse y accéder).

Par ailleurs, SafetyNex permet d'alerter le conducteur lorsqu'il s'engage trop vite sur un tronçon d'infrastructure dont il n'a pas perçu le danger. L'alerte intervient en temps réel et en amont du risque, si bien que le conducteur a le temps de ralentir et de faire ainsi baisser son risque. Cet aspect "aide à la conduite" et prévention des accidents est unique.



Lire l'article :

26 juin 2016

NEXYAD June NEWSLETTER issue : SafetyNex for Insurance Companies, BMW Tech Date, News of the ADAS & connected car world

NEXYAD June NEWSLETTER issue : SafetyNex for Insurance Companies, BMW Tech Date, News of the ADAS & connected car world

NEXYAD Newsletter (June Issue) features the NEXYAD module SafetyNex :

. SafetyNex is the only real time onboard risk assessment module that really measures risk of driving
. SafetyNex is already under deployment by Insurance Companies
. SafetyNex warns the driver before a potential danger (then it is an Advanced Driver Assistance System ; ADAS)
. SafetyNex will monitor the driverless car's behaviour : measurement of the risk it takes every second

SafetyNex has been selected by BMW at the BMW Tech Date.

On this newletter issue, NEXYAD also made a diggest of congresses on autonomour cars and car safety, and on
connected car.

Read the newsletter : 

09 juin 2016

NEXYAD at bmwtechdate in Paris

NEXYAD at bmwtechdate in Paris



Read more :

Posté par NEXYAD à 22:45 - Commentaires [1] - Permalien [#]
Tags : , , , , ,

04 juin 2016

NEXYAD speaker and exhibitor at Autonomous Vehicle Test & Development Congress in Stuttgart

NEXYAD speaker and exhibitor at Autonomous Vehicle Test & Development Congress in Stuttgart



The President CEO of NEXYAD made a presentation of the methodology AGENDA for ADAS specification, development, and validation.

This methodology is free (published) and may be use by anyone without NEXYAD : it will also lead to a free database usable worldwide 
through the internet.

To read more :

21 mai 2016



NEXYAD and INTEMPORA are together at this congress on automotive active safety.

The head of INTEMPORA, Nicolas du LAC is also speaker and presents a paper on ADAS validation.

Photo Nicolas DULAC



Read More :

Posté par NEXYAD à 18:55 - Commentaires [0] - Permalien [#]
Tags : , , , ,

15 mai 2016

Newsletter of NEXYAD : connected car the future on the road

Newsletter of NEXYAD : connected car the future on the road

Here is the NEXYAD Newsletter :


Posté par NEXYAD à 05:23 - Commentaires [0] - Permalien [#]
Tags : , , ,