SafetyNex is a thermometer of risk in driving (riskmeter)! Risk is computed in real time inside the onboard device.

SafetyNex is a « XAI » (see DARPA research program on Artificial Intelligence).

SafetyNex computes 20 times per second the risk that the driver takes. The « driver » may be a human being or an Artificial Intelligence. Then when the risk exceeds a maximum accepted risk value, it is possible to alert the human driver or the Artificial Intelligence (if the car is robotized), letting time to slow down and avoid a potential emergency situation.

SafetyNex can be also used to record risk and usage DATA that are fully GDPR compatible.

SafetyNex also gives :
. self-confidence of driver (or driving system)
. driving skills
. lacks of anticipation in driving


SafetyNex % board

Go to Global presentation of applications for motor INSURANCE

Driving risk is the risk taken by the driver at every moment during driving task.
Driver maybe a human being or the artificial intelligence (autonomous driving)



Let’s say in a manufacture there is a very dangerous machine that may grind up your hand. If you are 10 km away from the machine, risk is “very” low. If you are 1 km away from the machine, risk is the same. If you are 10 m away from the machine … risk is still very low … but if you come closer (let’s say 10 cm), suddenly risk becomes high ! This is not linear. In road safety, the Artificial Intelligence algorithm SafetyNex estimates 20 times per second the driving risk you take, and many people ask about relationship between “risk you take” and “accident”. This relationship is not deterministic (probabilities must be used) : risk is not linked directly to accident but rather to accident frequency (or probability) … and the relationship is a non linear curve called a “S” curve as shown on the figure below. It is possible then to use it to alert human driver (Vocal Driving Assistants) or to control autonomous driving (Autonomous Vehicle) in order to keep risk under the threshold of the “S” curve or not too far after the threshold. SafetyNex was calibrated in order to have 95% of accident frequency just after the threshold (validated on 50 million km).

A regular good driver will generate a SafetyNex driving risk(t), 20 times per second, between 0% and 70% with a maximum likehood between 30% and 60% depending on driver’s self confidence.
SafetyNex alerts at 90% and takes into account mostly [80%-100%] of driving risk slot to compute Safe Driving Score at the end of a trip, according to the S curve theory.


Contrary to what many companies do (risk scores based on statistics and data analysis), SafetyNex by Nexyad uses the true scientific method proven and validated : theory of risk developed by Frank E. Bird : “the triangle of risk”

This approach is in use in many domains confronted to risk management as the firemen, the FBI, in Nuclear Plants, etc.

NEXYAD is the first and only team that applied it to road safety.

It is very obvious, the same driving behaviour on a disused airport, on a highway, in front of a school, in a dense city approaching an intersection, etc… do not correspond to the same driving risk ! And no one can deny it.

If you measure driving behaviour without knowing driving context, it is impossible to compute driving risk. Training drivers not to do severe braking is very dangerous: they will hesitate even if a child surrounds in front of the car. Severe Braking is sometimes absolutely necessary. And that is why car manufacturers develop more efficient braking systems at each car generation (drum brake, disc brake, ABS, EABS emergency assisted braking systems), spending a lot of money for it !

If you take safe driving coaching course, they will teach to break your speed very harshly in case of any doubt. Road Safety should not use “intuition” of non-expert people or “belief”, but science and facts.

Just to make sure that our explanation makes sense, let us compare on a very simple case of urban risky situation (STOP sign) the harsh braking detection and the SafetyNex alert.


– Use case 1 : the driver arrives too fast approaching a stop sign. Instead of anticipating, this driver sees the stop sign at the very last minute and brakes very harshly. It is possible to put a threshold on acceleration value and then detect the harsh braking. This harsh braking detection obviously corresponds to a driving risk, and the figure 1 shows when it happens on the pathway.

SafetyNex predicts the next locations of the pathway, and estimates in real time if driving behaviour is adapted or not to the complexity and singulatities of road infrastructure ahead.

Because SafetyNex cannot predict that the driver is going to brake (the behaviour does not show it), SafetyNex driving risk rises as shown on figure 2.

One can notice that as soon as SafetyNex understands that the driver finally brakes enough to stop the car, then driving risk falls down very quicly. Driving risk rises BEFORE potential accident : first you take risk, and second you may have an accident.

SafetyNex and harsh braking criteria both detect that the driver took risk in such a situation : if you count alerts, you have 1 for harsh braking and 1 for SafetyNex.

What is the difference ? Well SafetyNex anticipates and then SafetyNex can alert the driver a few seconds before stop sign, letting time to slow down, where harsh braking criteria only monitors but cannot be used to alert because it has no anticipation feature.


– Use case 2 : It is exactly the same situation, but the driver doesn’t brake at all

Because there is no braking at all, the detection of harsh braking is not possible, as shown on figure 3 :

This driver that is much more dangerous than the previous one is not detected by harsh braking detection. Harsh braking detection is not effective on this use case.

SafetyNex works exactly the same way than in the previous use case : because it is not possible to forecast that the driver will brake, then risk rises as shown on Figure 4 :

Risk falls down only when situation is left behind : after crossing the stop sign, it is too late for risk assessment, it is an « alea jacta est » situation, you will have an accident or not depending on luck, there no possible anticipation.


. Conclusion :

Everytime that harsh braking corresponds to a real risk, SafetyNex also gives an alert. And SafetyNex still gives alerts in very dangerous situations where harsh braking detection is not effective.
SafetyNex is simply the next generation for driving risk assessment, you can now forget harsh braking detection and leave it all behind.

One more point, SafetyNex risk rises BEFORE dangerous situation, then you can alert driver and ACT on accident rate reduction.

SafetyNex can reduce accident rate by 20% for a regular inattentive driver (your ROI evaluation is easy to do).

Trick of numbers : stats have a meaning ONLY on very large numbers.
A black spot is an area where 5 falatities occured the 5 last years: black spot change every year.

Alerting on black spots: USE CASE
Road #N13 (France) between Saint Germain en Laye (NEXYAD office) and Paris La Défense : 160,000 vehicles per day. Then 58,4 million vehicles per year. Then 292 million vehicles in the last 5 years.
Let’s say that there is a black spot on this segment: a maximum of 5 vehicles (maybe less) had an accident with fatality… because one accident can lead to several fatalities.
Vehicles with no fatal accident : (292 million – 5) vehicles that didn’t have this problem…
The black spot is mostly a safe zone.
Observed frequency of fatal accident on the black spot: 5/292 million = 0,000000017 which means that on a black spot, fatality almost never happens.

Do you really want to be alerted for something that almost never happens?
=> Black spots recording (on maps) is not relevant for road safety alerts!

Modulation of Driving Risk with speed profile approaching STOP signs

Note : Driving Risk rises before STOP signs, and depending on speed (anticipation)

STOP sign is only an example, of course SafetyNex works the same way for curves, winding roads, intersections, school zones, pedestrian crossings, etc …

= Red alert (and for an active automated braking car, it would be trigger to anticipation braking)


Here is a demo of SafetyNex alerts during a real trip (using a simple implementation of SafetyNex API into a smartphone App made for demo ).
This App alerts driver BEFORE a dangerous situation, letting time to slow down and avoid a potential emergency situation (application to Vocal Driving Assistant for Automotive industry, or to Accident Prevention for Insurance / Fleet risk management). If you work on robotized car (ADAS or Autonomous Driving, just fancy that SafetyNex alerts your AI system intead of the human driver).

BEWARE with the statistics : “94% of severe personal damage accidents are due to human errors” doesn’t mean that you’ll save 94% of severe accident with autonomous driving : drivers do not only make mistakes they also drive well (1 accident every 70 000 km to 100 000 km, 3 dead every billion km – OCDE) … It is important to study also good driving and near misses (when driver has the right behaviour to avoid accident or to mitigate severity)… That’s what NEXYAD did during 15 years of research programs on road safety ^^ (that led to SafetyNex). See image (if you do not provide the “green” features, you will lose lives more than you gain with your driverless car. Our AI algorithm SafetyNex was made for this.

And SafetyNex is a XAI (eXplanable artificial Intelligence) so you can trust it (see Darpa research program on XAI).

Nexyad made 5 anime videos of 1mn each:



Load More

A software component easy to integrate to your applications (API/SDK)

Example of integration of SafetyNex API into a demo App for smartphone:
SafetyNex API into SafetyNex App

Mandatory (cope with 75% of driving risk)
Digital map Electronic Horizon – asynchronous, on demand
Accelerometers – 20 Hz
GPS (location and speed) – 1 Hz Time to collision (in s) – > 12 Hz Location on the lane – > 12 Hz
Size of free space – > 12 Hz
Time to collision – > 12 Hz
Interdistance – > 12 Hz
Number of vulnerables around – > 12 Hz
Weather visibility – > 1 Hz
Data stream alerts (weather, accident …)
Other inputs on demand (the more the best)

Real time
Risk(t) – 20Hz
Electronic Horizon – 20 Hz
Structure with alerts (orange/yellow alert, red alert + metadata) – 20 Hz
At the end of every trip (to build your data base)
Risk profile(trip)
Usage profile(trip)


software component

Required Inputs :
. Digital MAP
. Accelerometers

Optional Additional Inputs (*)

In real time :
Driving Risk (t) 20 times per second

At the end of trips :
Risk profile(trip)
Usage profile(trip)

(*) : data coming from sensors and from data flows : interdistance , time to collision, size of free space, presence of vulnerables, visibility ( quality and distance), road grip, warning accident ahead, warning construction area ahead, etc…


iOS, Android, Linux, Windows

Yes. Please follow this process :
Contact us
– Sign NDA
– Get Documentation

Example : SafetyNex API CPU consumption on an iPhone 5 architecture

SafetyNex works in every country where there exist a valuable digital map. We integrate the BENOMAD SDK into SafetyNex API that can read maps of HERE, TOM TOM, and OPEN STREET MAP. Please consult those maps in your application country and see if there is a valuable map (it is OK for about 200 countries).

SafetyNex integrates the SDK of the company Benomad to read and vectorise map. We use to read the HERE map (for its quality)! Benomad can also give access to TomTom and Open Street Map.

Distribution Licence agreement for OEMs and integrators.

A low cost integration of SafetyNex in smartphone is available for demo. Contact us.



Demo of SafetyNex on smartphone (driving with SafetyNex for real) :

Load More

Go to Global presentation of applications for motor INSURANCE

SafetyNex reduces accident rate by 20% (global accidents and also personal injuries).
SafetyNex records valuable data on a cloud.
We can help you to calculate your ROI for those two features in YOUR business case.
Contatc us :

Nexyad sales licences of software component (API) that you can integrate inside your own App or telematics device.

OEMs are already integrating SafetyNex API into final products for insurers. Nexyad can give you their contact if you are interested to buy those ready for deployment products.

Load More

Go to Global applications for OEMs

You know the risk that the driver is currently taking (in real time 20 times per second) then you can :

– Alert the driver when risk is too high, letting time to slow down and avoid emergency situation

– Use risk as context descriptor : when risk is high, it is not the moment to talk to the driver about something else

Scheme for technical integration is :

Exhausted STOP line marking Big vehicle masking the scene


Big vehicle masking the scene Intersection


Exhausted pedestrial markings Big vehicle masking the scene


Speed too fast for a masked tiny curve


Bad weather visibility Traffic jam behind the curve

Load More

At the end of every trip, SafetyNex records :
– Risk Profiles
– Usage Profiles (those data are fully compatible with European regulation RGPD)
– Global driving score of safe driving : from 0 to 100%

Risk profile : duration or distance (as you wish) spent in every risk slots

To read SafetyNex manual click here.

Usage profile: km, duration crossed by :
– Kind of infrastructure (urban, interurban, highway)
– Time slot (day, hour, etc.)
– zip code
– risk

All those variables can be sorted and filtered (by you) in the recorded data base

From risk profiles we extract:
– Self-confidence of driver
– Anticipation capability of driver
– Driving skill (ability to reproduce risk always the same value : repeatability of driving risk)

With those 3 dimensions it is possible to propose coaching and advices to the driver: how to improve their safety.

At the end of every trip, SafetyNex records :
– Risk Profiles
– Usage Profiles (those data are fully compatible with European regulation RGPD)
– Global driving score of safe driving : from 0 to 100%

Risk profile : duration or distance (as you wish) spent in every risk slots


Example of trip stats for driver :

SafetyNex Coaching - My Stats

Round table on Mobility TV about Autonomous Vehicle (NEXYAD CEO is 4th from left)


Interview of BMW group France CEO on French tv:


Interview on BFM Business of Rémi BASTIEN, VP Automotive prospective of RENAULT Group, President of the French Foundation on Autonomous Driving VEDECOM, President of the research cluster MOV’EO:

For English subtitles click the button on the video


Interview on BFM Business of Director of EMERTON, CEO of NEXYAD, and CEO of INTEMPORA, about new trends in Autonomous Vehicle.

SafetyNex is currently under integration by OEMs and integrators on several markets in several countries (Europe, USA, Asia)

SafetyNex API is in TRL9, with procedures and iterations of enhancement.

A roadmap of evolution is available to our customers and they can interact with priority levels if needed.

NEXYAD developed a back office architecture on PC, on the asynchronous real time environment RT-MAPS (INTEMPORA), in order to replay trips and audit any dysfonctional software behaviour, knowing that SafetyNex API is called by customer’s application program, that SafetyNex integrates BENOMAD SDK for digital map vectorization, and that BENOMAD reads the digital map (HERE, TOM TOM, or OPEN STREET MAP).

When a « bug » occurs, it is important to know quicly if it comes from :
. an error in the digital map,
. a bug in BENOMAD SDK
. a bug of SafetyNex
. a bug in the customer’s application software (that calls SafetyNex)

With our back office replay tools, errors and bugs are fully traceable.

A database of reference is replayed at every update for test of non regression.

– Explanation of GDPR for beginners

We do not intend to present the GDPR completely, we only give a few principles that will help you to understand what parts of your existing or future product may be in conflict with European regulations. For details and complete understanding please read official texts.

. Concept 1 : no recording of infridgement to the law Except if you are credited by a Government for that, you shouldn’t record infridgements to the law. In car telematics, this leads to a real problem when it comes about CAR SPEED. Indeed, car speed may be over the legal speed limit and then may contain an infridgement to the law. Same idea, you shouldn’t count infridgements to the law even if you do not record them (example : 10 overspeed alerts etc).
You can alert driver on overspeed, but not record it.

Note : not recording car speed means not recording it directly or indirectly : Precise geolocation and accelerations recording may be used to reshape car speed … This is a limitation to cloud computing based solutions that record raw data on a cloud and postprocess those data to extract intended information.

. Concept 2 : are recorded data NEEDED for the company that records ?
Example : if you manage a vehicles fleet for precious products transportation, you may argue that you need to know in real time the precise geolocation of all your vehicles. But if you are a car insurer or a car manufacturer, it will be hard to explain why you need to know where your customers go and when. It could be considered as « spying ».


– Solution of NEXYAD
SafetyNex API computes the risk that driver is currentlt taking, in real time.

Car Speed is necessary to compute this risk. So SafetyNex uses this value as input of the risk computing algorithm. The output is a risk value, and then you may record risk value without recording car speed, because risk is the « final variable » that you need.
All is computed INSIDE the onboard device (smartphone, telematics device, ADAS computer, …) and car speed recording is not needed at all.
Computing in real time INSIDE the onboard device every « final » variable is a good wayto be compliant. This is called « privacy by design ».


– Download offical French GDPR regulation text (available both in French and in English)
Note : You will notice that NEXYAD is quoted in page 3.




Load More