08 septembre 2019

ARTIFICIAL INTELLIGENCE FOR PROACTIVE TELEMATICS

ARTIFICIAL INTELLIGENCE FOR PROACTIVE TELEMATICS Onboard telematics for vehicles is a huge market  :   Appications are : . geolocation. predictive maintenance. eco-driving. navigation. IoT for ads and marketing. UBI (Usage Based Insurance). and now : ROAD SAFETY Road Safety is a very complex filed of study where everyone thinks he/she knows almost everything (because we are drivers) but that is much more complex than it seems : . there is a theory of risk (triangle of risk by Frak E. Bird) : quite no one has read it... [Lire la suite]

25 août 2019

An Autonomous Vehicle that drives like a good human driver

An Autonomous Vehicle that drives like a good human driver Autonomous véhicles are one of the main R&D subject in automotive sector. Autonomoy has been described in a functional way and classified in 6 levels, from 0 to 5. Today, intelligent cars that are for sale (TESLA, ...) are said to be level 3, and some car munifacturers claim that they have demo cars with a level 4. The chain of the Autonomous Driving System (AD System) is quite always a feed forward chain, from sensors to actuators, and applies or may apply Artificial... [Lire la suite]
07 août 2019

Disruption that makes autonomous driving level 5 possible : SafetyNex technology

Disruption that makes autonomous driving level 5 possible : SafetyNex technology Most consultant and experts on automotive prospection tend to postpone the arrival of full autonomous driving. Their method is simple : they consider the current level 3 autonomous systems, and they estimate the number of examples in a database and the number of operation calculation should be done to improve the level 3 and cover "every" use cases. But this method is wrong. Indeed, the current AD Systems can be described as a chain as follow... [Lire la suite]
29 juillet 2019

SELF-DRIVING CAR MUST DRIVE "WELL" IN REGULAR CONDITION … SOUNDS EASY ? READ THIS BEFORE AND THEN TELL

SELF-DRIVING CAR MUST DRIVE "WELL" IN REGULAR CONDITION … SOUNDS EASY ? READ THIS BEFORE AND THEN TELL Human drivers don't have the sharp reflexes of ADAS. But they have only 1 accident in average every 100 000 km and 3 fatalities in average every billion km (OECD). Drivers that have the best reflexes are in average the Young ones - 18 to 25 - (biology). However, they also have much more accident than the 50 years old drivers (not as fast as they used to be when they were 20). Well, it seems that finally road safety is not... [Lire la suite]
05 mai 2019

ROI of car and truck telematics deployment : disruption

ROI of car and truck telematics deployment : disruption Now there is a buzz about telematics devices and onboard smartphone Apps, even Dashcams, with applications to fleet management, motor insurance pricing, etc. Features are geolocation, predictive maintenance, eco-driving scoring, driving risk assessment ... All those features may bring a Return On Investment (ROI), but in the long term only. And long term (a few years) is not easy to predict. It is one reason why we hear so much but we see few real large scale deployments. ... [Lire la suite]
02 mai 2019

Disruption in autonomous driving : AD system adaptive to driving risk

Disruption in autonomous driving : AD system adaptive to driving risk NEXYAD has been developing an Artificial Intlligence - based software component that monitors the driving risk that an AD system is currntly taking (at each moment). It is the risk in terms of road safety (not the inherently functional safety of the AD system).It is the first time that the driving risk is explicitely computed and available in a car.Then the AD system can be aware of th risk it is currently taking.If risk is too high, it is possible to apply... [Lire la suite]

12 avril 2019

NEXYAD CEO SPEAKER AT A ROTARY+ECOLE DES MINES PARITECH CONFERENCE ON ARTIFICIAL INTELLIGENCE

NEXYAD CEO SPEAKER AT A ROTARY+ECOLE DES MINES PARITECH CONFERENCE ON ARTIFICIAL INTELLIGENCE Very intersting conference the 10th of April 2019, Ecole des Mines de Paris (Paritech), in Paris. 4 speakers from :  . GOOGLE . MICROSOFT . NEXYAD . STIM The focus was Artificial Intelligence (AI). NEXYAD CEO presented the applications of AI to Autonomous driving : . perception . fusion . situation understanding . situation holding . decision making . actuators + a disruption (SafetyNex technology) that consists in... [Lire la suite]
19 mars 2019

HIGH LEVEL FUNCTIONAL SPECIFICATION OF A SELF-DRIVING VEHICLE (POINT TO POINT, ANY DESTINATION) : WHAT ABOUT DRIVING RISK ?

HIGH LEVEL FUNCTIONAL SPECIFICATION OF A SELF-DRIVING VEHICLE (POINT TO POINT, ANY DESTINATION) : WHAT ABOUT DRIVING RISK ? A general usage self-Driving vehicle is an object that picks you at a point A (that may be anywhere) and takes you to a point B (that may be any reachable point from A), as fast as possible, in comfort and safety.And that's it (main features).   Now let's see each feature : a . as far as possible : it is the actual efficiency of transportation, as mobility is a key element of Economy b . comfort : it... [Lire la suite]
11 mars 2019

Now for two-wheels SafetyNex computes onboard at each moment the riding risk that the rider is currently taking

Now for two-wheels SafetyNex computes onboard at each moment the riding risk that the rider is currently taking Then it becomes the only software component that computes onboard, in real time, at each moment, the risk that the RIDER is currently taking. This new version comes after 2 years of the collaborative research project BIKER ANGEL of the National French Research Program FUI. Reminder : it is when Driving behaviour is inappropriate to Driving context that the risk appears. Contrary to what many people think : . there is... [Lire la suite]
03 février 2019

‘Explainable Artificial Intelligence’: Cracking open the black box of AI

‘Explainable Artificial Intelligence’: Cracking open the black box of AI At a demonstration of Amazon Web Services' new artificial intelligence image recognition tool last week, the deep learning analysis calculated with near certainty that a photo of speaker Glenn Gore depicted a potted plant. “It is very clever, it can do some amazing things but it needs a lot of hand holding still. AI is almost like a toddler. They can do some pretty cool things, sometimes they can cause a fair bit of trouble,” said AWS’ chief architect in his... [Lire la suite]