28 mai 2018

DEEP LEARNING FOR ONBOARD APPLICATIONS: HIDDEN TRAP

DEEP LEARNING FOR ONBOARD APPLICATIONS: HIDDEN TRAP Now Deep Learning is used in onboard detection and pattern recognition applications. NEXYAD for instance uses Deep Learning in RoadNex (road detection without need of markings + detection of free space), and ObstaNex (obstacles detection). But if you do not analyse your INDUSTRIAL project in detail, you may have bad surprises : everone thinks he/she knows that the more numerous the training examples, the most accurate the KPIs. Let's say you used 1 billion km to train and... [Lire la suite]

23 mai 2018

RELATIONSHIP BETWEEN DRIVING RISK YOU TAKE AND ACCIDENT : THE "S" CURVE THEORY

RELATIONSHIP BETWEEN DRIVING RISK YOU TAKE AND ACCIDENT : THE "S" CURVE THEORY 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... [Lire la suite]
08 mai 2018

Sometimes, accurate ADAS sensors are not enough

Sometimes, accurate ADAS sensors are not enough in road safety, there are many cases where accurate ADAS sensors detection is not enough, because dangerous situations come from the notion of "surprise". This video shows some examples : NEXYAD developed a real time dynamical driving risk assessment SafetyNex that reads difficulties of the infrastructure on the digital map. This map is an a priori knowledge that should be used in addition to sensors. To know more : https://www.youtube.com/watch?v=bY2aDm8kfy8
03 mai 2018

NEXYAD is proud to announce that their Aritificial Intelligence Algorithms go to Autonomous Driving market

NEXYAD is proud to announce that their Aritificial Intelligence Algorithms go to Autonomous Driving market French High Tech Startup ISFM (Intelligent Systems for Mobility) selected Nexyad artificial intelligence algorithms for their "Milla" Smart Shuttle. ISFM is one of the companies selected by the Ubimobility 2018 program  
16 avril 2018

2018 CNEJITA Symposium : How Artificial Intelligence of Autonomous Driving will be auditable in case of accident

How Artificial Intelligence of Autonomous Driving will be auditable in case of accident   2018 CNEJITA symposium : keyword = complexity NEXYAD explained how the AI based real time driving risk assessment SafetyNex can monitor autonomous driving artificial intelligence. Does AI follow rules of cautiousness ? Read more : https://www.cnejita.org/2018/01/colloque-2018-intelligence-artificielle-qui-sera-responsable/
Posté par NEXYAD à 00:05 - - Commentaires [0] - Permalien [#]
Tags : , , , , ,
10 avril 2018

Disruption brought by Artificial Intelligence in the Automotive field

Disruption brought by Artificial Intelligence in the Automotive field A new Artificial Intelligence algorithm (SafetyNex) brings disruption in many applications of the automotive domain : Applications of dynamic real time driving risk assessment (by SafetyNex) : . vocal driving assistants . ADAS . Autonomous Driving This Artificial Intelligence algorithm is developed and proposed by NEXYAD.  

07 avril 2018

NEW ARCHITECTURE FOR AUTONOMOUS DRIVING INVOLVING DRIVING RISK ASSESSMENT

NEW ARCHITECTURE FOR AUTONOMOUS DRIVING INVOLVING DRIVING RISK ASSESSMENT Architectures of Autonomous Driving systems use to be feed forward open loop chains that are supposed to give a good solution to any problem. Inputs come from sensors that are fusionned in order to bring a good situation understanding. Then a decision making system sends what to do to actuators. This works fine, but of course, whatever the number of validation scenarios, there will always exist cases where the glabal system is not adapted to the situation. ... [Lire la suite]
29 mars 2018

A French startup has all the Artificial Intelligence technologies needed to avoid many accidents such as recent UBER accident

A French startup has all the Artificial Intelligence technologies needed to avoid many automous car accidents such as the recent UBER accident We all saw videos of the UBER VOLVO accident. The dashcam video shows that visibility conditions were very poor and that the pedestrian is dressed in black (pullover) and crosses a road at night without any light and out of pedestrian crossing areas. This attitude is pure suicade and you wouldn't teach your children to behave this way. But even if this pedestrian shouldn't have been in the... [Lire la suite]
14 mars 2018

Soon, NEXYAD will transform your ordinary car into an intelligent car using ... your smartphone

Soon, NEXYAD will transform your ordinary car into an intelligent car using ... your smartphone NEXYAD developed 4 algorithm for intelligent connected car : . SafetyNex, system that alerts you while driving if and only if driving risk is too high. RoadNex, system that detects free space (drivable part of the road ahead). ObstaNex, system that detects obstacles. VisiNex, system that detects lacks of visibility (fog, snow, ...) All those modules are available to OEMs as API to be integrated inside valuable products (driving... [Lire la suite]
01 mars 2018

AI should help increasing road safety for robot taxi allowing to put them in function soon

AI should help increasing road safety for robot taxi allowing to put them in function soon Robot taxis are under testing in many cities such as Phoenix Arizona. Globally it works but the issue is still the rate of accident. Human driver has an accident in average about every 70 000 km and there are about 3 deads every billion km. This very high performance of human driver makes it difficult to automate driving, especially in urban traffic where road infrastructure characteristics are very complex. This explain why tests long more... [Lire la suite]