2 min read
Basically, Apex. AI designed a modular software stack for building autonomous systems. It easily integrates into existing systems as well as 3rd party software. An interesting thing they claim about their system is the fact that “The software is not designed for peak performance — it’s designed to never fail. We’ve built redundancies into the system design to ensures that single failures don’t lead to system-wide failures.”
Their two products are Apex.OS and Apex.Autonomy.
Apex.OS is a meta-operating system, which is an automotive version of ROS (Robot Operating System). It allows software developers to write safe and secure applications based on ROS 2 APIs.
Apex.OS is built with safety in mind. It is being certified according to the automotive functional safety standard ISO 26262 as a Safety Element out of Context (SEooC) up to ASIL D. It ensures system security through HSM support, process level security, encryption, authentication.
Apex.OS improves production code quality through the elimination of all unsafe code constructs. It ships with support for automotive hardware, i.e. ECUs and automotive sensors.
Moreover it comes with a complete documentation including examples, tutorials, design articles, and 24/7 customer support.
Apex.Autonomy provides developers with building blocks for autonomy. It has well-defined interfaces for easy integration with any existing autonomy stack.
It is written in C++, is easy to use, and can be run and tested on Linux, Linux RT, QNX, Windows, OSX. It is designed with production and ISO 26262 certification in mind and is CPU bound on x86_64 and amd64 architectures. A variety of LiDAR sensors are already integrated and tested.
Read more about the products on Apex. AI website.