DIH4AI: Low-code platform for the development of safe and trustable software modules for autonomous driving
Tutorial on the DIGIHALL Platform based on Papyrus for Robotics, for the design of vehicle software architectures and for the validation of behavior-tree based scenarios and autonomous driving policies in CARLA/ROS 2
The DIGIHALL Platform for trustworthy AI-based systems is a proof-of-concept technology stack for the development of software modules for safe, reliable and quality-assured autonomous transportation services. The platform is used in experiment I-PAR-5 (https://dih-par.dih4ai-portal.eu/group/i-par-5) and builds on top of the open-source frameworks Papyrus for Robotics (https://eclipse.dev/papyrus/components/robotics/), CARLA (https://carla.org/) and ROS 2 (https://www.ros.org/). It enables (i) a low-code approach to the specification of vehicles' software architecture and behavior; (ii) the safety analysis of designed behavior against road scenarios and traffic rules; (iii) testing of the composition of perception, supervision and control componenents to ensure safety, reliability and quality of service of the design. This AI Asset is a tutorial, which includes the full experiment description (motivation, results) and the instructions to download and run (i) the Papyrus for Robotics low-code platform and (ii) a docker container providing the CARLA simulator, the ROS 2 middleware (target of the code-generation process of Papyrus for Robotics) and the CARLA/ROS 2 bridge.
The DIGIHALL Platform for trustworthy AI-based systems is a proof-of-concept technology stack for the development of software modules for safe, reliable and quality-assured autonomous transportation services. The platform is used in experiment I-PAR-5 (https://dih-par.dih4ai-portal.eu/group/i-par-5) and builds on top of the open-source frameworks Papyrus for Robotics (https://eclipse.dev/papyrus/components/robotics/), CARLA (https://carla.org/) and ROS 2 (https://www.ros.org/). It enables (i) a low-code approach to the specification of vehicles' software architecture and behavior; (ii) the safety analysis of designed behavior against road scenarios and traffic rules; (iii) testing of the composition of perception, supervision and control componenents to ensure safety, reliability and quality of service of the design. This AI Asset is a tutorial, which includes the full experiment description (motivation, results) and the instructions to download and run (i) the Papyrus for Robotics low-code platform and (ii) a docker container providing the CARLA simulator, the ROS 2 middleware (target of the code-generation process of Papyrus for Robotics) and the CARLA/ROS 2 bridge.