Abstract: Applications are increasingly being developed based on complex autonomous systems driven by artificial intelligence. As smart robots are starting to replace humans in complicated or dangerous tasks on the road, in industry, or hospitals, their safety, autonomy, and trustworthiness are the subjects of concern. This is due to the increasing complexity of deployments, especially those of learned-enabled systems, not easily traced by continuous engineering (DevOps). The EU-funded H2020 FOCETA project plans to develop the foundation for continuous engineering of trustworthy learning-enabled autonomous systems integrating data-driven and model-based engineering. In this talk, I will highlight some of the research challenges that the project team tries to tackle together with some early reflections, including specification, V&V techniques, training, and runtime monitoring.
Presented at: ISO 26262 Digital Conference