AIthena is a research and innovation project on Connected and Cooperative Automated Mobility (CCAM) solutions that aims to build trustworthy, explainable, and accountable CCAM technologies.
CCAM solutions are increasingly present in vehicle technologies, which benefit from artificial intelligence (AI) through AI-based perception, situational awareness, and decision-making components.
But AI can be unfair, biased, and can be extremely sensitive to unexpected inputs.
Building explainable and trustworthy AI is the next mandatory step of technology development, incorporating among other equally important properties: robustness, privacy, explainability, accountability, and ethics.
Project use cases
The AIthena project has four use cases: perception, understanding, decision, and traffic.
With 17 partners, the AIthena project aims to harmonize methodology for AI design, development, and deployment in CCAM applications. The AIthena project is scheduled to run from November 2022 to October 2025.
Perception – Trustworthy Perception Systems for CCAMTrusted AI is needed to understand which objects are perceived? How different sensor information is used? How possible discrepancies are solved?
Understanding – AI extended situation awareness and understandingAI needs to understand communications, map information and perception layers. This includes understanding local dynamic maps (LDM) with accurate and complete knowledge about the scene.
Decision – Trustworthy and human understandable decision making
AI path planning and manoeuvring execution should maximize safety, comfort, and eco-driving. The user understands why, when, and how a decision is taken.
Traffic – AI based traffic management
AI models are analysed in macroscopic scenarios with interaction with other AI and non-AI systems. Trustworthiness is gained by benchmarking “good behaviour” of AI models in transport level contexts.