In the AITHENA Use Case 2: AI extended Situational Awareness/Understanding information from perception layers, communications and map information is fused into Local Dynamic Maps (LDM) to link layers (from static to dynamic) to achieve accurate and complete knowledge of the scene.

• AI models can be used to learn to predict possible evolutions of the scene and predict collisions or other situations. Trusted AI is needed to understand what data has been used to train the predictors and what edge cases are covered.

Collision prediction can be learned with AI models that learn from images or other raw data from sensors and produce detected events such as Time-To-Collision (TTC) values, cut-in probability or other equivalent collision risk estimators as a form of prediction of the near future road situation.

• Robust prediction of the intended movement of road users enables safe and predictable operation of AVs.

In interactive urban traffic environments, vehicles, as well as pedestrians and other road users, navigate highly complex road networks under a variety of environmental conditions while interacting with different types of road users. In this context, motion planning can only ensure the safety of all participants if the characteristics of the scenarios are taken into account.