Autonomous systems are being used in more and more areas of daily life. These autonomous systems are often referred to as "autonomous agents". These autonomous agents have to make human-understandable decisions, act together with humans or act in areas where humans are present. Explanations can be used for this purpose. These explanations can happen in many different ways and have different target groups, times and goals. This adaptation plays a major role when it comes to the acceptance and effectiveness of an explanation and thus the autonomous agent's decision.

In the future, fully autonomous agents should always be able to generate the right explanation in every situation. To achieve this, the agent must know the special features of different recipients, application domains and
situations. In order to develop good explainable autonomous agents, there are various
aspects to consider, which will be discussed in this proseminar.

• Definition of explanatory characteristics: What constitutes an explanation? Why are time, form and recipient relevant to generate the optimal explanation
• Domain-specific explanations: Which explanations are used in different application domains? How do these explanations differ in terms of their characteristics?
• What use cases and domains are there for explainability?

Course of the proseminar:
In the first week of the lecture there will be a meeting at which the selectable
topics will be presented. A sufficient number of topics will be provided,
to ensure a fair choice of topics. The presentations will be held in a
block seminar at the end of the lecture period and a paper of about 5 pages will be handed in before the
block seminar.