Project

With the increasing use of robots in industrial and everyday contexts, the need for systems that can interact flexibly and cooperatively with humans is growing. Collaborative robots (cobots) in particular, which share a common workspace with humans and can react to complex, dynamic environments, are coming into focus. A central challenge here is the context-related perception of the environment and the appropriate interpretation of human behavior.

Research questions

The project presented addresses this problem by systematically investigating difficult perception situations in human-robot collaborations. The focus here is on three central research questions: (1) How can a robot perceive action spaces in a context-sensitive manner and use them in the sense of addressee-oriented communication? (2) How can implicit human behavior patterns - such as facial expressions, gestures or changes in movement - be used to interpret mental states? (3) How can a more robust, interpretable movement planning be realized through active spatial coordination?

Goals

The aim of the SEMIAC project is to develop and evaluate a responsive, mobile robot system that uses implicit forms of communication, in particular the communication of interaction-relevant states and spatial prompting, to achieve automatic and adaptive coordination with human partners in cooperative situations.

Founding

The project is funded by the German Research Foundation (DFG) under grant No. 502483052 and is planned with a project duration of 3 years (2023 to 2026).