PULS
Foto: Matthias Friel
"Alexa, can you help me assemble this shelf?" Interactions like these are still far from the scientific reality and that's not merely because robotic hardware development is still lacking behind. The amount ofreasoning and human-robot cooperation that is required to solve this task is complex: The robot needs to understand what a shelf is, what needs to be done to assemble one, observe what the human is doing and infer what actions could best support the human in the given task. The aim of this project is to get an understanding of the complexity of such human-agent collaboration from a practical and theoretical perspective by discussing the relevant literature as well as implementing a well-constrained part of the general assembly-task described above.During the project, you will develop a multimodal and incremental dialogue system for an industrial robot arm. The task for the robot arm is to help a human with solving a Pentomino puzzle. Doing so requires the robot to observe a visual scene, identify puzzle pieces by shape, color and location in the scene, and hand over the correct puzzle piece verbally described by the human interaction partner. The project work will be performed in teams and the focus of each project will be determined in the beginning of the course. While the teams can work individually, the final goal is to integrate the pieces and prepare a full dialogue pipeline that allows a human to play the Pentomino-game together with our physical robot arm. The practical project work will be enhanced by a series of seminar talks and paper discussions to get a better understanding of the fundamentals of embodied interaction.
© Copyright HISHochschul-Informations-System eG