Doctoral research seminar on: "Enabling Robots to Learn Autonomous Decision Making from Humans" by Christoph Willibald, HCR/TUM
Conventional robot programming methods are not suited for non-experts to intuitively teach robots conditional tasks that involve decisions about how to react to different observations. For this reason, the potential of collaborative robots for production cannot yet be fully exploited. In this talk, I'll outline an active learning approach, in which the robot and the user collaborate to incrementally program a complex task. Starting with a basic model, the robot's task knowledge can be extended over time if new situations require additional skills. When detecting unknown situations, the robot triggers a teaching phase, in which the user decides to either refine an existing skill or demonstrate a new one. In a user study, our approach is compared to two state-of-the-art Programming by Demonstration frameworks on a real system. Increased intuitiveness and task performance of the method can be shown, allowing shop-floor workers to program industrial tasks with our framework.
Time: January 11, 2021, 11am. via zoom.