Projektbeschreibung
Roboter lernen mit verbesserter Methodik
Da die Robotertechnik in einer Vielzahl von Branchen und für viele Aspekte der Automatisierung äußerst nützlich ist, wird viel Arbeit in die Entwicklung und Programmierung von Robotern investiert. Aktuell werden Roboter so programmiert, dass sie über Nachahmung (der Roboter imitiert den Lehrenden) oder Verstärkung lernen (der Roboter lernt durch Versuch und Irrtum). Leider sind aber beide Methoden zeitaufwendig und teuer, sogar bei relativ einfachen Aufgaben. Das EU-finanzierte Projekt TERI will das Roboterlernen revolutionieren und stellt dazu eine neue Methode vor, die bereits von Menschen effizient genutzt wird: eine intermittierende Interaktion zwischen Roboter und Lehrkraft. So kann die Lehrkraft den Roboter in seinem Lernprozess besser anleiten und korrigieren, was – schneller und günstiger – bessere Ergebnisse liefert.
Ziel
Programming and re-programming robots is extremely time-consuming and expensive, which presents a major bottleneck for new industrial, agricultural, care, and household robot applications. My goal is to realize a scientific breakthrough in enabling robots to learn how to perform manipulation tasks from few human demonstrations, based on novel interactive machine learning techniques.
Current robot learning approaches focus either on imitation learning (mimicking the teacher’s movement) or on reinforcement learning (self-improvement by trial and error). Learning even moderately complex tasks in this way still requires infeasibly many iterations or task-specific prior knowledge that needs to be programmed in the robot. To render robot learning fast, effective, and efficient, I propose to incorporate intermittent robot-teacher interaction, which so far has been largely ignored in robot learning although it is a prominent feature in human learning. This project will deliver a completely new and better approach: robot learning will no longer rely on initial demonstrations only, but it will effectively use additional user feedback to continuously optimize the task performance. It will enable the user to directly perceive and correct undesirable behavior and to quickly guide the robot toward the target behavior. In my previous research I have made ground-breaking contributions to the existing learning paradigms and I am therefore ideally prepared to tackle the three-fold challenge of this project: developing theoretically sound techniques which are at the same time intuitive for the user and efficient for real-world applications.
The novel framework will be validated with generic real-world robotic force-interaction tasks related to handling and (dis)assembly. The potential of the newly developed teaching framework will be demonstrated with challenging bi-manual tasks and a final study evaluating how well novice human operators can teach novel tasks to a robot.
Wissenschaftliches Gebiet
Programm/Programme
Thema/Themen
Finanzierungsplan
ERC-STG - Starting GrantGastgebende Einrichtung
2628 CN Delft
Niederlande