Projektbeschreibung
Laufende Roboter machen große Fortschritte
Robotertechniken sind seit jeher ein Eckpfeiler moderner automatisierter Industrieprozesse. Gleichzeitig wird intensiv an Anwendungen im gewerblichen und industriellen Bereich geforscht. Jüngster Schwerpunkt dieser Forschungen sind Roboter, die auf Beinen laufen. Damit sind sie mobiler und können sich optimal an verschiedenste Gelände anpassen. Allerdings sind komplexere Situationen noch schwer zu meistern. Das EU-finanzierte Projekt LeMo forscht an Methoden, um erlerntes Verhalten direkt vom Simulator auf den Roboter zu übertragen und so dessen Bewegungsspielraum zu erweitern. Damit könnten derzeitige Hürden überwunden und die Mobilität von Robotern verbessert werden.
Ziel
Research and applications in legged robotics has made significant progress over the last decade, driven by more advanced actuation systems, better on-board computation, and significantly improved sensors for perceiving the environment. State-of-the-art model-based planning and control algorithms can plan for contact points and body motions to move legged systems over complex environments. However, these methods have shown clear performance limits when it comes to behaviours and situations that are more complex, and it is unclear if and how these limits can be overcome with classical control methods. On the other hand, recent advances in reinforcement learning has put forward unprecedented capabilities to learn control policies for complex behaviours.
With our preliminary findings, we were the first group to present methods that allow directly transferring learned behaviours from simulation to reality to create advanced motion skills for complex legged robots. This breakthrough has the potential to revolutionize the field of legged locomotion control. In this ERC project, we want to research this highly promising area and investigate the use of machine learning tools to make legged robots autonomously move in realistic outdoor scenarios. In three parallel research streams, we will learn how to accurately model the system dynamics from experience, how to abstractify, generate and coordinate different complex behaviours that involve multi-contact situations, and how to combine these with perception to enable autonomous navigation in complex environments. The proposed methods have the potential to overcome the limitations of commonly used optimization-based methods such as limited model accuracy, local minima, conservative performance, computational load and execution time, and it will help us to better understand the fundamentals of locomotion in robots and biology.
Wissenschaftliches Gebiet
- natural sciencescomputer and information sciencesartificial intelligencemachine learningreinforcement learning
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensors
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringrobotics
Programm/Programme
Thema/Themen
Finanzierungsplan
ERC-STG - Starting GrantGastgebende Einrichtung
8092 Zuerich
Schweiz