Conventional feedback control methods can solve various types of robot control problems very efficiently by capturing the structure with explicit models, such as rigid body equations of motion. However, many control problems in modern manufacturing deal with contacts and friction, which are difficult to capture with first-order physical modeling. Hence, applying control design methodologies to these kinds of problems often results in brittle and inaccurate controllers, which have to be manually tuned for deployment. Reinforcement learning (RL) methods have been demonstrated to be capable of learning continuous robot controllers from interactions with the environment, even for problems that include friction and contacts. In this paper, we study how we can solve difficult control problems in the real world by decomposing them into a part that is solved efficiently by conventional feedback control methods, and the residual which is solved with RL. The final control policy is a superposition of both control signals. We demonstrate our approach by training an agent to successfully perform a real-world block assembly task involving contacts and unstable objects.
Vorspann: Der 3D-Druck erobert die Entwicklungsabteilungen, weil er eine schnelle und flexible Fertigung von Prototypen ermöglicht. Wie bei jedem Fertigungsverfahren gibt es auch bei generativen Fertigungsverfahren „Best-Prac- tices”. Während allgemeine Richtlinien zum 3D-Druck- gerechten Konstruieren einen guten allgemeinen Überblick bieten, fehlen bislang Konstruktionsrichtlinien für die Dichtheit der gedruckten Teile. Einflussfaktoren wie Druck oder auch die Materialeigenschaften beeinflussen die Dichtheit eines Systems aus 3D-gedruckten Komponenten. Dieser Beitrag stellt eine Vorgehensweise für das 3D-Druck-gerechte Konstruieren vor, um 3D-gedruckte Systeme und Module zu dichten. Die Methoden werden anhand eines Mikro-Autonomen-Unterwasserfahrzeugs aufgezeigt.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.