Learning to close the gap: Combining task frame formalism and reinforcement learning for compliant vegetable cutting

Padalkar, A.A.PadalkarNieuwenhuisen, M.M.NieuwenhuisenSchneider, S.S.SchneiderSchulz, D.D.Schulz2022-03-142022-03-142020https://publica.fraunhofer.de/handle/publica/40935710.5220/0009590602210231Compliant manipulation is a crucial skill for robots when they are supposed to act as helping hands in everyday household tasks. Still, nowadays, those skills are hand-crafted by experts which frequently requires labor-intensive, manual parameter tuning. Moreover, some tasks are too complex to be specified fully using a task specification. Learning these skills, by contrast, requires a high number of costly and potentially unsafe interactions with the environment. We present a compliant manipulation approach using reinforcement learning guided by the Task Frame Formalism, a task specification method. This allows us to specify the easy to model knowledge about a task while the robot learns the unmodeled components by reinforcement learning. We evaluate the approach by performing a compliant manipulation task with a KUKA LWR 4+ manipulator. The robot was able to learn force control policies directly on the robot without using any simulation.en004Learning to close the gap: Combining task frame formalism and reinforcement learning for compliant vegetable cuttingconference paper