Efficient exploratory learning of inverse kinematics on a bionic elephant trunk
We present an approach to learn the inverse kinematics of the “bionic handling assistant”-an
elephant trunk robot. This task comprises substantial challenges including high …
elephant trunk robot. This task comprises substantial challenges including high …
Goal-directed tactile exploration for body model learning through self-touch on a humanoid robot
An early integration of tactile sensing into motor coordination is the norm in animals, but still
a challenge for robots. Tactile exploration through touches on the body gives rise to first …
a challenge for robots. Tactile exploration through touches on the body gives rise to first …
Goal babbling with unknown ranges: A direction-sampling approach
M Rolf - 2013 IEEE Third Joint International Conference on …, 2013 - ieeexplore.ieee.org
Goal babbling is a recent concept for the efficient bootstrapping of sensorimotor coordination
that is inspired by infants' early goal-directed movement attempts. Several studies have …
that is inspired by infants' early goal-directed movement attempts. Several studies have …
Hierarchical interest-driven goal babbling for efficient bootstrapping of sensorimotor skills
We propose a novel hierarchical online learning scheme for fast and efficient bootstrapping
of sensorimotor skills. Our scheme permits rapid data-driven robot model learning in a" …
of sensorimotor skills. Our scheme permits rapid data-driven robot model learning in a" …
Efficient policy search in low-dimensional embedding spaces by generalizing motion primitives with a parameterized skill memory
RF Reinhart, JJ Steil - Autonomous Robots, 2015 - Springer
Motion primitives are an established paradigm to generate complex motions from simpler
building blocks. A much less addressed issue is at which level to encode and how to …
building blocks. A much less addressed issue is at which level to encode and how to …
Efficient policy search with a parameterized skill memory
RF Reinhart, JJ Steil - 2014 IEEE/RSJ International Conference …, 2014 - ieeexplore.ieee.org
Motion primitives are an established paradigm to generate complex motions from simpler
building blocks. A much less addressed issue is at which level to encode and organize a …
building blocks. A much less addressed issue is at which level to encode and organize a …
Continuum worm-like robotic mechanism with decentral control architecture
Flexible continuum robots are utilized for operational areas, in which discretely structured
robots are not suitable due to their kinematic limitations. Continuum mechanisms feature …
robots are not suitable due to their kinematic limitations. Continuum mechanisms feature …
Online associative multi-stage goal babbling toward versatile learning of sensorimotor skills
We develop an online learning scheme inspired by the versatility of the human learning
system to bootstrap several sensorimotor skills in “Learning while Behaving” fashion. Our …
system to bootstrap several sensorimotor skills in “Learning while Behaving” fashion. Our …
[PDF][PDF] Multi-stage goal babbling for learning inverse models simultaneously
Online Goal Babbling has been proposed for directed learning of inverse kinematics from
scratch following the paradigm of” learning while behaving”. In this paper, we show that Goal …
scratch following the paradigm of” learning while behaving”. In this paper, we show that Goal …
[PDF][PDF] Efficient and stable online learning for developmental robots
R Rayyes - 2020 - scholar.archive.org
Efficient and Stable Online Learning for Developmental Robots Page 1 Efficient and Stable
Online Learning for Developmental Robots Von der Carl-Friedrich-Gauß-Fakultät der …
Online Learning for Developmental Robots Von der Carl-Friedrich-Gauß-Fakultät der …