Department for Automation, Biocybernetics and Robotics

Autonomous learning of pouring with a robot

Research activity duration: 2009 - 2010
Research area: Laboratory of Humanoid and Cognitive Robotics
Activity funding: EU
Keywords: Cognitive robotics, Robotics,
Activity leader: Bojan Nemec
Bojan Nemec
Aleš Ude

Minija Tamošiunaitè,

Vytautas Magnus University, Department of Informatics, Vileikos 8, 44404 Kaunas,Lithuania

Florentin Wörgöter,

University Göttingen, Institute for Physics 3 - Biophysics, Bernstein Center for Computational Neuroscience, Friedrich-Hund-Platz 1, 37077 Göttingen, Germany


Autonomous learning of pouring with a robot using reinforcement learning technique. Experiments were conducted on Hoap3 humanoid robot and Micubishi Pa10 robot arm


Example of reinforcement learning of pouring (PouringReinforcementLearning.avi, 6894 kb)


This Research is a part of the PACO+ project



  • Tamosiumaite M., Nemec B., Ude A., Wörgötter F., Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives, 2011. [More] [PDF]


  • Nemec B., Tamošiunaitè M., Wörgöter F., Ude A., Task adaptation thorough exploration and action sequencing, 2009. [More]