Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives

113 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Reinforcement learning in robotics: A survey (2013, background): “…for a T-ball batting task (Peters and Schaal, 2008c,b), an underactuated pendulum swing-up and a ball in a cup task (Kober and Peters, 2009), flipping a light switch (Buchli et al., 2011), pouring water (Tamošiūnaitė et al., 2011), and playing pool and manipulating a box (Pastor et al., 2011).”
Path Integral Policy Improvement with Covariance Matrix Adaptation (2012, methodology): “Take K samples θ k =1 ...”
Reasoning About Liquids via Closed-Loop Simulation (2017, background): “Several others have also performed the pouring task using a real robot [25, 13, 18, 29, 3, 22].”
Visual closed-loop control for pouring liquids (2016, background): “There is prior work related to robotic pouring, however, most of it either uses coarse simulations disconnected from real liquid perception and dynamics [9], [5] or constrained task spaces that bypass the need to perceive and reason directly about liquids [10], [11], [12], [13], [14].”
Applying statistical generalization to determine search direction for reinforcement learning of movement primitives (2012, background): “The learning of pouring was considered also in [22], where we learned to pour the whole bottle volume into a glass.”