Statistical Learning by Imitation of Competing Constraints in Joint Space and Task Space

By Sylvain Calinon, Aude Gemma Billard. 2009

126 citations recorded by the source corpus.

Subfields: Control and Systems Engineering

How researchers see this paper

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

In Control and Systems Engineering

Citations in the corpus

An Algorithmic Perspective on Imitation Learning (2018, background): “Behavioral Cloning Widrow and Smith [1964], Chambers and Michie [1969], Pomerleau [1988], Schaal et al.”
Imitation Learning of Positional and Force Skills Demonstrated via Kinesthetic Teaching and Haptic Input (2011, background): “The main reason is that it is easier for the user to move the motors one by one during demonstration than executing a natural coordinated movement [13].”
Intrinsically motivated goal exploration for active motor learning in robots: A case study (2010, background): “Social guidance is an important source of such constraints, which has been widely used in robot learning by demonstration/imitation learning [3], [4].”
Learning and Reproduction of Gestures by Imitation (2010, methodology): “GMR does not model the regression function directly but models a joint probability density function of the data.”
Keyframe-based Learning from Demonstration (2012, background): “Demonstrations often consist of arm joint and/or endeffector trajectories [9, 15].”
Using dVRK teleoperation to facilitate deep learning of automation tasks for an industrial robot (2017, background): “Calinon and Bil-lard [37] studied how to extract implicit joint and workspace constraints from kinesthetic demonstrations, and Phillips et al. [38] used kinesthetic teaching to learn door opening motions on a PR2.”
Trajectories and keyframes for kinesthetic teaching: A human-robot interaction perspective (2012, background): “Kinesthetic teaching may be challenging for everyday users who do not have experience manipulating a robot arm with many degrees of freedom.”
Robot Learning System Based on Adaptive Neural Control and Dynamic Movement Primitives (2019, background): “Probabilistic approaches have shown good performance in motion encoding [11]–[13].”
A tutorial on task-parameterized movement learning and retrieval (2015, background): “The consideration of non square At,j matrices is for example relevant for the consideration of soft constraints in both configuration and operational spaces (through Jacobian operators), see [15] for a preliminary work in this direction.”
Novel Interaction Strategies for Learning from Teleoperation (2012, background): “In LfD, demonstrations are often represented as arm joint trajectories and/or end-effector path (Calinon and Billard 2009).”