Incremental learning of gestures by imitation in a humanoid robot

By Sylvain Calinon, Aude Gemma Billard. 2007

476 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

An Incremental Self-Organizing Architecture for Sensorimotor Learning and Prediction (2017, methodology): “[35] showed that the Gaussian Mixture Regression (GMR) technique can be successfully applied for encoding demonstrated motion patterns incrementally through”
An Algorithmic Perspective on Imitation Learning (2018, methodology): “In [Calinon and Billard, 2007], GMMs are initialized with trajectories demonstrated by a human wearing a motion sensor.”
Unsupervised Perceptual Rewards for Imitation Learning (2016, background): “Previous work in LfD has successfully replicated gestures [8] and dual-arm manipulation [4] on real robotic systems.”
Helping Robots Learn: A Human-Robot Master-Apprentice Model Using Demonstrations via Virtual Reality Teleoperation (2020, background): “Processing techniques often involve keyframes [21], segmentation [22], [23], constraint extraction [24], [25], and reproduction [26], [27].”
Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection (2018, methodology): “For the online algorithms, we used an incremental GMM from [43], and pcStream2 [44]. pcStream2 is a stream clustering algorithm which detects outliers by measuring the Mahalanobis distance of new instances to known clusters. on the ﬁrst million packets, and then executed on the remainder.”
Combining Dynamical Systems control and programming by demonstration for teaching discrete bimanual coordination tasks to a humanoid robot (2008, background): “Bimanual coordination is not treated as a constraints per se, but emerges from requiring that the robot reproduces exactly the demonstrated joint trajectories [21], or some given object/hand relation [4].”
Learning grounded finite-state representations from unstructured demonstrations (2015, background): “A variety of approaches have been proposed for LfD, including supervised learning [Akgun et al., 2012; Atkeson and Schaal, 1997; Calinon and Billard, 2007; Chernova and Veloso, 2007; Dong and Williams, 2011; Grollman and Jenkins, 2008], (inverse) reinforcement learning [Abbeel and Ng, 2004;…”
Statistical Learning by Imitation of Competing Constraints in Joint Space and Task Space (2009, methodology): “[26] that when considering GMM, an incremental version of the EM algorithm can be used to update the GMM parameters when new data are available.”
Novel Interaction Strategies for Learning from Teleoperation (2012, methodology): “A modiﬁcation to the kinesthetic teaching interface is kinesthetic correction (Calinon and Billard 2007a; 2007b), where the teacher corrects aspects of a learned skill in an incremental learning interaction by using a subset of joints in subsequent demonstrations.”
Imitation Learning (2017, methodology): “This technique has been widely used with high DOF robots [Ikemoto et al. 2012; Berger et al. 2008; Vogt et al. 2014; Calinon and Billard 2007b].”
Learning the semantics of object–action relations by observation (2011, background): “…much attention in recent years and many contributions exist, but are often unrelated to manipulation recognition (Calinon and Billard 2004, 2005; Hakeem and Shah 2005; Maurer et al. 2005; Calinon and Billard 2007; Laptev and Perez 2007; Niebles et al. 2008; Dee et al. 2009; Gilbert et al. 2011).”
Incremental learning of full body motion primitives and their sequencing through human motion observation (2012, methodology): “This system is also extended to an on-line, interactive approach by developing a method for incremental training of the GMM structure (Calinon and Billard 2007b) and developing an interactive training approach combining demonstration and kinesthetic training (Calinon and Billard 2007a).”
Learning robot motion control with demonstration and advice-operators (2008, background): “The most common approach is to add more teacher demonstration data in problem areas of the state space, and then re-derive the policy [6], [7].”