Robot Programming by Demonstration

By Sylvain Calinon. 2009

325 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.

Citations in the corpus

Active learning of inverse models with intrinsically motivated goal exploration in robots (2013, positive): “ Social guidance is an important source of such constraints, widely studied in robot learning by demonstration/imitation where an external human demonstrator assists the robot in its learning process [1, 63, 18, 24, 59, 26, 60]. Typically, a robot teacher manually interacts with the robot by showing”
Self-Supervised Correspondence in Visuomotor Policy Learning (2019, background): “We point the reader to a number of existing reviews of learning from demonstration [27], [28].”
The KIT Motion-Language Dataset (2016, methodology): “on.humanoids.kit.edu khttp://webgl.org http://threejs.org 14 ! " # $ % & ' ( Figure 2: A screenshot of the Motion Annotation Tool during annotation. Visible are the annotator’s progress (1), the interactive visualizer (2), the playback controls (3), the input eld (4), the annotation in”
Incremental local online Gaussian Mixture Regression for imitation learning of multiple tasks (2010, methodology): “showed, through a series of advanced robotic experiments [1], [14], [2], [15], that the Gaussian Mixture Regression technique, introduced in [22], could be very successfully and easily used for encoding demonstrations through a GMM tuned with an expectation-maximization”
Learning Motion Skills from Expert Demonstrations and Own Experience using Gaussian Process Regression (2010, background): “Although imitation learning has been studied for decades, its mechanisms are not yet fully understood and there are many open questions that have been grouped into the broad categories relating to the questions of whom to imitate, what to imitate, how to imitate and when to imitate [1].”
Socially guided intrinsic motivation for robot learning of motor skills (2013, background): “…of demonstrated movements (Billard et al 2007; Grollman and Jenkins 2008; Chernova and Veloso 2009; Lopes et al. 2009b; Cederborg et al. 2010; Calinon 2009; Calinon and Billard 2007; Peters and Schaal 2008), or inverse reinforcement learning approaches (Abbeel and Ng 2004; Verma and Rao…”
Learning Navigation Subroutines from Egocentric Videos (2019, background): “Several works use learning from demonstration in scenarios where they have access to both the observations and the ground truth actions to solve the task [20, 21].”
Generative Adversarial Imitation from Observation (2018, background): “mely difﬁcult for system designers. Moreover, learning based solely on one’s own experience can be exceedingly slow. Concerns such as the ones above have given rise to the study of imitation learning [27, 4, 2], where agents instead attempt to learn a task by observing another, more expert agent per”
Towards transferring skills to flexible surgical robots with programming by demonstration and reinforcement learning (2016, methodology): “In this paper, we propose a data-driven strategy to accurately control the TSM manipulator with Programming by Demonstration (PbD) [20] and reinforcement learning [24].”
Learning to Reach Goals via Iterated Supervised Learning (2019, methodology): “GCSL is inspired by supervised imitation learning (Billard et al., 2008; Hussein et al., 2017) via behavioral cloning (Pomerleau, 1989).”
Learning To Reach Goals Without Reinforcement Learning (2019, methodology): “Our algorithm is based on ideas from imitation learning (Billard et al., 2008; Hussein et al., 2017) via behavioral cloning (Pomerleau, 1989) but it is not an imitation learning method.”
Learning Generalizable Control Programs (2011, unknown): “This approach is in direct contrastto muchof therecentwork in robotlearningthat focuseson programming by demonstration [ 3 ] and imitation learning [31].”
Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models (2011, background): “Programming by demonstration (PbD) is a powerful means to bootstrap robot learning by providing a few examples of the task at hand [1], [3].”
A survey of robot learning from demonstration (2009, unknown): “For example, one proposed categorization considers the broad spectrum of who, what, when and how to imitate, or subsets thereof [2,3].”