Learning Movement Primitives

By Stefan Schaal, Jan Peters, Jun Nakanishi, Auke Jan Ijspeert. 2005

433 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Control and Systems Engineering, Robotics & Control

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 Biomedical Engineering

In Control and Systems Engineering

In Robotics & Control

Citations in the corpus

Learning Parameterized Skills (2012, background): “Because the following experiments involve a multi-joint simulated robotic arm, we chose a policy representation that is particularly well-suited to robotics: Dynamic Movement Primitives (Schaal et al., 2004), or DMPs.”
Accelerating Reinforcement Learning with Learned Skill Priors (2020, background): “[28] Stefan Schaal, Jan Peters, Jun Nakanishi, and Auke Ijspeert.”
Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation (2017, background): “Behavioral cloning has led to many successes in robotics when a low-dimensional representation of environment state is available [31], [32], [33], [34].”
One-Shot Visual Imitation Learning via Meta-Learning (2017, background): “Efﬁcient imitation from a small number of demonstrations has been successful in scenarios where the state of the environment, such as the poses of objects, is known [8, 9, 10, 11].”
An Algorithmic Perspective on Imitation Learning (2018, methodology): “Dynamic movement primitives (DMPs) [Schaal et al., 2004, Ijspeert et al., 2013] and the stable estimator of dynamical systems (SEDS) approach [Khansari-Zadeh and Billard, 2011] are representations that explicitly satisfy the condition of smooth convergence to the goal state.”
Stochastic Neural Networks for Hierarchical Reinforcement Learning (2016, background): “There has also been work on learning skills in tasks with continuous actions (Schaal et al., 2005; Konidaris et al., 2011; Daniel et al., 2013; Ranchod et al., 2015).”
Neural probabilistic motor primitives for humanoid control (2018, neutral): “Note that this notion is related but distinct to the line of research into “movement primitives” (Schaal et al., 2003; Neumann et al., 2014) in the robotics literature.”
BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning (2022, positive): “Imitation learning has been successful in learning grasping and pick-place tasks from lowdimensional state [9, 10, 11, 12, 13, 14, 15].”
Probabilistic Movement Primitives (2013, methodology): “However, since ProMPs incorporate the variance of demonstrations, the increased flexibility and advantageous properties of the representation come at the price of requiring multiple demonstrations to learn the primitives as opposed to past approaches [17, 3] that can clone movements from a single de”
Hierarchical Relative Entropy Policy Search (2014, methodology): “We use Dynamic Movement Primitives [25] to represent the options.”
Learning Semantic Embedding Spaces for Slicing Vegetables (2019, methodology): “To learn the low-level control policy for the cutting action, we use Imitation Learning (IL) in conjunction with Dynamic Motor Primitives (DMPs) [16], [17].”
Incremental Semantically Grounded Learning from Demonstration (2013, methodology): “T , we can use LfD to learn the weights for the basis functions [18].”
Learning Interactively to Resolve Ambiguity in Reference Frame Selection (2020, background): “Alternatively, the works in [7], [8] and [9] use Movement Primitives for learning new tasks in few shots.”
A Survey on Policy Search for Robotics (2013, background): “1 2 Introduction”
Kinesthetic teaching via Fast Marching Square (2012, methodology): “One approach has been to use the concept of motion primitives [5].”
Hierarchical Control Using Networks Trained with Higher-Level Forward Models (2014, background): “Work on dynamical movement primitives (Ijspeert, Nakanishi, Hoffmann, Pastor, & Schaal, 2013; Schaal, Peters, Nakanishi, & Ijspeert, 2005) aims to construct lower-level control systems obeying attractor or limit cycle dynamics that simplify the production and planning of smooth, feedback-sensitive…”