Movement segmentation using a primitive library

By F. Meier, Evangelos A. Theodorou, Freek Stulp, Stefan Schaal. 2011

94 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

Benchmark for Skill Learning from Demonstration: Impact of User Experience, Task Complexity, and Start Configuration on Performance (2019, methodology): “Motion Segmentation for Pressing Task Since the pressing task includes two consecutive pressing primitives, we conducted experiments of the task once without and once with motion segmentation [24]–[27].”
Learning Robot Skills with Temporal Variational Inference (2020, background): “More recent efforts have sought to segment demonstrations into smaller behaviors, and fitting a model to the resulting segments (Niekum et al., 2012; Krishnan et al., 2018; Murali et al., 2016; Meier et al., 2011).”
Recent Advances in Robot Learning from Demonstration (2020, methodology): “Several methods for automated segmentation of demonstrations into sub-tasks, either based on the similarity of component sub-tasks (137, 138, 139, 140, 141, 142) or based on the occurrence of indicative events (25, 143, 144), have been explored.”
Towards learning hierarchical skills for multi-phase manipulation tasks (2015, unknown): “While some methods assume that a library of motor primitives already exists and focus on sequencing these primitives [30], [27], other approaches also learn the individual skills by segmenting the human demonstrations [29], [6], [14], [38].”
Discovering Motor Programs by Recomposing Demonstrations (2020, methodology): “, 2013), or first segmenting the demonstrations and fitting a model to each of the resultant segments (Niekum et al., 2012; Krishnan et al., 2018; Murali et al., 2016; Meier et al., 2011).”
A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms (2019, background): “The most direct approach [176, 60, 129, 281, 260, 79] is policy similarity, which measures skill similarity by fitting the data to a parameterized policy class and measuring distance in parameter space.”