Online Segmentation and Clustering From Continuous Observation of Whole Body Motions

Kulić, Dana; Takano, Wataru; Nakamura, Yoshihiko

doi:10.1109/tro.2009.2026508

Cited by 101 publications

(61 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [4] automatic segmentation of motion patterns based on HMMs have been used to group segments hierarchically, where higher level representations of symbols can then be used to orchestrate and generate low level robot movements. More recently, in [5], the authors propose on-line segmentation method based on HMMs that creates a tree of primitives; the lower nodes representing detailed movements with generality increasing towards the root. HMMs have also been used in conjunction with the superposition of movement primitives for the specific case of handwriting analysis [6].…”

Section: Related Workmentioning

confidence: 99%

Probabilistic segmentation applied to an assembly task

Lioutikov

Neumann

Maeda

et al. 2015

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

Abstract-Movement primitives are a well established approach for encoding and executing robot movements. While the primitives themselves have been extensively researched, the concept of movement primitive libraries has not received as much attention. Libraries of movement primitives represent the skill set of an agent and can be queried and sequenced in order to solve specific tasks. The goal of this work is to segment unlabeled demonstrations into an optimal set of skills. Our novel approach segments the demonstrations while learning a probabilistic representation of movement primitives. The method differs from current approaches by taking advantage of the often neglected, mutual dependencies between the segments contained in the demonstrations and the primitives to be encoded. Therefore, improving the combined quality of both segmentation and skill learning. Furthermore, our method allows incorporating domain specific insights using heuristics, which are subsequently evaluated and assessed through probabilistic inference methods. We demonstrate our method on a real robot application, where the robot segments demonstrations of a chair assembly task into a skill library. The library is subsequently used to assemble the chair in an order not present in the demonstrations.

show abstract

Section: Related Workmentioning

confidence: 99%

Probabilistic segmentation applied to an assembly task

Lioutikov

Neumann

Maeda

et al. 2015

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

show abstract

“…However, more recent work has used computationally expensive but principled statistical methods [Grollman andJenkins, 2010, Butterfield et al, 2010] to segment the data into multiple models as a way to avoid perceptual aliasing in the policy. Kulić et al [2009] use a principled, online and incremental method to perform segmentation, and use acquired motion primitives to build a hierarchy that can be used to improve later segmentation. Their method (unlike CST) is able to recognize and exploit repeated skills, but does not result in skills with goals and does not select skill-specific abstractions.…”

Section: Related Workmentioning

confidence: 99%

Robot learning from demonstration by constructing skill trees

Konidaris

Kuindersma

Grupen

et al. 2011

The International Journal of Robotics Research

247

189

View full text Add to dashboard Cite

We describe CST, an online algorithm for constructing skill trees from demonstration trajectories. CST segments a demonstration trajectory into a chain of component skills, where each skill has a goal and is assigned a suitable abstraction from an abstraction library. These properties permit skills to be improved efficiently using a policy learning algorithm. Chains from multiple demonstration trajectories are merged into a skill tree. We show that CST can be used to acquire skills from human demonstration in a dynamic continuous domain, and from both expert demonstration and learned control sequences on the uBot-5 mobile manipulator.

show abstract

“…The work of Kulić et al [15,14] is a notable exception. They used hidden Markov models for incremental learning and the hierarchical organization of motion primitives, but they do not focus on discovering new movements in these data.…”

Section: Introductionmentioning

confidence: 99%

Synthesis of New Dynamic Movement Primitives Through Search in a Hierarchical Database of Example Movements

Deniša

Ude

2015

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

This paper presents a novel approach to discovering motor primitives in a hierarchical database of example trajectories. An initial set of example trajectories is obtained by human demonstration. The trajectories are clustered and organized in a binary tree-like hierarchical structure, from which transition graphs at different levels of granularity are constructed. A novel procedure for searching in this hierarchical structure is presented. It can exploit the interdependencies between movements and can discover new series of partial paths. From these partial paths, complete new movements are generated by encoding them as dynamic movement primitives. In this way, the number of example trajectories that must be acquired with the assistance of a human teacher can be reduced. By combining the results of the hierarchical search with statistical generalization techniques, a complete representation of new, not directly demonstrated, movement primitives can be generated.

show abstract

Online Segmentation and Clustering From Continuous Observation of Whole Body Motions

Abstract: Design of bilateral teleoperation controllers for haptic exploration and telemanipulation of soft environment," IEEE Trans.

Cited by 101 publications

References 28 publications

Probabilistic segmentation applied to an assembly task

Probabilistic segmentation applied to an assembly task

Robot learning from demonstration by constructing skill trees

Synthesis of New Dynamic Movement Primitives Through Search in a Hierarchical Database of Example Movements

Contact Info

Product

Resources

About