Abstract | ||
---|---|---|
In this paper we propose a methodology for discovering new movement primitives in a database of example trajectories. The initial trajectory data, which is usually acquired from human demonstrations or by kinesthetic guiding, is clustered and organized into a binary tree, from which transition graphs at different levels of granularity are constructed. We show that new movements can be discovered by searching the transition graph, exploiting the interdependencies between the movements encoded by the graph. By connecting the results of the graph search with optimized interpolation and statistical generalization techniques, we can construct a complete representation for new movement primitives, which were not explicitly present in the original database of example trajectories. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-33926-4_21 | INTELLIGENT AUTONOMOUS SYSTEMS 12, VOL 1 |
Field | DocType | Volume |
Kinesthetic learning,Graph,State vector,Motor primitives,Computer science,Interpolation,Binary tree,Theoretical computer science,Granularity,Trajectory | Conference | 193 |
ISSN | Citations | PageRank |
2194-5357 | 1 | 0.38 |
References | Authors | |
14 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Miha Denisa | 1 | 4 | 2.26 |
Ales Ude | 2 | 898 | 85.11 |