Name
Title | ||
|---|---|---|
Representation and constrained planning of manipulation strategies in the context of Programming by Demonstration |
Abstract | ||
|---|---|---|
In Programming by Demonstration, a flexible representation of manipulation motions is necessary to learn and generalize from human demonstrations. In contrast to subsymbolic representations of trajectories, e.g. based on a Gaussian Mixture Model, a partially symbolic representation of manipulation strategies based on a temporal satisfaction problem with domain constraints is developed. By using constrained motion planning and a geometric constraint representation, generalization to different robot systems and new environments is achieved. In order to plan learned manipulation strategies the RRT-based algorithm by Stilman et al. is extended to consider, that multiple sets of constraints are possible during the extension of the search tree. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/ROBOT.2010.5509959 | ICRA |
Keywords | Field | DocType |
strategic planning,search tree,path planning,motion planning,optimization,gaussian mixture model,planning,programming,gaussian processes,trajectory | Programming by demonstration,Computer science,Control engineering,Theoretical computer science,Artificial intelligence,Gaussian process,Strategic planning,Trajectory,Automatic programming,Motion planning,Mixture model,Machine learning,Search tree | Conference |
Volume | Issue | ISSN |
2010 | 1 | 1050-4729 |
Citations | PageRank | References |
20 | 0.95 | 9 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rainer Jäkel | 1 | 63 | 5.99 |
| Sven R. Schmidt-Rohr | 2 | 103 | 8.80 |
| Martin Lösch | 3 | 82 | 6.35 |
| Rüdiger Dillmann | 4 | 2201 | 262.95 |