Abstract | ||
---|---|---|
This paper's intention is to adapt prediction algorithms well known in the field of time series analysis to problems being faced in the field of mobile robotics and Human-Robot-Interaction (HRI). The idea is to predict movement data by understanding it as time series. The prediction takes place with a black box model, which means that no further knowledge on motion dynamics is used then the past of the trajectory itself. This means, the suggested approaches are able to adapt to different situations. Several state-of-the-art algorithms such as Local Modeling, Cluster Weighted Modeling, Echo State Networks and Autoregressive Models are evaluated and compared. For experiments, real movement trajectories of a human are used. Since mobile robots highly depend on real-time application, computing time is also considered. Experiments show that Echo State Networks and Local Model show impressive results for long term motion prediction. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-642-03040-6_69 | Advances in Neuro-Information Processing |
Keywords | Field | DocType |
time series,time series analysis,human movement trajectories,mobile robotics,long term motion prediction,local modeling,local model,computing time,mobile robot,long term prediction,echo state networks,motion dynamic,human robot interaction,echo state network,autoregressive model | Autoregressive model,Time series,Long-term prediction,Computer science,Artificial intelligence,Cluster-weighted modeling,Black box,Trajectory,Mobile robot,Machine learning,Robotics | Conference |
Volume | ISSN | Citations |
5507 | 0302-9743 | 1 |
PageRank | References | Authors |
0.56 | 4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sven Hellbach | 1 | 63 | 9.77 |
Julian Eggert | 2 | 299 | 43.23 |
Edgar Körner | 3 | 424 | 48.91 |
Horst-Michael Gross | 4 | 761 | 92.05 |