Abstract | ||
---|---|---|
This paper presents a method based on extreme learning machine to learn motions from human demonstrations. We model a motion as an autonomous dynamical system and define sufficient conditions to ensure the global stability at the target. A detailed theoretic analysis is proposed on the constraints regarding to input and output weights which yields a globally stable reproduction of demonstrations. We solve the corresponding optimization problem using nonlinear programming and evaluate it on an available data set and a real robot. Combined with the generalization capacities of extreme learning machine, the results show that the human movement strategies within demonstrations can be generalized well. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICInfA.2015.7279303 | 2015 IEEE International Conference on Information and Automation |
Keywords | Field | DocType |
Nonlinear dynamical system,Extreme learning machine,Stability analysis | Online machine learning,Control theory,Computer science,Extreme learning machine,Nonlinear programming,Robot kinematics,Input/output,Control engineering,Dynamical systems theory,Computational learning theory,Optimization problem | Conference |
Citations | PageRank | References |
1 | 0.36 | 14 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jianbing Hu | 1 | 24 | 2.62 |
zining yang | 2 | 1 | 0.36 |
Wang Zhiyang | 3 | 19 | 9.99 |
Xinyu Wu | 4 | 515 | 80.44 |
Yongsheng Ou | 5 | 243 | 42.32 |