Learning of operator hand movements via least angle regression to be teached in a manipulator
- 14 Downloads
In this document, a control system is developed to allow a manipulator to learn and plan references from demonstrations given by an operator hand. Data entry is acquired by a sensor and is learned by the generalized learning model with least angle regression to create a desired reference in three dimensional space. A fifth reference profile is employed to smooth the desired reference. Direct and inverse kinematics are gotten to represent the transformation between the three dimensional space and each of the manipulator links. A dynamic model is gotten using Newton–Euler formulation. An evolving proportional derivative (PD) control is applied to get that the manipulator end effector follows the operator hand movements. The monitoring and control systems are implemented in an embedded platform for testing purposes.
KeywordsManipulator Least angle regression Reference Kinematics Model Embedded platform
Authors thank the Editor in Chief, and reviewers for their valuable comments which let to improve this result. They thank the Instituto Politécnico Nacional, the Consejo Nacional de Ciencia y Tecnología, and Secretaría de Investigación y Posgrado for their support.
- Angelov P, Skrjanc I, Blazic S (2015) A robust evolving cloud-based controller. In: Springer Handbook of Computational Intelligence, Springer, pp 1435–1449Google Scholar
- Khamassi I, Sayed-Mouchaweh M, Hammami M, Ghedira K (2016) Discussion and review on evolving data streams and concept drift adapting. Evol Syst. https://doi.org/10.1007/s12530-016-9168-2
- Lughofer E (2016) Evolving fuzzy systems—fundamentals, reliability, interpretability and useability. In: Angelov P (ed) Handbook of computational intelligence. World Scientific, New York, pp 67–135Google Scholar
- Paramo Carranza LA, Meda Campaña JA, Rubio JJ, Tapia Herrera R, Curtidor Lopez AV, Grande Meza A, Cazares Ramirez I (2017) Discrete-time Kalman filter for Takagi–Sugeno fuzzy models. Evol Syst 8(3):211–219Google Scholar