Neural learning of stable dynamical systems based on data-driven Lyapunov candidates
By Klaus Neumann, Andre Lemme, Jochen J. Steil. 2013
61 citations recorded by the source corpus.
Subfields: Control and Systems Engineering, Mechanical Engineering, Statistical and Nonlinear Physics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Control and Systems Engineering
- Harish Chaandar Ravichandar
- Ashwin P. Dani
- Iman Salehi
- Jochen J. Steil
- Klaus Neumann
- René Felix Reinhart
- Andre Lemme
- Sonia Chernova
In Mechanical Engineering
In Statistical and Nonlinear Physics
Citations in the corpus
- Learning Partially Contracting Dynamical Systems from Demonstrations (2017, methodology): “Lyapunov-based LfD approaches that use various parametrization of Lyapunov function such as quadratic Lyapunov function (V (x) = xTx) [3], weighted sum of asymmetric quadratic functions (WSAQF) [13], and neurally-imprinted Lyapunov candidate (NILC) [14] are studied in the literature.”
- Neural learning of vector fields for encoding stable dynamical systems (2014, methodology): “A recently published study in [22] shows how to learn flexible Lyapunov candidates that can be used to enforce asymptotic stability for complex and robust motion generation in”
- Learning robot motions with stable dynamical systems under diffeomorphic transformations (2015, methodology): “Lyapunov candidates are constructed by the neurally imprinted Lyapunov candidate (NILC) approach introduced recently in [19].”
- Fast diffeomorphic matching to learn globally asymptotically stable nonlinear dynamical systems (2016, unknown): “Neumann et al. [5] compute a “Neurally Imprinted Lyapunov Candidate” (NILC) via quadratic programming, obtaining similar restrictions to that of WSAQF.”