Learning robot motions with stable dynamical systems under diffeomorphic transformations

104 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Benchmark for Skill Learning from Demonstration: Impact of User Experience, Task Complexity, and Start Configuration on Performance (2019, background): “This behavior is in fact expected for all LfD approaches which learn first-order dynamical systems from demonstrations [2], [4]–[6].”
Learning position and orientation dynamics from demonstrations via contraction analysis (2018, methodology): “5, the qualitative performance of SEDS, CLF-DM(WSAQF),andCDSPalgorithmsonasimpleshape ( Angle ) and a more complex shape ( SharpC )) are shown.”
Learning Partially Contracting Dynamical Systems from Demonstrations (2017, methodology): “More specifically, as pointed out in [32], CLF-DM has the disadvantage of solving a separate optimization problem for parameter selection of the control Lyapunov function, which can lead to numerical stability issues in parameter selection.”
Fast diffeomorphic matching to learn globally asymptotically stable nonlinear dynamical systems (2016, unknown): “We evaluated our approach on the LASA Handwriting Dataset, similarly to [3, 4, 6].”
Recent Advances in Robot Learning from Demonstration (2020, methodology): “For instance, numerous dynamical-systems-based trajectory-learning methods provide strong convergence guarantees (70, 78, 80, 82, 99).”