@inproceedings {pub5652,
	title = {Learning Deep Dynamical Systems via Stable Neural ODEs},
	author = {Andreas Sochopoulos AND Michael Gienger AND Sethu Vijayakumar},
	year = {2024},
	month = {October},
	abstract = {Learning robust and intricate trajectories from
demonstrations in robotic tasks has been effectively addressed
through the utilization of Dynamical Systems (DS). State-of-
the-art DS learning methods ensure stability of the generated
trajectories however they have three shortcomings: a) the Ds
is assumed to have a single attractor, b) state derivative infor-
mation is assumed to be available in the learning process and
c) the state of the DS is assumed to be measurable at inference
time. We propose a class of provably stable latent DS with
possibly multiple attractors, that inherit the training methods
of Neural Ordinary Differential Equations, dropping thus the
dependency on state derivative information. A diffeomorphic
mapping for the output and a loss that captures time-invariant
trajectory similarity are proposed. We validate the efficacy
of our approach through experiments conducted on a public
dataset of handwritten shapes and within a simulated object
manipulation task.},
	publisher = {IEEE},
	url = {https://ieeexplore.ieee.org/document/10801826},
	booktitle = {IEEE International Conference on Intelligent Robots and Systems (IROS)}
}