An Energy-based Approach to Ensure the Stability of Learned Dynamical Systems

by   Matteo Saveriano, et al.
Leopold Franzens Universität Innsbruck

Non-linear dynamical systems represent a compact, flexible, and robust tool for reactive motion generation. The effectiveness of dynamical systems relies on their ability to accurately represent stable motions. Several approaches have been proposed to learn stable and accurate motions from demonstration. Some approaches work by separating accuracy and stability into two learning problems, which increases the number of open parameters and the overall training time. Alternative solutions exploit single-step learning but restrict the applicability to one regression technique. This paper presents a single-step approach to learn stable and accurate motions that work with any regression technique. The approach makes energy considerations on the learned dynamics to stabilize the system at run-time while introducing small deviations from the demonstrated motion. Since the initial value of the energy injected into the system affects the reproduction accuracy, it is estimated from training data using an efficient procedure. Experiments on a real robot and a comparison on a public benchmark shows the effectiveness of the proposed approach.


Learning Barrier Functions for Constrained Motion Planning with Dynamical Systems

Stable dynamical systems are a flexible tool to plan robotic motions in ...

Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems

Robotic tasks often require motions with complex geometric structures. W...

Stable Motion Primitives via Imitation and Contrastive Learning

Learning from humans allows non-experts to program robots with ease, low...

Incremental Skill Learning of Stable Dynamical Systems

Efficient skill acquisition, representation, and on-line adaptation to d...

Variational integration of learned dynamical systems

The principle of least action is one of the most fundamental physical pr...

Study of dynamical system based obstacle avoidance via manipulating orthogonal coordinates

In this paper, we consider the general problem of obstacle avoidance bas...

Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families

The correspondence between residual networks and dynamical systems motiv...

Please sign up or login with your details

Forgot password? Click here to reset