An Energy-based Approach to Ensure the Stability of Learned Dynamical Systems
This work addresses the challenge of ensuring stability in learned dynamical systems for robotics and motion generation, representing an incremental improvement over existing methods.
The paper tackles the problem of learning stable and accurate motions for non-linear dynamical systems from demonstrations by introducing a single-step approach that works with any regression technique, using energy considerations to stabilize the system with small deviations from demonstrated motions, and shows effectiveness in experiments on a real robot and a public benchmark.
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.