Learning Stable Dynamical Systems for Visual Servoing

TL;DR

This paper integrates imitation learning based on dynamical systems with visual servoing to enable adaptable, skill-rich robotic control that can learn from demonstrations and respond to environmental changes.

Contribution

It introduces a framework combining dynamical systems and visual servoing, allowing robots to learn skills from few demonstrations and adapt to environment variations.

Findings

Simulations validate the effectiveness of the combined approach.

Experiments demonstrate real-world applicability with a robot manipulator.

The method improves adaptability and skill transfer in robotic control.

Abstract

This work presents the dual benefit of integrating imitation learning techniques, based on the dynamical systems formalism, with the visual servoing paradigm. On the one hand, dynamical systems allow to program additional skills without explicitly coding them in the visual servoing law, but leveraging few demonstrations of the full desired behavior. On the other, visual servoing allows to consider exteroception into the dynamical system architecture and be able to adapt to unexpected environment changes. The beneficial combination of the two concepts is proven by applying three existing dynamical systems methods to the visual servoing case. Simulations validate and compare the methods; experiments with a robot manipulator show the validity of the approach in a real-world scenario.