Learning Orbitally Stable Systems for Diagrammatically Teaching

TL;DR

This paper introduces SDDT, a framework enabling robots to learn and execute cyclic motions based on user-drawn sketches, by modeling motions as stable dynamical systems and optimizing their limit cycles.

Contribution

The paper proposes a novel method to teach robots cyclic motions through diagrammatic sketches by modeling motions as orbitally stable systems and optimizing their limit cycles.

Findings

High accuracy in teaching complex cyclic motions

Effective in simulation and on real quadruped robot

Theoretically analyzes stability and behavior of learned systems

Abstract

Diagrammatic Teaching is a paradigm for robots to acquire novel skills, whereby the user provides 2D sketches over images of the scene to shape the robot's motion. In this work, we tackle the problem of teaching a robot to approach a surface and then follow cyclic motion on it, where the cycle of the motion can be arbitrarily specified by a single user-provided sketch over an image from the robot's camera. Accordingly, we contribute the Stable Diffeomorphic Diagrammatic Teaching (SDDT) framework. SDDT models the robot's motion as an Orbitally Asymptotically Stable (O.A.S.) dynamical system that learns to stablize based on a single diagrammatic sketch provided by the user. This is achieved by applying a \emph{diffeomorphism}, i.e. a differentiable and invertible function, to morph a known O.A.S. system. The parameterised diffeomorphism is then optimised with respect to the Hausdorff distance between the limit cycle of our modelled system and the sketch, to produce the desired robot motion. We provide novel theoretical insight into the behaviour of the optimised system and also empirically evaluate SDDT, both in simulation and on a quadruped with a mounted 6-DOF manipulator. Results show that we can diagrammatically teach complex cyclic motion patterns with a high degree of accuracy.