Geometry-aware manipulability learning, tracking, and transfer

Jaquier, Noémie; Rozo, Leonel; Caldwell, Darwin G; Calinon, Sylvain

doi:10.1177/0278364920946815

Back

Journal article

Geometry-aware manipulability learning, tracking, and transfer

Jaquier, Noémie ORCID Idiap Research Institute, Martigny, Switzerland
Rozo, Leonel Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genova, Italy
Caldwell, Darwin G Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genova, Italy
Calinon, Sylvain Idiap Research Institute, Martigny, Switzerland

2020-8-24

Published in:

The International Journal of Robotics Research. - SAGE Publications. - 2020, p. 027836492094681

Electrical and Electronic Engineering

English Body posture influences human and robot performance in manipulation tasks, as appropriate poses facilitate motion or the exertion of force along different axes. In robotics, manipulability ellipsoids arise as a powerful descriptor to analyze, control, and design the robot dexterity as a function of the articulatory joint configuration. This descriptor can be designed according to different task requirements, such as tracking a desired position or applying a specific force. In this context, this article presents a novel manipulability transfer framework, a method that allows robots to learn and reproduce manipulability ellipsoids from expert demonstrations. The proposed learning scheme is built on a tensor-based formulation of a Gaussian mixture model that takes into account that manipulability ellipsoids lie on the manifold of symmetric positive-definite matrices. Learning is coupled with a geometry-aware tracking controller allowing robots to follow a desired profile of manipulability ellipsoids. Extensive evaluations in simulation with redundant manipulators, a robotic hand and humanoids agents, as well as an experiment with two real dual-arm systems validate the feasibility of the approach.

Language