Geometry-aware manipulability learning, tracking, and transfer

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 novelmanipulability transferframework, 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.

Automated summary

This article introduces a novel manipulability transfer framework that allows robots to learn and reproduce manipulability ellipsoids from expert demonstrations, improving their performance in manipulation tasks. By considering the fact that manipulability ellipsoids lie on the manifold of symmetric positive-definite matrices and integrating a geometry-aware tracking controller, robots are able to follow the desired profile of manipulability ellipsoids effectively. Extensive evaluations in simulation and real experiments validate the feasibility of this approach with redundant manipulators, robotic hands, and humanoid agents.