Learning Riemannian Manifolds for Geodesic Motion Skills

Hadi Beik-mohammadi (Bosch Center for Artificial Intelligence),
Soren Hauberg (TU Denmark),
Georgios Arvanitidis (MPI for Intelligent Systems, Tübingen),
Gerhard Neumann (Karlsruhe Institute of Technology),
Leonel Rozo (Bosch Center for Artificial Intelligence)
Paper Website
Paper #082
Interactive Poster Session V Interactive Poster Session VIII

0d 00h 00m

0d 00h 00m


For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly. This demands learning models that capture relevant motion patterns, while offering enough flexibility to adapt the encoded skills to new requirements, such as dynamic obstacle avoidance. We introduce a Riemannian manifold perspective on this problem, and propose to learn a Riemannian manifold from human demonstrations on which geodesics are natural motion skills. We realize this with a variational autoencoder (VAE) over the space of position and orientations of the robot end-effector. Geodesic motion skills let a robot plan movements from and to arbitrary points on the data manifold. They also provide a straightforward method to avoid obstacles by redefining the ambient metric in an online fashion. Moreover, geodesics naturally exploit the manifold resulting from multiple-solution settings to design motions that were not demonstrated previously. We test our learning framework using a 7-DoF robotic manipulator, where the robot satisfactorily learns and reproduces realistic skills featuring elaborated motion patterns, avoids previously–unseen obstacles, and generates novel movements in multiple-solution settings.

Spotlight Presentation

Previous Paper Paper Website Next Paper