RMPflow: A Computational Graph for Automatic Motion Policy Generation
This work addresses motion policy generation for robotics, offering a novel method that is incremental in improving geometric consistency and efficiency.
The paper tackles the problem of generating motion policies for robots by introducing RMPflow, a computational graph that combines Riemannian Motion Policies (RMPs) to create expressive global policies with computational efficiency, and demonstrates its effectiveness in simplifying tasks like planning through clutter on high-DOF manipulation systems.
We develop a novel policy synthesis algorithm, RMPflow, based on geometrically consistent transformations of Riemannian Motion Policies (RMPs). RMPs are a class of reactive motion policies designed to parameterize non-Euclidean behaviors as dynamical systems in intrinsically nonlinear task spaces. Given a set of RMPs designed for individual tasks, RMPflow can consistently combine these local policies to generate an expressive global policy, while simultaneously exploiting sparse structure for computational efficiency. We study the geometric properties of RMPflow and provide sufficient conditions for stability. Finally, we experimentally demonstrate that accounting for the geometry of task policies can simplify classically difficult problems, such as planning through clutter on high-DOF manipulation systems.