RMPflow: A Geometric Framework for Generation of Multi-Task Motion Policies

TL;DR

RMPflow is a geometric framework that synthesizes multi-task robot motion policies by transforming and combining Riemannian Motion Policies, enabling reactive, stable, and efficient motion generation in complex environments.

Contribution

The paper introduces RMPflow, a novel algorithm that geometrically combines task-specific RMPs into a global policy with stability guarantees and computational efficiency.

Findings

RMPflow effectively handles cluttered environments with high degrees of freedom.

The geometric approach simplifies complex motion planning problems.

Experimental results demonstrate improved stability and responsiveness.

Abstract

Generating robot motion for multiple tasks in dynamic environments is challenging, requiring an algorithm to respond reactively while accounting for complex nonlinear relationships between tasks. In this paper, 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 that parameterize non-Euclidean behaviors as dynamical systems in intrinsically nonlinear task spaces. Given a set of RMPs designed for individual tasks, RMPflow can combine these 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 natural Riemannian geometry of task policies can simplify classically difficult problems, such as planning through clutter on high-DOF manipulation systems.