RMPflow: A Computational Graph for Automatic Motion Policy Generation
Authors:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Real-Time Perception Meets Reactive Motion GenerationIEEE Robotics and Automation Letters, 2018
- Approximately optimal continuous-time motion planning and control via Probabilistic Inference2017
- DART: dense articulated real-time tracking with consumer depth camerasAutonomous Robots, 2015
- Virtual Impedance Control for Safe Human-Robot InteractionJournal of Intelligent & Robotic Systems, 2015
- Batch Informed Trees (BIT*): Sampling-based optimal planning via the heuristically guided search of implicit random geometric graphs2015
- Understanding the geometry of workspace obstacles in Motion Optimization2015
- Rigid Body Dynamics Algorithms2008
- A unifying framework for robot control with redundant DOFsAutonomous Robots, 2007
- A new perspective on the tracking control of nonlinear structural and mechanical systemsProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2003
- A unified approach for motion and force control of robot manipulators: The operational space formulationIEEE Journal on Robotics and Automation, 1987