Motion Planning to Cartesian Targets Leveraging Large-Scale Dynamic Roadmaps

Abstract

In this paper, we achieve reliable, sub-second motion planning to Cartesian end-effector targets in changing real-world environments for a high degree-of-freedom <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(\mathbf{12} + \mathbf{7}$</tex> DoF), redundant robot. Several recent works have tackled a subset of these challenges, leveraging innovations in optimization, deep learning, and/or intelligent sampling. However, deployment of robots in real-world environments demands reliably tackling all three challenges: changing environments, fast planning, and high DoF robots. In this work, we leverage (1) large-scale Dynamic Roadmaps (DRM) enabled through GPU-accelerated collision-checking, combined with (2) an optimization-based local inverse kinematics (IK) solver. The high-level principle behind our approach is to offload as much computation either offline or onto the GPU as possible in order to simplify and speed up online planning. Even in changing environments, this enables fast planning in configuration space to a neighborhood of a target pose(s) specified in Cartesian space, whereby the final connection to the target pose is made via a local IK solver. We ran several experiments in an unmodified real-world grocery store with this motion planner on a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{12} + \mathbf{7}$</tex> DoF mobile manipulation robot executing a grocery fulfillment task, achieving ≈0.3s average planning times with 100% success rate across 950 motion plans.