ReMoSPLAT: Reactive Mobile Manipulation Control on a Gaussian Splat

TL;DR

ReMoSPLAT introduces a reactive control method for mobile manipulators that uses Gaussian Splat representations for obstacle avoidance, enabling effective navigation in cluttered environments without complex planning.

Contribution

The paper presents a novel quadratic program-based reactive controller leveraging Gaussian Splat for collision avoidance in mobile manipulation tasks.

Findings

Achieves real-time obstacle avoidance in cluttered scenes

Performs comparably to controllers with perfect environment knowledge

Demonstrates effectiveness in both simulation and real-world tests

Abstract

Reactive control can gracefully coordinate the motion of the base and the arm of a mobile manipulator. However, incorporating an accurate representation of the environment to avoid obstacles without involving costly planning remains a challenge. In this work, we present ReMoSPLAT, a reactive controller based on a quadratic program formulation for mobile manipulation that leverages a Gaussian Splat representation for collision avoidance. By integrating additional constraints and costs into the optimisation formulation, a mobile manipulator platform can reach its intended end effector pose while avoiding obstacles, even in cluttered scenes. We investigate the trade-offs of two methods for efficiently calculating robot-obstacle distances, comparing a purely geometric approach with a rasterisation-based approach. Our experiments in simulation on both synthetic and real-world scans demonstrate the feasibility of our method, showing that the proposed approach achieves performance comparable to controllers that rely on perfect ground-truth information.