Clutter-Aware Spill-Free Liquid Transport via Learned Dynamics

TL;DR

This paper introduces a novel algorithm for spill-free liquid handling in cluttered environments by combining path planning, parameterization, and machine learning to extend maneuverability and ensure spill-free trajectories.

Contribution

It presents a new method integrating RRT* planning, path parameterization, and a transformer-based classifier to achieve spill-free liquid transport in complex settings.

Findings

Extended feasible solution space at least 3x larger than previous methods

Successfully validated in real-world obstacle-rich scenarios

Handles containers with various shapes and fill levels

Abstract

In this work, we present a novel algorithm to perform spill-free handling of open-top liquid-filled containers that operates in cluttered environments. By allowing liquid-filled containers to be tilted at higher angles and enabling motion along all axes of end-effector orientation, our work extends the reachable space and enhances maneuverability around obstacles, broadening the range of feasible scenarios. Our key contributions include: i) generating spill-free paths through the use of RRT* with an informed sampler that leverages container properties to avoid spill-inducing states (such as an upside-down container), ii) parameterizing the resulting path to generate spill-free trajectories through the implementation of a time parameterization algorithm, coupled with a transformer-based machine-learning model capable of classifying trajectories as spill-free or not. We validate our approach in real-world, obstacle-rich task settings using containers of various shapes and fill levels and demonstrate an extended solution space that is at least 3x larger than an existing approach.