Uncertainty-aware Planning with Inaccurate Models for Robotized Liquid Handling

TL;DR

This paper introduces an uncertainty-aware Monte Carlo Tree Search algorithm that improves robotic liquid pouring by accounting for model inaccuracies, leading to more reliable planning even with limited training data.

Contribution

It presents a novel uncertainty-aware MCTS method that biases planning towards actions with lower uncertainty, enhancing robustness in liquid handling tasks.

Findings

Improved success rates in liquid pouring with minimal training data

Outperforms traditional planning methods in uncertain conditions

Demonstrates robustness in real-world robotic liquid handling

Abstract

Physics-based simulations and learning-based models are vital for complex robotics tasks like deformable object manipulation and liquid handling. However, these models often struggle with accuracy due to epistemic uncertainty or the sim-to-real gap. For instance, accurately pouring liquid from one container to another poses challenges, particularly when models are trained on limited demonstrations and may perform poorly in novel situations. This paper proposes an uncertainty-aware Monte Carlo Tree Search (MCTS) algorithm designed to mitigate these inaccuracies. By incorporating estimates of model uncertainty, the proposed MCTS strategy biases the search towards actions with lower predicted uncertainty. This approach enhances the reliability of planning under uncertain conditions. Applied to a liquid pouring task, our method demonstrates improved success rates even with models trained on minimal data, outperforming traditional methods and showcasing its potential for robust decision-making in robotics.