FLIP: Flowability-Informed Powder Weighing

2025-06-04

AI Summary

Laboratory robots face challenges in autonomous powder weighing due to high variability in powder flowability, complex physical interactions, and dynamic environmental conditions, leading to insufficient accuracy and poor generalization across materials and tasks. Method: This paper proposes a closed-loop “Perception–Simulation–Learning” framework. It introduces the angle of repose—a fundamental mechanical property of powders—as a quantitative flowability metric, integrated into Bayesian physics-informed simulation calibration and progressive curriculum learning. The approach unifies granular mechanics modeling, physics-engine-based simulation optimization, Bayesian inference, and real-time robotic control. Contribution/Results: Experiments demonstrate a mean weighing error of 2.12 ± 1.53 mg in real-world settings—significantly outperforming domain randomization and other baselines. The method exhibits strong generalization to unseen highly cohesive powders and novel target masses, enabling material-specific simulation modeling and robust policy transfer.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Autonomous manipulation of powders remains a significant challenge for robotic automation in scientific laboratories. The inherent variability and complex physical interactions of powders in flow, coupled with variability in laboratory conditions necessitates adaptive automation. This work introduces FLIP, a flowability-informed powder weighing framework designed to enhance robotic policy learning for granular material handling. Our key contribution lies in using material flowability, quantified by the angle of repose, to optimise physics-based simulations through Bayesian inference. This yields material-specific simulation environments capable of generating accurate training data, which reflects diverse powder behaviours, for training `robot chemists'. Building on this, FLIP integrates quantified flowability into a curriculum learning strategy, fostering efficient acquisition of robust robotic policies by gradually introducing more challenging, less flowable powders. We validate the efficacy of our method on a robotic powder weighing task under real-world laboratory conditions. Experimental results show that FLIP with a curriculum strategy achieves a low dispensing error of 2.12 +- 1.53 mg, outperforming methods that do not leverage flowability data, such as domain randomisation (6.11 +- 3.92 mg). These results demonstrate FLIP's improved ability to generalise to previously unseen, more cohesive powders and to new target masses.

Problem

• Enhancing robotic powder handling with flowability-informed learning
• Optimizing simulations via Bayesian inference for material-specific training
• Reducing powder dispensing errors in real-world lab conditions

Innovation

• Uses flowability-informed Bayesian simulation optimization
• Integrates flowability into curriculum learning strategy
• Achieves low dispensing error with cohesive powders