AEGIS: Assay-Aware Protocol Validation and Runtime Monitoring for Open-Source Liquid Handling Robots

2026-07-17

AI Summary

This work addresses the critical gap in reliability for open-source liquid handling robots—such as the Opentrons OT-2—which lack mechanisms to detect semantic protocol errors and runtime physical failures like leaks, bubbles, or missing tips. The authors propose the first end-to-end reliability assurance framework: a two-tiered system where the first layer combines a structured experimental rulebase with a large language model (LLM) to pre-validate protocol compliance, and the second layer employs a cascade of YOLO-based object detection, a PCA-driven world model, and a vision-language model (VLM) to monitor pipetting operations in real time and identify anomalies. Evaluated on a real OT-2 platform, the system achieves a protocol validation F1 score of 0.97, runtime monitoring average precision of 0.89 and F1 of 0.71, 100% detection of missing-tip faults, perfect recall (5/5) for partial dispensing errors, and a per-board hardware cost of only $1.63.

Abstract

Self-driving laboratories increasingly rely on low-cost liquid handlers such as the Opentrons OT-2, which ship without the pressure-based aspiration monitoring of Hamilton or Tecan systems and are typically run open-loop. Two failure modes go undetected: protocols that are syntactically valid but violate assay-specific invariants (e.g., tip reuse between a PCR template and a no-template control), and physical execution failures (partial dispense, air bubbles, missing tips) at runtime. We present AEGIS, a two-layer guardian for both. Layer 1 pairs a curated machine-readable assay rule database with an LLM that reasons over OT-2 Python code, reaching an adjusted F1 of 0.97 on a 24-protocol benchmark across five assay families and beating rules-only and LLM-only ablations across five backends; a free open-weight model ties the best proprietary one, so no paid API is required. Layer 2 fits a PCA world model to YOLO-cropped four-frame pipette trajectories; under a leakage-free leave-one-plate-out evaluation it reaches average precision 0.89 and operating-point F1 0.71 (AUROC 0.80), a deployment-faithful number that matches the live demonstration, and we characterize the small-pipette (p20) resolution limit (F1 0.47). A live demonstration on a physical OT-2 (five replicates per condition) catches planted no-tip failures deterministically and partial dispense on coloured dyes, with an always-VLM self-vote gate lifting partial-dispense recall to 5/5; transparent water is a principled limit of any front-view-only monitor, which AEGIS surfaces as low-confidence VLM reasoning rather than a wrong verdict. Cascade triage holds VLM cost near $1.63 per plate versus $10.33 for an always-VLM baseline. AEGIS is open source and, to our knowledge, the first system to unify pre-flight assay-aware validation with runtime visual monitoring for an open-source liquid handler.

Problem

• liquid handling robots
• assay validation
• runtime monitoring
• failure detection
• open-source automation

Innovation

• assay-aware validation
• runtime monitoring
• liquid handling robot
• large language model
• visual anomaly detection