# Robo-MLT reports 82% success on a lab robotics task

> Researchers describe a robot system that monitors laboratory workflows as it works and can replan after an operator removes a sample. It was tested in two tasks.

Oossa · 2026-11-11 · https://oossa.com/en/robo-mlt-reports-82-success-on-a-lab-robotics-task

Researchers introduced Robo-MLT, a system designed to help robots carry out medical laboratory workflows in the right order and recover when conditions change. It combines a workflow monitor with a learned system that generates physical actions.

In tests of blood gas analysis and blood sample tube sorting, Robo-MLT recorded success rates of 82% and 70%, respectively—30 and 22 percentage points above the π0.5 baseline. In a separate test, after an operator removed the sample the robot was handling, the system revised its plan and continued with the remaining samples.

## The facts

- The evaluation used 50 nominal configurations per method and 20 configurations involving sample removal.
- The paper was submitted to arXiv on November 9, 2026, and published there on November 11, 2026.

## Why it matters

For labs considering robotic automation, the reported recovery after sample removal suggests the system may handle one kind of interruption, but the results cover only the evaluated tasks and conditions.

## Sources & references

1. [Robo-MLT: Dual-System Robotic Manipulation for Long-Horizon Medical Laboratory Tasks](https://arxiv.org/abs/2611.13039) – arXiv cs.RO, 2026-11-11

Last updated: 2026-11-11