Saved in:
Bibliographic Details
Main Authors: Logan, Zachary, Dudash, Andrew, Negrón, Daniel
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.20465
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915878181797888
author Logan, Zachary
Dudash, Andrew
Negrón, Daniel
author_facet Logan, Zachary
Dudash, Andrew
Negrón, Daniel
contents We present an open-source robotic framework that integrates computer vision and machine learning based inverse kinematics to enable low-cost laboratory automation tasks such as colony picking and liquid handling. The system uses a custom trained U-net model for semantic segmentation of microbial cultures, combined with Mixture Density Network for predicating joint angles of a simple 5-DOF robot arm. We evaluated the framework using a modified robot arm, upgraded with a custom liquid handling end-effector. Experimental results demonstrate the framework's feasibility for precise, repeatable operations, with mean positional error below 1 mm and joint angle prediction errors below 4 degrees and colony detection capabilities with IoU score of 0.537 and Dice coefficient of 0.596.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20465
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An Open Source Computer Vision and Machine Learning Framework for Affordable Life Science Robotic Automation
Logan, Zachary
Dudash, Andrew
Negrón, Daniel
Robotics
We present an open-source robotic framework that integrates computer vision and machine learning based inverse kinematics to enable low-cost laboratory automation tasks such as colony picking and liquid handling. The system uses a custom trained U-net model for semantic segmentation of microbial cultures, combined with Mixture Density Network for predicating joint angles of a simple 5-DOF robot arm. We evaluated the framework using a modified robot arm, upgraded with a custom liquid handling end-effector. Experimental results demonstrate the framework's feasibility for precise, repeatable operations, with mean positional error below 1 mm and joint angle prediction errors below 4 degrees and colony detection capabilities with IoU score of 0.537 and Dice coefficient of 0.596.
title An Open Source Computer Vision and Machine Learning Framework for Affordable Life Science Robotic Automation
topic Robotics
url https://arxiv.org/abs/2603.20465