figshare
Browse

Husky robot. Synthetic Data for the Paper “Semantic Priority Navigation for Energy-Aware Mining Robots”

Version 11 2025-09-07, 13:31
Version 10 2025-09-06, 03:11
Version 9 2025-08-16, 20:31
Version 8 2025-08-07, 17:01
Version 7 2025-08-07, 16:28
Version 6 2025-08-07, 14:56
Version 5 2025-08-07, 14:43
Version 4 2025-08-07, 14:35
Version 3 2025-08-07, 14:30
Version 2 2025-08-07, 14:26
Version 1 2025-08-07, 14:24
journal contribution
posted on 2025-09-07, 13:31 authored by Claudio Urrea OñateClaudio Urrea Oñate, Kevin Valencia-Aragón, John Kern
<p dir="ltr"><b>Title</b>: Synthetic data and figures for Semantic Priority Navigation for Energy-Aware Mining Robots<br><br><b>Description</b>:This dataset contains synthetic experimental metrics generated from load-haul-dump scenarios simulated in Gazebo using the Robot Operating System (ROS) and the Husky robot simulator. The data supports the research presented in the paper "SemanticPriority Navigation for EnergyAware Mining Robots in ROS" (to be published). It includes the following files:</p><p><br></p><ul><li><b>data.csv</b>: A comma-separated values file with experimental results. Columns include Run, Condition (ON/OFF for semantic perception), ObstacleClass (e.g., backpack, chair, person), TotalTime_s (total time in seconds), TotalEffort (effort units), MinDistance_m (minimum distance in meters), File (associated bag file name), and Trajectory (list of timestamp/x/y coordinates). This file is suitable for general analysis and visualization.</li><li><b>data.parquet</b> (optional): A Parquet-formatted version of the same dataset, offering efficient storage and faster read times for large-scale processing with tools like pandas or Apache Spark.</li></ul><p dir="ltr"><b>Usage</b>:</p><ol><li>Download data.csv for standard analysis in tools like Excel, Python (pandas), or R.</li><li>Use data.parquet for optimized performance in big data frameworks.</li><li>The data can be validated using scripts and figures available at the associated GitHub repository: <a href="https://github.com/ClaudioUrrea/husky" rel="noopener noreferrer nofollow" target="_blank">https://github.com/ClaudioUrrea/husky</a>.</li><li>Key findings include a 34% increase in high-risk clearance, zero collisions, a 2.1% rise in mission time, and a 5.8% increase in estimated battery draw compared to a geometry-only baseline.</li></ol><p dir="ltr"><b>License</b>:<br>This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).</p><p><br></p><p dir="ltr"><b>Associated Resources</b>:</p><ul><li>GitHub Repository: <a href="https://github.com/ClaudioUrrea/husky" rel="noopener noreferrer nofollow" target="_blank">https://github.com/ClaudioUrrea/husky</a> (contains scripts, configs, and figures for reproducibility).</li><li>Paper Reference: To be added by editorial staff during production.</li></ul><p dir="ltr"><b>Notes</b>:</p><ul><li>The data is synthetic, derived from Gazebo simulations, and involves no human or animal subjects.</li><li>For further details on methodology, refer to the associated paper and GitHub repository.</li></ul><p><br></p>

Funding

This research received no external funding.

History