multi-target-track-using-a-single-agent
https://github.com/aanast01/multi-target-track-using-a-single-agent
Science Score: 67.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 1 DOI reference(s) in README -
✓Academic publication links
Links to: ieee.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (12.8%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: aanast01
- Language: MATLAB
- Default Branch: main
- Size: 802 KB
Statistics
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Multi-Castaway Tracking using an Autonomous Agent
This repository contains MATLAB code for implementing a multi-target tracking and following system using a single agent and optimization via the Gurobi solver. The goal of the system is to have the agent follow all targets while maintaining the lowest uncertainty of each target's location
Getting Started
Prerequisites
- MATLAB (Tested with version R2022b)
- Gurobi Optimizer (Tested with version 9.5.2)
Installation
- Clone or download the repository to your local machine
- Add the repository folder to the MATLAB path (either permanently or temporarily for the current session)
- Set up the Gurobi MATLAB Interface. Refer to the Gurobi documentation for more information on how to do this.
Usage
- Run the script main.m to begin the simulation. The script will then simulate the agent following the targets.
Inputs
- targetgroundtruth: Ground truth paths of the targets (see castaway ground truth folder)
- agentinitposition: Initial position of the agent [x,y,z].
Outputs
Single .mat file containing: - The agent's path - The agent's control vector
You can use the output .mat file with the renderedPlot.m file to for a 3D visualization of the whole simulation.
Methodology
The system uses optimization to determine the best control vector for the agent to follow the targets while maintaining the lowest uncertainty for each target's location. The optimization problem is formulated and solved using Gurobi.
Limitations
The current implementation has the following limitations: - Only a single agent is considered in the simulation. - The simulation does not account for object avoidance.
Future Work
Future work on this project could include: - Incorporating multiple agents in the simulation.
Citation
Acknowledgements
This work is funded by the Cyprus Research and Innovation Foundation under Grant Agreement EXCELLENCE/ 0421/0586 (GLIMPSE), by the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 739551 (KIOS CoE), and from the Government of the Republic of Cyprus through the Cyprus Deputy Ministry of Research, Innovation and Digital Policy.
Author
Contact
For any questions or feedback, please contact me via email: aanast01@ucy.ac.cy
Owner
- Login: aanast01
- Kind: user
- Repositories: 1
- Profile: https://github.com/aanast01
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - family-names: "Anastasiou" given-names: "Andreas" orcid: "https://orcid.org/0000-0003-2899-8522" title: "Multi-target track and follow using a single UAV agent" version: 1.0.0 date-released: 2023-12-05 url: "https://github.com/aanast01/Multi-target-track-and-follow-using-a-single-agent"