https://github.com/cimagroup/experimentst6.3.2_l1

This repository contains the experiments developed in the T6.3.2 of REXASI-PRO in Navground simulator.

https://github.com/cimagroup/experimentst6.3.2_l1

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (12.6%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

This repository contains the experiments developed in the T6.3.2 of REXASI-PRO in Navground simulator.

Basic Info
  • Host: GitHub
  • Owner: Cimagroup
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 167 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme

README.md

Experiments T6.3.2 - D6.3. Topology-based optimization of robot fleet behavior. Detection of stable topological patterns using persistent entropy

This repository contains data and experiments associated to "D6.3. Topology-based optimization of robot fleet behavior" performed for the European Project REXASI-PRO (REliable & eXplainable Swarm Intelligence for People with Reduced mObility) (HORIZON-CL4-HUMAN-01 programme under grant agreement n101070028), in concrete to subtask 6.3.2 and line 1. It has been created by the CIMAgroup research team at the University of Seville, Spain.

Repository structure

  • ExploratoryAnalysisWithouTopology Folder: It contains an exploratory analysis for behavior comparation.
  • RealScenarios Folder: It contains a realistic simulation environment for different scenarios: Cross and corridor.
  • T6-3-2-Experiments Folder: It contains the experiments that have developed for the specific purpose. It contains a folder for Cross Scenario and another one for Corridor Scenario. Each of them contains different notebooks, for different behaviors, comparing them, and for predicting collisions. In this folder, it is also a folder called IlustrationDeliverable, where images for the deliverable have been created.
  • TrajectoryAnalysis Folder: It contains experiments analyzing robot trajectories and their relation with collisions.
  • Twoormoretypeagents: It contains a simulation example with two type of agents.
  • function.py: Contains some functions that are useful and will be used in the rest of files.

Usage

1) Clone this repository and create a virtual enviromment:

bash python3 -m venv entorno python=3.10.12

2) Activate the virtual enviromment:

bash source entorno/bin/activate

3) Install Navground (we have used version 0.3.3, so using other version may vary or produces error):

bash pip install navground[all]

4) Install the necessary dependencies:

bash pip install jupyter notebook matplotlib scipy multiprocess gudhi plotly scikit-learn pandas ripser seaborn tqdm

Ok, you can now run experiments! :)

Note: In case of issues doing that in WSL, reinstall using the following distribution and reinstall Navground with the steps mentioned earlier:

  1. Remove the entire Ubuntu distribution: wsl --unregister distribution

  2. Install the WSL distribution: wsl --install -d Ubuntu-22.04

  3. sudo apt-get update

  4. wsl --set-default-version 2

Owner

  • Name: Combinatorial Image Analysis research group
  • Login: Cimagroup
  • Kind: organization

GitHub Events

Total
  • Public event: 1
Last Year
  • Public event: 1