Data

Tools

Indexes

Applications

Experiments

Open Source Science

cnn_bayes_swarm

https://github.com/adamslab-ub/cnn_bayes_swarm

Science Score: 44.0%

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
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.3%) to scientific vocabulary
Last synced: 8 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: adamslab-ub
  • Language: Python
  • Default Branch: master
  • Size: 3.07 MB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created 10 months ago · Last pushed 10 months ago
Metadata Files
Readme Citation

README.md

CNN-Bayes-Swarm

In this paper, we proposed a learning based real-time down-sampling method for swarm-search mission and validated its performance on the Bayes-Swarm algorithm for several environments. We designed input, output abstractions to use a Convolutional Neural Network (CNN) to intelligently down-sample the observations. The supplement associated with the paper can be found in the file Supplement.pdf

How to use the code:

Training:
    The folder train_env contains the codes to train a CNN architecture for real time down-sampling. To start the training, please run the file train_CNN.py <br/>
    The implementations of the functions "Generate Matrix" and "Nearest-Points" in Algorithm 1 of our paper are in the file "environment.py". <br/>
    You can change the number of robots and customize the robot trajectories in the file 'sample_trajectories.py' <br/>

Evaluation:
    The folder "test_env" contains the codes to evaluate the CNN down-sampler in the Bayes-Swarm algorithm in Env 2 of our paper. We have also provided the code implementations of other baseline down-samplers. 
    You can easily modify the signal source landscape in the source.py file

Citation:

Please cite our work if you find it useful.

Bhatt, A., Witter, J., KrishnaKumar, P., Paul, S., Chowdhury, S. "Learning-based Real-time Down-sampling for Scalable Decentralized Decision-Making in Swarm Search", Journal of Computing and Information Scince in Engineering (JCISE) (in press)

Owner

  • Name: ADAMS Lab
  • Login: adamslab-ub
  • Kind: user
  • Location: Buffalo, NY. USA
  • Company: University at Buffalo

Adaptive Design Algorithms, Models & Systems (ADAMS) Lab is directed by Dr. Souma Chowdhury, who is an Associate Professor of Mechanical and Aerospace Eng.

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: Bayes-Swarm-CNN
message: >-
  If you use this dataset, please cite it using the metadata
  from this file.
type: dataset
authors:
  - given-names: Aditya Bhatt
    email: abhatt4@buffalo.edu
    affiliation: ADAMS Lab
    orcid: 'https://orcid.org/0009-0005-0999-4413'
repository-code: 'https://github.com/adamslab-ub/CNN_Bayes_Swarm'

GitHub Events

Total
  • Member event: 1
  • Push event: 4
  • Create event: 1
Last Year
  • Member event: 1
  • Push event: 4
  • Create event: 1