This Python package implements environments such as the sky and an AntWorld of vegetation, using simple-to-install python packages, e.g. NumPy and SciPy. These environments contain information that humans can or cannot detect but invertebrates definitely can (e.g. polarised light in the sky). This package also contains some examples of how to use the InvertPy package.
Python package that allows the development of agents that observe their environment with their sensors, process this information using their brain components and act-back in their environment. This is useful for closed-loop experiments as the actions of the agents can also change their environment and therefore affect their observations.
Python package that implements the environments where the agents can get their observations from. These are models of the sky, 3D object (e.g. vegetation), odour gradients, etc, that affect what the agents observe using their sensors. These environments are in abstract form and are rendered using the sensors of the agents, designed for invertebrate observations, which allows for more invertebrate-like stimulation.
Python package implementing a variety of simulations and animations related to tasks that invertebrates are put through. These simulations collect logs of the data produced during the task and also allow for visualisation of the resulting behaviour by matplotlib animations.
In order to be able to use this code, the required packages are listed below:
- Python 3.8
- NumPy >= 1.20.1
- SciPy >= 1.6.1
- Matplotlib >= 3.3.4
- InvertPy
In order to install the package and reproduce the results of the manuscript you need to clone the code, navigate to the main directory of the project, install the dependencies and finally the package itself. Here is an example code that installs the package:
- Clone this repo.
mkdir ~/src
cd ~/src
git clone https://github.com/InsectRobotics/InvertSy.git
cd InvertSy
- Install the required libraries.
-
using pip :
pip install -r requirements.txt
-
using conda :
conda env create -f environment.yml
-
- Install the package.
- using pip :
pip install .
- using conda :
conda install .
- using pip :
Note that the pip project might be needed for the above installation.
If you have any issues installing or using the package, you can report it here.
The code is written by Evripidis Gkanias.
Copyright © 2021, Insect robotics Group, Institute of Perception, Action and Behaviour, School of Informatics, the University of Edinburgh.