Merge pull request #71 from gramaziokohler/55-add-references-to-docum…

…entation

#55 ref paper, improve README

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 * added a script and a component to merge datasets (#66)
+* reference to ARA paper
 
 ### Changed
 * fixed DataBool (#68)

README.md

@@ -8,7 +8,27 @@
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.14007759.svg)](https://doi.org/10.5281/zenodo.14007758)
 
 
-Grasshopper plugin for the AIXD toolkit.
+**Grasshopper plugin for data-driven and inverse design methods with generative AI.**
+
+
+**ARA** is a Grasshopper plugin that augments the design process with data-driven and inverse design approach by combining parametric models built in Grasshopper with generative AI models. It enables designers, architects and engineers to efficiently generate design solutions with the assistance of generative neural networks. The inverse design paradigm accelerates design exploration by providing many different design variants that match project objectives.
+
+With **ARA**, you can easily generate a project-specific the dataset from an existing parametric model definition in Grasshopper, and then train and deploy a custom autoencoder model to generate designs that satisfy the requested target values, such as performance metrics or design constraints.
+
+**ARA** also comes with various visualization tools for data analysis and performance evaluation.
+
+**ARA** is open-source and builds on top of the [AIXD: AI-eXtended Design toolkit](https://gitlab.renkulab.io/ai-augmented-design/aixd).
+
+## Getting started
+
+To get started, please have a look at the 
+[Easy Installation](https://gramaziokohler.github.io/aixd_ara/latest/installation.html), 
+[Tutorial](https://gramaziokohler.github.io/aixd_ara/latest/tutorial.html), 
+[Documentation](https://gramaziokohler.github.io/aixd_ara/latest/documentation.html) and 
+[Examples](https://gramaziokohler.github.io/aixd_ara/latest/examples.html),
+as well as our [paper](https://link.springer.com/chapter/10.1007/978-3-031-68275-9_19).
+
+
 
 ## Installation
 

docs/authors.rst

@@ -17,10 +17,33 @@ If you use **ARA** in your work, please cite it as:
 .. code-block:: text
     :caption: BibTeX
 
-    @misc{ara_2024,
+    @misc{ara_code_2024,
     title = {{ARA: Grasshopper plugin for data-driven and inverse design.}},
     author = {Apolinarska, Aleksandra Anna and Casas, Gonzalo and Salamanca, Luis},
     year = {2024},
     publisher = {GitHub},
     howpublished = {\url{https://github.com/gramaziokohler/aixd_ara}},
     }
+
+
+You can also cite the related publication, available `here <https://link.springer.com/chapter/10.1007/978-3-031-68275-9_19>`_: 
+
+
+.. code-block:: text
+    :caption: BibTeX
+
+    @InProceedings{ara_paper_2024,
+    title="ARA - Grasshopper Plugin for AI-Augmented Inverse Design",
+    author="Apolinarska, Aleksandra Anna and Casas, Gonzalo and Salamanca, Luis and Kohler, Matthias",
+    editor="Eversmann, Philipp and Gengnagel, Christoph and Lienhard, Julian and Ramsgaard Thomsen, Mette and Wurm, Jan",
+    booktitle="Scalable Disruptors",
+    year="2024",
+    publisher="Springer Nature Switzerland",
+    address="Cham",
+    pages="231--240",
+    isbn="978-3-031-68275-9",
+    doi={10.1007/978-3-031-68275-9_19},
+    url={https://doi.org/10.1007/978-3-031-68275-9_19}
+    }
+
+    

docs/index.rst

@@ -32,7 +32,6 @@ such as performance metrics or design constraints.
 
 **ARA** is open-source and builds on top of the `AIXD: AI-eXtended Design <https://aixd.ethz.ch>`_ toolkit. 
 
-
 .. attention::
 
    **ARA** was developed for Rhino 7 on Windows. It was not tested on other versions of Rhino or other operating systems.
@@ -53,7 +52,9 @@ In *inverse* design, the process is reversed: the designer specifies the desired
 In many cases, this is a one-to-many mapping, meaning that there are multiple design solutions that satisfy the target values. 
 Being able to obtain multiple equivalent solutions may be a valuable asset in the design process to explore different design alternatives.
 In **ARA**, the inverse design process is achieved by training a conditional (variational) autoencoder model - 
-a type of deep neural network (more details can be found `here <https://aixd.ethz.ch/docs/userguide/model.html>`_).
+a type of deep neural network (more details can be found `here <https://aixd.ethz.ch/docs/stable/userguide/model.html>`_).
+
+
 
 
 ----