AUTHOR=Andries Mihai , Dehban Atabak , Santos-Victor José TITLE=Automatic Generation of Object Shapes With Desired Affordances Using Voxelgrid Representation JOURNAL=Frontiers in Neurorobotics VOLUME=14 YEAR=2020 URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.00022 DOI=10.3389/fnbot.2020.00022 ISSN=1662-5218 ABSTRACT=

3D objects (artifacts) are made to fulfill functions. Designing an object often starts with defining a list of functionalities or affordances (action possibilities) that it should provide, known as functional requirements. Today, designing 3D object models is still a slow and difficult activity, with few Computer-Aided Design (CAD) tools capable to explore the design solution space. The purpose of this study is to explore shape generation conditioned on desired affordances. We introduce an algorithm for generating voxelgrid object shapes which afford the desired functionalities. We follow the principle form follows function, and assume that object forms are related to affordances they provide (their functions). First, we use an artificial neural network to learn a function-to-form mapping from a dataset of affordance-labeled objects. Then, we combine forms providing one or more desired affordances, generating an object shape expected to provide all of them. Finally, we verify in simulation whether the generated object indeed possesses the desired affordances, by defining and executing affordance tests on it. Examples are provided using the affordances contain-ability, sit-ability, and support-ability.