COSMO: Contextualized Scene Modeling with Boltzmann Machines
This work addresses scene understanding for robotics, offering a novel integration of key components but is incremental in its extension of existing methods.
The paper tackles scene modeling for robots by adapting Boltzmann Machines to integrate objects, relations, and affordances into a generative model, achieving improved performance on tasks like object estimation and relation estimation compared to baselines.
Scene modeling is very crucial for robots that need to perceive, reason about and manipulate the objects in their environments. In this paper, we adapt and extend Boltzmann Machines (BMs) for contextualized scene modeling. Although there are many models on the subject, ours is the first to bring together objects, relations, and affordances in a highly-capable generative model. For this end, we introduce a hybrid version of BMs where relations and affordances are introduced with shared, tri-way connections into the model. Moreover, we contribute a dataset for relation estimation and modeling studies. We evaluate our method in comparison with several baselines on object estimation, out-of-context object detection, relation estimation, and affordance estimation tasks. Moreover, to illustrate the generative capability of the model, we show several example scenes that the model is able to generate.