Hierarchy of GANs for learning embodied self-awareness model
This work addresses incremental self-awareness modeling for semi-autonomous vehicles, focusing on detecting abnormalities in complex environments.
The paper tackles the problem of learning hierarchical self-awareness models for embodied agents by introducing a cross-modal GANs approach that processes high-dimensional visual data, enabling self-supervised detection of model levels and demonstrating real experiments on semi-autonomous ground vehicles.
In recent years several architectures have been proposed to learn embodied agents complex self-awareness models. In this paper, dynamic incremental self-awareness (SA) models are proposed that allow experiences done by an agent to be modeled in a hierarchical fashion, starting from more simple situations to more structured ones. Each situation is learned from subsets of private agent perception data as a model capable to predict normal behaviors and detect abnormalities. Hierarchical SA models have been already proposed using low dimensional sensorial inputs. In this work, a hierarchical model is introduced by means of a cross-modal Generative Adversarial Networks (GANs) processing high dimensional visual data. Different levels of the GANs are detected in a self-supervised manner using GANs discriminators decision boundaries. Real experiments on semi-autonomous ground vehicles are presented.