Joint Learning of Unsupervised Object-Based Perception and Control

This paper is concerned with object-based perception control (OPC), which allows for joint optimization of hierarchical object-based perception and decision making. We define the OPC framework by extending the Bayesian brain hypothesis to support object-based latent representations and propose an unsupervised end-to-end solution method. We develop a practical algorithm and analyze the convergence of the perception model update. Experiments on a high-dimensional pixel environment justify the learning effectiveness of our object-based perception control approach.