Active Sensing with Predictive Coding and Uncertainty Minimization

TL;DR

This paper introduces a biologically inspired active sensing approach combining predictive coding and uncertainty minimization, enabling autonomous exploration and efficient visual scene categorization in complex environments.

Contribution

It presents a novel, task-independent exploration method based on biological principles, demonstrating improved data efficiency and interpretability in visual exploration tasks.

Findings

Successfully discovers environmental transition distributions and features.

Builds unsupervised representations for efficient scene categorization.

Achieves superior data efficiency and learning speed over baselines.

Abstract

We present an end-to-end procedure for embodied exploration inspired by two biological computations: predictive coding and uncertainty minimization. The procedure can be applied to exploration settings in a task-independent and intrinsically driven manner. We first demonstrate our approach in a maze navigation task and show that it can discover the underlying transition distributions and spatial features of the environment. Second, we apply our model to a more complex active vision task, where an agent actively samples its visual environment to gather information. We show that our model builds unsupervised representations through exploration that allow it to efficiently categorize visual scenes. We further show that using these representations for downstream classification leads to superior data efficiency and learning speed compared to other baselines while maintaining lower parameter complexity. Finally, the modularity of our model allows us to probe its internal mechanisms and analyze the interaction between perception and action during exploration.