Log In Sign Up

Self-Calibrating Active Binocular Vision via Active Efficient Coding with Deep Autoencoders

by   Charles Wilmot, et al.

We present a model of the self-calibration of active binocular vision comprising the simultaneous learning of visual representations, vergence, and pursuit eye movements. The model follows the principle of Active Efficient Coding (AEC), a recent extension of the classic Efficient Coding Hypothesis to active perception. In contrast to previous AEC models, the present model uses deep autoencoders to learn sensory representations. We also propose a new formulation of the intrinsic motivation signal that guides the learning of behavior. We demonstrate the performance of the model in simulations.


An active efficient coding model of the optokinetic nystagmus

Optokinetic nystagmus (OKN) is an involuntary eye movement responsible f...

Active Perception and Representation for Robotic Manipulation

The vast majority of visual animals actively control their eyes, heads, ...

Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Active Tasks

One of the ultimate promises of computer vision is to help robotic agent...

Exploitation of Image Statistics with Sparse Coding in the Case of Stereo Vision

The sparse coding algorithm has served as a model for early processing i...

SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency

In this paper, we explore how we can build upon the data and models of I...