A deep active inference model of the rubber-hand illusion

by   Thomas Rood, et al.

Understanding how perception and action deal with sensorimotor conflicts, such as the rubber-hand illusion (RHI), is essential to understand how the body adapts to uncertain situations. Recent results in humans have shown that the RHI not only produces a change in the perceived arm location, but also causes involuntary forces. Here, we describe a deep active inference agent in a virtual environment, which we subjected to the RHI, that is able to account for these results. We show that our model, which deals with visual high-dimensional inputs, produces similar perceptual and force patterns to those found in humans.


End-to-End Pixel-Based Deep Active Inference for Body Perception and Action

We present a pixel-based deep Active Inference algorithm (PixelAI) inspi...

Tactile Roughness Perception of Virtual Gratings by Electrovibration

Realistic display of tactile textures on touch screens is a big step for...

Deep Active Inference for Partially Observable MDPs

Deep active inference has been proposed as a scalable approach to percep...

Active inference body perception and action for humanoid robots

One of the biggest challenges in robotics systems is interacting under u...

Active Perception with Neural Networks

Active perception has been employed in many domains, particularly in the...

Nonmodular architectures of cognitive systems based on active inference

In psychology and neuroscience it is common to describe cognitive system...

Deep Active Visual Attention for Real-time Robot Motion Generation: Emergence of Tool-body Assimilation and Adaptive Tool-use

Sufficiently perceiving the environment is a critical factor in robot mo...