A deep active inference model of the rubber-hand illusion
This work addresses how the body adapts to uncertain situations, specifically for understanding perception and action in neuroscience and robotics, but it is incremental as it applies an existing method to a new domain.
The researchers tackled the problem of modeling sensorimotor conflicts in the rubber-hand illusion (RHI) using a deep active inference agent, and the result was that their model produced perceptual and force patterns similar to humans, accounting for involuntary forces observed in experiments.
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.