Active inference body perception and action for humanoid robots

Abstract

Providing artificial agents with the same computational models of biological systems is a way to understand how intelligent behaviours may emerge. We present an active inference body perception and action model working for the first time in a humanoid robot. The model relies on the free energy principle proposed for the brain, where both perception and action goal is to minimise the prediction error through gradient descent on the variational free energy bound. The body state (latent variable) is inferred by minimising the difference between the observed (visual and proprioceptive) sensor values and the predicted ones. Simultaneously, the action makes sensory data sampling to better correspond to the prediction made by the inner model. We formalised and implemented the algorithm on the iCub robot and tested in 2D and 3D visual spaces for online adaptation to visual changes, sensory noise and discrepancies between the model and the real robot. We also compared our approach with classical inverse kinematics in a reaching task, analysing the suitability of such a neuroscience-inspired approach for real-world interaction. The algorithm gave the robot adaptive body perception and upper body reaching with head object tracking (toddler-like), and was able to incorporate visual features online (in a closed-loop manner) without increasing the computational complexity. Moreover, our model predicted involuntary actions in the presence of sensorimotor conflicts showing the path for a potential proof of active inference in humans.

arXiv commentUnder review

References in corpus (7)

• A Novel Adaptive Controller for Robot Manipulators based on Active Inference
• Adaptive robot body learning and estimation through predictive coding
• End-to-End Pixel-Based Deep Active Inference for Body Perception and Action
• An active inference implementation of phototaxis
• Robots as Powerful Allies for the Study of Embodied Cognition from the Bottom Up
• Drifting perceptual patterns suggest prediction errors fusion rather than hypothesis selection: replicating the rubber-hand illusion on a robot
• Visual end-effector tracking using a 3D model-aided particle filter for humanoid robot platforms

Cited by in corpus (8)

• Robot in the mirror: toward an embodied computational model of mirror self-recognition
• Bayesian Mechanics for Stationary Processes
• Modeling motor control in continuous-time Active Inference: a survey
• Goal-directed Planning and Goal Understanding by Active Inference: Evaluation Through Simulated and Physical Robot Experiments
• On efficient computation in active inference
• Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation
• Towards Stochastic Fault-tolerant Control using Precision Learning and Active Inference
• Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perception