Active-Inference

AiMTT aims to cultivate a highly skilled and diverse AI talent pool equipped to address the opportunities and challenges of AI in mobility, transport, and logistics. By combining real-world case studies with knowledge development, this initiative fosters deep expertise in the field.

This talk presents a principled mathematical framework for deriving information-seeking behavior in intelligent agents, grounded in Bayesian inference and the free energy principle.

We present the design of an autoregressive active inference agent in the form of message passing on a factor graph.

CONTACT-AI aims to transform legged robots into contact-rich explorers, where legs are used to walk but also to cautiously manipulate the environment to resolve ambiguities in visual perception and navigate unknown terrain.

Gaussian approximations to nonlinear observation functions hat are sensitive to curvature, such as a second-order Taylor approximation, produce a state-dependent ambiguity term in expected free energy minimization.

We propose an adaptive model-predictive controller that balances driving the system to a goal state and seeking system observations that are informative with respect to the parameters of a nonlinear autoregressive exogenous model.

Design of an intelligent autonomous system for quadrupedal robot locomotion using Active Inference (AIF). AIF is a neuroscience-based framework of perception and action, and could bring us closer to how animals learn to walk.

Computation in biological brain tissue consumes several orders of magnitude less power than silicon-based systems. Motivated by this fact, this project aims to develop the world’s first hybrid neuro-in-silico Artificial Intelligence (AI) computer.