Unbiased active inference for classical control
Active inference is a mathematical framework that originated in computational neuroscience.
Recently, it has been demonstrated as a promising approach for constructing goal-driven …
Recently, it has been demonstrated as a promising approach for constructing goal-driven …
Active inference for integrated state-estimation, control, and learning
This work presents an approach for control, state-estimation and learning model (hyper)
parameters for robotic manipulators. It is based on the active inference framework …
parameters for robotic manipulators. It is based on the active inference framework …
A novel adaptive controller for robot manipulators based on active inference
More adaptive controllers for robot manipulators are needed, which can deal with large
model uncertainties. This letter presents a novel active inference controller (AIC) as an …
model uncertainties. This letter presents a novel active inference controller (AIC) as an …
Multimodal vae active inference controller
C Meo, P Lanillos - 2021 IEEE/RSJ International Conference on …, 2021 - ieeexplore.ieee.org
Active inference, a theoretical construct inspired by brain processing, is a promising
alternative to control artificial agents. However, current methods do not yet scale to high …
alternative to control artificial agents. However, current methods do not yet scale to high …
Active inference in robotics and artificial agents: Survey and challenges
Active inference is a mathematical framework which originated in computational
neuroscience as a theory of how the brain implements action, perception and learning …
neuroscience as a theory of how the brain implements action, perception and learning …
Learning policies for continuous control via transition models
It is doubtful that animals have perfect inverse models of their limbs (eg, what muscle
contraction must be applied to every joint to reach a particular location in space). However …
contraction must be applied to every joint to reach a particular location in space). However …
Active inference or control as inference? A unifying view
Active inference (AI) is a persuasive theoretical framework from computational neuroscience
that seeks to describe action and perception as inference-based computation. However, this …
that seeks to describe action and perception as inference-based computation. However, this …
Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perception
P Lanillos, M van Gerven - arXiv preprint arXiv:2105.04261, 2021 - arxiv.org
Unlike robots, humans learn, adapt and perceive their bodies by interacting with the world.
Discovering how the brain represents the body and generates actions is of major importance …
Discovering how the brain represents the body and generates actions is of major importance …
Variational inference for predictive and reactive controllers
Active inference is a general framework for decision-making prominent neuroscience that
utilizes variational inference. Recent work in robotics adopted this framework for control and …
utilizes variational inference. Recent work in robotics adopted this framework for control and …
Deep active inference in control tasks
A Zelenov, V Krylov - 2021 International Conference on …, 2021 - ieeexplore.ieee.org
Modern robotic control tasks are usually solved by applying reinforcement learning
techniques. In this paper we show that deep active inference can be applied for creating …
techniques. In this paper we show that deep active inference can be applied for creating …