Questa pagina è stata tradotta automaticamente dall'inglese. Visualizza l'originale in inglese.
Roboticists, AI researchers, embodied-cognition groups, and builders of autonomous instruments.
A research scaffold for embodied agents, active sensing, expected-free-energy control, and robotic learning.
In questa pagina
Robotics is a natural test bed for active inference because perception, planning, action, and uncertainty are coupled in the same physical loop, and action can be chosen both to accomplish goals and to improve the information available for future control.
Embodied systems must select actions that achieve goals and reduce uncertainty about objects, tasks, and operating conditions. Active inference makes the epistemic part of action selection explicit, unifying state estimation, control, and exploration under a single free-energy objective rather than bolting exploration onto a reward signal.
A modular report should track the robot body, sensor model, action policy, preferred outcomes, and evaluation environment separately, so a simulation result, a laboratory manipulator, and a field instrument are not collapsed into one claim. Recurring patterns include generative models of robot dynamics, expected-free-energy policy selection, active vision, hierarchical/hybrid controllers, and deep or contrastive active inference for high-dimensional control.
The next pass should gather adaptive-controller case studies, manipulation and navigation results, deep active-inference on real hardware, and benchmarks against reinforcement learning and classical control. Each record should state whether it is theory, simulation, hardware, or deployed instrumentation, and whether it scales beyond low-dimensional settings.
Christopher L. Buckley, Chang Sub Kim, Simon McGregor, Anil K. Seth (2017). The free energy principle for action and perception: A mathematical review. Journal of Mathematical Psychology. DOI: 10.1016/j.jmp.2017.09.004. Thomas Parr, Giovanni Pezzulo, Karl J. Friston (2022). Active Inference: The Free Energy Principle in Mind, Brain, and Behavior. MIT Press. Giovanni Pezzulo, Francesco Rigoli, Karl J. Friston (2017). Active Inference, homeostatic regulation and adaptive behavioural control. Progress in Neurobiology. DOI: 10.1016/j.pneurobio.2017.08.001. Pablo Lanillos, Cristian Meo, Corrado Pezzato, et al. (2021). Active Inference in Robotics and Artificial Agents: Survey and Challenges. arXiv. DOI: 10.48550/arXiv.2112.01871. Lancelot Da Costa, Thomas Parr, Noor Sajid, Sebastijan Veselic, Victorita Neacsu, Karl J. Friston (2020). Active inference on discrete state-spaces: A synthesis. Journal of Mathematical Psychology. DOI: 10.1016/j.jmp.2020.102447.
Superfici chiave
Use action to reduce uncertainty about objects, tasks, and operating conditions, not just to maximise reward.
Evaluate actions by expected outcomes and information gain via expected free energy minimization.
Track simulator, hardware, repository, and benchmark status separately for every claim.
Risorse correlate
I collegamenti esterni vengono risolti dal registro condiviso, quindi le destinazioni visibili ai visitatori rimangono centralizzate e verificabili.
Audience: Researcher
Public ecosystem shortlink for Institute context, projects, activities, and conceptual maps.
Audience: Developer
Public GitHub organization for Institute repositories and open-source work.
Audience: Developer
Project repository for multiagent Active Inference modeling work.
Audience: Developer
Generalized Notation Notation project repository for model communication.
Audience: Developer
Geospatial modeling repository connected to ecological and bioregional applications.
Audience: Researcher
Research and publication-oriented repository for the Active Inference Journal.
Audience: Contributor
Public Project Preparation shortlink for making proposed work legible and actionable.
Audience: Contributor
Public project measurement shortlink for reporting progress and outputs.
Audience: Researcher
Public Active Inference Ontology shortlink for shared conceptual infrastructure.
Audience: Researcher
External paper repository surfaced from the official research page.
Audience: Researcher
Reachable arXiv reference surfaced from the official research page.
Audience: Researcher
Reachable arXiv reference surfaced from the official research page.
Pagine ufficiali
Audience: Researcher
Official research entry point, currently resolving to the research overview.
Audience: Researcher
Official research overview page.
Audience: Developer
Official Knowledge Engineering page.
Audience: Developer
Official Active Blockference page.
Audience: Researcher
Official theoretical neurobiology page.
Audience: Contributor
Public projects shortlink for project directories and activity-linked work.
Audience: Contributor
Public project measurement shortlink for reporting progress and outputs.
Audience: Researcher
Public Active Inference Ontology shortlink for shared conceptual infrastructure.
Repositori
Audience: Researcher
Computational meta-analysis of Active Inference literature with nanopublication and knowledge-graph outputs.
Audience: Researcher
Ontology-oriented repository for shared Active Inference concepts and decentralized science knowledge infrastructure.
Audience: Developer
Notebook-based applied Active Inference work connected to blockchain-adjacent and generative modeling examples.
Audience: Developer
Python models and materials for ant-inspired multiagent Active Inference.
Audience: Researcher
Active Inference & Category Theory
Audience: Researcher
Public content repository for the Active Inference Journal and related publication infrastructure.
Audience: Researcher
Active Entity Ontology for Science
Audience: Developer
Public ants repository in the ActiveInferenceInstitute GitHub namespace.