Cargando…
Active Vision for Robot Manipulators Using the Free Energy Principle
Occlusions, restricted field of view and limited resolution all constrain a robot's ability to sense its environment from a single observation. In these cases, the robot first needs to actively query multiple observations and accumulate information before it can complete a task. In this paper,...
Autores principales: | Van de Maele, Toon, Verbelen, Tim, Çatal, Ozan, De Boom, Cedric, Dhoedt, Bart |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7973267/ https://www.ncbi.nlm.nih.gov/pubmed/33746730 http://dx.doi.org/10.3389/fnbot.2021.642780 |
Ejemplares similares
-
Embodied Object Representation Learning and Recognition
por: Van de Maele, Toon, et al.
Publicado: (2022) -
The Free Energy Principle for Perception and Action: A Deep Learning Perspective
por: Mazzaglia, Pietro, et al.
Publicado: (2022) -
Learning Generative State Space Models for Active Inference
por: Çatal, Ozan, et al.
Publicado: (2020) -
Model Reduction Through Progressive Latent Space Pruning in Deep Active Inference
por: Wauthier, Samuel T., et al.
Publicado: (2022) -
Computational Optimization of Image-Based Reinforcement Learning for Robotics
por: Ferraro, Stefano, et al.
Publicado: (2022)