no code implementations • 6 Mar 2024 • Ajith Anil Meera, Pablo Lanillos
To evaluate our theoretical account, we framed the decision-making within the tool selection problem, where the agent has to select the best robot arm for a particular control task.
no code implementations • 15 Aug 2023 • Ajith Anil Meera, Pablo Lanillos
The accurate estimation of the noise covariance matrix (NCM) in a dynamic system is critical for state estimation and control, as it has a major influence in their optimality.
no code implementations • 14 Jan 2023 • Tadahiro Taniguchi, Shingo Murata, Masahiro Suzuki, Dimitri Ognibene, Pablo Lanillos, Emre Ugur, Lorenzo Jamone, Tomoaki Nakamura, Alejandra Ciria, Bruno Lara, Giovanni Pezzulo
Therefore, in this paper, we clarify the definitions, relationships, and status of current research on these topics, as well as missing pieces of world models and predictive coding in conjunction with crucially related concepts such as the free-energy principle and active inference in the context of cognitive and developmental robotics.
1 code implementation • 25 Dec 2022 • Filip S. Slijkhuis, Sander W. Keemink, Pablo Lanillos
The neuroscience theory of Spike Coding Networks (SCNs) offers a fully analytical solution for implementing dynamical systems in recurrent spiking neural networks -- while maintaining irregular, sparse, and robust spiking activity -- but it's not clear how to directly apply it to control problems.
no code implementations • 16 Sep 2022 • Justus Huebotter, Serge Thill, Marcel van Gerven, Pablo Lanillos
It is doubtful that animals have perfect inverse models of their limbs (e. g., what muscle contraction must be applied to every joint to reach a particular location in space).
no code implementations • 28 Aug 2022 • Jonathan Bauermeister, Pablo Lanillos
The underlying processes that enable self-perception are crucial for understanding multisensory integration, body perception and action, and the development of the self.
1 code implementation • 13 Dec 2021 • Cristian Meo, Giovanni Franzese, Corrado Pezzato, Max Spahn, Pablo Lanillos
Adaptation to external and internal changes is major for robotic systems in uncertain environments.
no code implementations • 3 Dec 2021 • Pablo Lanillos, Cristian Meo, Corrado Pezzato, Ajith Anil Meera, Mohamed Baioumy, Wataru Ohata, Alexander Tschantz, Beren Millidge, Martijn Wisse, Christopher L. Buckley, Jun Tani
Active inference is a mathematical framework which originated in computational neuroscience as a theory of how the brain implements action, perception and learning.
no code implementations • 22 Sep 2021 • Justus F. Hübotter, Pablo Lanillos, Jakub M. Tomczak
In the experiments, we show that applying regularization on membrane potential and spiking output successfully avoids both dead and bursting neurons and significantly decreases the reconstruction error of the spiking auto-encoder.
no code implementations • 9 Sep 2021 • Daniel Burghardt, Pablo Lanillos
Knowing the position of the robot in the world is crucial for navigation.
1 code implementation • 9 Sep 2021 • Niels van Hoeffelen, Pablo Lanillos
Despite the potential of active inference for visual-based control, learning the model and the preferences (priors) while interacting with the environment is challenging.
no code implementations • 10 May 2021 • Pablo Lanillos, Marcel van Gerven
Unlike robots, humans learn, adapt and perceive their bodies by interacting with the world.
1 code implementation • 7 Mar 2021 • Cristian Meo, Pablo Lanillos
Active inference, a theoretical construct inspired by brain processing, is a promising alternative to control artificial agents.
no code implementations • 9 Nov 2020 • Matej Hoffmann, Shengzhi Wang, Vojtech Outrata, Elisabet Alzueta, Pablo Lanillos
Self-recognition or self-awareness is a capacity attributed typically only to humans and few other species.
1 code implementation • 8 Sep 2020 • Otto van der Himst, Pablo Lanillos
Deep active inference has been proposed as a scalable approach to perception and action that deals with large policy and state spaces.
1 code implementation • 17 Aug 2020 • Thomas Rood, Marcel van Gerven, Pablo Lanillos
Understanding how perception and action deal with sensorimotor conflicts, such as the rubber-hand illusion (RHI), is essential to understand how the body adapts to uncertain situations.
no code implementations • 11 Apr 2020 • Pablo Lanillos, Jordi Pages, Gordon Cheng
Self/other distinction and self-recognition are important skills for interacting with the world, as it allows humans to differentiate own actions from others and be self-aware.
1 code implementation • 28 Dec 2019 • Cansu Sancaktar, Marcel van Gerven, Pablo Lanillos
We present a pixel-based deep active inference algorithm (PixelAI) inspired by human body perception and action.
no code implementations • 25 Jun 2019 • Michael Deistler, Yagmur Yener, Florian Bergner, Pablo Lanillos, Gordon Cheng
In this work, we investigate the generation of tactile hallucinations on biologically inspired, artificial skin.
no code implementations • 24 Jun 2019 • Pablo Lanillos, Daniel Oliva, Anja Philippsen, Yuichi Yamashita, Yukie Nagai, Gordon Cheng
This survey presents the most relevant neural network models of autism spectrum disorder and schizophrenia, from the first connectionist models to recent deep network architectures.
no code implementations • 7 Jun 2019 • Guillermo Oliver, Pablo Lanillos, Gordon Cheng
We present an active inference body perception and action model working for the first time in a humanoid robot.
no code implementations • 15 Jan 2019 • German Diez-Valencia, Takuya Ohashi, Pablo Lanillos, Gordon Cheng
Artificial self-perception is the machine ability to perceive its own body, i. e., the mastery of modal and intermodal contingencies of performing an action with a specific sensors/actuators body configuration.
no code implementations • 27 Jul 2018 • Amir Rasouli, Pablo Lanillos, Gordon Cheng, John K. Tsotsos
In this paper, we propose a new model that actively extracts visual information via visual attention techniques and, in conjunction with a non-myopic decision-making algorithm, leads the robot to search more relevant areas of the environment.