Searched for: subject%3A%22active%255C%2Binference%22
(1 - 20 of 25)

Pages

List view
Grid view
document
Benist, Bram (author)
This master thesis introduces Hierarchical Active Inference Control (HAIC) as a control method for nonholonomic systems. This method only requires tuning of a minimal number of hyperparameters and has a relative low computation load. HAIC is based on recent research done in the application of the neuroscientific theory of Active Inference for...
master thesis 2023
document
Anil Meera, A. (author)
The potential impact of a grand unified theory of the brain on the robotics community might be immense, as it might hold the key to the general artificial intelligence. Such a theory might make revolutionary leaps in robot intelligence by improving the quality of our lives. The last two decades have witnessed the rise of one such brain theory -...
doctoral thesis 2023
document
Pezzato, C. (author), Hernández, Carlos (author), Bonhof, S.D. (author), Wisse, M. (author)
In this article, we propose a hybrid combination of active inference and behavior trees (BTs) for reactive action planning and execution in dynamic environments, showing how robotic tasks can be formulated as a free-energy minimization problem. The proposed approach allows handling partially observable initial states and improves the...
journal article 2023
document
Jousma, Sjoerd (author)
This thesis is inspired by Active Inference to contribute to its improvement in the Robotics work field. However, the results and applications of this thesis are useful in a broader perspective, namely in any field that makes use of derivatives and the forecasting of a time-series signal. The goal of this study is to determine a new approach for...
master thesis 2022
document
Mâachou, Mohammed (author)
Achieving human-like action planning requires profound reasoning and context-awareness capabilities. It is especially true for autonomous robotic mobile manipulation in dynamic environments. In the case of component failure, the autonomous robotic system requires reliable adaptation capabilities combined with a consistent understanding of the...
master thesis 2022
document
Meijers, Willem (author)
The autonomy of mobile robots has been greatly improved in recent decades. For these robots, the field of search and rescue is of particular interest. This thesis introduces a new method to let a mobile robot (Spot by Boston Dynamics) explore and search for victims in unknown environments. Existing methods include coverage, which aims to fully...
master thesis 2022
document
van der Meer, Bob (author)
Active Inference control is a novel control method based on the free energy principle, which combines action, perception and learning [1][2]. The first Active Inference controller showed promising results on a 7-DOF robot arm for a pick and placing task, however it took nearly six seconds to converge which is too slow [2]. This thesis aims to...
master thesis 2022
document
Anil Meera, A. (author), Novicky, Filip (author), Parr, Thomas (author), Friston, Karl (author), Lanillos, Pablo (author), Sajid, Noor (author)
Computational models of visual attention in artificial intelligence and robotics have been inspired by the concept of a saliency map. These models account for the mutual information between the (current) visual information and its estimated causes. However, they fail to consider the circular causality between perception and action. In other...
journal article 2022
document
Veldhuis, Erik (author)
This research proposes a new differentiator for estimating higher order derivatives of an input signal. The main reason why higher order derivatives are necessary is that Active Inference makes use of generalized coordinates. This means that it keeps internally track of higher order temporal derivatives of states, inputs and measurements. The...
master thesis 2021
document
Bos, Fred (author)
The free energy principle is a recent theory that originates from the neuroscience. It provides a unified framework that combines action perception and learning in the human brain. This research aims to implement the perception aspect of the free energy principle into robotics. This is achieved via the dynamic expectation maximisation (DEM)...
master thesis 2021
document
meo, cristian (author)
Active inference, a theoretical construct inspired by brain processing, is a promising approach to control artificial agents. Here we present a novel multimodal active inference torque controller for industrial arms that improves the adaptive characteristics of previous active inference approaches but also enables multimodal integration with any...
master thesis 2021
document
Deken, Mitchel (author)
Active inference is a novel brain theory based on the free energy principle, stating that every organism, in order to stay alive, minimizes a certain free energy. This theory is being translated into robot control, hoping to mimic the capabilities of the brain. Research in this field of robotics is still quite young, and active inference has yet...
master thesis 2021
document
Coehoorn, Jesse (author)
The Free Energy Principle, which underlies Active Inference (AI), is a way to explain human perception and behaviour. Previous literature has hinted at a relation between AI and Linear-Quadratic Gaussian (LQG) control, the latter being a textbook controller. AI and LQG are, however, defined with different settings in mind: LQG has access to...
master thesis 2021
document
Daniel Noel, Alejandro (author)
Intelligent agents must pursue their goals in complex environments with partial information and often limited computational capacity. Reinforcement learning methods have achieved great success by creating agents that optimize engineered reward functions, but which often struggle to learn in sparse-reward environments, generally require many...
master thesis 2021
document
Pancham, Naresh (author)
Active inference is a neuroscientific theory, which states that all living systems (e.g. the human brain) minimize a quantity termed the free energy. By minimizing this free energy, living systems keep an accurate representation of the world in their internal model (learning), are provided with an optimal way of acting on the world (action...
master thesis 2021
document
van Vucht, Victor (author)
Active inference is a method for state estimation and control actions that is based on the Free Energy principle, which explains how biological agents infer the state of their environment and act upon it by maintaining a model of that environment and evaluating predictions. This method merges both action and sensory processing and is therefore a...
master thesis 2021
document
Baioumy, Mohamed (author), Pezzato, C. (author), Ferrari, Riccardo M.G. (author), Hernández, Carlos (author), Hawes, Nick (author)
This work presents a novel fault-tolerant control scheme based on active inference. Specifically, a new formulation of active inference which, unlike previous solutions, provides unbiased state estimation and simplifies the definition of probabilistically robust thresholds for fault-tolerant control of robotic systems using the free-energy. The...
conference paper 2021
document
Hijne, Iris (author)
This thesis is a contribution to the research on Active Inference for Robotics. Active Inference is an intricate, intriguing theory from neuroscience, a field in which it has already gained a greater following and popularity. This theory, based on the underlying Free Energy Principle, provides a unified account of perception, action and learning...
master thesis 2020
document
van Roessel, L. (author)
Active inference is a process theory arising from neuroscience which casts perception, action, planning and learning under one optimisation criterion: minimisation of free energy. Current literature on the implementation of discrete state-space active inference focuses on scalability, the comparison to reinforcement learning and its performance...
master thesis 2020
document
Pezzato, C. (author), Ferrari, Riccardo M.G. (author), Hernández, Carlos (author)
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 adaptive control scheme for industrial robots. This scheme is easily scalable to high degrees-of-freedom, and it maintains high performance even in the presence of...
journal article 2020
Searched for: subject%3A%22active%255C%2Binference%22
(1 - 20 of 25)

Pages

List view
Grid view