papers

Publications (62)

cs.AI2017

Decoupled Learning of Environment Characteristics for Safe Exploration

Pieter Van Molle, Tim Verbelen, Steven Bohez +3

Reinforcement learning is a proven technique for an agent to learn a task. However, when learning a task using reinforcement learning, the agent cannot distinguish the characterist…

cs.LG2024

From pixels to planning: scale-free active inference

Karl Friston, Conor Heins, Tim Verbelen +7

This paper describes a discrete state-space model -- and accompanying methods -- for generative modelling. This model generalises partially observed Markov decision processes to in…

cs.RO2020

Learning to Catch Piglets in Flight

Ozan Çatal, Lawrence De Mol, Tim Verbelen +1

Catching objects in-flight is an outstanding challenge in robotics. In this paper, we present a closed-loop control system fusing data from two sensor modalities: an RGB-D camera a…

cs.AI2023

Learning Spatial and Temporal Hierarchies: Hierarchical Active Inference for navigation in Multi-Room Maze Environments

Daria de Tinguy, Toon Van de Maele, Tim Verbelen +1

Cognitive maps play a crucial role in facilitating flexible behaviour by representing spatial and conceptual relationships within an environment. The ability to learn and infer the…

cs.RO2024

Representing Positional Information in Generative World Models for Object Manipulation

Stefano Ferraro, Pietro Mazzaglia, Tim Verbelen +2

Object manipulation capabilities are essential skills that set apart embodied agents engaging with the world, especially in the realm of robotics. The ability to predict outcomes o…

cs.AI2023

Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels

Sai Rajeswar, Pietro Mazzaglia, Tim Verbelen +4

Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but require large amounts of interactions between the…

cs.SD2020

Rhythm, Chord and Melody Generation for Lead Sheets using Recurrent Neural Networks

Cedric De Boom, Stephanie Van Laere, Tim Verbelen +1

Music that is generated by recurrent neural networks often lacks a sense of direction and coherence. We therefore propose a two-stage LSTM-based model for lead sheet generation, in…

cs.LG2021

A learning gap between neuroscience and reinforcement learning

Samuel T. Wauthier, Pietro Mazzaglia, Ozan Çatal +3

Historically, artificial intelligence has drawn much inspiration from neuroscience to fuel advances in the field. However, current progress in reinforcement learning is largely foc…

q-bio.NC2024

Bridging Cognitive Maps: a Hierarchical Active Inference Model of Spatial Alternation Tasks and the Hippocampal-Prefrontal Circuit

Toon Van de Maele, Bart Dhoedt, Tim Verbelen +1

Cognitive problem-solving benefits from cognitive maps aiding navigation and planning. Previous studies revealed that cognitive maps for physical space navigation involve hippocamp…

cs.RO2021

LatentSLAM: unsupervised multi-sensor representation learning for localization and mapping

Ozan Çatal, Wouter Jansen, Tim Verbelen +2

Biologically inspired algorithms for simultaneous localization and mapping (SLAM) such as RatSLAM have been shown to yield effective and robust robot navigation in both indoor and…

q-bio.NC2025

Active inference and artificial reasoning

Karl Friston, Lancelot Da Costa, Alexander Tschantz +4

This technical note considers the sampling of outcomes that provide the greatest amount of information about the structure of underlying world models. This generalisation furnishes…

cs.LG2018

Privacy Aware Offloading of Deep Neural Networks

Sam Leroux, Tim Verbelen, Pieter Simoens +1

Deep neural networks require large amounts of resources which makes them hard to use on resource constrained devices such as Internet-of-things devices. Offloading the computations…

cs.NE2023

Active Inference in Hebbian Learning Networks

Ali Safa, Tim Verbelen, Lars Keuninckx +5

This work studies how brain-inspired neural ensembles equipped with local Hebbian plasticity can perform active inference (AIF) in order to control dynamical agents. A generative m…

cs.LG2022

The Free Energy Principle for Perception and Action: A Deep Learning Perspective

Pietro Mazzaglia, Tim Verbelen, Ozan Çatal +1

The free energy principle, and its corollary active inference, constitute a bio-inspired theory that assumes biological agents act to remain in a restricted set of preferred states…

cs.SE2022

Software Engineering Practices for Machine Learning

Peter Kriens, Tim Verbelen

In the last couple of years we have witnessed an enormous increase of machine learning (ML) applications. More and more program functions are no longer written in code, but learnt…

cs.LG2019

Bayesian policy selection using active inference

Ozan Çatal, Johannes Nauta, Tim Verbelen +2

Learning to take actions based on observations is a core requirement for artificial agents to be able to be successful and robust at their task. Reinforcement Learning (RL) is a we…

cs.RO2023

FMCW Radar Sensing for Indoor Drones Using Learned Representations

Ali Safa, Tim Verbelen, Ozan Catal +4

Frequency-modulated continuous-wave (FMCW) radar is a promising sensor technology for indoor drones as it provides range, angular as well as Doppler-velocity information about obst…

cs.LG2022

Curiosity-Driven Exploration via Latent Bayesian Surprise

Pietro Mazzaglia, Ozan Catal, Tim Verbelen +1

The human intrinsic desire to pursue knowledge, also known as curiosity, is considered essential in the process of skill acquisition. With the aid of artificial curiosity, we could…

cs.RO2017

Sensor Fusion for Robot Control through Deep Reinforcement Learning

Steven Bohez, Tim Verbelen, Elias De Coninck +3

Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured s…

cs.RO2023

Object-Centric Scene Representations using Active Inference

Toon Van de Maele, Tim Verbelen, Pietro Mazzaglia +2

Representing a scene and its constituent objects from raw sensory data is a core ability for enabling robots to interact with their environment. In this paper, we propose a novel a…

cs.AI2025

Theory of Mind Using Active Inference: A Framework for Multi-Agent Cooperation

Riddhi J. Pitliya, Ozan Çatal, Toon Van de Maele +2

Theory of Mind (ToM) -- the ability to understand that others can have differing knowledge and goals -- enables agents to reason about others' beliefs while planning their own acti…

cs.RO2022

Fusing Event-based Camera and Radar for SLAM Using Spiking Neural Networks with Continual STDP Learning

Ali Safa, Tim Verbelen, Ilja Ocket +4

This work proposes a first-of-its-kind SLAM architecture fusing an event-based camera and a Frequency Modulated Continuous Wave (FMCW) radar for drone navigation. Each sensor is pr…

cs.AI2020

Deep Active Inference for Autonomous Robot Navigation

Ozan Çatal, Samuel Wauthier, Tim Verbelen +2

Active inference is a theory that underpins the way biological agent's perceive and act in the real world. At its core, active inference is based on the principle that the brain is…

q-bio.NC2023

Active Inference and Intentional Behaviour

Karl J. Friston, Tommaso Salvatori, Takuya Isomura +10

Recent advances in theoretical biology suggest that basal cognition and sentient behaviour are emergent properties of in vitro cell cultures and neuronal networks, respectively. Su…

cs.LG2022

Home Run: Finding Your Way Home by Imagining Trajectories

Daria de Tinguy, Pietro Mazzaglia, Tim Verbelen +1

When studying unconstrained behaviour and allowing mice to leave their cage to navigate a complex labyrinth, the mice exhibit foraging behaviour in the labyrinth searching for rewa…

cs.LG2018

Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations

Xander Steenbrugge, Sam Leroux, Tim Verbelen +1

In this work we explore the generalization characteristics of unsupervised representation learning by leveraging disentangled VAE's to learn a useful latent space on a set of relat…

cs.CV2016

Lazy Evaluation of Convolutional Filters

Sam Leroux, Steven Bohez, Cedric De Boom +5

In this paper we propose a technique which avoids the evaluation of certain convolutional filters in a deep neural network. This allows to trade-off the accuracy of a deep neural n…

cs.RO2024

Learning Dynamic Cognitive Map with Autonomous Navigation

Daria de Tinguy, Tim Verbelen, Bart Dhoedt

Inspired by animal navigation strategies, we introduce a novel computational model to navigate and map a space rooted in biologically inspired principles. Animals exhibit extraordi…

cs.RO2021

A Low-Complexity Radar Detector Outperforming OS-CFAR for Indoor Drone Obstacle Avoidance

Ali Safa, Tim Verbelen, Lars Keuninckx +5

As radar sensors are being miniaturized, there is a growing interest for using them in indoor sensing applications such as indoor drone obstacle avoidance. In those novel scenarios…

cs.LG2021

Dynamic Narrowing of VAE Bottlenecks Using GECO and L0 Regularization

Cedric De Boom, Samuel Wauthier, Tim Verbelen +1

When designing variational autoencoders (VAEs) or other types of latent space models, the dimensionality of the latent space is typically defined upfront. In this process, it is po…

cs.RO2023

FOCUS: Object-Centric World Models for Robotics Manipulation

Stefano Ferraro, Pietro Mazzaglia, Tim Verbelen +1

Understanding the world in terms of objects and the possible interplays with them is an important cognition ability, especially in robotics manipulation, where many tasks require r…

cs.AI2024

GenRL: Multimodal-foundation world models for generalization in embodied agents

Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt +2

Learning generalist embodied agents, able to solve multitudes of tasks in different domains is a long-standing problem. Reinforcement learning (RL) is hard to scale up as it requir…

cs.AI2023

Integrating cognitive map learning and active inference for planning in ambiguous environments

Toon Van de Maele, Bart Dhoedt, Tim Verbelen +1

Living organisms need to acquire both cognitive maps for learning the structure of the world and planning mechanisms able to deal with the challenges of navigating ambiguous enviro…

cs.RO2025

Navigation and Exploration with Active Inference: from Biology to Industry

Daria de Tinguy, Tim Verbelen, Bart Dhoedt

By building and updating internal cognitive maps, animals exhibit extraordinary navigation abilities in complex, dynamic environments. Inspired by these biological mechanisms, we p…

cs.RO2022

Learning to SLAM on the Fly in Unknown Environments: A Continual Learning Approach for Drones in Visually Ambiguous Scenes

Ali Safa, Tim Verbelen, Ilja Ocket +4

Learning to safely navigate in unknown environments is an important task for autonomous drones used in surveillance and rescue operations. In recent years, a number of learning-bas…

cs.CV2023

Symmetry and Complexity in Object-Centric Deep Active Inference Models

Stefano Ferraro, Toon Van de Maele, Tim Verbelen +1

Humans perceive and interact with hundreds of objects every day. In doing so, they need to employ mental models of these objects and often exploit symmetries in the object's shape…

cs.LG2023

Supervised structure learning

Karl J. Friston, Lancelot Da Costa, Alexander Tschantz +10

This paper concerns structure learning or discovery of discrete generative models. It focuses on Bayesian model selection and the assimilation of training data or content, with a s…

cs.AI2024

Exploring and Learning Structure: Active Inference Approach in Navigational Agents

Daria de Tinguy, Tim Verbelen, Bart Dhoedt

Drawing inspiration from animal navigation strategies, we introduce a novel computational model for navigation and mapping, rooted in biologically inspired principles. Animals exhi…

cs.AI2024

Choreographer: Learning and Adapting Skills in Imagination

Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt +2

Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with the ability to control and influence the env…

cs.AI2021

Disentangling What and Where for 3D Object-Centric Representations Through Active Inference

Toon Van de Maele, Tim Verbelen, Ozan Catal +1

Although modern object detection and classification models achieve high accuracy, these are typically constrained in advance on a fixed train set and are therefore not flexible to…

cs.RO2025

Bio-Inspired Topological Autonomous Navigation with Active Inference in Robotics

Daria de Tinguy, Tim Verbelen, Emilio Gamba +1

Achieving fully autonomous exploration and navigation remains a critical challenge in robotics, requiring integrated solutions for localisation, mapping, decision-making and motion…

cs.RO2021

Towards bio-inspired unsupervised representation learning for indoor aerial navigation

Ni Wang, Ozan Catal, Tim Verbelen +2

Aerial navigation in GPS-denied, indoor environments, is still an open challenge. Drones can perceive the environment from a richer set of viewpoints, while having more stringent c…

cs.LG2022

Learning Generative Models for Active Inference using Tensor Networks

Samuel T. Wauthier, Bram Vanhecke, Tim Verbelen +1

Active inference provides a general framework for behavior and learning in autonomous agents. It states that an agent will attempt to minimize its variational free energy, defined…

cs.CV2025

Variational Bayes Gaussian Splatting

Toon Van de Maele, Ozan Catal, Alexander Tschantz +2

Recently, 3D Gaussian Splatting has emerged as a promising approach for modeling 3D scenes using mixtures of Gaussians. The predominant optimization method for these models relies…

cs.NE2017

Transfer Learning with Binary Neural Networks

Sam Leroux, Steven Bohez, Tim Verbelen +3

Previous work has shown that it is possible to train deep neural networks with low precision weights and activations. In the extreme case it is even possible to constrain the netwo…

cs.LG2019

A Survey on Distributed Machine Learning

Joost Verbraeken, Matthijs Wolting, Jonathan Katzy +3

The demand for artificial intelligence has grown significantly over the last decade and this growth has been fueled by advances in machine learning techniques and the ability to le…

cs.CV2018

Visualizing Convolutional Neural Networks to Improve Decision Support for Skin Lesion Classification

Pieter Van Molle, Miguel De Strooper, Tim Verbelen +3

Because of their state-of-the-art performance in computer vision, CNNs are becoming increasingly popular in a variety of fields, including medicine. However, as neural networks are…

cs.RO2024

Spatial and Temporal Hierarchy for Autonomous Navigation using Active Inference in Minigrid Environment

Daria de Tinguy, Toon van de Maele, Tim Verbelen +1

Robust evidence suggests that humans explore their environment using a combination of topological landmarks and coarse-grained path integration. This approach relies on identifiabl…

q-bio.NC2026

Schema-based active inference supports rapid generalization of experience and frontal cortical coding of abstract structure

Toon Van de Maele, Tim Verbelen, Dileep George +1

Schemas -- abstract relational structures that capture the commonalities across experiences -- are thought to underlie humans' and animals' ability to rapidly generalize knowledge,…

cs.LG2024

Contrastive Active Inference

Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt

Active inference is a unifying theory for perception and action resting upon the idea that the brain maintains an internal model of the world by minimizing free energy. From a beha…

cs.AI2024

Free Energy in a Circumplex Model of Emotion

Candice Pattisapu, Tim Verbelen, Riddhi J. Pitliya +2

Previous active inference accounts of emotion translate fluctuations in free energy to a sense of emotion, mainly focusing on valence. However, in affective science, emotions are o…

cs.CV2018

Learning to Grasp from a Single Demonstration

Pieter Van Molle, Tim Verbelen, Elias De Coninck +3

Learning-based approaches for robotic grasping using visual sensors typically require collecting a large size dataset, either manually labeled or by many trial and errors of a robo…

cs.RO2025

Towards smart and adaptive agents for active sensing on edge devices

Devendra Vyas, Nikola Pižurica, Nikola Milović +3

TinyML has made deploying deep learning models on low-power edge devices feasible, creating new opportunities for real-time perception in constrained environments. However, the ada…

cs.AI2025

AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models

Conor Heins, Toon Van de Maele, Alexander Tschantz +11

Current deep reinforcement learning (DRL) approaches achieve state-of-the-art performance in various domains, but struggle with data efficiency compared to human learning, which le…

cs.RO2025

Mobile Manipulation with Active Inference for Long-Horizon Rearrangement Tasks

Corrado Pezzato, Ozan Çatal, Toon Van de Maele +2

Despite growing interest in active inference for robotic control, its application to complex, long-horizon tasks remains untested. We address this gap by introducing a fully hierar…

cs.AI2024

Belief sharing: a blessing or a curse

Ozan Catal, Toon Van de Maele, Riddhi J. Pitliya +3

When collaborating with multiple parties, communicating relevant information is of utmost importance to efficiently completing the tasks at hand. Under active inference, communicat…

cs.RO2023

Learning to Navigate from Scratch using World Models and Curiosity: the Good, the Bad, and the Ugly

Daria de Tinguy, Sven Remmery, Pietro Mazzaglia +2

Learning to navigate unknown environments from scratch is a challenging problem. This work presents a system that integrates world models with curiosity-driven exploration for auto…

cs.CV2022

Disentangling Shape and Pose for Object-Centric Deep Active Inference Models

Stefano Ferraro, Toon Van de Maele, Pietro Mazzaglia +2

Active inference is a first principles approach for understanding the brain in particular, and sentient agents in general, with the single imperative of minimizing free energy. As…

cs.RO2026

Online Structure Learning and Planning for Autonomous Robot Navigation using Active Inference

Daria de tinguy, Tim Verbelen, Emilio Gamba +1

Autonomous navigation in unfamiliar environments requires robots to simultaneously explore, localise, and plan under uncertainty, without relying on predefined maps or extensive tr…

cs.CV2021

Fail-Safe Human Detection for Drones Using a Multi-Modal Curriculum Learning Approach

Ali Safa, Tim Verbelen, Ilja Ocket +3

Drones are currently being explored for safety-critical applications where human agents are expected to evolve in their vicinity. In such applications, robust people avoidance must…

cs.AI2023

Inferring Hierarchical Structure in Multi-Room Maze Environments

Daria de Tinguy, Toon Van de Maele, Tim Verbelen +1

Cognitive maps play a crucial role in facilitating flexible behaviour by representing spatial and conceptual relationships within an environment. The ability to learn and infer the…

cs.LG2020

Learning Perception and Planning with Deep Active Inference

Ozan Çatal, Tim Verbelen, Johannes Nauta +2

Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiment…