Publications (62)
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…
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…
Learning to Catch Piglets in Flight
Ozan Ãatal, 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…
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…
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…
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…
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…
A learning gap between neuroscience and reinforcement learning
Samuel T. Wauthier, Pietro Mazzaglia, Ozan Ãatal +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…
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…
LatentSLAM: unsupervised multi-sensor representation learning for localization and mapping
Ozan Ãatal, 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…
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…
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…
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…
The Free Energy Principle for Perception and Action: A Deep Learning Perspective
Pietro Mazzaglia, Tim Verbelen, Ozan Ãatal +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…
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…
Bayesian policy selection using active inference
Ozan Ãatal, 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…
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…
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…
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…
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…
Theory of Mind Using Active Inference: A Framework for Multi-Agent Cooperation
Riddhi J. Pitliya, Ozan Ãatal, 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…
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…
Deep Active Inference for Autonomous Robot Navigation
Ozan Ãatal, 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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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,…
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…
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…
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…
Towards smart and adaptive agents for active sensing on edge devices
Devendra Vyas, Nikola Pižurica, Nikola MiloviÄ +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…
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…
Mobile Manipulation with Active Inference for Long-Horizon Rearrangement Tasks
Corrado Pezzato, Ozan Ãatal, 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…
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…
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…
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…
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…
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…
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…
Learning Perception and Planning with Deep Active Inference
Ozan Ãatal, 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…