arXiv subjects

Pieter Simoens

Publications and source records attributed to Pieter Simoens.

At least 19 recordsLinked to original sources

arXiv2026

Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents

This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents. Inspired by Overcooked, the suite comprises cooking scenarios that require temporal decision making. The tasks and reward functions are designed such that temporal information is unobserved yet critical for optimal performance. The environment is intentionally kept simple to enable controlled experiments and support biologically plausible models. Evaluation metrics are designed to expose limitations in timing abilities of RL agents, and we report baselines using a non-recurrent, a recurrent, and a biologically plausible model. This work ultimately aims to underscore the need to incorporate time perception and temporal processing in artificial agents designed for human robot interaction and deployment in time dependent human societies.

cs.AI↗

arXiv2026

Including the Cost of Irreducible Uncertainty in the Policy Compression Framework

AI decision-support systems can benefit from anticipating biases in human decision-making. Many such biases may arise from human cognitive limitations. The policy compression framework models decision-making as a trade-off between reward maximization and the cognitive cost of encoding state-dependent action policies, formalized as the mutual information between states and actions (policy complexity). We argue that this account is incomplete because it treats conditional entropy--the irreducible uncertainty about which action should be selected given a state--as costless, even though empirical evidence suggests that it modulates reaction times. We therefore extend the framework by defining cognitive cost as the sum of policy complexity and a weighted conditional-entropy term, governed by a new parameter, $\eta$. The resulting optimal policy retains the standard exponential form but becomes sharper as $\eta$ increases, allowing policy precision to vary more independently of reward sensitivity. This modification implies that the standard policy compression framework may underestimate the cognitive cost of action selection, and it has the potential to better account for biases in human decision-making. At the same time, it introduces additional complexity for fitting the model to human data, which future work will need to address.

q-bio.NC↗

arXiv2026

Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens

Self-supervised learning has emerged as a powerful paradigm for learning visual representations without manual annotations, yet most methods still operate on a single modality and therefore miss the complementary structure available from heterogeneous sensors. We present Le MuMo JEPA, a self-supervised framework that learns unified representations from RGB images and aligned companion modalities. In our driving experiments, the second modality is camera-aligned LiDAR depth; we also evaluate RGB-thermal training and transfer on the Teledyne FLIR ADAS benchmark. Our approach extends LeJEPA to the multi-modal setting by learning fusion tokens that act as a latent bottleneck between modality-specific patch stems inside a shared transformer. Our default model employs a pruned fusion strategy: after an initial cross-modal attention layer, modality-specific tokens are dropped, forcing cross-modal information into the shared fusion-token grid as an efficient latent bottleneck before Sketched Isotropic Gaussian Regularization (SIGReg) is applied to the joint multimodal CLS embedding. On Waymo, Le MuMo JEPA gives the strongest performance-efficiency trade-off on downstream patch probes among the from-scratch multimodal baselines, improving CenterNet detection and dense depth while remaining competitive on segmentation. Under from-scratch training on nuScenes, Le MuMo JEPA remains the strongest model, and it also gives the best FLIR results, especially after Waymo-initialized fine-tuning. It also retains the best overall accuracy-efficiency balance in our study at substantially lower compute, memory, and estimated training time.

cs.CV↗

arXiv2026

The Alignment Flywheel: A Governance-Centric Hybrid MAS for Architecture-Agnostic Safety

Multi-agent systems provide mature methodologies for role decomposition, coordination, and normative governance, capabilities that remain essential as increasingly powerful autonomous decision components are embedded within agent-based systems. While learned and generative models substantially expand system capability, their safety behavior is often entangled with training, making it opaque, difficult to audit, and costly to update after deployment. This paper formalizes the Alignment Flywheel as a governance-centric hybrid MAS architecture that decouples decision generation from safety governance. A Proposer, representing any autonomous decision component, generates candidate trajectories, while a Safety Oracle returns raw safety signals through a stable interface. An enforcement layer applies explicit risk policy at runtime, and a governance MAS supervises the Oracle through auditing, uncertainty-driven verification, and versioned refinement. The central engineering principle is patch locality: many newly observed safety failures can be mitigated by updating the governed oracle artifact and its release pipeline rather than retracting or retraining the underlying decision component. The architecture is implementation-agnostic with respect to both the Proposer and the Safety Oracle, and specifies the roles, artifacts, protocols, and release semantics needed for runtime gating, audit intake, signed patching, and staged rollout across distributed deployments. The result is a hybrid MAS engineering framework for integrating highly capable but fallible autonomous systems under explicit, version-controlled, and auditable oversight.

cs.MA↗

arXiv2026

Interactionless Inverse Reinforcement Learning: A Data-Centric Framework for Durable Alignment

AI alignment is growing in importance, yet many current approaches learn safety behavior by directly modifying policy parameters, entangling normative constraints with the underlying policy. This often yields opaque, difficult-to-edit alignment artifacts and reduces their reuse across models or deployments, a failure mode we term Alignment Waste. We propose Interactionless Inverse Reinforcement Learning, a framework for learning inspectable, editable, and reusable reward artifacts separately from policy optimization. We further introduce the Alignment Flywheel, a human-in-the-loop lifecycle for iteratively auditing, patching, and hardening these artifacts through automated evaluation and refinement. Together, these ideas recast alignment from a disposable training expense into a durable, verifiable engineering asset.

cs.LG↗

arXiv2026

Efficient On-Board Processing of Oblique UAV Video for Rapid Flood Extent Mapping

Effective disaster response relies on rapid disaster response, where oblique aerial video is the primary modality for initial scouting due to its ability to maximize spatial coverage and situational awareness in limited flight time. However, the on-board processing of high-resolution oblique streams is severely bottlenecked by the strict Size, Weight, and Power (SWaP) constraints of Unmanned Aerial Vehicles (UAVs). The computational density required to process these wide-field-of-view streams precludes low-latency inference on standard edge hardware. To address this, we propose Temporal Token Reuse (TTR), an adaptive inference framework capable of accelerating video segmentation on embedded devices. TTR exploits the intrinsic spatiotemporal redundancy of aerial video by formulating image patches as tokens; it utilizes a lightweight similarity metric to dynamically identify static regions and propagate their precomputed deep features, thereby bypassing redundant backbone computations. We validate the framework on standard benchmarks and a newly curated Oblique Floodwater Dataset designed for hydrological monitoring. Experimental results on edge-grade hardware demonstrate that TTR achieves a 30% reduction in inference latency with negligible degradation in segmentation accuracy (< 0.5% mIoU). These findings confirm that TTR effectively shifts the operational Pareto frontier, enabling high-fidelity, real-time oblique video understanding for time-critical remote sensing missions

cs.CV↗

arXiv2025

Ising Machines for Model Predictive Path Integral-Based Optimal Control

We present a sampling-based Model Predictive Control (MPC) method that implements Model Predictive Path Integral (MPPI) as an \emph{Ising machine}, suitable for novel forms of probabilistic computing. By expressing the control problem as a Quadratic Unconstrained Binary Optimization (QUBO) problem, we map MPC onto an energy landscape suitable for Gibbs sampling from an Ising model. This formulation enables efficient exploration of (near-)optimal control trajectories. We demonstrate that the approach achieves accurate trajectory tracking compared to a reference MPPI implementation, highlighting the potential of Ising-based MPPI for real-time control in robotics and autonomous systems.

eess.SY↗

arXiv2025

Privacy-Preserving Computer Vision for Industry: Three Case Studies in Human-Centric Manufacturing

The adoption of AI-powered computer vision in industry is often constrained by the need to balance operational utility with worker privacy. Building on our previously proposed privacy-preserving framework, this paper presents its first comprehensive validation on real-world data collected directly by industrial partners in active production environments. We evaluate the framework across three representative use cases: woodworking production monitoring, human-aware AGV navigation, and multi-camera ergonomic risk assessment. The approach employs learned visual transformations that obscure sensitive or task-irrelevant information while retaining features essential for task performance. Through both quantitative evaluation of the privacy-utility trade-off and qualitative feedback from industrial partners, we assess the framework's effectiveness, deployment feasibility, and trust implications. Results demonstrate that task-specific obfuscation enables effective monitoring with reduced privacy risks, establishing the framework's readiness for real-world adoption and providing cross-domain recommendations for responsible, human-centric AI deployment in industry.

cs.CV↗

arXiv2025

Modulation of temporal decision-making in a deep reinforcement learning agent under the dual-task paradigm

This study explores the interference in temporal processing within a dual-task paradigm from an artificial intelligence (AI) perspective. In this context, the dual-task setup is implemented as a simplified version of the Overcooked environment with two variations, single task (T) and dual task (T+N). Both variations involve an embedded time production task, but the dual task (T+N) additionally involves a concurrent number comparison task. Two deep reinforcement learning (DRL) agents were separately trained for each of these tasks. These agents exhibited emergent behavior consistent with human timing research. Specifically, the dual task (T+N) agent exhibited significant overproduction of time relative to its single task (T) counterpart. This result was consistent across four target durations. Preliminary analysis of neural dynamics in the agents' LSTM layers did not reveal any clear evidence of a dedicated or intrinsic timer. Hence, further investigation is needed to better understand the underlying time-keeping mechanisms of the agents and to provide insights into the observed behavioral patterns. This study is a small step towards exploring parallels between emergent DRL behavior and behavior observed in biological systems in order to facilitate a better understanding of both.

cs.AI↗

arXiv2025

In-Field Mapping of Grape Yield and Quality with Illumination-Invariant Deep Learning

This paper presents an end-to-end, IoT-enabled robotic system for the non-destructive, real-time, and spatially-resolved mapping of grape yield and quality (Brix, Acidity) in vineyards. The system features a comprehensive analytical pipeline that integrates two key modules: a high-performance model for grape bunch detection and weight estimation, and a novel deep learning framework for quality assessment from hyperspectral (HSI) data. A critical barrier to in-field HSI is the ``domain shift" caused by variable illumination. To overcome this, our quality assessment is powered by the Light-Invariant Spectral Autoencoder (LISA), a domain-adversarial framework that learns illumination-invariant features from uncalibrated data. We validated the system's robustness on a purpose-built HSI dataset spanning three distinct illumination domains: controlled artificial lighting (lab), and variable natural sunlight captured in the morning and afternoon. Results show the complete pipeline achieves a recall (0.82) for bunch detection and a $R^2$ (0.76) for weight prediction, while the LISA module improves quality prediction generalization by over 20% compared to the baselines. By combining these robust modules, the system successfully generates high-resolution, georeferenced data of both grape yield and quality, providing actionable, data-driven insights for precision viticulture.

cs.CV↗

arXiv2025

Emergent time-keeping mechanisms in a deep reinforcement learning agent performing an interval timing task

Drawing parallels between Deep Artificial Neural Networks (DNNs) and biological systems can aid in understanding complex biological mechanisms that are difficult to disentangle. Temporal processing, an extensively researched topic, is one such example that lacks a coherent understanding of its underlying mechanisms. In this study, we investigate temporal processing in a Deep Reinforcement Learning (DRL) agent performing an interval timing task and explore potential biological counterparts to its emergent behavior. The agent was successfully trained to perform a duration production task, which involved marking successive occurrences of a target interval while viewing a video sequence. Analysis of the agent's internal states revealed oscillatory neural activations, a ubiquitous pattern in biological systems. Interestingly, the agent's actions were predominantly influenced by neurons exhibiting these oscillations with high amplitudes and frequencies corresponding to the target interval. Parallels are drawn between the agent's time-keeping strategy and the Striatal Beat Frequency (SBF) model, a biologically plausible model of interval timing. Furthermore, the agent maintained its oscillatory representations and task performance when tested on different video sequences (including a blank video). Thus, once learned, the agent internalized its time-keeping mechanism and showed minimal reliance on its environment to perform the timing task. A hypothesis about the resemblance between this emergent behavior and certain aspects of the evolution of biological processes like circadian rhythms, has been discussed. This study aims to contribute to recent research efforts of utilizing DNNs to understand biological systems, with a particular emphasis on temporal processing.

q-bio.NC↗

arXiv2025

Cognitive Effort in the Two-Step Task: An Active Inference Drift-Diffusion Model Approach

High-level theories rooted in the Bayesian Brain Hypothesis often frame cognitive effort as the cost of resolving the conflict between habits and optimal policies. In parallel, evidence accumulator models (EAMs) provide a mechanistic account of how effort arises from competition between the subjective values of available options. Although EAMs have been combined with frameworks like Reinforcement Learning to bridge the gap between high-level theories and process-level mechanisms, relatively less attention has been paid to their implications for a unified notion of cognitive effort. Here, we combine Active Inference (AIF) with the Drift-Diffusion Model (DDM) to investigate whether the resulting AIF-DDM can simultaneously account for effort arising from both habit violation and value discriminability. To our knowledge, this is the first time AIF has been combined with an EAM. We tested the AIF-DDM on a behavioral dataset from the two-step task and compared its predictions to an information-theoretic definition of cognitive effort based on AIF. The model's predictions successfully accounted for second-stage reaction times but failed to capture the dynamics of the first stage. We argue the latter discrepancy likely stems from the experimental design rather than a fundamental flaw in the model's assumptions about cognitive effort. Accordingly, we propose several modifications of the two-step task to better measure and isolate cognitive effort. Finally, we found that integrating the DDM significantly improved parameter recovery, which could help future studies to obtain more reliable parameter estimates.

q-bio.NC↗

arXiv2025

Mixture of Autoencoder Experts Guidance using Unlabeled and Incomplete Data for Exploration in Reinforcement Learning

Recent trends in Reinforcement Learning (RL) highlight the need for agents to learn from reward-free interactions and alternative supervision signals, such as unlabeled or incomplete demonstrations, rather than relying solely on explicit reward maximization. Additionally, developing generalist agents that can adapt efficiently in real-world environments often requires leveraging these reward-free signals to guide learning and behavior. However, while intrinsic motivation techniques provide a means for agents to seek out novel or uncertain states in the absence of explicit rewards, they are often challenged by dense reward environments or the complexity of high-dimensional state and action spaces. Furthermore, most existing approaches rely directly on the unprocessed intrinsic reward signals, which can make it difficult to shape or control the agent's exploration effectively. We propose a framework that can effectively utilize expert demonstrations, even when they are incomplete and imperfect. By applying a mapping function to transform the similarity between an agent's state and expert data into a shaped intrinsic reward, our method allows for flexible and targeted exploration of expert-like behaviors. We employ a Mixture of Autoencoder Experts to capture a diverse range of behaviors and accommodate missing information in demonstrations. Experiments show our approach enables robust exploration and strong performance in both sparse and dense reward environments, even when demonstrations are sparse or incomplete. This provides a practical framework for RL in realistic settings where optimal data is unavailable and precise reward control is needed.

cs.LG↗

arXiv2025

Enabling Privacy-Aware AI-Based Ergonomic Analysis

Musculoskeletal disorders (MSDs) are a leading cause of injury and productivity loss in the manufacturing industry, incurring substantial economic costs. Ergonomic assessments can mitigate these risks by identifying workplace adjustments that improve posture and reduce strain. Camera-based systems offer a non-intrusive, cost-effective method for continuous ergonomic tracking, but they also raise significant privacy concerns. To address this, we propose a privacy-aware ergonomic assessment framework utilizing machine learning techniques. Our approach employs adversarial training to develop a lightweight neural network that obfuscates video data, preserving only the essential information needed for human pose estimation. This obfuscation ensures compatibility with standard pose estimation algorithms, maintaining high accuracy while protecting privacy. The obfuscated video data is transmitted to a central server, where state-of-the-art keypoint detection algorithms extract body landmarks. Using multi-view integration, 3D keypoints are reconstructed and evaluated with the Rapid Entire Body Assessment (REBA) method. Our system provides a secure, effective solution for ergonomic monitoring in industrial environments, addressing both privacy and workplace safety concerns.

cs.CV↗

arXiv2025

Adaptive Clustering for Efficient Phenotype Segmentation of UAV Hyperspectral Data

Unmanned Aerial Vehicles (UAVs) combined with Hyperspectral imaging (HSI) offer potential for environmental and agricultural applications by capturing detailed spectral information that enables the prediction of invisible features like biochemical leaf properties. However, the data-intensive nature of HSI poses challenges for remote devices, which have limited computational resources and storage. This paper introduces an Online Hyperspectral Simple Linear Iterative Clustering algorithm (OHSLIC) framework for real-time tree phenotype segmentation. OHSLIC reduces inherent noise and computational demands through adaptive incremental clustering and a lightweight neural network, which phenotypes trees using leaf contents such as chlorophyll, carotenoids, and anthocyanins. A hyperspectral dataset is created using a custom simulator that incorporates realistic leaf parameters, and light interactions. Results demonstrate that OHSLIC achieves superior regression accuracy and segmentation performance compared to pixel- or window-based methods while significantly reducing inference time. The method`s adaptive clustering enables dynamic trade-offs between computational efficiency and accuracy, paving the way for scalable edge-device deployment in HSI applications.

cs.CV↗

arXiv2024

Predicting change in time production -- A machine learning approach to time perception

Time perception research has advanced significantly over the years. However, some areas remain largely unexplored. This study addresses two such under-explored areas in timing research: (1) A quantitative analysis of time perception at an individual level, and (2) Time perception in an ecological setting. In this context, we trained a machine learning model to predict the direction of change in an individual's time production. The model's training data was collected using an ecologically valid setup. We moved closer to an ecological setting by conducting an online experiment with 995 participants performing a time production task that used naturalistic videos (no audio) as stimuli. The model achieved an accuracy of 61%. This was 10 percentage points higher than the baseline models derived from cognitive theories of timing. The model performed equally well on new data from a second experiment, providing evidence of its generalization capabilities. The model's output analysis revealed that it also contained information about the magnitude of change in time production. The predictions were further analysed at both population and individual level. It was found that a participant's previous timing performance played a significant role in determining the direction of change in time production. By integrating attentional-gate theories from timing research with feature importance techniques from machine learning, we explained model predictions using cognitive theories of timing. The model and findings from this study have potential applications in systems involving human-computer interactions where understanding and predicting changes in user's time perception can enable better user experience and task performance.

cs.HC↗

arXiv2024

Reward Machine Inference for Robotic Manipulation

Learning from Demonstrations (LfD) and Reinforcement Learning (RL) have enabled robot agents to accomplish complex tasks. Reward Machines (RMs) enhance RL's capability to train policies over extended time horizons by structuring high-level task information. In this work, we introduce a novel LfD approach for learning RMs directly from visual demonstrations of robotic manipulation tasks. Unlike previous methods, our approach requires no predefined propositions or prior knowledge of the underlying sparse reward signals. Instead, it jointly learns the RM structure and identifies key high-level events that drive transitions between RM states. We validate our method on vision-based manipulation tasks, showing that the inferred RM accurately captures task structure and enables an RL agent to effectively learn an optimal policy.

cs.RO↗

arXiv2024

Learning Task Specifications from Demonstrations as Probabilistic Automata

Specifying tasks for robotic systems traditionally requires coding expertise, deep domain knowledge, and significant time investment. While learning from demonstration offers a promising alternative, existing methods often struggle with tasks of longer horizons. To address this limitation, we introduce a computationally efficient approach for learning probabilistic deterministic finite automata (PDFA) that capture task structures and expert preferences directly from demonstrations. Our approach infers sub-goals and their temporal dependencies, producing an interpretable task specification that domain experts can easily understand and adjust. We validate our method through experiments involving object manipulation tasks, showcasing how our method enables a robot arm to effectively replicate diverse expert strategies while adapting to changing conditions.

cs.RO↗