Publications

Virtual Reality (VR) applications require robust user identification systems to ensure secure access to equipment and protect worker identities. Motion tracking data from VR headsets and controllers has emerged as a powerful behavioral biometric, with recent studies demonstrating identification accuracies exceeding 94% across a large user base. However, the application of modern deep learning architectures, particularly State Space Models (SSM), to VR scenarios remains largely unexplored. In this work, we benchmark user identification performance across the large-scale Who is Alyx VR dataset, gathering data from 71 users playing the popular HalfLife:Alyx game. We evaluate both established architectures (Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), Temporal Convolutional Network (TCN), Transformer) and the emerging SSMs on time series motion data. Our results provide the first comprehensive benchmark of state-of-the-art and novel architectures for VR user identification, establishing baseline performance metrics for future privacy-preserving authentication systems in manufacturing environments.

Human–Robot Collaboration (HRC) has become a key enabler of productivity, adaptability, and improved ergonomics in modern manufacturing environments. Despite this, many existing task allocation strategies for HRC are based on restrictive assumptions and rely on static or heuristic methods that limit their ability to cope with human variability and human factors, such as stress and work-load. In this work, we explore the use of value-based Reinforcement Learning (RL) for online task scheduling in a collaborative assembly context. We developed a simulated two different simulated setups. The first setup assessed the ability of the RL scheduler to optimize system performance under conditions of high variability in human execution. In the second setup, we modeled the operator’s stress level and incorporated it directly into the objective function optimized by the RL agent. Results from the first setup indicate that the RL agent can effectively adapt task allocation in response to fluctuating human performance. Meanwhile, the second setup demonstrates the agent’s capacity to balance productivity with operator well-being by explicitly trading off performance and stress.

Anomaly Detection (AD) is crucial in industrial settings to streamline operations by detecting underlying issues. Conventional methods merely label observations as normal or anomalous, lacking crucial insights. In Industry 5.0, interpretable outcomes become desirable to enable users to understand the rationale behind model decisions. This paper presents the first industrial application of ExIFFI, a recent approach for fast, efficient explanations for the Extended Isolation Forest EIF AD method. ExIFFI is tested on four industrial datasets, demonstrating superior explanation effectiveness, computational efficiency and improved raw anomaly detection performances. ExIFFI reaches over 90% of average precision on the benchmarks considered in the study and outperforms state-of-the-art Explainable Artificial Intelligence XAI approaches in terms of the feature selection proxy task metric which was specifically introduced to quantitatively evaluate model explanations.

Predictive Maintenance (PdM) is pivotal in Industry 4.0 and 5.0, proactively enhancing efficiency through accurate equipment Remaining Useful Life (RUL) prediction, thus optimizing maintenance scheduling and reducing unexpected failures and premature interventions. This paper introduces a novel RUL estimation approach leveraging State Space Models (SSM) for efficient long-term sequence modeling. To handle model uncertainty, Simultaneous Quantile Regression (SQR) is integrated into the SSM, enabling multiple quantile estimations. The proposed method is benchmarked against traditional sequence modelling techniques (Long Short Term Memory (LSTM), Transformer, Informer) using the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset. Results demonstrate superior accuracy and computational efficiency of SSM models, underscoring their potential for high-stakes industrial applications.

As Machine Learning grows in popularity across various fields, equity has become a key focus for the AI community. However, fairness-oriented approaches are still underexplored in smart mobility. Addressing this gap, our study investigates the balance between performance optimization and algorithmic fairness in shared micromobility services providing a novel framework based on Reinforcement Learning. Exploiting Q-learning, the proposed methodology achieves equitable outcomes in terms of the Gini index across different areas characterized by their distance from central hubs. Through vehicle rebalancing, the provided scheme maximizes operator performance while ensuring fairness principles for users, reducing iniquity by up to 85% while only increasing costs by 30% (w.r.t. applying no equity adjustment). A case study with synthetic data validates our insights and highlights the importance of fairness in urban micromobility.

Continuous control Deep Reinforcement Learning (RL) approaches are known to suffer from estimation biases, leading to suboptimal policies. This paper introduces innovative methods in RL, focusing on addressing and exploiting estimation biases in Actor-Critic methods for continuous control tasks, using Deep Double Q-Learning. We design a Bias Exploiting (BE) mechanism to dynamically select the most advantageous estimation bias during training of the RL agent. Most State-of-the-art Deep RL algorithms can be equipped with the BE mechanism, without hindering performance or computational complexity. Our extensive experiments across various continuous control tasks demonstrate the effectiveness of our approaches. We show that RL algorithms equipped with this method can match or surpass their counterparts, particularly in environments where estimation biases significantly impact learning. The results underline the importance of bias exploitation in improving policy learning in RL.

This report describes our proposed solution for the second AI Olympics competition held at IROS 2024. Our solution is based on a recent Model-Based Reinforcement Learning algorithm named MC-PILCO. Besides briefly reviewing the algorithm, we discuss the most critical aspects of the MC-PILCO implementation in the tasks at hand.

In the following report, we describe the solution we propose for the AI Olympics competition held at IROS 2024. Our solution is based on a Model-free Deep Reinforcement Learning approach combined with an evolutionary strategy. We briefly describe the algorithms that have been used and then provide details of the approach.

Anomaly detection (AD) is a crucial process often required in industrial settings. Anomalies can signal underlying issues within a system, prompting further investigation. Industrial processes aim to streamline operations as much as possible, encompassing the production of the final product, making AD an essential mean to reach this goal. Conventional anomaly detection methodologies typically clas-sify observations as either normal or anomalous without providing insight into the reasons behind these classifications. Consequently, in light of the emergence of Industry 5.0, a more desirable approach involves providing interpretable outcomes, enabling users to understand the rationale behind the results. This paper presents the first industrial application of ExIFFI, a recently developed approach focused on the production of fast and efficient explanations for the Extended Isolation Forest (EIF) Anomaly detection method. ExIFFI is tested on two publicly available industrial datasets demonstrating superior effectiveness in explanations and computational efficiency with the respect to other state-of-the-art explainable AD models.

Anomaly Detection (AD) focuses on identifying unusual patterns in complex datasets and systems. While Machine Learning and Decision Support Systems (DSS) are effective for this, simply detecting anomalies often falls short in real-world scenarios, especially in engineering contexts where diagnostics and maintenance are essential. Users need clear explanations behind anomaly predictions to understand the root causes and trust the model. The unsupervised nature of AD complicates the development of interpretable tools. To address this, we propose the Extended Isolation Forest Feature Importance (ExIFFI), a new approach that explains the predictions of the Extended Isolation Forest (EIF), applicable to all Isolation Forest models that split using hyperplanes. ExIFFI provides both global and local explanations by analyzing feature importance. Additionally, we introduce Enhanced Extended Isolation Forest (EIF+), an improved version of EIF, designed to better detect unseen anomalies by modifying the splitting strategy of hyperplanes. We compare various unsupervised AD methods across five synthetic and eleven real-world datasets using the Average Precision metric. EIF+consistently outperforms EIF in all scenarios, demonstrating superior generalization. To validate the interpretability, we propose a new metric — AUCFS (Area Under the Curve of Feature Selection) — which uses feature selection as a performance indicator. ExIFFI proves more effective than other unsupervised interpretation methods, excelling in 8 out of 11 real-world datasets and correctly identifying anomalous features in synthetic datasets. Finally, we provide open-source code to encourage further research and reproducibility.