arXiv subjects

Abdelhafid Zenati

Publications and source records attributed to Abdelhafid Zenati.

4 recordsLinked to original sources

arXiv2026

Lightweight Spatiotemporal Highway Lane Detection via 3D-ResNet and PINet with ROI-Aware Attention

This paper presents a lightweight, end-to-end highway lane detection architecture that jointly captures spatial and temporal information for robust performance in real-world driving scenarios. Building on the strengths of 3D convolutional neural networks and instance segmentation, we propose two models that integrate a 3D-ResNet encoder with a Point Instance Network (PINet) decoder. The first model enhances multi-scale feature representation using a Feature Pyramid Network (FPN) and Self-Attention mechanism to refine spatial dependencies. The second model introduces a Region of Interest (ROI) detection head to selectively focus on lane-relevant regions, thereby improving precision and reducing computational complexity. Experiments conducted on the TuSimple dataset (highway driving scenarios) demonstrate that the proposed second model achieves 93.40% accuracy while significantly reducing false negatives. Compared to existing 2D and 3D baselines, our approach achieves improved performance with fewer parameters and reduced latency. The architecture has been validated through offline training and real-time inference in the Autonomous Systems Laboratory at City, St George's University of London. These results suggest that the proposed models are well-suited for integration into Advanced Driver Assistance Systems (ADAS), with potential scalability toward full Lane Assist Systems (LAS).

cs.CV↗

arXiv2025

A Dynamical Systems Framework for Reinforcement Learning Safety and Robustness Verification

The application of reinforcement learning to safety-critical systems is limited by the lack of formal methods for verifying the robustness and safety of learned policies. This paper introduces a novel framework that addresses this gap by analyzing the combination of an RL agent and its environment as a discrete-time autonomous dynamical system. By leveraging tools from dynamical systems theory, specifically the Finite-Time Lyapunov Exponent (FTLE), we identify and visualize Lagrangian Coherent Structures (LCS) that act as the hidden "skeleton" governing the system's behavior. We demonstrate that repelling LCS function as safety barriers around unsafe regions, while attracting LCS reveal the system's convergence properties and potential failure modes, such as unintended "trap" states. To move beyond qualitative visualization, we introduce a suite of quantitative metrics, Mean Boundary Repulsion (MBR), Aggregated Spurious Attractor Strength (ASAS), and Temporally-Aware Spurious Attractor Strength (TASAS), to formally measure a policy's safety margin and robustness. We further provide a method for deriving local stability guarantees and extend the analysis to handle model uncertainty. Through experiments in both discrete and continuous control environments, we show that this framework provides a comprehensive and interpretable assessment of policy behavior, successfully identifying critical flaws in policies that appear successful based on reward alone.

cs.AI↗

arXiv2025

Validation of Neural Network Controllers for Uncertain Systems Through Keep-Close Approach: Robustness Analysis and Safety Verification

Among the major challenges in neural control system technology is the validation and certification of the safety and robustness of neural network (NN) controllers against various uncertainties including unmodelled dynamics, nonlinearities, and time delays. One way in providing such validation guarantees is to maintain the closed-loop system output with a NN controller when its input changes within a bounded set, close to the output of a robustly performing closed-loop reference model. This paper presents a novel approach to analysing the performance and robustness of uncertain feedback systems with NN controllers. Due to the complexity of analysing such systems, the problem is reformulated as the problem of dynamical tracking errors between the closed-loop system with a neural controller and an ideal closed-loop reference model. Then, the approximation of the controller error is characterised by adopting the differential mean value theorem (DMV) and the Integral Quadratic Constraints (IQCs) technique. Moreover, the Relative Integral Square Error (RISE) and the Supreme Square Error (SSE) bounded set are derived for the output of the error dynamical system. The analysis is then performed by integrating Lyapunov theory with the IQCs-based technique. The resulting worst-case analysis provides the user a prior knowledge about the worst case of RISE and SSE between the reference closed-loop model and the uncertain system controlled by the neural controller.

eess.SY↗

arXiv2023

Explainability in Deep Reinforcement Learning, a Review into Current Methods and Applications

The use of Deep Reinforcement Learning (DRL) schemes has increased dramatically since their first introduction in 2015. Though uses in many different applications are being found, they still have a problem with the lack of interpretability. This has bread a lack of understanding and trust in the use of DRL solutions from researchers and the general public. To solve this problem, the field of Explainable Artificial Intelligence (XAI) has emerged. This entails a variety of different methods that look to open the DRL black boxes, ranging from the use of interpretable symbolic Decision Trees (DT) to numerical methods like Shapley Values. This review looks at which methods are being used and for which applications. This is done to identify which models are the best suited to each application or if a method is being underutilised.

cs.LG↗