arXiv subjects

Juraj Gazda

Publications and source records attributed to Juraj Gazda.

9 recordsLinked to original sources

arXiv2026

Minimum Bisection Problem: Machine Learning-Based Penalty Parameter Tuning for Optimization on Quantum Annealers

The Minimum Bisection Problem is a fundamental, computationally hard graph partitioning problem with applications in parallel computing, network design, and large-scale data processing. When formulated as a Quadratic Unconstrained Binary Optimization problem for quantum annealing, solution quality depends critically on the penalty parameter that enforces balanced partitions. Selecting this parameter is problem-dependent and typically relies on manual tuning or heuristics. This paper proposes a machine learning-based approach for automatic penalty-parameter tuning developed specifically for the Minimum Bisection Problem. We first derive a graph-dependent initial penalty estimate and then use two Gradient Boosting Regressor models to predict the endpoints of an effective penalty-multiplier interval from the number of nodes, graph density, and the initial estimate. The final penalty is obtained from the predicted interval and used to construct the model solved by D-Wave's quantum annealing solvers. The models were calibrated on 607 Erdős-Rényi graphs, with Metis and Kernighan-Lin as classical references, and evaluated on 126 independently generated instances with up to 4000 nodes. Under the adopted experimental setup, the predicted penalties enabled the hybrid solver to return balanced partitions for all evaluation instances and lower cut values than Metis in every case.

quant-ph↗

arXiv2026

A Strong Linear Baseline for Whole-Heart Cardiac Shape Completion on CT, with an Open Eleven-Structure Statistical Shape Model

Public cardiac cohorts annotate different subsets of the heart, so shapes from separate sources cannot be pooled without shared correspondence. Among released cardiac shape resources, none we identified carries the atrial appendage, pulmonary veins, and caval stumps as separate blocks in one mesh. Completion benchmarks also compare deep models against a least-squares projection onto shape modes, not the conditional estimator the same fitted model implies. We release an eleven- structure cardiac computed-tomography (CT) statistical shape model, built from 383 automatically labelled cases in 11 571-vertex correspondence, and compare completion estimators under one frozen internal split and endpoint. On a 76-case internal list held out from fitting, a closed-form conditional-Gaussian estimator reconstructed the missing non-chamber structures at 3.717 mm mean per-vertex error, averaged equally over one, three, five, and nine observed structures. A five-refit mask-conditioned graph variational autoencoder reached 5.248 mm and nearest-neighbour retrieval 8.931 mm. The paired difference was 1.531 mm (95% confidence interval 1.384 to 1.711), and the ordering held in a raw-coordinate sensitivity arm. Expert manual labels exist for 58 external CT cases, but our registered reference is close enough to score only five structures. There the closed-form estimator again had lower average surface distance, 95th-percentile Hausdorff distance, and Chamfer error for both completed atria. On a second public benchmark of 20 cases the reference was close enough for three of four completed structures, and the same ordering held there. Four structures have no expert reference. The released model and its completion operator support cohort-unification research on aligned CT, not clinical use.

cs.AI↗

arXiv2026

Quantum Annealing for Realistic Traffic Flow Optimization: Clustering and Data-Driven QUBO

This article presents a scalable, data-driven formulation of city-wide Traffic Flow Optimization as a Quadratic Unconstrained Binary Optimization problem and evaluates its performance using quantum annealing and classical solvers on realistic urban networks. The framework builds a time-resolved congestion model from simulated mobility data by sampling vehicle trajectories at fixed intervals, identifying leader-follower interactions on shared road segments. In addition to congestion, the model incorporates route-duration penalties and an analytically derived penalty parameter that enforces one-hot route selection, ensuring feasible assignments while balancing network-wide congestion reduction and individual travel times. To mitigate the combinatorial growth of interactions in large-scale instances, the approach employs Leiden clustering to partition vehicles into dense communities that can be optimized independently. The resulting subproblems are solved using D-Wave's quantum annealer, exact mixed-integer programming via Gurobi, and several classical metaheuristics, and are evaluated on multiple city maps with up to 25,000 vehicles. Across large scenarios, the hybrid quantum annealing approach consistently produces feasible solutions within approximately 1% of Gurobi's objective values, while maintaining stable runtimes. Both methods outperform shortest-route baselines, achieving reductions in the proposed congestion-cost objective of up to 24.4% for the hybrid quantum approach and 29.4% for Gurobi. Finally, the study highlights the critical role of the underlying city map, showing that network structure directly influences interaction density, problem formulation, and the efficiency of embedding and solving on current quantum annealing hardware.

quant-ph↗

arXiv2026

Multi-Agent Route Planning as a QUBO Problem

Multi-Agent Route Planning considers selecting vehicles, each associated with a single predefined route, such that route-level coverage utility is maximized while redundant spatial overlaps are limited. This paper gives a formal problem definition, proves NP-hardness by reduction from the Weighted Set Packing problem, and derives a Quadratic Unconstrained Binary Optimization formulation whose coefficients directly encode route utility rewards and pairwise overlap penalties. A single penalty parameter $λ$ controls the coverage--overlap trade-off. We distinguish between a soft regime, which supports multi-objective exploration, and a hard regime, in which the penalty is strong enough to effectively enforce near-disjoint routes. We describe a practical pipeline for generating city instances, constructing candidate routes, building the QUBO matrix, and solving it with a binary quadratic programming baseline (Gurobi), simulated annealing, and D-Wave hybrid quantum annealing. Experiments on Barcelona instances with up to $10{,}000$ vehicles reveal a clear coverage--overlap knee and show that Pareto-optimal solutions are mainly obtained under the hard-penalty regime, while D-Wave hybrid solvers and Gurobi achieve very similar objective values on matching configurations with only minor runtime differences as problem size grows.

cs.RO↗

arXiv2025

Radiance Field Delta Video Compression in Edge-Enabled Vehicular Metaverse

Connected and autonomous vehicles (CAVs) offload computationally intensive tasks to multi-access edge computing (MEC) servers via vehicle-to-infrastructure (V2I) communication, enabling applications within the vehicular metaverse, which transforms physical environment into the digital space enabling advanced analysis or predictive modeling. A core challenge is physical-to-virtual (P2V) synchronization through digital twins (DTs), reliant on MEC networks and ultra-reliable low-latency communication (URLLC). To address this, we introduce radiance field (RF) delta video compression (RFDVC), which uses RF-encoder and RF-decoder architecture using distributed RFs as DTs storing photorealistic 3D urban scenes in compressed form. This method extracts differences between CAV-frame capturing actual traffic and RF-frame capturing empty scene from the same camera pose in batches encoded and transmitted over the MEC network. Experiments show data savings up to 71% against H.264 codec and 44% against H.265 codec under different conditions as lighting changes, and rain. RFDVC also demonstrates resilience to transmission errors, significantly outperforming the standard codec in non-rainy conditions with up to a +0.26 structural similarity index measure (SSIM) improvement over H.264 codec, and maintaining a +0.18 SSIM improvement even in challenging rainy conditions, both measured at a block error rate (BLER) of 0.25.

eess.SP↗

arXiv2024

3CSim: CARLA Corner Case Simulation for Control Assessment in Autonomous Driving

We present the CARLA corner case simulation (3CSim) for evaluating autonomous driving (AD) systems within the CARLA simulator. This framework is designed to address the limitations of traditional AD model training by focusing on non-standard, rare, and cognitively challenging scenarios. These corner cases are crucial for ensuring vehicle safety and reliability, as they test advanced control capabilities under unusual conditions. Our approach introduces a taxonomy of corner cases categorized into state anomalies, behavior anomalies, and evidence-based anomalies. We implement 32 unique corner cases with adjustable parameters, including 9 predefined weather conditions, timing, and traffic density. The framework enables repeatable and modifiable scenario evaluations, facilitating the creation of a comprehensive dataset for further analysis.

cs.RO↗

arXiv2024

Distributed Radiance Fields for Edge Video Compression and Metaverse Integration in Autonomous Driving

The metaverse is a virtual space that combines physical and digital elements, creating immersive and connected digital worlds. For autonomous mobility, it enables new possibilities with edge computing and digital twins (DTs) that offer virtual prototyping, prediction, and more. DTs can be created with 3D scene reconstruction methods that capture the real world's geometry, appearance, and dynamics. However, sending data for real-time DT updates in the metaverse, such as camera images and videos from connected autonomous vehicles (CAVs) to edge servers, can increase network congestion, costs, and latency, affecting metaverse services. Herein, a new method is proposed based on distributed radiance fields (RFs), multi-access edge computing (MEC) network for video compression and metaverse DT updates. RF-based encoder and decoder are used to create and restore representations of camera images. The method is evaluated on a dataset of camera images from the CARLA simulator. Data savings of up to 80% were achieved for H.264 I-frame - P-frame pairs by using RFs instead of I-frames, while maintaining high peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) qualitative metrics for the reconstructed images. Possible uses and challenges for the metaverse and autonomous mobility are also discussed.

cs.CV↗

arXiv2023

Neural radiance fields in the industrial and robotics domain: applications, research opportunities and use cases

The proliferation of technologies, such as extended reality (XR), has increased the demand for high-quality three-dimensional (3D) graphical representations. Industrial 3D applications encompass computer-aided design (CAD), finite element analysis (FEA), scanning, and robotics. However, current methods employed for industrial 3D representations suffer from high implementation costs and reliance on manual human input for accurate 3D modeling. To address these challenges, neural radiance fields (NeRFs) have emerged as a promising approach for learning 3D scene representations based on provided training 2D images. Despite a growing interest in NeRFs, their potential applications in various industrial subdomains are still unexplored. In this paper, we deliver a comprehensive examination of NeRF industrial applications while also providing direction for future research endeavors. We also present a series of proof-of-concept experiments that demonstrate the potential of NeRFs in the industrial domain. These experiments include NeRF-based video compression techniques and using NeRFs for 3D motion estimation in the context of collision avoidance. In the video compression experiment, our results show compression savings up to 48\% and 74\% for resolutions of 1920x1080 and 300x168, respectively. The motion estimation experiment used a 3D animation of a robotic arm to train Dynamic-NeRF (D-NeRF) and achieved an average peak signal-to-noise ratio (PSNR) of disparity map with the value of 23 dB and an structural similarity index measure (SSIM) 0.97.

cs.RO↗

arXiv2022

Fast and computationally efficient generative adversarial network algorithm for unmanned aerial vehicle-based network coverage optimization

The challenge of dynamic traffic demand in mobile networks is tackled by moving cells based on unmanned aerial vehicles. Considering the tremendous potential of unmanned aerial vehicles in the future, we propose a new heuristic algorithm for coverage optimization. The proposed algorithm is implemented based on a conditional generative adversarial neural network, with a unique multilayer sum-pooling loss function. To assess the performance of the proposed approach, we compare it with the optimal core-set algorithm and quasi-optimal spiral algorithm. Simulation results show that the proposed approach converges to the quasi-optimal solution with a negligible difference from the global optimum while maintaining a quadratic complexity regardless of the number of users.

cs.LG↗