Searcharxiv⌕ Search

arXiv subjects

Ahmed Khalil

Publications and source records attributed to Ahmed Khalil.

10 recordsLinked to original sources
arXiv2026

Cryogenic piezoelectric effects in thin film strontium titanate devices

Next generation quantum technologies will need to rely on efficient transduction between electrical, optical, and mechanical quantum degrees of freedom to generate large-scale entanglement over large distances. The performance of such transducers is fundamentally limited by the cryogenic properties of the underlying materials. Here, we demonstrate that engineering strain in ferroelectric thin-film strontium titanate ($\mathrm{SrTiO_3}$) not only results in an exceptionally large Pockels coefficient, but also in a robust linear piezoelectric response at cryogenic temperatures, surpassing previous thin-film benchmarks. We measure piezoelectric tensor elements of $d_{15} = 151.8 \pm 1.5$ pm/V and $d_{33} = 54.8 \pm 4$ pm/V, and an effective photoelastic coefficient of $p_{\mathrm{eff}}$ = 0.56 at 5~K. Utilizing these enhanced properties, we demonstrate the first $\mathrm{SrTiO_3}$-on-oxide acousto-optic modulator with a voltage-length product ($V_{\pi}L$) of $0.874 \pm 0.084$ V cm, outperforming state-of-the-art unreleased modulators that typically feature a $V_{\pi}L$ of a few V cm. Our results establish thin-film $\mathrm{SrTiO_3}$ as a promising material system for integrated quantum photonics operating at cryogenic temperatures.

physics.optics↗
arXiv2026

Game-Theoretic Autonomous Driving: A Graphs of Convex Sets Approach

Multi-vehicle autonomous driving couples strategic interaction with hybrid (discrete-continuous) maneuver planning under shared safety constraints. We introduce IBR-GCS, an Iterative Best Response (IBR) planning approach based on the Graphs of Convex Sets (GCS) framework that models highway driving as a generalized noncooperative game. IBR-GCS integrates combinatorial maneuver reasoning, trajectory planning, and game-theoretic interaction within a unified framework. The key novelty is a vehicle-specific, strategy-dependent GCS construction. Specifically, at each best-response update, each vehicle builds its own graph conditioned on the current strategies of the other vehicles, with vertices representing lane-specific, time-varying, convex, collision-free regions and edges encoding dynamically feasible transitions. This yields a shortest-path problem in GCS for each best-response step, which admits an efficient convex relaxation that can be solved using convex optimization tools without exhaustive discrete tree search. We then apply an iterative best-response scheme in which vehicles update their trajectories sequentially and provide conditions under which the resulting inexact updates converge to an approximate generalized Nash equilibrium. Simulation results across multi-lane, multi-vehicle scenarios demonstrate that IBR-GCS produces safe trajectories and strategically consistent interactive behaviors.

cs.MA↗
arXiv2025

Ensemble Kalman Inversion for Constrained Nonlinear MPC: An ADMM-Splitting Approach

This work proposes a novel Alternating Direction Method of Multipliers (ADMM)-based Ensemble Kalman Inversion (EKI) algorithm for solving constrained nonlinear model predictive control (NMPC) problems. First, stage-wise nonlinear inequality constraints in the NMPC problem are embedded via an augmented Lagrangian with nonnegative slack variables. We then show that the resulting unconstrained augmented-Lagrangian primal subproblem admits a Bayesian interpretation: under independent Gaussian virtual observations, its minimizers coincide with MAP estimators, enabling solution via EKI. However, since the nonnegativity constraint on the slacks is a hard constraint not naturally encoded by a Gaussian model, our proposed algorithm yields a two-block ADMM scheme that alternates between (i) an inexact primal step that minimizes the augmented-Lagrangian objective (implemented via EKI rollouts), (ii) a nonnegativity projection for the slacks, and (iii) a dual ascent step. To balance exploration and convergence, an annealing schedule tempers sampling covariances while a penalty schedule increases constraint enforcement over outer iterations, encouraging global search early and precise constraint satisfaction later. We evaluate the proposed controller on a 6-DOF UR5e manipulation benchmark in MuJoCo, comparing it against DIAL-MPC (an iterative MPPI variant) as the arm traverses a cluttered tabletop environment.

math.OC↗
arXiv2025

Distributed and Localized Covariance Control of Coupled Systems: A System Level Approach

This work is concerned with the finite-horizon optimal covariance steering of networked systems governed by discrete-time stochastic linear dynamics. In contrast with existing work that has only considered systems with dynamically decoupled agents, we consider a dynamically coupled system composed of interconnected subsystems subject to local communication constraints. In particular, we propose a distributed algorithm to compute the localized optimal feedback control policy for each individual subsystem, which depends only on the local state histories of its neighboring subsystems. Utilizing the system-level synthesis (SLS) framework, we first recast the localized covariance steering problem as a convex SLS problem with locality constraints. Subsequently, exploiting its partially separable structure, we decompose the latter problem into smaller subproblems, introducing a transformation to deal with nonseparable instances. Finally, we employ a variation of the consensus alternating direction method of multipliers (ADMM) to distribute computation across subsystems on account of their local information and communication constraints. We demonstrate the effectiveness of our proposed algorithm on a power system with 36 interconnected subsystems.

math.OC↗
arXiv2024

TransformerMPC: Accelerating Model Predictive Control via Transformers

In this paper, we address the problem of reducing the computational burden of Model Predictive Control (MPC) for real-time robotic applications. We propose TransformerMPC, a method that enhances the computational efficiency of MPC algorithms by leveraging the attention mechanism in transformers for both online constraint removal and better warm start initialization. Specifically, TransformerMPC accelerates the computation of optimal control inputs by selecting only the active constraints to be included in the MPC problem, while simultaneously providing a warm start to the optimization process. This approach ensures that the original constraints are satisfied at optimality. TransformerMPC is designed to be seamlessly integrated with any MPC solver, irrespective of its implementation. To guarantee constraint satisfaction after removing inactive constraints, we perform an offline verification to ensure that the optimal control inputs generated by the MPC solver meet all constraints. The effectiveness of TransformerMPC is demonstrated through extensive numerical simulations on complex robotic systems, achieving up to 35x improvement in runtime without any loss in performance.

cs.RO↗
arXiv2023

Cybersecurity in Motion: A Survey of Challenges and Requirements for Future Test Facilities of CAVs

The way we travel is changing rapidly, and Cooperative Intelligent Transportation Systems (C-ITSs) are at the forefront of this evolution. However, the adoption of C-ITSs introduces new risks and challenges, making cybersecurity a top priority for ensuring safety and reliability. Building on this premise, this paper presents an envisaged Cybersecurity Centre of Excellence (CSCE) designed to bolster research, testing, and evaluation of the cybersecurity of C-ITSs. We explore the design, functionality, and challenges of CSCE's testing facilities, outlining the technological, security, and societal requirements. Through a thorough survey and analysis, we assess the effectiveness of these systems in detecting and mitigating potential threats, highlighting their flexibility to adapt to future C-ITSs. Finally, we identify current unresolved challenges in various C-ITS domains, with the aim of motivating further research into the cybersecurity of C-ITSs.

cs.CR↗
arXiv2023

LL-VQ-VAE: Learnable Lattice Vector-Quantization For Efficient Representations

In this paper we introduce learnable lattice vector quantization and demonstrate its effectiveness for learning discrete representations. Our method, termed LL-VQ-VAE, replaces the vector quantization layer in VQ-VAE with lattice-based discretization. The learnable lattice imposes a structure over all discrete embeddings, acting as a deterrent against codebook collapse, leading to high codebook utilization. Compared to VQ-VAE, our method obtains lower reconstruction errors under the same training conditions, trains in a fraction of the time, and with a constant number of parameters (equal to the embedding dimension $D$), making it a very scalable approach. We demonstrate these results on the FFHQ-1024 dataset and include FashionMNIST and Celeb-A.

cs.LG↗
arXiv2023

Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL

Recent works have shown that tackling offline reinforcement learning (RL) with a conditional policy produces promising results. The Decision Transformer (DT) combines the conditional policy approach and a transformer architecture, showing competitive performance against several benchmarks. However, DT lacks stitching ability -- one of the critical abilities for offline RL to learn the optimal policy from sub-optimal trajectories. This issue becomes particularly significant when the offline dataset only contains sub-optimal trajectories. On the other hand, the conventional RL approaches based on Dynamic Programming (such as Q-learning) do not have the same limitation; however, they suffer from unstable learning behaviours, especially when they rely on function approximation in an off-policy learning setting. In this paper, we propose the Q-learning Decision Transformer (QDT) to address the shortcomings of DT by leveraging the benefits of Dynamic Programming (Q-learning). It utilises the Dynamic Programming results to relabel the return-to-go in the training data to then train the DT with the relabelled data. Our approach efficiently exploits the benefits of these two approaches and compensates for each other's shortcomings to achieve better performance. We empirically show these in both simple toy environments and the more complex D4RL benchmark, showing competitive performance gains.

cs.LG↗
arXiv2022

RLOps: Development Life-cycle of Reinforcement Learning Aided Open RAN

Radio access network (RAN) technologies continue to evolve, with Open RAN gaining the most recent momentum. In the O-RAN specifications, the RAN intelligent controllers (RICs) are software-defined orchestration and automation functions for the intelligent management of RAN. This article introduces principles for machine learning (ML), in particular, reinforcement learning (RL) applications in the O-RAN stack. Furthermore, we review the state-of-the-art research in wireless networks and cast it onto the RAN framework and the hierarchy of the O-RAN architecture. We provide a taxonomy for the challenges faced by ML/RL models throughout the development life-cycle: from the system specification to production deployment (data acquisition, model design, testing and management, etc.). To address the challenges, we integrate a set of existing MLOps principles with unique characteristics when RL agents are considered. This paper discusses a systematic model development, testing and validation life-cycle, termed: RLOps. We discuss fundamental parts of RLOps, which include: model specification, development, production environment serving, operations monitoring and safety/security. Based on these principles, we propose the best practices for RLOps to achieve an automated and reproducible model development process. At last, a holistic data analytics platform rooted in the O-RAN deployment is designed and implemented, aiming to embrace and fulfil the aforementioned principles and best practices of RLOps.

cs.NI↗