ABSTRACT We present the results of an exploratory investigation of applying a hybrid quantum-classical architecture to an off-road vehicle mobility problem, namely the generation of go/no-go maps posed as a machine learning problem. The premise of this work rests on two observations. First, quantum computing allows in principle for algorithms that provide a speedup over the best known classical counterparts. However, as it is to be expected of such novel and complex tools (both hardware and algorithmic) at this early developmental stage, current quantum algorithms do not always perform well on real-world problems. Second, complex physics-based vehicle and terramechanics models and simulations, currently advocated for high-fidelity high-accuracy ground vehicle–terrain interaction analyses, pose significant computational burden, especially when applied to mobility studies which may require numerous simulation runs. We describe the Quantum-Assisted Helmholtz Machine formulation, suitable to be implemented on a quantum annealer such as the D-Wave 2000Q machine, discuss the high-performance classical computing framework used to generate through simulation the training and test sets, and provide the results of our investigations and analysis into the performance of the machine learning model and its predictive capabilities for generating go/no-go mobility maps. This work represents a contribution to an ongoing effort of exploring the applicability of the emerging field of quantum computing to challenging engineering and scientific problems.
ABSTRACT We present the results of an exploratory investigation of applying a hybrid quantum-classical architecture to an off-road vehicle mobility problem, namely the generation of go/no-go maps posed as a machine learning problem. The premise of this work rests on two observations. First, quantum computing allows in principle for algorithms that provide a speedup over the best known classical counterparts. However, as it is to be expected of such novel and complex tools (both hardware and algorithmic) at this early developmental stage, current quantum algorithms do not always perform well on real-world problems. Second, complex physics-based vehicle and terramechanics models and simulations, currently advocated for high-fidelity high-accuracy ground vehicle–terrain interaction analyses, pose significant computational burden, especially when applied to mobility studies which may require numerous simulation runs. We describe the Quantum-Assisted Helmholtz Machine formulation, suitable to be implemented on a quantum annealer such as the D-Wave 2000Q machine, discuss the high-performance classical computing framework used to generate through simulation the training and test sets, and provide the results of our investigations and analysis into the performance of the machine learning model and its predictive capabilities for generating go/no-go mobility maps. This work represents a contribution to an ongoing effort of exploring the applicability of the emerging field of quantum computing to challenging engineering and scientific problems.
Quantum annealing algorithms belong to the class of meta-heuristic tools, applicable for solving binary optimization problems. Hardware implementations of quantum annealing, such as the quantum processing units (QPUs) produced by D-Wave Systems, have been subject to multiple analyses in research, with the aim of characterizing the technology's usefulness for optimization and sampling tasks. In this paper, we present a real-world application that uses quantum technologies. Specifically, we show how to map certain parts of the real-world traffic flow optimization problem to be suitable for quantum annealing. We show that time-critical optimization tasks, such as continuous redistribution of position data for cars in dense road networks, are suitable candidates for quantum applications. Due to the limited size and connectivity of current-generation D-Wave QPUs, we use a hybrid quantum and classical approach to solve the traffic flow problem.
Abstract Machine learning has been presented as one of the key applications for near-term quantum technologies, given its high commercial value and wide range of applicability. In this work, we introduce the quantum-assisted Helmholtz machine: a hybrid quantum–classical framework with the potential of tackling high-dimensional real-world machine learning datasets on continuous variables. Instead of using quantum computers only to assist deep learning, as previous approaches have suggested, we use deep learning to extract a low-dimensional binary representation of data, suitable for processing on relatively small quantum computers. Then, the quantum hardware and deep learning architecture work together to train an unsupervised generative model. We demonstrate this concept using 1644 quantum bits of a D-Wave 2000Q quantum device to model a sub-sampled version of the MNIST handwritten digit dataset with 16 × 16 continuous valued pixels. Although we illustrate this concept on a quantum annealer, adaptations to other quantum platforms, such as ion-trap technologies or superconducting gate-model architectures, could be explored within this flexible framework.
Quantum computing has emerged as a transformative paradigm, leveraging principles of quantum mechanics to tackle computationally intractable problems. This manuscript explores the potential of quantum computing for solving complex engineering problems—specifically optimization, simulation, and data analysis tasks—using technologies and methodologies available up to 2022. We examine both gate-based and quantum annealing approaches, outline experimental frameworks, and compare performance against classical counterparts. Results from simulated benchmark problems demonstrate promising speedups in select cases, though practical adoption is constrained by hardware limitations such as qubit coherence times and noise. The study concludes by highlighting avenues for integrating hybrid quantum-classical workflows in engineering, along with a discussion of current constraints and future directions. Over the past decade, research efforts have focused on understanding how quantum phenomena like superposition and entanglement can be harnessed to realize computational advantages for specific problem classes. In particular, combinatorial optimization problems—ubiquitous in engineering design and logistics—offer fertile ground for quantum algorithms such as the Quantum Approximate Optimization Algorithm (QAOA) and quantum annealing. Additionally, quantum simulation techniques, including the Variational Quantum Eigensolver (VQE), promise to accelerate the modeling of physical systems at the molecular and materials level, potentially informing the design of next-generation structural and functional materials. Beyond raw algorithmic performance, this paper carefully assesses the end‑to‑end workflow, accounting for overheads in problem encoding, error mitigation, and classical post‑processing. We also present a detailed analysis of resource utilization—quantified by qubit counts, circuit depths, and annealing schedules—highlighting trade‑offs between solution quality and execution time. Ultimately, our findings underscore that, while pure quantum speedups remain rare in 2022, hybrid approaches harnessing both quantum and classical resources can yield practical benefits for small‑to‑medium scale engineering tasks. This expanded evaluation provides a roadmap for researchers and practitioners interested in applying quantum computing to real‑world engineering challenges.
The article tackled the challenge of real-time data processing in dynamic, large-scale systems by examining machine learning strategies enhanced through quantum computing. As sectors such as smart cities and autonomous vehicles generated high-velocity, complex data, conventional algorithms faced limitations in adaptability and efficiency. This study systematically reviewed advanced quantum methodologies including quantum support vector machines, quantum particle swarm optimization, and quantum-enhanced gradient boosting and highlighted performance improvements over classical models. By leveraging specialized hardware and frameworks like GPUs and federated learning, these quantum-enhanced models achieved superior accuracy, scalability, and computational efficiency. Key stages in the proposed framework, such as data preprocessing and model adaptation, maximized efficiency, enabling real-time adaptability in dynamically changing environments. Findings demonstrated that integrating quantum techniques addressed significant computational challenges, showing strong potential for applications requiring rapid data response, minimal latency, and scalability. This research underscores the transformative impact of quantum-enhanced machine learning, offering robust solutions that could reshape complex, data-intensive industries dependent on real-time processing, such as healthcare, transportation, and finance. Future advancements in quantum computing could further solidify machine learning’s role in managing the demands of an increasingly data-driven world.
Quantum computing has demonstrated remarkable prowess in addressing factorization issues and unordered search problems, showcasing its quantum parallelism capabilities that enable exponential speed-up for specific computational challenges. However, the seamless integration of classical and quantum computing to harness accelerated computation speed presents unique challenges. This paper delves into the intricacies of this integration, focusing on the current state of quantum machine learning (QML) and evaluating the performance of classical and quantum algorithms in terms of accuracy. To address these challenges, we conducted experiments utilizing three datasets for binary classification, implementing both classical Support Vector Machine (SVM) and Quantum SVM (QSVM) algorithms. Our investigations reveal that the QSVM algorithm consistently outperforms its classical counterpart on complex datasets. Notably, the performance gap between quantum and classical models widens with increasing dataset complexity, shedding light on the susceptibility of simple classical models to overfitting when confronted with intricate datasets.Despite the ongoing development required for quantum hardware with ample resources, our findings underscore the significant potential of quantum machine learning, particularly in unsupervised learning and generative models. As we move forward, it is imperative to channel more efforts into exploring novel quantum learning models capable of harnessing the inherent power of quantum mechanics to overcome the constraints of classical machine learning. This research contributes to the ongoing discourse on the future of quantum computing, emphasizing the need for continued exploration and innovation in quantum machine learning methodologies.
Quantum machine learning is one of the fields where quantum computers are expected to bring advantages over classical methods. However, the limited size of current computers restricts the exploitation of the full potential of quantum machine learning methods. Additionally, different computing paradigms, both quantum and classical, each have their own strengths and weaknesses. Obtaining optimal results with algorithms thus requires algorithms to be tweaked to the underlying computational paradigm, and the tasks to be optimally distributed over the available computational resources. In this work, we explore the potential gains from combining different computing paradigms to solve the complex task of data classification for three different datasets. We use a gate-based quantum model to implement a quantum kernel and implement a complex feature map. Next, we formulate a quadratic unconstrained optimisation problem to be solved on quantum annealing hardware. We then evaluate the losses on classical hardware and reconfigure the model parameters accordingly. We tested this so-called triple-hybrid quantum support vector machine on various data sets, and find that it achieves higher precision than other support vector machines (both quantum and classical) on complex quantum data, whereas it achieves varying performance on simple classical data using limited training. For the complex data sets, the triple-hybrid version converges faster, requiring fewer circuit evaluations.