This study develops a hybrid quantum-classical framework for constrained vehicle routing problems, focusing on the pickup-and-delivery problem with time windows. Instead of casting the full routing problem as a stand-alone quantum optimization task, we embed shallow quantum samplers inside the repair phase of an Adaptive Large Neighbourhood Search (ALNS) heuristic. A Deep Q-Network controller decides whether each reduced repair subproblem should be handled by a classical repair heuristic or by a quantum sampler, using features that describe the local repair structure and predicted hardware reliability. IBM Heron experiments are used to calibrate an empirical noise-aware model for local quantum repair circuits. Across the tested instances, quantum repair is admissible in only about 16% of reduced repair states and is not superior on average. However, under selected matched repair budgets, quantum-enabled repair reduces the final gap relative to standard ALNS in 29 of 36 tested settings. These results suggest that near-term quantum sampling is most useful as a selective local repair mechanism rather than as a replacement for classical routing heuristics.
Journal reference
In the proceedings of 2026 IEEE Quantum Week (IEEE International Conference on Quantum Computing and Engineering)
Comments
Funding source: Natural Sciences and Engineering Research Council and Canada Research Chair
This study develops a hybrid quantum-classical framework for constrained vehicle routing problems, focusing on the pickup-and-delivery problem with time windows. Instead of casting the full routing problem as a stand-alone quantum optimization task, we embed shallow quantum samplers inside the repair phase of an Adaptive Large Neighbourhood Search (ALNS) heuristic. A Deep Q-Network controller decides whether each reduced repair subproblem should be handled by a classical repair heuristic or by a quantum sampler, using features that describe the local repair structure and predicted hardware reliability. IBM Heron experiments are used to calibrate an empirical noise-aware model for local quantum repair circuits. Across the tested instances, quantum repair is admissible in only about 16% of reduced repair states and is not superior on average. However, under selected matched repair budgets, quantum-enabled repair reduces the final gap relative to standard ALNS in 29 of 36 tested settings. These results suggest that near-term quantum sampling is most useful as a selective local repair mechanism rather than as a replacement for classical routing heuristics.
Hybrid quantum optimization for vehicle routing faces a practical bottleneck: direct QUBO encodings of CVRP quickly exceed near-term qubit and gate budgets, while quantum evaluations are expensive, noise-limited, and sensitive to backend and circuit configuration. We address this gap with an end-to-end decomposition pipeline that converts CVRP into bounded-width quantum subproblems and treats quantum execution as a decision problem within the optimization loop. Starting from a Fisher--Jaikumar assignment linearization, we apply Lagrangian relaxation to dualize customer-assignment couplers, yielding independent per-vehicle knapsack subproblems that admit QUBO/Ising evaluation. To replace brittle subgradient tuning, we learn a multiplier-update controller using expert-guided pretraining followed by reinforcement-learning fine-tuning, with rewards based on execution-realized progress and route reconstruction. We also introduce a constrained contextual bandit as a hardware-aware execution layer that selects backend and circuit configuration with feasibility screening, enabling adaptation across heterogeneous noisy resources and parallel multi-QPU scheduling. Computational results on multiple CVRPLIB families show that the decomposition yields stable bounded-width subproblems across instance sizes, learned multiplier updates improve end-to-end routing quality relative to classical subgradient control under matched budgets, and hardware-mode configuration reduces median optimality gaps relative to static execution choices in our test set. We do not claim quantum advantage. Instead, the contribution is a practical end-to-end framework for scaling hybrid quantum CVRP optimization through OR decomposition, learning-augmented dual control, and adaptive hardware-aware execution.
Graph coarsening reduces the large Quadratic Unconstrained Binary Optimization (QUBO) formulations arising when vehicle-routing problems are solved by quantum annealing. Nearby customers with compatible time windows are merged into super-nodes, the reduced problem is solved, and the solution is expanded to the original graph. For the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW), existing coarsening heuristics require family-specific tuning and remain unreliable on random instances. We address these limitations on the Solomon benchmark using simulated annealing and a D-Wave Advantage2 processor. We first introduce adaptive penalty calibration. Uniform penalty scaling has little effect, whereas controlling the internal coefficient range substantially improves raw samples. Removing non-binding constraints, normalising binding ones, and scaling the remaining penalties reduces mean raw constraint violations from 33.0 to 0.06 at the same solver budget (p=3.7e-11, n=56). A variable-count-preserving control attributes this gain to conditioning rather than problem size. Second, we replace the hand-tuned merge score with a graph neural network (GNN) using one configuration across all families. At N=10, it achieves 100% feasibility across all Solomon families, including R-type (100% vs. 80% for the tuned heuristic). Across N=10,...,100, feasibility is 83% vs. 69%, with the GNN better or tied on 85/90 instance-size pairs. At N=80,100, the difference is significant (p=0.002; 25/25 pairs), while the QUBO remains approximately 5-6 times smaller. Finally, hardware experiments reproduce the conditioning effect at fixed logical variable count: feasible samples increase from 0.02% to 39% across 13 instances. Classical repair with local search remains a reference bound for end-to-end solution cost.
Solving large-scale Capacitated Vehicle Routing Problems with Time Windows (CVRPTW) remains challenging because strict operational constraints and scale limit both exact and heuristic methods. We present a hybrid classical-quantum architecture combining Mixed Integer Linear Programming (MILP) with vehicle-level Quadratic Unconstrained Binary Optimization (QUBO), solved using Toshiba SQBM+ and QAOA on Rigetti Ankaa-3 and IQM Emerald quantum processors. The decomposition avoids the variable growth and constraint-enforcement difficulties of monolithic CVRPTW QUBO formulations. We evaluate the framework on five realistic benchmarks derived from London traffic and location data, spanning 10--70 customers, using a validation pipeline enforcing feasibility and monotone improvement over classical baselines. SQBM+ achieves verified fleet-distance reductions of 2.80% (7,927 m) for the 25-customer instance and 0.22% (1,186 m) for the 55-customer instance. QAOA experiments establish a current hardware boundary for reliable constraint satisfaction at subproblems of up to 4 customers (16 qubits). Diagnostic results identify assignment-level time-window tightness, rather than local route optimization, as the dominant scalability bottleneck. The results demonstrate a practical near-term role for hybrid classical-quantum optimization while establishing empirical limits for current quantum hardware.
Quantum computing (QC) stands at the cusp of revolutionizing computation, yet its near-term potential, constrained by Noisy Intermediate-Scale Quantum (NISQ) devices, remains underexplored. This dissertation investigates how hybrid quantum-classical algorithms can address combinatorial optimization challenges in logistics, focusing on vehicle routing and drone delivery—NP-hard problems with exponential solution spaces that defy classical exhaustive methods. Amidst NISQ limitations like limited qubits and high noise, we confront key challenges: encoding complex constraints, e.g., time windows, battery capacity, into quantum models, balancing quantum and classical components for scalability, and accessing scarce quantum resources. By integrating quantum annealing (QA) and the Quantum Approximate Optimization Algorithm (QAOA) with classical heuristics, this work demonstrates QC’s practical utility, advancing both optimization theory and real-world logistics applications. The dissertation unfolds across four core contributions. First, the Hybrid Quantum Tabu Search (HQTS) optimally solves the 50-location Capacitated Vehicle Routing Problem (CVRP), achieving a 4.72% optimality gap. Secondly, we refine HQTS to reach a 2.15% gap with enhanced QA utilization, outperforming prior hybrids on standard datasets. Third, adapting HQTS for the CVRPTWwith D-Wave’s Constrained Quadratic Model solver yields a 3.85% gap on 100-location instances, leveraging a novel heuristic to ensure time-window feasibility where quantum outputs falter. Lastly, QUADRO, a pioneering framework for drone delivery, employs QAOA-driven routing and hybrid scheduling, minimizing transit time and makespan for fleets of 2–11 drones needing fewer than 100 qubits, rivaling classical benchmarks on adapted Augerat datasets. These advances, tested via D-Wave’s Advantage system and Qiskit simulations, showcase hybrid strategies that mitigate NISQ constraints, delivering scalable, feasible solutions to logistics challenges. This work establishes near-term QC’s viability for combinatorial optimization, bridging theoretical promise with practical impact. Synthesizing quantum exploration with classical refinement achieves competitive performance, e.g., matching or surpassing Google ORTools in select CVRPTW cases, while illuminating NISQ limits, such as feasibility degradation beyond small scales. These hybrid strategies deliver scalable, feasible solutions, from a 2.15% optimality gap for CVRP to effective drone fleet management with fewer than 100 qubits, illuminating quantum computing’s potential despite its current constraints. Ultimately, this dissertation positions hybrid QC as a transformative tool for optimization challenges, offering a robust foundation for scaling quantum optimization into operational reality.
Vehicle Routing Problems (VRPs) remain computationally challenging at scale. Since Noisy Intermediate-Scale Quantum (NISQ) devices are not yet mature enough for direct end-to-end Capacitated Vehicle Routing Problem (CVRP) optimization, this study evaluated quantum kernels as structural preprocessing modules for classical routing pipelines. We proposed a hybrid quantum-classical framework in which shallow quantum feature maps generated customer-to-customer similarity matrices from spatial coordinates and normalized demand. These matrices were used as precomputed affinities for spectral clustering, followed by capacity-aware adjustment, reinforcement-learning-based initialization, and Adaptive Large Neighborhood Search (ALNS) refinement. Experiments on eight CVRPLIB instances showed that the proposed ZFeatureMap-based decomposition achieved an optimality gap below 2.0% across all tested instances. Compared with the coordinate-based k -means decomposition baseline under the same downstream pipeline, it improved routing cost on five instances, tied on one, and performed worse on two. The proposed method outperformed SCIP on most instances under the same 60-second limit, but did not outperform PyVRP, which achieved zero optimality gap on all tested instances. Geometrically compact clusters, measured by the Silhouette score, did not necessarily yield better routing performance. Hardware experiments on IBM Quantum’s ibm_kobe processor suggested that clustering-relevant kernel structure remained observable under the tested shallow-circuit NISQ setting, although this should not be interpreted as evidence of scalable routing advantage or real-time QPU deployability. Dense all-pair kernel estimation incurs an ON2 preprocessing cost, and scalability, noise, and feature-dimension growth remain important limitations. Despite these limitations, the results suggest that quantum kernels may serve as complementary routing-aware decomposition modules within classical optimization pipelines, particularly for offline structural preprocessing.
The central claim of this thesis is simple but underappreciated: the primary bottleneck in near-term quantum computing is not a shortage of algorithms; it is a lack of systematic decision-making. Which problem instances should we test? Which circuit architectures are worth training? Which hyperparameters actually drive performance, and which are distractions? Today’s quantum hardware sits in an uncomfortable middle ground. It is expressive enough to explore nontrivial quantum dynamics, yet it is too noisy and shallow for the theoretical speedups that motivate the field. This thesis argues that applying machine learning to classical control decisions in hybrid quantum classical methods is one of the most tractable ways to make these methods genuinely useful in this regime. This argument is developed through four research questions, each addressing a distinct decision-making layer and illustrating the thesis. The first asks whether the decisions inside a hybrid heuristic can be learned rather than hand-coded. Chapter 4 analyzes Recursive QAOA (RQAOA), a promising yet brittle approach to combinatorial optimization, and identifies regimes in which its fixed-elimination strategy fails. It then replaces that strategy with a reinforcement learning policy, RL-RQAOA, that adapts to instance structure. The resulting method performs better on the constructed failure cases while remaining competitive elsewhere. The broader point is that learned classical control policies can materially improve hybrid quantum heuristics without increasing quantum depth, which is a significant practical advantage on constrained hardware. The second question evaluates whether the quantum optimization algorithm benchmarking instances we use are principled. Chapter 5 observes that much benchmarking in this space is driven by convenience. Researchers test on whatever graphs are readily available and then report aggregate performance. Instead, the chapter proposes a generative pipeline that couples a permutation-invariant graph autoencoder with evolutionary optimization to deliberately construct Max-Cut instances that strongly discriminate between a quantum-inspired solver, RQAOA, and a strong classical baseline, Goemans-Williamson, in both directions. By connecting solver behavior to structural graph features, the chapter turns benchmarking from a static choice into an interpretable experimental tool. The generated instances also expose failure modes that random graphs often fail to reveal. The third question asks what changes when realistic noise constraints are taken seriously during circuit design, not only during execution. Chapter 6 develops RLQAS, a reinforcement learning framework for quantum architecture search that incorporates noise assumptions informed by real IBM device characteristics throughout training, rather than treating noise as a post hoc correction. Paired with an efficient Pauli transfer matrix simulation, the framework makes large-scale noisy circuit search computationally feasible. The circuits it discovers are compact, trainable, and achieve competitive accuracy on ground-state energy tasks. This suggests that hardware-aware circuit design is tractable and can yield materially different choices than noise-agnostic search. The fourth question asks: even when the circuit architecture is fixed, how much of what we attribute to quantum model design is actually due to hyperparameter sensitivity? Chapter 7 extends functional ANOVA to quantum neural networks to quantify which hyperparameter choices drive performance variance. The finding is clear. Learning rate, circuit depth, and data encoding/reuploading dominate, while many architectural micro-choices contribute far less than the literature often implies. Rather than stopping at diagnosis, the chapter turns these importance rankings into data-driven priors that accelerate hyperparameter optimization. It converts a critique into a practical improvement. Taken together, these contributions form a coherent toolkit for developing and evaluating hybrid quantum–classical methods in the NISQ regime. While the work does not eliminate the fundamental constraints of shallow, noisy hardware, it clarifies what can be improved immediately and how to do so in a reproducible manner. The broader goal is to help shift near-term quantum research from isolated demonstrations toward an engineering discipline, in which algorithms, benchmarks, and model-selection practices can be compared fairly, stress-tested rigorously, and iterated systematically as hardware matures.