arXiv subjects

Bilal Farooq

Publications and source records attributed to Bilal Farooq.

At least 19 recordsLinked to original sources

arXiv2026

Assessment of Latent Pedestrian-Vehicle Interaction Risk Profiles at Midblock Crossing in VR

Pedestrian safety at midblock crossings is a critical concern in mixed traffic environments where autonomous vehicles (AVs) and human-driven vehicles (HDVs) share the road. Pedestrians often infer intent from vehicle motion in AV encounters, making them vulnerable to small shifts in conflict margins. This study investigates whether virtual reality (VR) crossing sessions separate into distinct interaction risk profiles and whether AV-only sessions shift profile prevalence compared to HDV-only sessions. Using large-scale immersive VR experiments from Toronto, Canada, and Newcastle, England, we compute surrogate safety measures (SSMs) and apply latent profile analysis (LPA) to identify distinct pedestrian crossing stances, ranging from risk-accepting to highly cautious. Key findings show that Newcastle exhibits a higher prevalence of high-urgency risk profiles in AV-only sessions, indicating that AVs contribute to higher-risk encounters. In contrast, Toronto shows no significant difference between AV-only and HDV-only sessions, suggesting that contextual factors influence the impact of AVs on pedestrian safety.

physics.soc-ph↗

arXiv2026

Vehicle-Routing Clustering by Sparse Quantum Relaxation

This paper studies the cluster-assignment layer of a cluster-first-route-second decomposition for the capacitated pickup-and-delivery problem with time windows (CPDPTW), instead of a direct route-ordering quadratic unconstrained binary optimization (QUBO). Sample-based subspace diagonalization (SQD) degenerates to best-of-shots for any diagonal optimization Hamiltonian, so a useful transfer to routing requires non-diagonal relaxation. Quantum random access optimization (QRAO) provides this non-diagonality by encoding binary variables through non-commuting quantum random access code (QRAC) observables. CPDPTW-derived conflict graphs expose a routing-specific obstruction because dense objectives and penalty-encoded constraints destroy QRAO compression. We keep the Hamiltonian sparse by encoding only the sparsified objective and enforcing one-hot, capacity, and cluster time-budget feasibility by repair after rounding. We make no quantum-advantage claim. Under strong repair the classical pass alone reaches near-optimal cost at the tested sizes. The result is a regime map linking sparsification, achieved compression, linear-combination-of-unitaries (LCU) 1-norm, heavy-hex two-qubit depth, sampling drift, and final routing quality on Qiskit Aer, calibrated FakeTorino, and IBM Heron ibm_quebec. Across a 108-row ideal-calibrated-hardware evaluation grid spanning four to twelve pickup-delivery request pairs, the hardware slice has mean gap 0.0016 and mean device-vs-ideal total variation distance (TVD) 0.279; a decoder ablation at sizes six through twelve isolates the non-diagonal signal.

quant-ph↗

arXiv2026

Feasible and Novel Synthetic Population Generation with Tabular and Sequential Travel Attributes

Synthetic populations are critical inputs for activity-based travel demand models, yet generating realistic populations from limited survey data remains challenging. Small samples miss valid attribute combinations, known as sampling zeros, and generative models may also produce infeasible structural zeros. Moreover, realistic synthetic populations must capture both static socio-demographic attributes and sequential travel behaviour, such as trip chains. This paper proposes a regularized two-stage generative framework to address these challenges, where regularization refers to additional loss terms that guide the generator toward broader valid coverage and fewer infeasible samples. In Stage 1, a Wasserstein GAN with gradient penalty is augmented with three regularization terms, IGP, LDR, and CLAP, to improve feasibility, diversity, and novelty in tabular population synthesis. In Stage 2, Transformer and LSTM-Attention models generate sequential travel attributes, including departure time, trip purpose, and travel mode, conditioned on the synthesized tabular profiles. We also introduce novelty and count-aware metrics to evaluate whether valid unseen combinations are recovered and generated in realistic proportions. Results show that regularized models outperform the vanilla WGAN-GP across feasibility, diversity, and novelty. Regularization increases feasibility by 2.1 to 3.7 percentage points and novelty by 6.6 to 10.0 percentage points, improving sampling-zero recovery without sacrificing feasibility. The F1 score improves by 6.3 to 8.6 percentage points. For sequential attributes, LSTM-Attention best matches the trip-length distribution, while Transformer achieves higher overall sequential F1, 90.6\% versus 89.1\%. Cross-stage validation confirms strong consistency between generated mobility status and generated trip chains.

cs.LG↗

arXiv2026

Q-SCM: A Quantum-Sequential Choice Model for Driver Mental State Evolution

We propose a Quantum-Sequential Choice Model (Q-SCM) for modelling driver mental state evolution in interactive traffic environments. The proposed framework retains the classical latent class choice structure, but replaces the conventional class membership formulation with a quantum cognitive state model. A unique feature of this model is that the quantum component is confined to the class membership layer, while the action choice layer remains a classical RUM. The driver's latent state is represented as a two-state quantum system on the Bloch sphere including neutral and defensive states. Perceptual cues, including separation distance, closing time-to-collision (CTTC), and lane deviation induce sequential unitary rotations governed by Pauli matrices. This formulation allows the model to capture memory, phase effects, cue order dependence, and transitions between behavioural regimes that depend on prior cue history. To ensure well-behaved state evolution, we introduce three control mechanisms: a monotonicity constraint that prevents pendulum-like overshoot, a geodesic safeguard mechanism that ensures convergence toward the defensive state under sustained threat exposure, and a relaxation step that allows recovery toward the neutral baseline when the threat weakens. The model is estimated using 85,754 observations from 9,610 drivers extracted from naturalistic trajectories. The empirical results show that defensive state formation is not governed only by the instantaneous values of traffic cues, but also by the accumulated cue history and the order in which cues are processed.

econ.EM↗

arXiv2026

Integrated Optimization of Automated Warehouse Operations and Last-Mile Transport for Differentiated On-Demand Delivery

In the context of differentiated on-demand goods delivery services, this study proposes an integrated optimization method for automated guided vehicles (AGVs) based smart warehouse operations and the last-mile multi-modal transport. A deep reinforcement learning algorithm for multi-objective joint scheduling is designed to establish a dynamic connection between two systems, solving key challenges such as achieving high-throughput continuous order scheduling, meeting competing requirements, and improving the overall system sensitivity and adaptability. For warehouse optimization within this framework, we propose an improved algorithm based on multi-objective, Multi-Reward Machines-A* Guided Deep Q-Network (MORM-AGDQN), which combines service level, system cost, and external transportation demand. For external optimization, we propose an improved algorithm based on a Multi-Reward, Multi Head attention-Heterogeneous Capacity Vehicle Routing Problem (MRMH-HCVRP) framework, which incorporates the optimized scheduling order sequence and grouping, combined with customer location, demand, and priority, vehicle capacity, speed, and service range. The results show that the proposed framework significantly outperforms traditional methods, achieving 100% on-time delivery rate for warehousing operations. After joint optimization, the average delivery time for the last mile was reduced by 29.3% to 53.2%, the total transportation distance was reduced by 46.4%, the high-priority service rate was increased to over 92%, and a balance was maintained between operating costs and customer satisfaction.

cs.LG↗

arXiv2026

RL-Guided Quantum-ALNS for Constrained VRP

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.

quant-ph↗

arXiv2026

Mobility Behaviour of Immigrants in Canada: Analyzing Mode Choice Using GPS Panel Data and Mixed Logit Models

We examine these relationships using a panel dataset of more than 80,000 trip observations from 100 participants through a custom-built mobile application. A joint revealed preference (RP) and stated preference (SP) framework is used to estimate multinomial logit (MNL) and mixed logit (MXL) models. The level of integration is represented through a composite index capturing economic, social, civic, and health dimensions of integration. Results indicate two distinct patterns. First, the estimated models suggest that new immigrants in the sample exhibit lower sensitivity to in-vehicle travel time than Canadian-born respondents. The mixed logit specification suggests that the value of travel time for the sampled immigrants is approximately 66% lower than that of Canadian-born residents, with a immigrant-to-Canadian-born ratio of 0.34 that is consistent across both MXL specifications. Second, higher levels of integration are associated with reduced transit use and greater car reliance. A one standard deviation increase in the integration index decreases the probability of choosing public transit by approximately five percentage points. The joint RP-SP specification allows the inclusion of emerging e-mobility alternatives not yet observed in revealed behaviour; these face no inherent preference penalty, competing purely on their level-of-service attributes. Out-of-sample validation using five-fold cross-validation produces a mean prediction accuracy between 80% and 82% across model specifications. The findings suggest that transit policies in immigrant-receiving cities could prioritize service quality improvements, particularly reductions in access time, which are approximately three times more effective than fare reductions in shifting immigrants toward transit use.

econ.EM↗

arXiv2026

A bi-level priority sorting framework for flexible AGV service scheduling in smart warehouses

This paper proposes a bi-level optimization framework to coordinate Automated Guided Vehicle (AGV) flexible operations in smart independent warehouses, addressing the critical challenge of balancing high-throughput order fulfillment with stringent cost control. The framework is designed to simultaneously optimize flexible customer service level, system cost, and operational efficiency. The first level dynamically adjusts real-time scheduling parameters, such as order commitment times and delay tolerance, based on predefined customer priority categories. The second level performs real-time routing optimization for each AGV by identifying the shortest feasible paths while avoiding conflicts. For complex multi-capacity package picking tasks, two heuristic rules, priority, deadline, with shortest path (PDSP) and delay cost with shortest path (DCSP), are applied to multi-capacity package picking tasks and further training is carried out using the reinforcement learning algorithm of A* guided deep Q-learning (AGDQN). Comprehensive simulation experiments, conducted across diverse warehouse layouts and order demand patterns, demonstrate that the proposed framework equipped with both heuristic rules consistently reduces average order delay and total system costs by over 50% during peak demand periods. This is achieved while maintaining a service level above 90% and maximizing AGV utilization. The method also exhibits superior flexibility and sustained efficiency under normal and fluctuating demand scenarios. Additional ablation studies confirm that the proposed priority sorting mechanism delivers robust performance advantages when tested with various other reinforcement learning baselines.

math.OC↗

arXiv2026

Copula-ResLogit: A Deep-Copula Framework for Unobserved Confounding Effects

A key challenge in travel demand analysis is the presence of unobserved factors that may generate non-causal dependencies, obscuring the true causal effects. To address the issue, the study introduces a novel deep learning based fully interpretable joint modelling framework, Copula-ResLogit, which integrates the flexibility of Residual Neural Network (ResNet) architectures with the dependence capturing capabilities of copula models. This hybrid structure enables us to first detect unobserved confounding through traditional copula function based joint modelling and then mitigate these hidden associations by incorporating deep learning components. The study applies this framework to two case studies, including the relationship between stress levels and wait time of pedestrians when crossing mid block in VR and the dependencies between travel mode choice and travel distance in London travel behaviour data. Results show that Copula-ResLogit substantially reduces or eliminates the dependencies, demonstrating the ability of residual layers to account for hidden confounding effects.

cs.LG↗

arXiv2026

From GEV to ResLogit: Spatially Correlated Discrete Choice Models for Pedestrian Movement Prediction

High frequency pedestrian motion forecasting when interacting with autonomous vehicles (AVs) can be enhanced through the use of behavioural frameworks, such as discrete choice models, that can explicitly account for correlation among similar movement alternatives. We formulate the pedestrian next step choice as a spatial discrete choice defined by a grid of speed adjustment and heading change. Using naturalistic pedestrian-AV encounters from nuScenes and Argoverse 2 (1 sec decision interval), we estimate a multinomial logit baseline and four spatial generalized extreme value (GEV) specifications (SCL, GSCL, SCNL, and GSCNL). We then compare them to a residual neural network logit (ResLogit) model that learns cross alternative effects while retaining an interpretable linear utility component. Across the evaluated data, spatial GEV structures yield only marginal improvements over multinomial logit, whereas ResLogit achieves a substantially better fit and produces behaviourally coherent errors concentrated among neighbouring grid cells. The results suggest that in dense, high frequency spatial choice sets, learning based residual corrections can capture proximity induced correlation more effectively than analyst specified GEV nesting structures, while maintaining interpretability.

physics.soc-ph↗

arXiv2026

Enhancing Diversity and Feasibility: Joint Population Synthesis from Multi-source Data Using Generative Models

Generating realistic synthetic populations is essential for agent-based models (ABM) in transportation and urban planning. Current methods face two major limitations. First, many rely on a single dataset or follow a sequential data fusion and generation process, which means they fail to capture the complex interplay between features. Second, these approaches struggle with sampling zeros (valid but unobserved attribute combinations) and structural zeros (infeasible combinations due to logical constraints), which reduce the diversity and feasibility of the generated data. This study proposes a novel method to simultaneously integrate and synthesize multi-source datasets using a Wasserstein Generative Adversarial Network (WGAN) with gradient penalty. This joint learning method improves both the diversity and feasibility of synthetic data by defining a regularization term (inverse gradient penalty) for the generator loss function. For the evaluation, we implement a unified evaluation metric for similarity, and place special emphasis on measuring diversity and feasibility through recall, precision, and the F1 score. Results show that the proposed joint approach outperforms the sequential baseline, with recall increasing by 7\% and precision by 15\%. Additionally, the regularization term further improves diversity and feasibility, reflected in a 10\% increase in recall and 1\% in precision. We assess similarity distributions using a five-metric score. The joint approach performs better overall, and reaches a score of 88.1 compared to 84.6 for the sequential method. Since synthetic populations serve as a key input for ABM, this multi-source generative approach has the potential to significantly enhance the accuracy and reliability of ABM.

cs.AI↗

arXiv2026

Modelling Pedestrian Behaviour in Autonomous Vehicle Encounters Using Naturalistic Dataset

Understanding how pedestrians adjust their movement when interacting with autonomous vehicles (AVs) is essential for improving safety in mixed traffic. This study examines micro-level pedestrian behaviour during midblock encounters in the NuScenes dataset using a hybrid discrete choice-machine learning framework based on the Residual Logit (ResLogit) model. The model incorporates temporal, spatial, kinematic, and perceptual indicators. These include relative speed, visual looming, remaining distance, and directional collision risk proximity (CRP) measures. Results suggest that some of these variables may meaningfully influence movement adjustments, although predictive performance remains moderate. Marginal effects and elasticities indicate strong directional asymmetries in risk perception, with frontal and rear CRP showing opposite influences. The remaining distance exhibits a possible mid-crossing threshold. Relative speed cues appear to have a comparatively less effect. These patterns may reflect multiple behavioural tendencies driven by both risk perception and movement efficiency.

physics.soc-ph↗

arXiv2025

Latent Class Logit Kernel Framework for Surrogate Safety: Identifying Behavioural Thresholds through Conflict Indicator Profiles

Crash data objectively characterize road safety but are rare and often unsuitable for proactive safety management. Traffic conflict indicators such as time-to-collision (TTC) provide continuous measures of collision proximity but require thresholds to distinguish routine from safety-critical interactions. Extreme Value Theory (EVT) offers statistically defined thresholds, yet these do not necessarily represent how drivers perceive and respond to conflict. This study introduces a behavioural modelling framework that identifies candidate behavioural thresholds (CBTs) by explicitly modelling how drivers adjust their movements under conflict conditions. The framework is based on a Latent Class Logit Kernel (LC-LK) model that captures inter-class heterogeneity (routine vs. defensive driving) and intra-class correlation between overlapping spatial alternatives. This yields probability curves showing how the likelihood of defensive manoeuvres varies with conflict indicators, from which CBTs such as inflection points and crossovers can be extracted. The framework tests four hypotheses: (1) drivers exhibit varying degrees of membership in both low- and high-risk classes; (2) membership shifts systematically with conflict values, revealing behavioural thresholds; (3) this relationship follows a logistic shape, with stable behaviour at safe levels and rapid transitions near critical points; and (4) even in free flow, drivers maintain a baseline caution level. Application to naturalistic roundabout trajectories revealed stable TTC thresholds (0.8-1.1 s) but unstable MTTC2 estimates (e.g., 34 s), suggesting cognitive limits in processing complex indicators. Overall, the framework complements EVT by offering a structured, behaviourally grounded method for identifying and validating thresholds in surrogate safety analysis.

physics.soc-ph↗

arXiv2025

Towards Locally Deployable Fine-Tuned Causal Large Language Models for Mode Choice Behaviour

This study investigates the adoption of open-access, locally deployable causal large language models (LLMs) for travel mode choice prediction and introduces LiTransMC, the first fine-tuned causal LLM developed for this task. We systematically benchmark eleven open-access LLMs (1-12B parameters) across three stated and revealed preference datasets, testing 396 configurations and generating over 79,000 mode choice decisions. Beyond predictive accuracy, we evaluate models generated reasoning using BERTopic for topic modelling and a novel Explanation Strength Index, providing the first structured analysis of how LLMs articulate decision factors in alignment with behavioural theory. LiTransMC, fine-tuned using parameter efficient and loss masking strategy, achieved a weighted F1 score of 0.6845 and a Jensen-Shannon Divergence of 0.000245, surpassing both untuned local models and larger proprietary systems, including GPT-4o with advanced persona inference and embedding-based loading, while also outperforming classical mode choice methods such as discrete choice models and machine learning classifiers for the same dataset. This dual improvement, i.e., high instant-level accuracy and near-perfect distributional calibration, demonstrates the feasibility of creating specialist, locally deployable LLMs that integrate prediction and interpretability. Through combining structured behavioural prediction with natural language reasoning, this work unlocks the potential for conversational, multi-task transport models capable of supporting agent-based simulations, policy testing, and behavioural insight generation. These findings establish a pathway for transforming general purpose LLMs into specialized and explainable tools for transportation research and policy formulation, while maintaining privacy, reducing cost, and broadening access through local deployment.

cs.CL↗

arXiv2025

Quantum Machine Learning in Transportation: A Case Study of Pedestrian Stress Modelling

Quantum computing has opened new opportunities to tackle complex machine learning tasks, for instance, high-dimensional data representations commonly required in intelligent transportation systems. We explore quantum machine learning to model complex skin conductance response (SCR) events that reflect pedestrian stress in a virtual reality road crossing experiment. For this purpose, Quantum Support Vector Machine (QSVM) with an eight-qubit ZZ feature map and a Quantum Neural Network (QNN) using a Tree Tensor Network ansatz and an eight-qubit ZZ feature map, were developed on Pennylane. The dataset consists of SCR measurements along with features such as the response amplitude and elapsed time, which have been categorized into amplitude-based classes. The QSVM achieved good training accuracy, but had an overfitting problem, showing a low test accuracy of 45% and therefore impacting the reliability of the classification model. The QNN model reached a higher test accuracy of 55%, making it a better classification model than the QSVM and the classic versions.

cs.LG↗

arXiv2025

Quantum-Efficient Reinforcement Learning Solutions for Last-Mile On-Demand Delivery

Quantum computation has demonstrated a promising alternative to solving the NP-hard combinatorial problems. Specifically, when it comes to optimization, classical approaches become intractable to account for large-scale solutions. Specifically, we investigate quantum computing to solve the large-scale Capacitated Pickup and Delivery Problem with Time Windows (CPDPTW). In this regard, a Reinforcement Learning (RL) framework augmented with a Parametrized Quantum Circuit (PQC) is designed to minimize the travel time in a realistic last-mile on-demand delivery. A novel problem-specific encoding quantum circuit with an entangling and variational layer is proposed. Moreover, Proximal Policy Optimization (PPO) and Quantum Singular Value Transformation (QSVT) are designed for comparison through numerical experiments, highlighting the superiority of the proposed method in terms of the scale of the solution and training complexity while incorporating the real-world constraints.

quant-ph↗

arXiv2025

Vision-based Perception System for Automated Delivery Robot-Pedestrians Interactions

The integration of Automated Delivery Robots (ADRs) into pedestrian-heavy urban spaces introduces unique challenges in terms of safe, efficient, and socially acceptable navigation. We develop the complete pipeline for a single vision sensor based multi-pedestrian detection and tracking, pose estimation, and monocular depth perception. Leveraging the real-world MOT17 dataset sequences, this study demonstrates how integrating human-pose estimation and depth cues enhances pedestrian trajectory prediction and identity maintenance, even under occlusions and dense crowds. Results show measurable improvements, including up to a 10% increase in identity preservation (IDF1), a 7% improvement in multiobject tracking accuracy (MOTA), and consistently high detection precision exceeding 85%, even in challenging scenarios. Notably, the system identifies vulnerable pedestrian groups supporting more socially aware and inclusive robot behaviour.

cs.RO↗

arXiv2025

A Coalition Game for On-demand Multi-modal 3D Automated Delivery System

We introduce a multi-modal autonomous delivery optimization framework as a coalition game for a fleet of UAVs and ADRs operating in two overlaying networks to address last-mile delivery in urban environments, including high-density areas and time-critical applications. The problem is defined as multiple depot pickup and delivery with time windows constrained over operational restrictions, such as vehicle battery limitation, precedence time window, and building obstruction. Utilizing the coalition game theory, we investigate cooperation structures among the modes to capture how strategic collaboration can improve overall routing efficiency. To do so, a generalized reinforcement learning model is designed to evaluate the cost-sharing and allocation to different modes to learn the cooperative behaviour with respect to various realistic scenarios. Our methodology leverages an end-to-end deep multi-agent policy gradient method augmented by a novel spatio-temporal adjacency neighbourhood graph attention network using a heterogeneous edge-enhanced attention model and transformer architecture. Several numerical experiments on last-mile delivery applications have been conducted, showing the results from the case study in the city of Mississauga, which shows that despite the incorporation of an extensive network in the graph for two modes and a complex training structure, the model addresses realistic operational constraints and achieves high-quality solutions compared with the existing transformer-based and classical methods. It can perform well on non-homogeneous data distribution, generalizes well on different scales and configurations, and demonstrates a robust cooperative performance under stochastic scenarios across various tasks, which is effectively reflected by coalition analysis and cost allocation to signify the advantage of cooperation.

cs.LG↗