Research | AI for Smart Mobility Lab

01 / CURRENT PROJECTS

Current projects

Enhancing Safety and Trust in Mixed Traffic Environments with Connected and Automated Vehicles

The project aims to enhance safety and trust in mixed traffic environments by developing an integrated framework for interactions between Connected and Automated Vehicles (CAVs) and Vulnerable Road Users (VRUs). The research combines multimodal sensing, perception, behavior and intent prediction, VRU adversarial behavior recognition, cooperative perception, and risk-aware decision-making to enable automated vehicles to recognize both normal and potentially unsafe or adversarial VRU behaviors and respond appropriately. The framework will be validated through advanced simulation, hardware-in-the-loop, vehicle-in-the-loop, and controlled field testing, supporting Saudi Vision 2030 goals for safe, trustworthy, and human-centered autonomous mobility.

Funding KFUPM Deanship of ResearchDuration 2026 to 2029

Contextual Observability of Software-Defined Vehicles

SDV architecture decouples hardware and software, enabling OEMs to manage, update, and enhance vehicle features and functions through software alone. However, SDVs introduce unique challenges in ensuring system resilience, reliability, and real-time fault diagnosis. Observability is critical in such environments but remains underdeveloped for SDVs. This project aims to develop a testbed for SDV contextual observability that enables collecting multimodal telemetry data, facilitating continuous monitoring, advanced analytics, causal inferencing, and automated incident response.

Funding IRC for Smart Mobility and Logistics (SML) at KFUPMDuration 2025 to 2027

Agentic AI-based Framework for Seamless Integrated Mobility

Aligning with Saudi Vision 2030, this project supports Saudi Arabia's goals to increase public transit use and improve accessibility for all citizens, including individuals with disabilities, the elderly, and low-income groups. The research focuses on developing an agentic AI-based framework for Seamless Integrated Mobility (SIM), envisioned as a unified platform that integrates multimodal transportation options.

Funding KFUPM Deanship of ResearchDuration 2025 to 2027

SmartDispatch: AI-driven Optimization for Eco-Efficient Last-Mile Delivery

Saudi Arabia is a major market for eCommerce, with a growing number of people shopping online regularly. This growth has driven an increase in last-mile delivery services, creating a need for more efficient digital platforms. This project addresses the eco-efficient and adaptive routing problem during both liveheading and deadheading states of delivery vehicles, including trucks, cars, cargo bikes, and motorcycles. By optimizing last-mile delivery routes, the project contributes to Saudi Arabia's goal of significantly reducing transportation costs by 2030.

Funding IRC for Smart Mobility and Logistics (SML) at KFUPMDuration 2025 to 2026

02 / SAMPLES OF PREVIOUS PROJECTS

Samples of previous projects

General Motors Projects

Before joining KFUPM, the PI served as the AI and Smart Mobility Technical Leader at General Motors Canada. He led AI/ML projects focused on software-defined vehicles, connected and automated driving technologies, active safety systems, and prognostics, achieving successful technology insertions. He co-invented and filed 72 patents, trade secrets, and defensive publications, earning recognition as “Inventor of the Month” multiple times by GM's Global Patent & Invention Management team. The advanced features developed were for future GM vehicle models; therefore, further details cannot be disclosed due to confidentiality agreements with GM. Additional information about the filed patents can be found here.

VRU Crossing Intent Prediction

This research project introduces an innovative framework for pedestrian crossing intention prediction. The framework incorporates an image enhancement pipeline, which enables the detection and rectification of various defects that may arise during unfavorable weather conditions. Subsequently, a transformer-based network, featuring a self-attention mechanism, is employed to predict the crossing intentions of target pedestrians. This augmentation enhances the model's resilience and accuracy in classification tasks. Through evaluation on the JAAD dataset, our framework attains state-of-the-art performance while maintaining a notably low inference time. Moreover, a deployment environment is established to assess the real-time performance of the model.

Funding IoT Research Laboratory, Ontario Tech UniversityDuration 2022 to 2024image enhancement, self-attention, vision transformers

Robustness of Deep Learning-based VRU Detection Models

This research project highlights the critical role of accurate pedestrian detection in assisted and automated driving systems to enhance road safety. Real-world deployment faces challenges like image corruption and occlusions, addressed here through robust, stylized, and occluded training techniques. Robust training uses intentionally corrupted examples to simulate real-world scenarios, significantly improving model resilience. Stylized training employs Adaptive Instance Normalization (AdaIN) to introduce texture and style variations, enriching the dataset. Occluded training generates datasets simulating different occlusion levels, improving performance on occluded samples. Together these methods achieve a 2 to 4 percent performance boost, establishing a foundation for deploying reliable pedestrian detection models in complex environments.

Funding Nile UniversityDuration 2022 to 2024assisted and automated driving, VRU detection, model robustness

Optimal Placement of Bus Stops

Bus systems play an important role in the modern city, and carefully designed bus stop locations can lift overall transportation efficiency and save time for passengers. A Particle Swarm Optimization (PSO)-based approach is proposed to find the optimal placement of bus stops in the Waterloo and Kitchener area. The selection takes into account neighborhood population, family income, age distribution, and other factors, with the goal of minimizing average passenger travel time. Experimental results on real bus lines showed that both PSO and adaptive PSO provide shorter average commuting time than the original routes, using fewer stops.

Funding University of TorontoDuration 2022 to 2023optimal placement, swarm intelligence, particle swarm optimization

Future of Public Transport Experience

E-payment for public transport is a use case built by DM TECH featuring a smart bus-station experience. The concept was designed to visualize the influence of digitalizing public transport accessibility, ticketing, and payment. The experience is also available in VR for user-friendly and interactive simulation.