Active Autonomous Driving Motion Planning
Risk-Aware Autonomous Driving
Research on real-time local planning and decision-making under uncertainty for autonomous driving in dynamic urban traffic.
Research
Research Agenda
Decision-making, control, and data for deployable autonomous systems
My research is centered on autonomous driving and intelligent transportation systems, with emphasis on decision-making under uncertainty, risk-aware planning, connected mobility, and deployable autonomy stacks. I work across optimization, control, learning, and dataset-driven research infrastructure to address problems that matter in real traffic environments.
4 Research Threads
15 Publications
5 Journal Articles
8 Conference Papers
Research Threads
The main lines of my work, each organized as a focused project page with methods, questions, and representative outputs.
Active ITS Eco-Driving
Intelligent Transportation Systems
Optimization and control for eco-driving, signal coordination, and connected emergency-vehicle prioritization in mixed traffic.
Active Learning-Based Control Optimization
Learning-Based Control and Optimization
Reinforcement learning, control design, and optimization methods for autonomous and dynamic engineering systems.
Active Trajectory Prediction Datasets
Trajectory Prediction and Research Datasets
Trajectory-prediction research, benchmark design, privacy-aware datasets, and data-driven scene understanding for autonomous driving.
Methodological Toolkit
A mix of optimization, simulation, control, and learning methods used across research problems.
Planning and Optimization
Risk-aware decision-making under uncertainty
I develop local planning and optimization methods that account for uncertainty, safety constraints, and real-time feasibility in dynamic traffic environments.
Control and Learning
Data-informed control for engineering systems
I combine reinforcement learning with classical control and systems modeling to design controllers that remain interpretable and engineering-relevant.
Transportation Systems
Infrastructure-aware autonomy in mixed traffic
I study how connected and autonomous vehicles can interact with traffic infrastructure to improve travel time, energy efficiency, and emergency response.
Datasets and Evaluation
Benchmarks, prediction, and research infrastructure
I contribute to trajectory-prediction surveys, multi-task benchmark datasets, anonymization workflows, and data-driven evaluation pipelines for autonomous-driving research.
Platforms and Research Stack
The software and simulation ecosystem behind the research.
Autonomous Driving and Robotics
Simulation and autonomy tooling
Traffic and Control Infrastructure
Traffic simulation and modeling
Engineering Workflow
Development and experimentation
Research Style
Practical, reproducible, deployment-aware
- Problem-driven research tied to real traffic or robotic settings.
- Emphasis on tractable methods, implementation realism, and validation.
- Integration of theory, simulation, datasets, and system-level evaluation.
Representative Outputs
Selected publications that illustrate the breadth of the research program.
Motion Planning
Online Risk-Bounded Graph-Based Local Planning for Autonomous Driving with Theoretical Guarantees
Develops a real-time local planner with explicit risk bounds and theoretical guarantees for autonomous driving.
Transportation Systems
Multiple Intelligent Control Strategies for Travel-Time Reduction of Connected Emergency Vehicles
Presents intelligent control strategies for connected emergency vehicles using path planning and signal intervention.
Prediction and Survey
Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions
Surveys recent trajectory-prediction methods and maps the field’s unresolved technical gaps.
Datasets
EMT: A Visual Multi-Task Benchmark Dataset for Autonomous Driving in the Arab Gulf Region
Introduces a benchmark dataset tailored to multi-task autonomous-driving research and evaluation.