Xinling Li

Xinling Li is a graduate student in civil and environmental engineering whose research lies at the intersection of AI, optimization, and urban mobility. She designs algorithms that enable large-scale, on-demand transportation systems to operate efficiently and equitably in the face of uncertainty. With a focus on ride-sharing networks that serve large networks with dense demand, Xinling combines multi-agent reinforcement learning with robust optimization to develop adaptive strategies for vehicle dispatching and rebalancing. As a MathWorks Fellow, she will use MATLAB’s toolboxes to model and simulate complex agent interactions under dynamic traffic conditions. Xinling has leveraged MATLAB throughout her academic journey, from prototyping coverage-control algorithms and solving vehicle-routing problems to building real-time visualizations of fleet behavior. Her work is powered by MATLAB’s Optimization, Statistics, Image Processing, and Parallel Computing Toolboxes, which enable rapid iteration, model interpretability, and computational scalability. Xinling’s work paves the way for the future of intelligent urban mobility, with the capacity to transform how cities design, operate, and scale more inclusive transportation systems.