Automated Taxi Routing and Planning

Our research in automated taxi routing problems includes areas such as multiclass traffic assignment, taxi fleet optimization, trip-vehicle assignment, and vehicle route planning. We have a particular focus on shared automated taxi routing in dynamic transportation networks, aiming to provide door-to-door mobility service for travelers and enable ride-sharing among different requests. Key Capabilities: - Vehicle routing optimization - Vehicle fleet management - Traffic congestion impacts analysis - System performance evaluation

MoST project - Vehicle Autonomy and Network Optimisation

TSE Lab is part of a key program project that was awarded by the Chinese Minstry of Science and Technology with a total funding of ¥20m RMB to investigate the technologies and theories for cooperative transportation management and control systems (grant no. 2018YFB1600500). The project is led by Beijing University of Aeronautics and Astronautics. A consortium includes Tsinghua University, Tongji University, Jilin University and Zhejiang University who will work together aim to advance our understandings on potential impacts of connected autonomous vehicles (CAVs) on our society and develop models and theories to optimize the transportation system with different levels of market penetration of CAVs.

Royal Society project - Urban Traffic Management and Control

The project is led by Dr Simon Hu to develop methods of real-time traffic and air quality management and decision support systems for urban traffic operation. We propose an urban traffic decision support system which will rely on statistical learning and cloud computing to process massive, multi-source, and heterogeneous traffic and pollutant data. Such system will be able to generate nonlinear but computationally efficient real-time relationships between multiresolution urban road traffic states and environmental measures of effectiveness to support proactive traffic control (e.

Transfer Learning in Traffic Engineering

We devote to designing transferable and self-adaptive models to handle the dynamic changes and data insufficient problems in short-term traffic prediction. Both model and sample based transfer strategies are investigated to reveal the rules of transferable features, and deal with a seires of complex and volatile scenarios in traffic state estimation. Key Capabilities: - Transfer learning - Domain adaptation - Self-adaptive model