ITSC 2021
158 papers
The 2021 edition of the IEEE International Conference on Intelligent Transportation Systems (ITSC) presented 183 papers centered on autonomous agent planning, traffic coordination, and trajectory prediction. Research themes emphasized multi-modal prediction, hierarchical games for strategic incentive design, and socially aware motion planning for interactive driving environments. Central topics included grounding trajectory predictions in static scene geometry and scaling coordination mechanisms across general network graphs.
Technical contributions included the introduction of open-source tools like the OpenCDA framework for cooperative driving and the CommonRoad Scenario Designer for map conversion. Other work explored ensemble architectures for imbalanced data, adversarial networks for learning from collision data, and graph convolutional neural networks for traffic monitoring. Prolific authors for the year included Nanning Zheng, Shitao Chen, and Matthias Althoff. The proceedings reflected a trend toward utilizing game theory to model stakeholder interactions and improving behavioral fidelity in mixed autonomy traffic control systems.
Top Research Directions
Research directions most represented by ITSC 2021 papers.
Top Authors
Impactful Papers
Papers from ITSC 2021 that shaped research clusters.
Foundational
Game Theory to Study Interactions between Mobility Stakeholders
foundational
The Non-Linear Dynamics of Policy Interv
Perspective, Survey and Trends: Public Driving Datasets and Toolsets for Autonomous Driving Virtual
foundational
Standardizing Safety Evaluation for Auto
Influential
An Interaction-aware Evaluation Method for Highly Automated Vehicles
influential
Social Utility Weighting in Multi-Agent
An Interaction-aware Evaluation Method for Highly Automated Vehicles
influential
Modeling Heterogeneous Driving Styles in
Reinforcement Learning for Ridesharing: A Survey
influential
Mean Field Approximation for Scalable Mu
HOME: Heatmap Output for future Motion Estimation
influential
Probabilistic Trajectory Forecasting for
Belief state separated reinforcement learning for autonomous vehicle decision making under uncertain
influential
Decoupling Estimation and Control in Net
Papers
« prev Page 4/4