ITSC 2022

173 papers
The 2022 edition of the IEEE International Conference on Intelligent Transportation Systems (ITSC) featured 211 papers, with a primary focus on multi-agent reinforcement learning (MARL) and its applications to autonomous mobility. Key research directions included centralized training with decentralized execution, communication-aware coordination, and credit assignment within cooperative multi-agent systems. Technical contributions addressed challenges in non-stationary environments and partially observable settings, alongside the development of formal safety shields for deep reinforcement learning and monotonic value factorization. Beyond reinforcement learning, the conference explored topics such as anomaly detection via normalizing flow density estimation and open vocabulary object detection. Transportation-specific studies included traffic disruption modeling in multi-modal networks, train scheduling optimization for virtual coupling, and the use of social media data for transport policy. Prolific contributors to this year's proceedings included Nanning Zheng, Matthias Althoff, and Xiao Wang. The research collectively reflects a trend toward integrating cyber-physical-social systems and enhancing the safety and personalization of autonomous driving styles.

Top Research Directions

Research directions most represented by ITSC 2022 papers.

Safe Reinforcement Learning via Constrained Markov Decision Processes 3
Overcoming Sensor Occlusion Through Collaborative Perception 2
Benchmarking Behavioral Realism in Socially Aware Systems 1
Passive Network Traffic Analysis for Behavioral Profiling 1
Neural Feature Sharing for Bandwidth Efficient Cooperative Perception 1
Integrating Lateral and Longitudinal Vehicle Control 1
Modeling Road Network Topology for Autonomous Driving 1
Parameter Sharing for Scalable Multi Agent Learning 1
Simulating Complex Systems with Agent Based Modeling 1
Single-Level Reductions for Bilevel Optimization 1
Generalizing Autonomous Driving Beyond Simplified Environments 1
Proactive Autonomous Planning via Leader Follower Games 1
Goal-Conditioned Motion Forecasting via Destination Anchoring 1
Mitigating Stale Data Interference in Experience Replay 1
Overcoming the Idealized Communication Assumption in Cooperative Driving 1

Top Authors

AuthorPapers
Matthias Althoff6
Nanning Zheng6
Yisheng Lv5
Alois Knoll4
Chen Lv4
Diange Yang4
Christoph Stiller3
Fei-Yue Wang3
Javier Del Ser3
J. Marius Zöllner3
Kun Jiang3
Michael Botsch3
Wei Ma3
Wolfgang Utschick3
Xu Chen3
Yi Yang3
Zhiyong Cui3
Axel Plinge2
Bjoern Eskofier2
Christopher Mutschler2

Impactful Papers

Papers from ITSC 2022 that shaped research clusters.

Influential

Papers

Title
Spatial-Temporal Graph-Based Transformer Model for Traffic Flow Forecasting
SST-Calib: Simultaneous Spatial-Temporal Parameter Calibration between LIDAR and Camera
Stochastic Multimodal Interaction Prediction for Urban Driving
SUPS: A Simulated Underground Parking Scenario Dataset for Autonomous Driving
Testing Scenarios Construction for Connected and Automated Vehicles Based on Dynamic Trajectory Clustering Method
The Analysis of Traffic Variables for EV's Driving Efficiency in Urban Traffic Condition
The Braess's Paradox in Dynamic Traffic
Towards a Very Large Scale Traffic Simulator for Multi-Agent Reinforcement Learning Testbeds
Towards Better Driver Safety: Empowering Personal Navigation Technologies with Road Safety Awareness
Towards City-Scale Traffic Prediction: Cluster Graph Wavelet Networks
Towards Traffic Scene Description: The Semantic Scene Graph
Traffic Anomaly Detection in Intelligent Transport Applications with Time Series Data using Informer
Traffic Anomaly Detection Via Conditional Normalizing Flow
Traffic disruption modelling with mode shift in multi-modal networks
Trip Prediction by Leveraging Trip Histories from Neighboring Users
Two-stream LSTM Network with Hybrid Attention for Vehicle Trajectory Prediction
Uncertainty-Aware Online Merge Planning with Learned Driver Behavior
Unveiling the Influential Factors for Public Transportation Incentives Using Adaptive Stacking Extreme Gradient Boosting
USC: Uncompromising Spatial Constraints for Safety-Oriented 3D Object Detectors in Autonomous Driving
Vehicle- RSU Interaction Behavior Modeling and RSU Deployment Evaluation for Bus Priority
Vessel Behaviour Classification from AIS Without Geographical Biases
WaveLearner: A Knowledge-Combined Reinforcement Learning to Understand Coordinated Traffic Signal Control along Urban Arteries
What to Sense When There is no Sensor: Ex-novo Traffic Flow Estimation for Non-Sensed Roads

« prev Page 4/4