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
Modeling Freight-Sharing Platform Operations for Optimal Compensation Strategy Using Markov Decision Processes
Modelling road hazards and the effect on AV safety of hazardous failures
Model predictive control of bus platoons in a circular route considering dispatching, holding and boarding limits
MONA: The Munich Motion Dataset of Natural Driving
Motion Embedding for On-road Motion Object Detection for Intelligent Vehicle Systems
Motion Planning and Control for Multi Vehicle Autonomous Racing at High Speeds
MS-GCN: Multi-Stream Graph Convolution Network for Driver Head Pose Estimation
Multi-agent Reinforcement Learning-based Twin-vehicle Fair Cooperative Driving in Dynamic Highway Scenarios
Multi-L: A Novel Multi-Robot Cooperative Localization Method in Indoor Environment
Multiple Goals Network for Pedestrian Trajectory Prediction in Autonomous Driving
Multi-train Cooperative Control-Oriented MEC Deployment Strategy
NEMO: Future Object Localization Using Noisy Ego Priors
Novel trajectory prediction algorithm using a full dataset: comparison and ablation studies
Offline Reinforcement Learning for Autonomous Driving with Real World Driving Data
On the Potential of Randomization-based Neural Networks for Driving Behavior Classification
Outlier-robust Inverse Reinforcement Learning and Reward-based Detection of Anomalous Driving Behaviors
Out-of-Distribution Detection for LiDAR-based 3D Object Detection
Passive and Active Learning of Driver Behavior from Electric Vehicles
PAT: Point Cloud Analysis with Local Filter Embedding in Transformer
PillarGrid: Deep Learning-Based Cooperative Perception for 3D Object Detection from Onboard-Roadside LiDAR
Predicting Parameters for Modeling Traffic Participants
Predictive Adaptive Cruise Control for Heavy-duty Vehicle based on Cloud Control System
Private Location Sharing for Decentralized Routing Services
QueueLearner: A Knowledge-Combined Reinforcement Learning to Understand Queuing Evolution in Isolated Traffic Signal Control
Real-time Adaptive Background Subtraction for Traffic Scenarios at Signalized Intersections Based on Roadside Fish-eye Cameras
Real-time Attention-Augmented Spatio-Temporal Networks for Video-based Driver Activity Recognition
Real-time Pseudo-LiDAR 3D object detection with geometric constraints
ReCoAt: A Deep Learning-based Framework for Multi-Modal Motion Prediction in Autonomous Driving Application
Reinforcement Learning for Curbside Space Management with Infrastructure Autonomy and Mixed Vehicle Connectivity
Representation Learning of Rare Temporal Conditions for Travel Time Prediction
Resource Allocation in Software-Defined Vehicles: ILP Model Formulation and Solver Evaluation
Responsibility-associated Multi-agent Collision Avoidance with Social Preferences
Road Extraction Assisted Offset Regression Method in Cross-view Image- based Geo-localization
Road Traffic Law Adaptive Decision-making for Self-Driving Vehicles
Robust estimation of airport declared capacity
Route Planning by Merging Local Edges into Domains with LSTM
Row-wise LiDAR Lane Detection Network with Lane Correlation Refinement
Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking
Safe and Rule-Aware Deep Reinforcement Learning for Autonomous Driving at Intersections
Safe Decision-making for Lane-change of Autonomous Vehicles via Human Demonstration-aided Reinforcement Learning
Safe Reinforcement Learning for Urban Driving using Invariably Safe Braking Sets
Safety Co-Pilot: A System for Autonomous Vehicle to Make Decision Safer and Smarter
Safety Implications of Runtime Adaptation to Changing Operating Conditions
Search on Traffic Design Method of Left Turn with U-turn at Grade Intersection
Self-Supervised Traffic Advisors: Distributed, Multi-view Traffic Prediction for Smart Cities
Semantic 3D Grid Maps for Autonomous Driving
Semantic-enhanced Graph Voxelization for Pillar-based 3D Detection from Point Clouds
Sequential Cooperative Energy and Time-Optimal Lane Change Maneuvers for Highway Traffic
SIND: A Drone Dataset at Signalized Intersection in China
SMART-eFlo: An Integrated SUMO-Gym Framework for Multi-Agent Reinforcement Learning in Electric Fleet Management Problem

« prev Page 3/4 next »