ITSC 2023

237 papers
The 2023 edition of the International Conference on Intelligent Transportation Systems (ITSC) featured 264 papers centered on autonomous planning, safety evaluation, and reinforcement learning. Research themes emphasized safety in constrained environments, utilizing reflective feedback loops, automated red teaming, and Lagrangian methods for safe exploration. A significant portion of the work focused on bridging global planning with local reinforcement learning and developing socially aware motion planning for interactive driving scenarios. Technical trends from this year included the advancement of bird's-eye view (BEV) representations for road line mapping and urban driving policies. Other prominent areas of study involved neurosymbolic systems for probabilistic reasoning, vision transformers with parallel self-attention, and the application of decentralized autonomous organizations to traffic control. Prolific contributors included Nanning Zheng, Shitao Chen, and J. Marius Zöllner. Their collective work addressed challenges in spatial computing, robust driving policy learning, and the extraction of stay regions from location trajectories using weak supervision.

Top Research Directions

Research directions most represented by ITSC 2023 papers.

Deep Learning for Spatiotemporal Flow Forecasting 2
Modeling Heterogeneous Driving Styles in Autonomous Navigation 2
Trajectory Planning and Control in Mixed Autonomy Traffic 2
Modeling Reciprocal Dynamics in Multi-Agent Trajectory Prediction 2
Spatio-Temporal Graph Neural Networks 2
Robust Perception Through Complementary Sensor Fusion 2
Integrating Microscopic Vehicle Interactions into Traffic Models 1
Reinforcement Learning for Automated Failure Discovery 1
Integrating LiDAR and Cameras for 3D Scene Understanding 1
Integrating Lateral and Longitudinal Vehicle Control 1
Relative Coordinate Frames for Generalizable Control 1
Disentangling Space and Time in Motion Forecasting 1
Balancing Stakeholder Objectives in Urban Transit Optimization 1
Managing Vulnerability and Evolution Risks in Immutable Smart Contracts 1
The Vulnerability of Predictive Models to Exogenous Shocks 1

Top Authors

AuthorPapers
Nanning Zheng17
Yisheng Lv9
J. Marius Zöllner8
Xingyuan Dai7
Alois Knoll6
Javier Del Ser6
Shaoyi Du5
Matthias Althoff4
Zhiqiang Tian4
Daniel Cremers3
Fan Zhou3
Fei-Yue Wang3
Luc Van Gool3
Matteo Matteucci3
Scott Sanner3
Serge Hoogendoorn3
Wolfgang Utschick3
Alexander Liniger2
Cathy Wu2
Christoph Stiller2

Impactful Papers

Papers from ITSC 2023 that shaped research clusters.

Influential

Papers

Title
Path Tracking Control for Connected Automated Vehicle Using Lateral Stability Envelope at Handling Limits
Paving the Ways for Vehicles-in-the-loop: Wireless Integration of Autonomous Vehicles into Mixed Reality Proving Grounds and Test Areas
Pedestrian Environment Model for Automated Driving
Penalty-Based Imitation Learning With Cross Semantics Generation Sensor Fusion for Autonomous Driving
Perimeter Control Using Deep Reinforcement Learning: A Model-Free Approach Towards Homogeneous Flow Rate Optimization
PeRP: Personalized Residual Policies For Congestion Mitigation Through Co-operative Advisory Systems
Personalized Decision-Making and Control for Automated Vehicles Based on Generative Adversarial Imitation Learning
Personalized Trajectory Planning Algorithm Considering Passenger Motion Sickness Level
PillarDAN: Pillar-based Dual Attention Attention Network for 3D Object Detection with 4D RaDAR
Point Cloud Completion by Larger Receptive Fields for Intelligent Vehicles
PointHGSA: Efficient Point Cloud Understanding with Hypergraph-Based Self-Attention Network
Predicting Passenger Flow Using Graph Neural Networks with Scheduled Sampling on Bus Networks
Predicting the Vehicle Turn-in Rates of Highway Service Area: A Random Forest Approach
Predicting Trip Activities and Modes Using Long Short-Term Memory Models and Geospatial Representations
Prediction and Interpretation of Vehicle Trajectories in the Graph Spectral Domain
Prior Based Online Lane Graph Extraction from Single Onboard Camera Image
Radar Enlightens the Dark: Enhancing Low-Visibility Perception for Automated Vehicles with Camera-Radar Fusion
Real-time Autonomous Vehicle Navigation under Unknown Dynamics
Real-Time, Secure, and Computationally Efficient Navigation: A Prediction-Planning Framework Using Occupancy Grid Map
Rebalancing Autonomous Electric Vehicles for Mobility-on-Demand by Data-Driven Model Predictive Control
Reconstructing Transit Vehicle Trajectory Using High-Resolution GPS Data
Representation Learning of Rare Temporal Conditions for Travel Time Prediction
Research on Battery Fault Diagnosis Method Based on Entropy
Research on Strategy for Delay Recovery of Urban Rapid Rail Transit Trains Based on Coyote Optimization Algorithm
Resting Your Car for Cash: Incentive Mechanism Based TNC Car Scheduling for Carbon Neutrality
Rethinking Trajectory Prediction in Real-World Applications: An Online Task-Free Continual Learning Perspective
Robot Crowd Navigation Based on Spatio-Temporal Interaction Graphs and Danger Zones
Robust and Precise Sidewalk Detection with Ensemble Learning: Enhancing Road Safety and Facilitating Curb Space Management
Robust Driving Policy Learning with Guided Meta Reinforcement Learning
RoW-based Parallel Control for Mixed Traffic Scenario: A Case Study on Lane-Changing
Safe and Comfortable Motion Planning for Bumpy Road Driving
Safe Reinforcement Learning for Mixed-Autonomy Platoon Control
SAFE: Saliency-Aware Counterfactual Explanations for DNN-based Automated Driving Systems
Safety Reinforced Model Predictive Control (SRMPC): Improving MPC with Reinforcement Learning for Motion Planning in Autonomous Driving
SAVME: Efficient Safety Validation for Autonomous Systems Using Meta-Learning
Scalable Adaptive Traffic Light Control Over a Traffic Network Including Transit Delays
Scale Drift-free Visual-inertial Odometry for Ground Vehicles in Highway Scenarios
Scaling up the Optimal Safe Control of Connected and Automated Vehicles to a Traffic Network: A Hierarchical Framework of Modular Control Zones
SceneDiffusion: Conditioned Latent Diffusion Models for Traffic Scene Prediction
SEIP: Simulation-based Design and Evaluation of Infrastructure-based Collective Perception
Semantic Bird's-Eye View Road Line Mapping
Semantic Map Learning of Traffic Light to Lane Assignment based on Motion Data
Semantic Segmentation of Railway Infrastructure Based on Virtual Model Synthetic Data
Semi-Automatic Ground Truth Trajectory Estimation and Smoothing using Roadside Cameras
SKoPe3D: A Synthetic Dataset for Vehicle Keypoint Perception in 3D from Traffic Monitoring Cameras
Spatial Estimation of Ground-Level Temperature for Climate-Sensitive Urban Mobility using Image-to-Image Deep Neural Networks
Spatio-Temporal Transformer with Clustering and Dilated Attention for Traffic Prediction
SSN: Sequential Spatial Network for Trajectory Prediction in Bird's-Eye View
Stability Analysis of Connected Automated Vehicle Platoon Controller Under Unreliable Communication Conditions
ST-GIN: An Uncertainty Quantification Approach in Traffic Data Imputation with Spatio-Temporal Graph Attention and Bidirectional Recurrent United Neural Networks

« prev Page 4/5 next »