ITSC 2019
160 papers
The 2019 IEEE Intelligent Transportation Systems Conference (ITSC) featured 174 papers centered on autonomous navigation and connected vehicle systems. Research themes focused on collaborative perception for connected driving and Bird’s Eye View representations for LiDAR point cloud processing. Notable work addressed visual navigation and SLAM, specifically regarding perceptual aliasing and robust place recognition across environmental variations. Other research directions included vectorized lane graph construction, motion estimation, and the development of anytime algorithms for real-time deliberation in autonomous systems.
Methodological trends highlighted the application of deep reinforcement learning for car-following control and self-supervised flow estimation using geometric regularization. The year’s contributions also explored the operational aspects of intelligent transport, including agent-based simulations for shared automated electric vehicles and the analysis of public concerns regarding shared mobility security. Prolific authors included Alois C. Knoll, Christoph Stiller, and Nanning Zheng. Collectively, the research emphasized multi-vehicle interaction modeling and the integration of semantic information for real-time 3D object detection.
Top Research Directions
Research directions most represented by ITSC 2019 papers.
Top Authors
Impactful Papers
Papers from ITSC 2019 that shaped research clusters.
Foundational
Relational Recurrent Neural Networks For Vehicle Trajectory Prediction
foundational
Dynamic Threat Prioritization in Multi-A
Relational Recurrent Neural Networks For Vehicle Trajectory Prediction
foundational
Interaction Aware Motion Prediction for
Online Inference and Detection of Curbs in Partially Occluded Scenes with Sparse LIDAR
foundational
Bird's Eye View Projection for 3D Percep
Self-Supervised Flow Estimation using Geometric Regularization with Applications to Camera Image and
foundational
Masking Dynamic Objects in Self-Supervis
Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labe
foundational
Mitigating the LiDAR Annotation Bottlene
Influential
Evaluation Uncertainty in Data-Driven Self-Driving Testing
influential
Efficient Rare Event Estimation for Safe
Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validatio
influential
Virtual Stress Testing for Safety Critic
Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmenta
influential
High Precision Localization with Commodi
Relational Recurrent Neural Networks For Vehicle Trajectory Prediction
influential
Modeling Temporal Dependencies with Recu
Anytime Lane-Level Intersection Estimation Based on Trajectories of Other Traffic Participants
influential
Overcoming Sensor Occlusion Through Coll
Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization
influential
Accelerating Trajectory Optimization for
Generating All the Roads to Rome: Road Layout Randomization for Improved Road Marking Segmentation
influential
Generative Synthesis for Long Tailed Dis
Human-Like Decision-Making for Automated Driving in Highways
influential
Modeling Reciprocal Dynamics in Multi-Ag
Evaluation Uncertainty in Data-Driven Self-Driving Testing
influential
Resampling Methods for Uncertainty Quant
LACI: Low-effort Automatic Calibration of Infrastructure Sensors
influential
Online Calibration of Misaligned Sensors