13 papers
Sybil-TraceGuard: Traceability-enhanced Sybil Guardian for Connected and Autonomous Vehicles Using Dynamic Semi-supervised GNN
Qian Xu, Jiaxun Zhang, Chengyue Wang +1
Connected and autonomous vehicles (CAVs) face severe Sybil attacks, where attackers exploit privacy-preserving pseudonym-switching mechanisms to anomaly alternate identities while…
TRACER: Training-Free Closed-Loop Structured Inference for Traffic Accident Reconstruction
Yanchen Guan, Chengyue Wang, Bin Rao +5
Traffic accident reconstruction is a forensic inverse problem that requires recovering physically consistent motion from sparse and heterogeneous evidence. Existing learning-based…
Learning from the Unseen: Generative Data Augmentation for Geometric-Semantic Accident Anticipation
Yanchen Guan, Haicheng Liao, Chengyue Wang +4
Anticipating traffic accidents is a critical yet unresolved problem for autonomous driving, hindered by the inherent complexity of modeling interactions between road users and the…
Cooperative Safety Intelligence over V2X Networks: A Survey
Jiaxun Zhang, Qian Xu, Zhenning Li +3
Vehicle-to-Everything (V2X) cooperation is reshaping traffic safety from an ego-centric sensing problem into a networked intelligence problem involving distributed sensing, coopera…
Predict and Resist: Long-Term Accident Anticipation under Sensor Noise
Xingcheng Liu, Bin Rao, Yanchen Guan +6
Accident anticipation is essential for proactive and safe autonomous driving, where even a brief advance warning can enable critical evasive actions. However, two key challenges hi…
Differentiable Semantic Meta-Learning Framework for Long-Tail Motion Forecasting in Autonomous Driving
Bin Rao, Chengyue Wang, Haicheng Liao +7
Long-tail motion forecasting is a core challenge for autonomous driving, where rare yet safety-critical events-such as abrupt maneuvers and dense multi-agent interactions-dominate…
World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous Driving
Yanchen Guan, Haicheng Liao, Chengyue Wang +3
Reliable anticipation of traffic accidents is essential for advancing autonomous driving systems. However, this objective is limited by two fundamental challenges: the scarcity of…
Domain-Enhanced Dual-Branch Model for Efficient and Interpretable Accident Anticipation
Yanchen Guan, Haicheng Liao, Chengyue Wang +4
Developing precise and computationally efficient traffic accident anticipation system is crucial for contemporary autonomous driving technologies, enabling timely intervention and…
Eyes on the Road, Mind Beyond Vision: Context-Aware Multi-modal Enhanced Risk Anticipation
Jiaxun Zhang, Haicheng Liao, Yumu Xie +4
Accurate accident anticipation remains challenging when driver cognition and dynamic road conditions are underrepresented in predictive models. In this paper, we propose CAMERA (Co…
AMD: Adaptive Momentum and Decoupled Contrastive Learning Framework for Robust Long-Tail Trajectory Prediction
Bin Rao, Haicheng Liao, Yanchen Guan +4
Accurately predicting the future trajectories of traffic agents is essential in autonomous driving. However, due to the inherent imbalance in trajectory distributions, tail data in…
Beyond Patterns: Harnessing Causal Logic for Autonomous Driving Trajectory Prediction
Bonan Wang, Haicheng Liao, Chengyue Wang +7
Accurate trajectory prediction has long been a major challenge for autonomous driving (AD). Traditional data-driven models predominantly rely on statistical correlations, often ove…
LATTE: Lightweight Attention-based Traffic Accident Anticipation Engine
Jiaxun Zhang, Yanchen Guan, Chengyue Wang +3
Accurately predicting traffic accidents in real-time is a critical challenge in autonomous driving, particularly in resource-constrained environments. Existing solutions often suff…
GS-Net: Heterogeneous Vehicle Data Reuse via Generalizable Plug-and-Play 3DGS Module
Yichen Zhang, Zihan Wang, Jiali Han +5
End-to-end autonomous driving is increasingly data-driven, yet data reuse across vehicles remains limited. Each new vehicle often requires additional data collection and retraining…