Towards Safe Autonomy in Hybrid Traffic: Detecting Unpredictable Abnormal Behaviors of Human Drivers via Information Sharing
Not on the map. Why?
Abstract (arXiv)
Hybrid traffic which involves both autonomous and human-driven vehicles would be the norm of the autonomous vehicles practice for a while. On the one hand, unlike autonomous vehicles, human-driven vehicles could exhibit sudden abnormal behaviors such as unpredictably switching to dangerous driving modes, putting its neighboring vehicles under risks; such undesired mode switching could arise from numbers of human driver factors, including fatigue, drunkenness, distraction, aggressiveness, etc. On the other hand, modern vehicle-to-vehicle communication technologies enable the autonomous vehicles to efficiently and reliably share the scarce run-time information with each other. In this paper, we propose, to the best of our knowledge, the first efficient algorithm that can (1) significantly improve trajectory prediction by effectively fusing the run-time information shared by surrounding autonomous vehicles, and can (2) accurately and quickly detect abnormal human driving mode switches or abnormal driving behavior with formal assurance without hurting human drivers privacy. To validate our proposed algorithm, we first evaluate our proposed trajectory predictor on NGSIM and Argoverse datasets and show that our proposed predictor outperforms the baseline methods. Then through extensive experiments on SUMO simulator, we show that our proposed algorithm has great detection performance in both highway and urban traffic. The best performance achieves detection rate of 97.3%, average detection delay of 1.2s, and 0 false alarm.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 23 of its 84 references that are in the map. First posted on arXiv 23 Aug 2023.
Builds on
23 of 84 references.
References · 23
- 2017Attention Is All You Needcited by 60,361
- 2020Center-based 3D Object Detection and Trackingcited by 1,144
- 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
- 2018Convolutional Social Pooling for Vehicle Trajectory Predictioncited by 221
- 2021Multimodal Motion Prediction with Stacked Transformerscited by 208
- 2020Transformer Networks for Trajectory Forecastingcited by 181
- 2020Spatial-Temporal Transformer Networks for Traffic Flow Forecastingcited by 180
- 2019Multi-Agent Tensor Fusion for Contextual Trajectory Predictioncited by 131
- 2018TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agentscited by 111
- 2019A Survey of Deep Learning Applications to Autonomous Vehicle Controlcited by 106
- 2018MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localizationcited by 84
- 2018TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactionscited by 82
11 more
- 2019Conditional Generative Neural System for Probabilistic Trajectory Predictioncited by 76
- 2020Diverse and Admissible Trajectory Forecasting through Multimodal Context Understandingcited by 68
- 2018Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecturecited by 55
- 2019Jointly Learnable Behavior and Trajectory Planning for Self-Driving Vehiclescited by 51
- 2018LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networkscited by 41
- 2019Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMscited by 34
- 2018Governing autonomous vehicles: emerging responses for safety, liability, privacy, cybersecurity, and industry riskscited by 21
- 2020Multi-Head Attention based Probabilistic Vehicle Trajectory Predictioncited by 12
- 2020Trajformer: Trajectory Prediction with Local Self-Attentive Contexts for Autonomous Drivingcited by 6
- 2021Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Networkcited by 6
- 2017AutonoVi: Autonomous Vehicle Planning with Dynamic Maneuvers and Traffic Constraintscited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 2.
3 papers.