Critical Example Mining for Vehicle Trajectory Prediction using Flow-based Generative Models
Not on the map. Why?
Abstract (arXiv)
Precise trajectory prediction in complex driving scenarios is essential for autonomous vehicles. In practice, different driving scenarios present varying levels of difficulty for trajectory prediction models. However, most existing research focuses on the average precision of prediction results, while ignoring the underlying distribution of the input scenarios. This paper proposes a critical example mining method that utilizes a data-driven approach to estimate the rareness of the trajectories. By combining the rareness estimation of observations with whole trajectories, the proposed method effectively identifies a subset of data that is relatively hard to predict BEFORE feeding them to a specific prediction model. The experimental results show that the mined subset has higher prediction error when applied to different downstream prediction models, which reaches +108.1% error (greater than two times compared to the average on dataset) when mining 5% samples. Further analysis indicates that the mined critical examples include uncommon cases such as sudden brake and cancelled lane-change, which helps to better understand and improve the performance of prediction models.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 21 Oct 2024.
Builds on
17 of 30 references.
References · 17
- 2022Generative Adversarial Networkscited by 5,603
- 2015Variational Inference with Normalizing Flowscited by 2,161
- 2014NICE: Non-linear Independent Components Estimationcited by 1,052
- 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
- 2021Deep Long-Tailed Learning: A Surveycited by 416
- 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 292
- 2018Dataset Distillationcited by 224
- 2018Convolutional Social Pooling for Vehicle Trajectory Predictioncited by 221
- 2023Dataset Distillation: A Comprehensive Reviewcited by 126
- 2018An LSTM Network for Highway Trajectory Predictioncited by 81
- 2021Multi-modal Motion Prediction with Transformer-based Neural Network for Autonomous Drivingcited by 73
- 2021On Exposing the Challenging Long Tail in Future Prediction of Traffic Actorscited by 48
5 more
- 2018Naturalistic Driver Intention and Path Prediction using Recurrent Neural Networkscited by 29
- 2022Long-Tail Prediction Uncertainty Aware Trajectory Planning for Self-driving Vehiclescited by 22
- 2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19
- 2019Joint Interaction and Trajectory Prediction for Autonomous Driving using Graph Neural Networkscited by 17
- 2022Taming the Long Tail of Deep Probabilistic Forecastingcited by 7
Built on by
Citing papers per year: 2025: 1.
1 paper.