自动驾驶论文总结

预测

光栅化

代表性论文

1. Motion Prediction of Traffic Actors for Autonomous Driving using Deep Convolutional Networks (Uber)
2. MultiPath (Waymo)

问题

1. 渲染信息丢失
2. 感受野有限
3. 高计算复杂度

图神经网络

1. VectorMap (waymo 2020)
2. LaneGCN (uber 2020)

Transformer

1. mmTransformer (2021)
2. WayFormer
3. QCNet (2023 CVPR，还没看懂)

基于锚点

1. DenseTNT

生成式模型

1. Social gan: Socially acceptable trajectories with generative adversarial networks (CVPR 2018)
2. Tranjectron++

Metrics

1. b-minFDE：(1-p_i)^2 * minFDE_i
2. b-minADE：(1-p_i)^2 * minADE_i
   参考：https://eval.ai/web/challenges/challenge-page/454/evaluation

端到端

光栅化

1. End-to-end Interpretable Neural Motion Planner (uber 2019)
2. P3 (uber)

图神经网络

Transformer

1. UniAD
2. VAD

采样

1. Curve-based sampler (NMP )

2. Lane-based sampler (P3 uber 2020)

3. Retrieval-based sampler (MP3)

4. 如何理解agent centric