BriefGPT.xyz
Aug, 2021
DenseTNT: 密集目标集的端到端轨迹预测
DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets
HTML
PDF
Junru Gu, Chen Sun, Hang Zhao
TL;DR
本文提出一种名为DenseTNT的无锚和端到端轨迹预测模型，并介绍了一种离线优化技术，为我们的在线模型提供多重未来的伪标签。实验表明，DenseTNT在Argoverse运动预测基准测试中排名第一，并成为2021 Waymo开放数据集运动预测挑战的第一名。
Abstract
Due to the stochasticity of human behaviors, predicting the future trajectories of road agents is challenging for
autonomous driving
. Recently, goal-based multi-
trajectory prediction
methods are proved to be effe
→