BriefGPT.xyz
Jul, 2023
ADAPT: 高效的多智能体轨迹预测与适应
ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation
HTML
PDF
Görkay Aydemir, Adil Kaan Akan, Fatma Güney
TL;DR
通过动态权重学习，我们提出了ADAPT，这是一种新方法，可以有效地预测复杂交通场景中所有代理的轨迹，相比现有方法，我们在Argoverse和Interaction数据集中以较小的计算开销取得更好的表现。
Abstract
Forecasting future trajectories of
agents
in complex traffic scenes requires reliable and efficient predictions for all
agents
in the scene. However, existing methods for
→