BriefGPT.xyz
Jun, 2020
MANTRA:用存储增强网络进行多轨迹预测
MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction
HTML
PDF
Francesco Marchetti, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo
TL;DR
本论文提出了一种基于记忆增强神经网络的多模态轨迹预测方法,该方法可以在复杂场景中安全地规划自主车辆路径,并且通过非参数化的记忆模块,可以不断改进预测效果。
Abstract
autonomous vehicles
are expected to drive in complex scenarios with several independent non cooperating agents.
path planning
for safely navigating in such environments can not just rely on perceiving present loc
→