MGTR:基于LiDAR的多粒度Transformer运动预测
MGTR: Multi-Granular Transformer for Motion Prediction with LiDAR
AI总结:
本文提出MGTR,一种多粒度Transformer编码器-解码器网络,结合LiDAR语义特征处理不同交通代理,在Waymo运动预测基准上排名第一。
摘要:
运动预测一直是自动驾驶系统中的关键组成部分,因为它处理涉及不同类型移动代理的高度不确定和复杂场景。在本文中,我们提出了一个多粒度Transformer(MGTR)框架,这是一个编码器-解码器网络,利用不同粒度的上下文特征来处理不同类型的交通代理。为了进一步增强MGTR的能力,我们利用LiDAR点云数据,通过从现成的LiDAR特征提取器中融入LiDAR语义特征。我们在Waymo开放数据集运动预测基准上评估了MGTR,并展示了所提出的方法达到了最先进的性能,在其排行榜上排名第一(https://waymo.com/open/challenges/2023/motion-prediction/)。
英文摘要:
Motion prediction has been an essential component of autonomous driving systems since it handles highly uncertain and complex scenarios involving moving agents of different types. In this paper, we propose a Multi-Granular TRansformer (MGTR) framework, an encoder-decoder network that exploits context features in different granularities for different kinds of traffic agents. To further enhance MGTR's capabilities, we leverage LiDAR point cloud data by incorporating LiDAR semantic features from an off-the-shelf LiDAR feature extractor. We evaluate MGTR on Waymo Open Dataset motion prediction benchmark and show that the proposed method achieved state-of-the-art performance, ranking 1st on its leaderboard (https://waymo.com/open/challenges/2023/motion-prediction/).
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。