arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.01971cs.CV
收藏

Snapshot:迈向城市交通环境中以应用为中心的行人轨迹预测模型

Snapshot: Towards Application-centered Models for Pedestrian Trajectory Prediction in Urban Traffic Environments

Technical University of Munich(慕尼黑工业大学);School of Engineering & Design(工程与设计学院);Munich Institute of Robotics and Machine Intelligence(慕尼黑机器人与机器智能研究所)

Nico Uhlemann, Yipeng Zhou, Tobias Simeon Mohr, Markus Lienkamp

AI总结:

针对城市交通行人轨迹预测,本文基于 Argoverse 2 构建专用基准,并提出模块化前馈网络 Snapshot,以更少信息将 ADE 降低8.8%,且具备实时性、鲁棒性和自动驾驶落地能力。

摘要:

本文探讨城市交通中的行人轨迹预测,同时关注模型精度与现实世界适用性。尽管已有一些有前景的方法,但它们通常围绕排除交通相关信息的行人数据集展开,或采用既不具备实时能力也不够鲁棒的架构。为解决这些局限,我们首先基于 Argoverse 2 引入一个专用基准,专门面向交通环境中的行人。随后,我们提出 Snapshot,这是一种模块化前馈神经网络,其性能优于当前最先进方法,将平均位移误差(ADE)降低了8.8%,同时使用的信息显著更少。尽管采用以智能体为中心的编码方案,Snapshot 仍展现出可扩展性、实时性能以及对不同运动历史的鲁棒性。此外,通过将 Snapshot 集成到模块化自动驾驶软件栈中,我们展示了其现实世界适用性。

英文摘要:

This paper explores pedestrian trajectory prediction in urban traffic while focusing on both model accuracy and real-world applicability. While promising approaches exist, they often revolve around pedestrian datasets excluding traffic-related information, or resemble architectures that are either not real-time capable or robust. To address these limitations, we first introduce a dedicated benchmark based on Argoverse 2, specifically targeting pedestrians in traffic environments. Following this, we present Snapshot, a modular, feed-forward neural network that outperforms the current state of the art, reducing the Average Displacement Error (ADE) by 8.8% while utilizing significantly less information. Despite its agent-centric encoding scheme, Snapshot demonstrates scalability, real-time performance, and robustness to varying motion histories. Moreover, by integrating Snapshot into a modular autonomous driving software stack, we showcase its real-world applicability.

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。

↑