arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.13936cs.AI
收藏

一种通用的物理引导因果模型用于自动驾驶中的轨迹预测

A Generalizable Physics-guided Causal Model for Trajectory Prediction in Autonomous Driving

Zhenyu Zong, Yuchen Wang, Haohong Lin, Lu Gan, Huajie Shao

AI总结:

本文提出了一种通用的物理引导因果模型,通过解耦场景编码器和因果ODE解码器提升自动驾驶中的零样本轨迹预测能力。

摘要:

交通代理的轨迹预测对于安全的自动驾驶至关重要。然而,实现有效零样本泛化到以前未见的领域仍是一个重大挑战。受不同领域中运动学一致性的启发,我们旨在纳入领域不变的知识以增强零样本轨迹预测能力。关键挑战包括:1)有效提取领域不变的场景表示,2)将不变特征与运动学模型整合以实现泛化的预测。为了解决这些挑战,我们提出了一种新的通用物理引导因果模型(PCM),其包含两个核心组件:解耦场景编码器,它采用干预基于的解耦来从场景中提取领域不变特征,以及因果ODE解码器,它采用因果注意力机制有效地将运动学模型与有意义的上下文信息整合。在真实世界自动驾驶数据集上的广泛实验表明,我们的方法在未见城市中表现出优越的零样本泛化性能,显著优于竞争基线。源代码已发布在https://github.com/ZY-Zong/Physics-guided-Causal-Model。

英文摘要:

Trajectory prediction for traffic agents is critical for safe autonomous driving. However, achieving effective zero-shot generalization in previously unseen domains remains a significant challenge. Motivated by the consistent nature of kinematics across diverse domains, we aim to incorporate domain-invariant knowledge to enhance zero-shot trajectory prediction capabilities. The key challenges include: 1) effectively extracting domain-invariant scene representations, and 2) integrating invariant features with kinematic models to enable generalized predictions. To address these challenges, we propose a novel generalizable Physics-guided Causal Model (PCM), which comprises two core components: a Disentangled Scene Encoder, which adopts intervention-based disentanglement to extract domain-invariant features from scenes, and a CausalODE Decoder, which employs a causal attention mechanism to effectively integrate kinematic models with meaningful contextual information. Extensive experiments on real-world autonomous driving datasets demonstrate our method's superior zero-shot generalization performance in unseen cities, significantly outperforming competitive baselines. The source code is released at https://github.com/ZY-Zong/Physics-guided-Causal-Model.

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。

↑