用物理规律引导因果模型，让自动驾驶轨迹预测在新城市零样本泛化。
A Generalizable Physics-guided Causal Model for Trajectory Prediction in Autonomous Driving
- 通过干预解耦提取场景的域不变特征
- 因果ODE解码器融合运动规律与上下文信息
- 在未见城市上显著优于现有方法
交通参与者轨迹预测对自动驾驶安全至关重要。然而，在此前未见过的场景中实现有效的零样本泛化仍是重大挑战。鉴于运动学在不同场景中具有稳定性，我们旨在引入域不变知识以增强零样本轨迹预测能力。主要挑战包括：1）有效提取域不变的场景表征；2）将不变特征与运动学模型结合以实现泛化预测。为此，我们提出一种新型通用物理引导因果模型（PCM），包含两个核心组件：解耦场景编码器，采用基于干预的解耦方法从场景中提取域不变特征；因果ODE解码器，利用因果注意力机制将运动学模型与有意义的上下文信息有效融合。在真实世界自动驾驶数据集上的大量实验表明，该方法在未见城市中展现出卓越的零样本泛化性能，显著优于竞争性基线。源代码已发布于 https://github.com/ZY-Zong/Physics-guided-Causal-Model。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。