用证据深度学习实时估算轨迹预测的不确定性，提升自动驾驶安全性。
Evidential Uncertainty Estimation for Multi-Modal Trajectory Prediction
- 基于正态逆伽马与狄利克雷分布，单次前向传播同时估计位置和模式不确定性
- 在Argoverse数据集上保持高精度的同时，提供可靠且校准良好的不确定性估计
- 适合需要可信预测结果的自动驾驶系统，尤其关注罕见或高风险场景
准确的轨迹预测对自动驾驶至关重要，但行为不确定性和感知噪声使该任务极具挑战。现有多模态轨迹预测模型虽能生成多个合理未来路径并附带概率，但有效量化不确定性仍是开放问题。本文提出一种基于证据深度学习的新方法，可实时估计位置和模式两类不确定性。方法采用正态逆伽马分布建模位置不确定性，狄利克雷分布建模模式不确定性。与基于采样的方法不同，本方法在一次前向传播中即可完成两类不确定性的推断，显著提升效率。此外，我们引入基于不确定性的重要性采样策略，在训练中优先处理低频的高不确定性样本，减少冗余更新。我们在Argoverse 1和Argoverse 2数据集上进行了广泛评估，结果表明该方法在保持高预测精度的同时，能提供可靠且校准良好的不确定性估计。
原文摘要 · Abstract (English)
Accurate trajectory prediction is crucial for autonomous driving, yet uncertainty in agent behavior and perception noise makes it inherently challenging. While multi-modal trajectory prediction models generate multiple plausible future paths with associated probabilities, effectively quantifying uncertainty remains an open problem. In this work, we propose a novel multi-modal trajectory prediction approach based on evidential deep learning that estimates both positional and mode probability uncertainty in real time. Our approach leverages a Normal Inverse Gamma distribution for positional uncertainty and a Dirichlet distribution for mode uncertainty. Unlike sampling-based methods, it infers both types of uncertainty in a single forward pass, significantly improving efficiency. Additionally, we experimented with uncertainty-driven importance sampling to improve training efficiency by prioritizing underrepresented high-uncertainty samples over redundant ones. We perform extensive evaluations of our method on the Argoverse 1 and Argoverse 2 datasets, demonstrating that it provides reliable uncertainty estimates while maintaining high trajectory prediction accuracy.
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。