用扩散模型提升短时轨迹预测的准确率与不确定性校准
DD-MDN: Human Trajectory Forecasting with Diffusion-Based Dual Mixture Density Networks and Uncertainty Self-Calibration
- 基于扩散模型与双混合密度网络，自学习路径锚点与分布
- 在短观察窗口下仍保持高精度，且不确定性预测更可靠
- 适合自动驾驶、人机交互等需可信预测的场景
人类轨迹预测（HTF）旨在根据历史轨迹和环境信息预估未来运动，广泛应用于自动驾驶、智能监控和人机交互。现有工作多关注精度、社交交互建模和轨迹多样性，但对不确定性建模、校准及短时观测下的鲁棒性关注不足，而这对于路径规划与避障等下游任务至关重要。本文提出DD-MDN，一种端到端的概率化轨迹预测模型，兼具高位置精度、校准后的不确定性估计和对短时观测的鲁棒性。该方法采用少样本去噪扩散主干与双混合密度网络，无需预设锚点或终点，自主学习校准后的停留区域与概率排序的路径锚点，并由此生成多样化轨迹假设。在ETH/UCY、SDD、inD和IMPTC数据集上的实验表明，该方法在短时观测下仍达到领先精度，且不确定性建模更为可靠。代码已开源：https://github.com/kav-institute/ddmdn。
原文摘要 · Abstract (English)
Human Trajectory Forecasting (HTF) predicts future human movements from past trajectories and environmental context, with applications in Autonomous Driving, Smart Surveillance, and Human-Robot Interaction. While prior work has focused on accuracy, social interaction modeling, and diversity, little attention has been paid to uncertainty modeling, calibration, and forecasts from short observation periods, which are crucial for downstream tasks such as path planning and collision avoidance. We propose DD-MDN, an end-to-end probabilistic HTF model that combines high positional accuracy, calibrated uncertainty, and robustness to short observations. Using a few-shot denoising diffusion backbone and a dual mixture density network, our method learns self-calibrated residence areas and probability-ranked anchor paths, from which diverse trajectory hypotheses are derived, without predefined anchors or endpoints. Experiments on the ETH/UCY, SDD, inD, and IMPTC datasets demonstrate state-of-the-art accuracy, robustness at short observation intervals, and reliable uncertainty modeling. The code is available at: https://github.com/kav-institute/ddmdn.
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。