提升多智能体轨迹预测的生成速度与精度，实现单步推理。
ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Prediction
- 引入师生一致性训练，强化教师对学生的监督信号。
- 在Argoverse 2数据集上实现更快推理与更高准确率。
- 适合自动驾驶等实时性要求高的场景使用。
多智能体轨迹预测中的扩散模型受限于迭代去噪过程，导致推理延迟，难以应用于自动驾驶等时间敏感场景。虽然基于DDIM和有指导的初始噪声分布的快速采样方法部分缓解了该问题，但或无法实现真正的单步生成，或受噪声分布限制。一致性模型（CMs）可通过将噪声直接映射到数据实现高质量单步生成，但训练困难。本文提出ECTraj，一种增强的一致性模型框架，通过改进训练与条件生成策略。其采用学生-教师一致性训练机制：学生生成标准输出，教师则显式融合自身预测与部分真实轨迹，提供更强监督。同时利用CM直接去噪能力，在训练中实现top-K多样本生成。结合条件生成与增强的一致性目标，显著提升推理速度与预测精度，在大规模Argoverse 2数据集上建立新的基准。
原文摘要 · Abstract (English)
Diffusion models for multi-agent trajectory prediction are limited by iterative denoising, which causes inference latency that hinders their use in time-critical settings like autonomous driving. Fast-sampling variants using DDIM and informed initial noise distributions partially alleviate this issue, but they either fail to achieve true single-step generation or are constrained by the chosen noise distribution. Consistency Models (CMs) offer high-quality one-step generation by mapping noise directly to data, but are difficult to train from scratch. We propose ECTraj, an enhanced CM pipeline with improved training and conditional generation for trajectory prediction. Our framework extends the student-teacher consistency training scheme: the student produces standard outputs, while the teacher explicitly fuses its predictions with parts of the ground truth to give stronger supervision. We also exploit CMs' direct denoising for top-K multi-shot generation during training. Combining conditional generation with this enhanced consistency objective yields faster inference and improved prediction accuracy, establishing competitive new benchmarks on the large-scale Argoverse 2 dataset.
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。