提出通用自监督框架，提升自动驾驶运动预测的泛化能力。
SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction
- 结合对比与重建学习，不依赖特定模型和数据集。
- 在多个数据集上使预测误差降低10.6%，效果稳定提升。
- 适合需要跨场景、跨数据训练的自动驾驶研究者。
预测周边交通参与者未来运动是自动驾驶车辆在复杂人机混合环境中安全运行的关键。然而，大规模驾驶数据集的稀缺限制了鲁棒且可泛化的运动预测模型的发展，使其难以捕捉复杂交互关系与道路结构。受自然语言处理和计算机视觉中自监督学习（SSL）进展启发，现有方法多聚焦于特定模型架构或单一数据集，缺乏可扩展性与泛化能力。为此，本文提出 SmartPretrain，一种模型无关、数据无关的通用自监督学习框架。该方法融合对比与重建两种学习范式，无需架构约束即可有效表征时空演化与交互行为。同时，采用多数据集混合采样策略，显著提升数据量与多样性。大量实验证明，SmartPretrain 在多个数据集、数据划分及主流指标上均持续提升先进模型性能，例如使 Forecast-MAE 的 MissRate 降低 10.6%。结果表明，SmartPretrain 是突破小数据局限的统一可扩展解决方案。代码已开源。
原文摘要 · Abstract (English)
Predicting the future motion of surrounding agents is essential for autonomous vehicles (AVs) to operate safely in dynamic, human-robot-mixed environments. However, the scarcity of large-scale driving datasets has hindered the development of robust and generalizable motion prediction models, limiting their ability to capture complex interactions and road geometries. Inspired by recent advances in natural language processing (NLP) and computer vision (CV), self-supervised learning (SSL) has gained significant attention in the motion prediction community for learning rich and transferable scene representations. Nonetheless, existing pre-training methods for motion prediction have largely focused on specific model architectures and single dataset, limiting their scalability and generalizability. To address these challenges, we propose SmartPretrain, a general and scalable SSL framework for motion prediction that is both model-agnostic and dataset-agnostic. Our approach integrates contrastive and reconstructive SSL, leveraging the strengths of both generative and discriminative paradigms to effectively represent spatiotemporal evolution and interactions without imposing architectural constraints. Additionally, SmartPretrain employs a dataset-agnostic scenario sampling strategy that integrates multiple datasets, enhancing data volume, diversity, and robustness. Extensive experiments on multiple datasets demonstrate that SmartPretrain consistently improves the performance of state-of-the-art prediction models across datasets, data splits and main metrics. For instance, SmartPretrain significantly reduces the MissRate of Forecast-MAE by 10.6%. These results highlight SmartPretrain's effectiveness as a unified, scalable solution for motion prediction, breaking free from the limitations of the small-data regime. Codes are available at https://github.com/youngzhou1999/SmartPretrain
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。