TrajTok通过融合数据与规则方法，提升轨迹生成的准确性与鲁棒性。
TrajTok: Technical Report for 2025 Waymo Open Sim Agents Challenge
- 采用数据驱动与规则结合的轨迹分词策略，增强覆盖与对称性
- 在Waymo挑战中实现0.7852的现实性评分，表现优异
- 适合自动驾驶行为预测研究者参考使用
本文介绍TrajTok，一种用于离散下一个词预测型行为生成模型的轨迹分词器，结合了数据驱动与规则驱动的方法，具备更优的覆盖率、对称性与鲁棒性，并引入空间感知的标签平滑方法以优化交叉熵损失。我们将该分词器与损失函数应用于SMART模型，在2025年Waymo Open Sim Agents Challenge中取得0.7852的现实性评分，性能领先。相关代码未来将开源。
原文摘要 · Abstract (English)
In this technical report, we introduce TrajTok, a trajectory tokenizer for discrete next-token-prediction based behavior generation models, which combines data-driven and rule-based methods with better coverage, symmetry and robustness, along with a spatial-aware label smoothing method for cross-entropy loss. We adopt the tokenizer and loss for the SMART model and reach a superior performance with realism score of 0.7852 on the Waymo Open Sim Agents Challenge 2025. We will open-source the code in the future.
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。