无需训练即可预测多路径轨迹，用少量数据也能稳定运行。
Non-Parametric Spatiotemporal Trajectory Prediction via State-Conditioned Transition Sampling
- 基于历史状态构建转移表，用核函数匹配相似轨迹
- 在仅10%数据时仍保持稳定，远超5700万参数的Transformer
- 适合数据稀缺地区快速部署，无硬件依赖
我们提出一种无需训练的多模态轨迹预测方法，在不依赖GPU和零参数学习的前提下，性能可媲美5700万参数的Transformer。该方法构建历史状态到下一位置的转移表，并通过空间距离、朝向、速度和时间上下文的乘积核进行邻居检索。两种推理模式共享同一表示：多样性惩罚采样生成覆盖不同合理路径的轨迹，束搜索则找到最高概率路径。在TrAISformer基准（丹麦海上AIS数据）上，该方法在全量数据下表现相当，而在数据稀缺场景中显著领先——当训练数据仅为10%时，其性能依然稳定，而TrAISformer则出现灾难性退化。这使得新地理区域的部署仅需原有数据量的十分之一。
原文摘要 · Abstract (English)
We present a training-free method for multi-modal trajectory prediction that achieves comparable accuracy to a 57M-parameter transformer while requiring no GPU and zero learned parameters. The method builds a transition table of historical state-to-next position pairs and retrieves neighbors using a product kernel over spatial proximity, bearing, speed, and temporal context. Two inference modes operate over this shared representation: diversity-penalized sampling produces trajectories covering distinct plausible routes, while beam search finds the highest-likelihood path. On the TrAISformer benchmark (Danish Maritime AIS), our method achieves competitive accuracy at full data availability and dramatically outperforms the transformer in data-scarce regimes---remaining stable down to 10% of training data where TrAISformer degrades catastrophically. This enables deployment in new geographic regions from an order of magnitude less historical data.
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。