发表机构
Amazon Web Services（亚马逊网络服务）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出一种无训练的非参数时空轨迹预测方法，无需GPU和学习参数，在数据充足时精度与57M参数Transformer相当，数据稀缺时性能显著更优，可从少量历史数据部署到新区域。
AI 中文摘要
本文提出一种无训练的多模态轨迹预测方法，其精度可与57M参数的Transformer相当，且无需GPU和任何学习到的参数。该方法构建历史状态到下一个位置对的转移表，通过空间邻近度、方位角、速度和时间上下文上的乘积核检索邻居。在该共享表示上有两种推理模式：多样性惩罚采样生成覆盖不同可行路线的轨迹，束搜索找到最高概率路径。在TrAISformer基准（丹麦海事AIS）上，该方法在数据充足时达到有竞争力的精度，在数据稀缺场景中显著优于Transformer——在训练数据仅为10%时仍保持稳定，而TrAISformer则出现灾难性性能下降。这使得该方法可从少一个数量级的历史数据中部署到新的地理区域，且无需GPU训练。
英文摘要
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.
CommentsAccepted at the 34th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL '26), Riverside, CA, USA, November 3-6, 2026. 4 pages
