arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.15906cs.CV
收藏

通过神经随机微分方程提高跨域轨迹预测的迁移性

Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equation

KAIST(韩国科学技术院)

Daehee Park, Jaewoo Jeong, Kuk-Jin Yoon

AI总结:

针对跨数据集轨迹预测迁移性差的问题,提出基于神经随机微分方程连续与随机表示的方法,结合数据集特定扩散网络,在多个基准数据集上验证了其有效提升跨域迁移性能。

摘要:

多智能体轨迹预测对于各种实际应用至关重要,推动了包括车辆和行人轨迹在内的大规模轨迹数据集的构建。然而,由于外部因素和数据采集策略的不同,数据集之间存在差异。外部因素包括地理差异和驾驶风格,而数据采集策略包括数据采集频率、历史/预测长度以及检测器/跟踪器误差。因此,在大规模数据集上训练的模型在其他小规模数据集上的迁移性能有限,限制了对现有大规模数据集的利用。为了解决这一限制,我们提出了一种基于神经随机微分方程(NSDE)的连续和随机表示的方法,以缓解由数据采集策略引起的差异。我们利用连续表示处理任意时间步长的优势,以及随机表示处理检测器/跟踪器误差的优势。此外,我们提出了一种数据集特定的扩散网络及其训练框架,以处理数据集特定的检测/跟踪误差。我们在流行的基准数据集上验证了我们的方法相对于最先进的轨迹预测模型的有效性:nuScenes、Argoverse、Lyft、INTERACTION和Waymo开放运动数据集(WOMD)。在各种源和目标数据集配置上的性能提升显示了我们的方法在解决跨数据集差异方面的泛化能力。

英文摘要:

Multi-agent trajectory prediction is crucial for various practical applications, spurring the construction of many large-scale trajectory datasets, including vehicles and pedestrians. However, discrepancies exist among datasets due to external factors and data acquisition strategies. External factors include geographical differences and driving styles, while data acquisition strategies include data acquisition rate, history/prediction length, and detector/tracker error. Consequently, the proficient performance of models trained on large-scale datasets has limited transferability on other small-size datasets, bounding the utilization of existing large-scale datasets. To address this limitation, we propose a method based on continuous and stochastic representations of Neural Stochastic Differential Equations (NSDE) for alleviating discrepancies due to data acquisition strategy. We utilize the benefits of continuous representation for handling arbitrary time steps and the use of stochastic representation for handling detector/tracker errors. Additionally, we propose a dataset-specific diffusion network and its training framework to handle dataset-specific detection/tracking errors. The effectiveness of our method is validated against state-of-the-art trajectory prediction models on the popular benchmark datasets: nuScenes, Argoverse, Lyft, INTERACTION, and Waymo Open Motion Dataset (WOMD). Improvement in performance gain on various source and target dataset configurations shows the generalized competence of our approach in addressing cross-dataset discrepancies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑