Scholarlink

<p>To effectively respond to sudden events in dynamic and complex environments, trajectory prediction systems must have rapid inference capabilities and low error. This is challenging because it requires using low-complexity models to achieve high-precision predictions, which means having an appropriate balance between inference speed and prediction error. To address this challenge, we present a trajectory prediction model based on diffusion for optimizing predicted trajectories — TrajDiffRefine. The core of the proposed TrajDiffRefine is to construct a simple network for initial predictions, followed by diffusion which progressively refines the predictions. This approach significantly accelerates the inference process while ensuring the precision of the final predictions. Moreover, Initial Estimator accounts for the stochasticity and multi-modal nature of human behavior, including variability in individual decision-making, interaction dynamics, and environmental influences. The introduction of indeterminacy effectively improves prediction performance. Experiments on three real-world datasets—NBA, SDD, and ETH-UCY—show that the proposed method outperforms others in terms of both prediction error and efficiency.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

TrajDiffRefine: refinement of spatio-temporal stochastic trajectory prediction via diffusion

  • 期刊论文

  • 发表日期：

    2025年8月19日

查看全文
  • Xiangyun Tan,
  • Qi Zou

摘要

To effectively respond to sudden events in dynamic and complex environments, trajectory prediction systems must have rapid inference capabilities and low error. This is challenging because it requires using low-complexity models to achieve high-precision predictions, which means having an appropriate balance between inference speed and prediction error. To address this challenge, we present a trajectory prediction model based on diffusion for optimizing predicted trajectories — TrajDiffRefine. The core of the proposed TrajDiffRefine is to construct a simple network for initial predictions, followed by diffusion which progressively refines the predictions. This approach significantly accelerates the inference process while ensuring the precision of the final predictions. Moreover, Initial Estimator accounts for the stochasticity and multi-modal nature of human behavior, including variability in individual decision-making, interaction dynamics, and environmental influences. The introduction of indeterminacy effectively improves prediction performance. Experiments on three real-world datasets—NBA, SDD, and ETH-UCY—show that the proposed method outperforms others in terms of both prediction error and efficiency.