适应长度偏移:用于轨迹预测的 FlexiLength 网络
Adapting to Length Shift: FlexiLength Network for Trajectory Prediction
AI总结:
针对轨迹预测中观测长度变化导致性能下降的问题,本文提出 FlexiLength 网络(FLN),通过 FlexiLength 校准与适应模块学习时间不变表示,在多个数据集上验证了其有效性和灵活性。
摘要:
轨迹预测在自动驾驶、机器人和场景理解等多种应用中发挥着重要作用。现有方法主要专注于开发紧凑的神经网络,以在公共数据集上提高预测精度,通常采用标准化的输入时长。然而,当这些模型在观测长度变化的情况下进行评估时,会出现一个显著的问题,导致性能大幅下降,我们将这一现象称为观测长度偏移(Observation Length Shift)。为了解决这一问题,我们引入了一个通用且有效的框架,即 FlexiLength 网络(FLN),以增强现有轨迹预测技术对不同观测时长的鲁棒性。具体而言,FLN 将具有不同观测长度的轨迹数据进行整合,结合 FlexiLength 校准(FLC)来获取时间不变表示,并采用 FlexiLength 适应(FLA)进一步细化这些表示,以实现更准确的未来轨迹预测。在多个数据集(即 ETH/UCY、nuScenes 和 Argoverse 1)上的综合实验证明了我们所提出的 FLN 框架的有效性和灵活性。
英文摘要:
Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding. Existing approaches mainly focus on developing compact neural networks to increase prediction precision on public datasets, typically employing a standardized input duration. However, a notable issue arises when these models are evaluated with varying observation lengths, leading to a significant performance drop, a phenomenon we term the Observation Length Shift. To address this issue, we introduce a general and effective framework, the FlexiLength Network (FLN), to enhance the robustness of existing trajectory prediction techniques against varying observation periods. Specifically, FLN integrates trajectory data with diverse observation lengths, incorporates FlexiLength Calibration (FLC) to acquire temporal invariant representations, and employs FlexiLength Adaptation (FLA) to further refine these representations for more accurate future trajectory predictions. Comprehensive experiments on multiple datasets, ie, ETH/UCY, nuScenes, and Argoverse 1, demonstrate the effectiveness and flexibility of our proposed FLN framework.
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。