用梯度检测轨迹预测中的分布偏移，无需修改原模型
Forecasting the Past: Gradient-Based Distribution Shift Detection in Trajectory Prediction
- 通过前半段轨迹预测后半段，用梯度大小做分布偏移评分
- 在Shifts和Argoverse数据集上显著提升偏移检测准确率
- 可提前发现自动驾驶规划器的碰撞风险，适合安全验证
轨迹预测模型在真实自动驾驶场景中常因训练与测试条件的分布差异而失效。这种行为或环境上的分布偏移会引发模型在陌生情境下做出错误预测，构成重大风险。本文提出一种自监督方法：后验训练一个解码器，以自监督任务从轨迹前半段预测后半段。该预测损失对解码器最后一层的梯度L2范数作为分布偏移得分。该方法不干扰原预测模型性能，且在Shifts和Argoverse数据集上显著提升了轨迹预测的分布偏移检测能力。此外，我们证明该方法还可用于在Highway模拟器中早期检测深度Q网络运动规划器的碰撞。源代码已开源：https://github.com/Michedev/forecasting-the-past。
原文摘要 · Abstract (English)
Trajectory prediction models often fail in real-world automated driving due to distributional shifts between training and test conditions. Such distributional shifts, whether behavioural or environmental, pose a critical risk by causing the model to make incorrect forecasts in unfamiliar situations. We propose a self-supervised method that trains a decoder in a post-hoc fashion on the self-supervised task of forecasting the second half of observed trajectories from the first half. The L2 norm of the gradient of this forecasting loss with respect to the decoder's final layer defines a score to identify distribution shifts. Our approach, first, does not affect the trajectory prediction model, ensuring no interference with original prediction performance and second, demonstrates substantial improvements on distribution shift detection for trajectory prediction on the Shifts and Argoverse datasets. Moreover, we show that this method can also be used to early detect collisions of a deep Q-Network motion planner in the Highway simulator. Source code is available at https://github.com/Michedev/forecasting-the-past.
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。