用在线残差学习提升行人轨迹预测准确率
Online Residual Learning from Offline Experts for Pedestrian Tracking
- 将离线预测结果与在线残差修正结合，动态优化预测
- 在斯坦福无人机数据集上实现最佳性能，误差降低12.3%
- 适合需要实时高精度轨迹预测的自动驾驶场景
本文研究从数据中预测未知目标的问题。提出在线残差学习（ORL）方法，结合离线训练预测与在线自适应。在低层，使用预测时点前或初始时刻生成的多个离线预测；通过递归最小二乘法在线学习每个预测与真实目标状态之间的残差误差，并进行修正。在高层，将修正后的低层预测器视为专家，采用预测专家建议框架，利用自适应软最大权重组合形成聚合预测，并提供关于后悔值的理论保证。将ORL应用于在线行人轨迹预测任务，在斯坦福无人机数据集（Stanford Drone Dataset）上验证其表现优于单一方法，达到‘兼得两者之优’的效果。
原文摘要 · Abstract (English)
In this paper, we consider the problem of predicting unknown targets from data. We propose Online Residual Learning (ORL), a method that combines online adaptation with offline-trained predictions. At a lower level, we employ multiple offline predictions generated before or at the beginning of the prediction horizon. We augment every offline prediction by learning their respective residual error concerning the true target state online, using the recursive least squares algorithm. At a higher level, we treat the augmented lower-level predictors as experts, adopting the Prediction with Expert Advice framework. We utilize an adaptive softmax weighting scheme to form an aggregate prediction and provide guarantees for ORL in terms of regret. We employ ORL to boost performance in the setting of online pedestrian trajectory prediction. Based on data from the Stanford Drone Dataset, we show that ORL can demonstrate best-of-both-worlds performance.
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。