High capacity end-to-end approaches for human motion prediction have the ability to represent subtle nuances in human behavior, but struggle with robustness to out of distribution inputs and tail events. Planning-based prediction, on the other hand, can reliably output decent-but-not-great predictions: it is much more stable in the face of distribution shift, but it has high inductive bias, missing important aspects that drive human decisions, and ignoring cognitive biases that make human behavior suboptimal. In this work, we analyze one family of approaches that strive to get the best of both worlds: use the end-to-end predictor on common cases, but do not rely on it for tail events / out-of-distribution inputs -- switch to the planning-based predictor there. We contribute an analysis of different approaches for detecting when to make this switch, using an autonomous driving domain. We find that promising approaches based on ensembling or generative modeling of the training distribution might not be reliable, but that there very simple methods which can perform surprisingly well -- including training a classifier to pick up on tell-tale issues in predicted trajectories.
翻译:人类运动预测的高端到终端能力方法能够代表人类行为中微妙的细微细微差别,但与强力抗争以摆脱分配投入和尾部事件。另一方面,基于规划的预测可以可靠地输出像样但非伟大的预测:在分配变化面前,这种预测更加稳定得多,但在分配变化面前,它具有很高的感应偏差,缺失了驱动人类决策的重要方面,忽视了使人类行为不尽人意的认知偏见。在这项工作中,我们分析一套努力获得两个世界最佳的方法:在常见情况下使用端到端预测器,但并不依赖它来进行尾端事件/分配之外的预测 -- -- 转换到基于规划的预测或预测的预测。我们用自主的驱动领域对不同方法进行分析,以便在进行这种转换时加以检测。我们发现,基于培训分布的组合或基因化模型的有希望的方法可能并不可靠,但有非常简单的方法可以发挥出惊人的作用 -- -- 包括培训分类员在预测的轨迹中选择。