具有可解释行为不确定性的人类轨迹预测
Human Trajectory Forecasting with Explainable Behavioral Uncertainty
AI总结：
本文提出结合贝叶斯神经网络与行为随机微分方程的 BNSP-SFM 模型，在提升人类轨迹预测精度的同时提供可解释的行为不确定性量化，并展现出更强的跨场景泛化能力。
摘要：
人类轨迹预测有助于理解和预测人类行为，支持从社交机器人到自动驾驶汽车等应用，因此得到了广泛研究。现有方法大多可分为无模型方法和基于模型的方法。无模型方法提供更优的预测精度但缺乏可解释性，而基于模型的方法提供可解释性但预测效果不佳。结合两种方法论，我们提出了一种新的贝叶斯神经随机微分方程模型 BNSP-SFM，其中行为 SDE 模型与贝叶斯神经网络（BNNs）相结合。神经网络提供优越的预测能力，而 SDE 提供强可解释性，并能在行为和观测中量化不确定性。我们表明，与 11 种最先进方法相比，BNSP-SFM 的预测精度最高可提升 50%。BNSP-SFM 还能更好地泛化到环境不同、人群密度差异极大的场景（约为测试数据的 20 倍）。最后，BNSP-SFM 可以提供带置信度的预测，以更好地解释潜在的行为原因。代码将在录用后发布。
英文摘要：
Human trajectory forecasting helps to understand and predict human behaviors, enabling applications from social robots to self-driving cars, and therefore has been heavily investigated. Most existing methods can be divided into model-free and model-based methods. Model-free methods offer superior prediction accuracy but lack explainability, while model-based methods provide explainability but cannot predict well. Combining both methodologies, we propose a new Bayesian Neural Stochastic Differential Equation model BNSP-SFM, where a behavior SDE model is combined with Bayesian neural networks (BNNs). While the NNs provide superior predictive power, the SDE offers strong explainability with quantifiable uncertainty in behavior and observation. We show that BNSP-SFM achieves up to a 50% improvement in prediction accuracy, compared with 11 state-of-the-art methods. BNSP-SFM also generalizes better to drastically different scenes with different environments and crowd densities (~ 20 times higher than the testing data). Finally, BNSP-SFM can provide predictions with confidence to better explain potential causes of behaviors. The code will be released upon acceptance.
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。
