Accurate long-term trajectory prediction in complex scenes, where multiple agents (e.g., pedestrians or vehicles) interact with each other and the environment while attempting to accomplish diverse and often unknown goals, is a challenging stochastic forecasting problem. In this work, we propose MUSE, a new probabilistic modeling framework based on a cascade of Conditional VAEs, which tackles the long-term, uncertain trajectory prediction task using a coarse-to-fine multi-factor forecasting architecture. In its Macro stage, the model learns a joint pixel-space representation of two key factors, the underlying environment and the agent movements, to predict the long and short-term motion goals. Conditioned on them, the Micro stage learns a fine-grained spatio-temporal representation for the prediction of individual agent trajectories. The VAE backbones across the two stages make it possible to naturally account for the joint uncertainty at both levels of granularity. As a result, MUSE offers diverse and simultaneously more accurate predictions compared to the current state-of-the-art. We demonstrate these assertions through a comprehensive set of experiments on nuScenes and SDD benchmarks as well as PFSD, a new synthetic dataset, which challenges the forecasting ability of models on complex agent-environment interaction scenarios.
翻译:在复杂的场景中,多种物剂(例如行人或车辆)在试图实现多样化和往往不为人知的目标的同时彼此互动和环境是具有挑战性的随机预测问题。在这项工作中,我们提出MUSE,这是一个基于一系列有条件VAE的新的概率模型框架,它利用粗到软多因因素预测结构处理长期、不确定的轨迹预测任务。在宏观阶段,模型学习了两种关键因素的联合像素空间代表,即基本环境和物剂运动,以预测长期和短期运动目标。在这项工作中,我们建议MUSE,一个基于一系列条件性VAE的微小概率模型,用于预测单个物剂轨迹。在两个阶段中,VAE的骨干能够自然地计算出颗粒度和多因因素预测结构的共同不确定性。结果,MUSE提供了多样化和同时的更精确的空间模型,用以预测长期和短期运动目标。微小阶段阶段学习了精细的SDFS-S-S-S-S-S-S-S-S-S-SD-S-S-S-SID-S-S-S-SID-S-Sent-SIS-ass-Sex-Sex-Sex-ass-Sex-Sideal-Sex-Sex-Seximviview-S-S-S-S-S-SD-S-S-S-S-S-S-S-SD-S-S-S-S-S-S-S-S-S-S-SD-S-S-S-SD-SD-S-S-SD-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-S-