Navigating dynamic physical environments without obstructing or damaging human assets is of quintessential importance for social robots. In this work, we solve autonomous drone navigation's sub-problem of predicting out-of-domain human and agent trajectories using a deep generative model. Our method: General-PECNet or G-PECNet observes an improvement of 9.5\% on the Final Displacement Error (FDE) on 2020's benchmark: PECNet through a combination of architectural improvements inspired by periodic activation functions and synthetic trajectory (data) augmentations using Hidden Markov Models (HMMs) and Reinforcement Learning (RL). Additionally, we propose a simple geometry-inspired metric for trajectory non-linearity and outlier detection, helpful for the task. Code available at $\href{https://github.com/Aryan-Garg/PECNet-Pedestrian-Trajectory-Prediction.git}{GitHub}$

翻译：摘要：在动态物理环境中导航而不阻碍或损坏人类资产，对于社交机器人至关重要。本研究通过深度生成模型解决自主无人机导航的子问题——预测领域外的人类和智能体轨迹。我们的方法（通用PECNet，即G-PECNet）在2020年基准模型PECNet的基础上，结合受周期激活函数启发的架构改进与基于隐马尔可夫模型（HMM）和强化学习（RL）的合成轨迹（数据）增强，将最终位移误差（FDE）降低了9.5%。此外，我们提出了一种基于几何的简单度量，用于轨迹非线性和异常值检测，这对任务具有重要意义。代码可在$\href{https://github.com/Aryan-Garg/PECNet-Pedestrian-Trajectory-Prediction.git}{GitHub}$获取。