论文标题
轨迹++：具有异质数据的动态可行的轨迹预测
Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data
论文作者
论文摘要
关于人类运动的推理是安全和社会意识的机器人导航的重要先决条件。结果，多代理行为预测已成为现代人类互动系统（例如自动驾驶汽车）的核心组成部分。尽管存在许多用于轨迹预测的方法，但大多数没有强制执行动态约束，也不考虑环境信息（例如，地图）。为此，我们提出了轨迹++，这是一种模块化图形结构的复发模型，可预测一般数量的不同代理的轨迹，同时结合了试剂动力学和异质数据（例如，语义图）。轨迹++设计为与机器人计划和控制框架紧密集成；例如，它可以产生可选的预测，这些预测是根据自我主动运动计划进行的。我们在几种具有挑战性的现实轨迹预测数据集上展示了它的性能，表现优于各种各样的最先进的确定性和生成性方法。
Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation. As a result, multi-agent behavior prediction has become a core component of modern human-robot interactive systems, such as self-driving cars. While there exist many methods for trajectory forecasting, most do not enforce dynamic constraints and do not account for environmental information (e.g., maps). Towards this end, we present Trajectron++, a modular, graph-structured recurrent model that forecasts the trajectories of a general number of diverse agents while incorporating agent dynamics and heterogeneous data (e.g., semantic maps). Trajectron++ is designed to be tightly integrated with robotic planning and control frameworks; for example, it can produce predictions that are optionally conditioned on ego-agent motion plans. We demonstrate its performance on several challenging real-world trajectory forecasting datasets, outperforming a wide array of state-of-the-art deterministic and generative methods.
