We consider the problem of predicting the future trajectory of scene agents from egocentric views obtained from a moving platform. This problem is important in a variety of domains, particularly for autonomous systems making reactive or strategic decisions in navigation. In an attempt to address this problem, we introduce TITAN (Trajectory Inference using Targeted Action priors Network), a new model that incorporates prior positions, actions, and context to forecast future trajectory of agents and future ego-motion. In the absence of an appropriate dataset for this task, we created the TITAN dataset that consists of 700 labeled video-clips (with odometry) captured from a moving vehicle on highly interactive urban traffic scenes in Tokyo. Our dataset includes 50 labels including vehicle states and actions, pedestrian age groups, and targeted pedestrian action attributes that are organized hierarchically corresponding to atomic, simple/complex-contextual, transportive, and communicative actions. To evaluate our model, we conducted extensive experiments on the TITAN dataset, revealing significant performance improvement against baselines and state-of-the-art algorithms. We also report promising results from our Agent Importance Mechanism (AIM), a module which provides insight into assessment of perceived risk by calculating the relative influence of each agent on the future ego-trajectory. The dataset is available at https://usa.honda-ri.com/titan

中文翻译：

---

TITAN：使用动作先验预测未来

我们考虑从移动平台获得的以自我为中心的视图预测场景代理的未来轨迹的问题。这个问题在许多领域都很重要，特别是对于在导航中做出反应性或战略决策的自主系统。为了解决这个问题，我们引入了 TITAN（使用目标动作先验网络的轨迹推断），这是一种新模型，它结合了先前的位置、动作和上下文来预测代理的未来轨迹和未来的自我运动。在没有适合此任务的数据集的情况下，我们创建了 TITAN 数据集，其中包含 700 个标记的视频剪辑（带里程计），这些视频剪辑是从东京高度互动的城市交通场景中的移动车辆中捕获的。我们的数据集包括 50 个标签，包括车辆状态和动作、行人年龄组、和有针对性的行人动作属性，这些属性按层次组织，对应于原子、简单/复杂上下文、传输和交流动作。为了评估我们的模型，我们对 TITAN 数据集进行了大量实验，揭示了相对于基线和最先进算法的显着性能改进。我们还报告了我们的代理重要性机制 (AIM) 的有希望的结果，该模块通过计算每个代理对未来自我轨迹的相对影响来深入了解感知风险的评估。数据集可在 https://usa.honda-ri.com/titan 获得 揭示了相对于基线和最先进算法的显着性能改进。我们还报告了我们的代理重要性机制 (AIM) 的有希望的结果，该模块通过计算每个代理对未来自我轨迹的相对影响来深入了解感知风险的评估。数据集可在 https://usa.honda-ri.com/titan 获得 揭示了相对于基线和最先进算法的显着性能改进。我们还报告了我们的代理重要性机制 (AIM) 的有希望的结果，该模块通过计算每个代理对未来自我轨迹的相对影响来深入了解感知风险的评估。数据集可在 https://usa.honda-ri.com/titan 获得