TITAN：使用行动优先级的未来预测
TITAN: Future Forecast using Action Priors
摘要：
我们考虑的问题，预测未来的轨迹场景代理从自我中心的意见，从移动平台。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性决策的自主系统。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理），这是一种新的模型，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。在没有合适的数据集用于此任务的情况下，我们创建了TITAN数据集，该数据集由700个标记的视频剪辑（具有里程计）组成，这些视频剪辑是从东京高度交互式城市交通场景中的移动车辆上捕获的。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，运输和交流动作。为了评估我们的模型，我们在TITAN数据集上进行了大量的实验，结果显示，与基线和最先进的算法相比，性能有了显著的提高。我们还报告了我们的代理重要性机制（AIM），一个模块，通过计算每个代理对未来自我轨迹的相对影响，提供了深入了解感知风险的评估有希望的结果。该数据集可在https://usa.honda-ri.com/titan上获得
英文摘要：
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
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。
