Coordination Funds

在过去的几年里，我们已经看到计算机系统在对互联网上的图像或视频片段进行分类或为游戏应用实时分析人体姿势方面取得了巨大的进步。然而，这些系统分析过去，或者在实时系统的情况下分析现在，延迟几毫秒。对于移动系统必须与人类反应或交互的应用程序，这是不够的。例如，与人类合作的机器人不仅需要感知当前的情况，还需要预测人类的行为和由此产生的未来情况，以便计划自己的行动。在这个项目中，我们的目标是开发技术，为需要预测人类行为的应用奠定基础。该项目不是在有限的范围内解决问题，而是解决所有相关方面，包括从毫秒到小时的时间范围，以及从详细的人体运动到粗略的动作标签的粒度。为了确保所开发的方法不局限于单一任务，而是可以应用于各种各样的应用，我们不是孤立地解决子问题，而是共同解决所有相关方面。因此，目标是开发一个框架，从长期预测的离散活动标签到短期预测的详细人类运动，在各个层面无缝地预测人类行为。作为一个应用场景，我们专注于人类支持机器人，在家里支持残疾人或老年人。由于人口结构的变化，德国和其他国家的人口结构将发生巨大变化，人类支持机器人可以填补我们需要面对的缺口。然而，它们需要能够在不同的粒度级别上预测人类行为，以便被接受和高效。机器人需要知道什么时候需要它的帮助，但它不应该挡道。在协作环境中，机器人被期望与人类一起完成任务。这既需要预测意图，也需要预测详细的动作，例如，在一起组装一个物体或准备一顿饭的时候。

In the last years, we have seen a tremendous progress in the capabilities of computer systems to classify image or video clips taken from the Internet or to analyze human pose in real-time for gaming applications. These systems, however, analyze the past or in the case of real-time systems the present with a delay of a few milliseconds. For applications, where a moving system has to react or interact with humans, this is insufficient. For instance, robots collaborating with humans need not only to perceive the current situation, but they need to anticipate human actions and the resulting future situations in order to plan their own actions.In this project, we aim to develop the technology that lays the foundation for applications that require the anticipation of human behavior. Instead of addressing the problem at a limited scope, the project addresses all relevant aspects including time horizons ranging from milliseconds to hours and granularity ranging from detailed human motion to coarse action labels. To ensure that the developed methods are not limited to a single task but can be applied for a large variety of applications, we do not solve sub-problems in isolation but address all relevant aspects jointly. The goal is therefore to develop a framework that seamlessly anticipates human behavior at all levels ranging from discrete activity labels for long-term prediction to detailed human motion for short term prediction.As a scenario for an application, we focus on human support robots that support impaired or elderly people at home. Human support robots can fill the gap that we need to face due to the demographic change that will change the population structure in Germany and other countries dramatically. However, they need the ability to anticipate human behavior at various levels of granularity in order to be accepted and be efficient. The robot needs to know when its help is needed, but it should not stand in the way. In a collaborative setting, the robot is expected to complete tasks together with a human. This requires to anticipate both the intention but also detailed movements, e.g., when jointly assembling an object or preparing a meal.