arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1803.02015cs.ROcs.HC
收藏

多模态多人行为的生成式建模

Generative Modeling of Multimodal Multi-Human Behavior

Stanford University(斯坦福大学)

Boris Ivanovic, Edward Schmerling, Karen Leung, Marco Pavone

摘要:

这项工作提出了一种方法,用于建模和预测人类行为的设置与N人互动的高度多模态的情况下(即有许多可能的高度不同的未来)。一个激励性的例子包括机器人在拥挤的环境中与人类互动,例如自动驾驶汽车与人类驾驶的车辆一起运行,或者在仓库中进行人机协作装箱。我们在这种不确定的环境中建模人类行为的方法是将场景中的人类建模为图形模型中的节点,边编码它们之间的关系。对于每个人,我们从多人交互的数据集中学习未来动作的多模态概率分布。学习这样的分布是有条件的变分自编码器和概率图形模型的深度学习近似理论的最新进展。具体来说,我们学习的动作分布条件的互动历史,邻近的人类行为,和候选人的未来代理行为,以考虑到响应动态。我们展示了这样的建模方法在建模篮球运动员的轨迹,一个高度多模态,多人的情况下,作为许多机器人应用程序的代理的性能。

英文摘要:

This work presents a methodology for modeling and predicting human behavior in settings with N humans interacting in highly multimodal scenarios (i.e. where there are many possible highly-distinct futures). A motivating example includes robots interacting with humans in crowded environments, such as self-driving cars operating alongside human-driven vehicles or human-robot collaborative bin packing in a warehouse. Our approach to model human behavior in such uncertain environments is to model humans in the scene as nodes in a graphical model, with edges encoding relationships between them. For each human, we learn a multimodal probability distribution over future actions from a dataset of multi-human interactions. Learning such distributions is made possible by recent advances in the theory of conditional variational autoencoders and deep learning approximations of probabilistic graphical models. Specifically, we learn action distributions conditioned on interaction history, neighboring human behavior, and candidate future agent behavior in order to take into account response dynamics. We demonstrate the performance of such a modeling approach in modeling basketball player trajectories, a highly multimodal, multi-human scenario which serves as a proxy for many robotic applications.

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。

↑