arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1712.01949cs.AI
收藏

通过从观察到的动作分布学习嵌入来识别计划

Recognizing Plans by Learning Embeddings from Observed Action Distributions

Arizona State University(亚利桑那州立大学)

Yantian Zha, Yikang Li, Sriram Gopalakrishnan, Baoxin Li, Subbarao Kambhampati

摘要:

视觉活动识别的最新进展提高了自动视频监控等应用的可能性。然而,有效的方法,这样的问题需要能够识别的代理商的计划,从视频信息。尽管传统的计划识别算法依赖于对复杂的计划领域模型的访问,但最近一个有希望的方向涉及直接从观察到的活动序列DUP学习近似(或浅)领域模型。一个限制是,这种方法期望观察到的动作序列作为输入。在许多涉及原始数据视觉/传感的情况下,在任何给定时间点的具体行动都存在相当大的不确定性。在这种情况下,我们所能期望的最多是关于当时行动的概率信息。然后,输入将是这些观察到的动作分布的序列。在这项工作中,我们解决的问题,构建一个有效的数据接口,允许一个计划识别模块直接处理这样的观察分布。这样的接口就像低级感知模块和高级计划识别模块之间的桥梁一样工作。我们提出两种方法。第一个涉及将分布序列重新采样为单个动作序列,我们可以从中学习基于学习到的动作(词)嵌入的动作亲和力模型,用于计划识别。第二种是通过我们提出的Distr 2 vec(distribution to vector)模型直接学习动作分布嵌入,构建用于计划识别的亲和度模型。

英文摘要:

Recent advances in visual activity recognition have raised the possibility of applications such as automated video surveillance. Effective approaches for such problems however require the ability to recognize the plans of agents from video information. Although traditional plan recognition algorithms depend on access to sophisticated planning domain models, one recent promising direction involves learning approximated (or shallow) domain models directly from the observed activity sequences DUP. One limitation is that such approaches expect observed action sequences as inputs. In many cases involving vision/sensing from raw data, there is considerable uncertainty about the specific action at any given time point. The most we can expect in such cases is probabilistic information about the action at that point. The input will then be sequences of such observed action distributions. In this work, we address the problem of constructing an effective data-interface that allows a plan recognition module to directly handle such observation distributions. Such an interface works like a bridge between the low-level perception module, and the high-level plan recognition module. We propose two approaches. The first involves resampling the distribution sequences to single action sequences, from which we could learn an action affinity model based on learned action (word) embeddings for plan recognition. The second is to directly learn action distribution embeddings by our proposed Distr2vec (distribution to vector) model, to construct an affinity model for plan recognition.

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。

↑