Victor A. Romero-Cano, Juan I. Nieto, Gabriel Agamennoni
{"title":"Unsupervised motion learning from a moving platform","authors":"Victor A. Romero-Cano, Juan I. Nieto, Gabriel Agamennoni","doi":"10.1109/IVWORKSHOPS.2013.6615234","DOIUrl":null,"url":null,"abstract":"Learning motion patterns in dynamic environments is a key component of any context-aware robotic system, and probabilistic mixture models provide a sound framework for mining these patterns. This paper presents an approach for learning motion models from trajectories provided by the tracking system of a moving platform. We present a learning approach in which a Linear Dynamical System (LDS) is augmented with a discrete hidden variable that has a number of states equal to the number of behaviours in the environment. As a result, a mixture of linear dynamical systems (MLDSs) capable of explaining several motion behaviours is developed. The model is learned by means of the Expectation Maximization (EM) algorithm.","PeriodicalId":251198,"journal":{"name":"2013 IEEE Intelligent Vehicles Symposium (IV)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE Intelligent Vehicles Symposium (IV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IVWORKSHOPS.2013.6615234","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Learning motion patterns in dynamic environments is a key component of any context-aware robotic system, and probabilistic mixture models provide a sound framework for mining these patterns. This paper presents an approach for learning motion models from trajectories provided by the tracking system of a moving platform. We present a learning approach in which a Linear Dynamical System (LDS) is augmented with a discrete hidden variable that has a number of states equal to the number of behaviours in the environment. As a result, a mixture of linear dynamical systems (MLDSs) capable of explaining several motion behaviours is developed. The model is learned by means of the Expectation Maximization (EM) algorithm.