Unsupervised Human Activity Analysis for Intelligent Mobile Robot

被引:0
|
作者
Duckworth, Paul [1 ]
机构
[1] Univ Oxford, Oxford, England
来源
KUNSTLICHE INTELLIGENZ | 2018年 / 32卷 / 04期
关键词
Human activity analysis; Mobile robotics; Qualitative spatio-temporal representation; Probabilistic machine learning; Latent Dirichlet allocation;
D O I
10.1007/s13218-018-0558-4
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The success of intelligent mobile robots operating and collaborating with humans in daily living environments depends on their ability to generalise and learn human movements, and obtain a shared understanding of an observed scene. In this thesis we aim to understand human activities being performed in real-world environments from long-term observation from an autonomous mobile robot. A number of qualitative spatial-temporal representations are used to capture different aspects of the relations between human subjects and their environment. Analogous to information retrieval on text corpora, a generative probabilistic technique is used to recover latent, semantically-meaningful concepts in the encoded observations in an unsupervised manner. The small number of concepts discovered are considered as human activity classes, granting the robot a low-dimensional understanding of visually observed complex scenes. Finally, variational inference is used to facilitate incremental updating of such concepts allowing for efficient learning and updating of human activity models over time, resulting in efficient life-long learning.
引用
收藏
页码:291 / 294
页数:4
相关论文
共 50 条
  • [1] Unsupervised Human Activity Analysis for Intelligent Mobile Robot
    Paul Duckworth
    [J]. KI - Künstliche Intelligenz, 2018, 32 (4) : 291 - 294
  • [2] Unsupervised human activity analysis for intelligent mobile robots
    Duckworth, Paul
    Hogg, David C.
    Cohn, Anthony G.
    [J]. ARTIFICIAL INTELLIGENCE, 2019, 270 : 67 - 92
  • [3] Unsupervised Activity Recognition Using Latent Semantic Analysis on a Mobile Robot
    Duckworth, Paul
    Alomari, Muhannad
    Gatsoulis, Yiannis
    Hogg, David C.
    Cohn, Anthony G.
    [J]. ECAI 2016: 22ND EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, 285 : 1062 - 1070
  • [4] Latent Dirichlet Allocation for Unsupervised Activity Analysis on an Autonomous Mobile Robot
    Duckworth, Paul
    Alomari, Muhannad
    Charles, James
    Hogg, David C.
    Cohn, Anthony G.
    [J]. THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 3819 - 3826
  • [5] A human interface for an intelligent mobile robot
    Graefe, V
    Bischoff, R
    [J]. RO-MAN '97 SENDAI: 6TH IEEE INTERNATIONAL WORKSHOP ON ROBOT AND HUMAN COMMUNICATION, PROCEEDINGS, 1997, : 194 - 199
  • [6] Human Activity Recognition for Mobile Robot
    Olatunji, Iyiola E.
    [J]. 3RD ANNUAL INTERNATIONAL CONFERENCE ON INFORMATION SYSTEM AND ARTIFICIAL INTELLIGENCE (ISAI2018), 2018, 1069
  • [7] Human observation based mobile robot navigation in intelligent space
    Sasaki, Takeshi
    Hashimoto, Hideki
    [J]. 2006 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-12, 2006, : 1044 - +
  • [8] Modeling human-robot interaction for intelligent mobile robotics
    Rogers, TE
    Peng, J
    Zein-Sabatto, S
    [J]. 2005 IEEE International Workshop on Robot and Human Interactive Communication (RO-MAN), 2005, : 36 - 41
  • [9] Intelligent Mobile Robot Navigation
    Omrane, Hajer
    Masmoudi, Mohamed Slim
    Masmoudi, Mohamed
    [J]. 2017 INTERNATIONAL CONFERENCE ON SMART, MONITORED AND CONTROLLED CITIES (SM2C), 2017, : 27 - 31
  • [10] Human-following mobile robot in a distributed intelligent sensor network
    Morioka, K
    Lee, JH
    Hashimoto, H
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2004, 51 (01) : 229 - 237