[1]梁志伟,马旭东,戴先中.融合人运动模式分析的服务机器人和谐导航[J].东南大学学报(自然科学版),2008,38(3):401-406.[doi:10.3969/j.issn.1001-0505.2008.03.008]
 Liang Zhiwei,Ma Xudong,Dai Xianzhong.Harmonious navigation mechanisms utilizing motion patterns of people[J].Journal of Southeast University (Natural Science Edition),2008,38(3):401-406.[doi:10.3969/j.issn.1001-0505.2008.03.008]
点击复制

融合人运动模式分析的服务机器人和谐导航()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
38
期数:
2008年第3期
页码:
401-406
栏目:
自动化
出版日期:
2008-05-20

文章信息/Info

Title:
Harmonious navigation mechanisms utilizing motion patterns of people
作者:
梁志伟 马旭东 戴先中
东南大学复杂工程系统测量与控制教育部重点实验室, 南京 210096
Author(s):
Liang Zhiwei Ma Xudong Dai Xianzhong
Key Laboratory of MCCSE of Ministry of Education, Southeast University, Nanjing 210096, China
关键词:
模糊K均值算法 运动模式 和谐导航 多摄像头跟踪
Keywords:
fuzzy K-means algorithm motion patterns harmonious navigation multi-camera tracking
分类号:
TP24
DOI:
10.3969/j.issn.1001-0505.2008.03.008
摘要:
提出一种学习人典型运动模式的方法,并利用该方法对环境中的人的行为做出预测,协调机器人以达到与人和谐共处的导航目的.算法首先通过非重叠多摄像头采集人在环境中不同地点间的运动轨迹; 其次,应用两层模糊K均值算法分别对这些运动轨迹进行空间和时间序列上的分类,并利用TSC标准对每一次分类结果进行评估; 然后建立每一聚类运动模式的概率方程,依此实现对摄像头网络观测下人运动行为的预测,进而调整机器人的导航策略以达到与人和谐共处的导航目的.实验展示了该算法能够快速地利用人的运动调整其导航行为.
Abstract:
A technique for learning collections of trajectories that characterize representative motion patterns of persons is proposed, and this algorithm is applied to predict the motions of persons and direct the robot to harmoniously coexist with people. Data recorded with a camera network is clustered hierarchically using fuzzy K-means algorithm based on spatial and temporal information respectively, and the quality of each clustering results is evaluated by the tightness and separation criterion(TSC). Then each motion pattern is represented with a chain of Gaussian distributions. As a result, whenever the camera network detects a person it computes a probabilistic estimate about which motion pattern the person might be engaged in. During path planning the robot then uses this belief to improve its navigation behavior. Practical experiments demonstrate that our approach allows a robot to quickly adapt its navigation plans according to the activities of the persons.

参考文献/References:

[1] Nonaka S,Inoue K,Arai T.Evaluation of human sense of security for coexisting robots using virtual realty [C] //Proceedings of the IEEE Int Conf on Robotics and Automation.New Orleans,LA,2004:2770-2775.
[2] Bennewitz M,Burgard W,Cielniak G,et al.Learning motion patterns of people for compliant robot motion [J]. The International Journal of Robotics Research,2003,24(1):31-48.
[3] Junejo I N,Javed O,Shah M.Multi feature path modeling for video surveillance [C] //Proceeding of the IEEE Int Conf Pattern Recognition.Washington,USA,2004:710-719.
[4] Schulz D,Burgard W,Fox D,et al.Tracking multiple moving targets with a mobile robot using particle filters and statistical data association [C] //Proceeding of the IEEE Int Conf on Robotics and Automation. Seoul,Korea,2001:1665-1670.
[5] Kluge B,Kohler C,Prassler E.Fast and robust tracking of multiple moving objects with a laser range finder [C] //Proceeding of the IEEE Int Conf on Robotics and Automation.Seoul,Korea,2001:1683-1688.
[6] Hu W,Xie D,Tan T.Learning patterns of activity using fuzzy self-organizing neural network [J].IEEE Tran System,Man and Cybernetics-Part B,2004,34(3):1618-1626.
[7] Xie X,Beni G.A validity measure for fuzzy clustering [J]. IEEE Trans Pattern Analysis and Machine Intelligence,1991,13(8):841-847.
[8] Bennewitz M,Burgard W,Thrun S.Exploiting constraints during prioritized path planning for teams of mobile robots [C] //Proceedings of the IEEE Int Conf on Intelligent Robots and Systems.Maui,USA,2001:393-398.
[9] Zhou Jiangli,Yu Shengsheng,Xiao Degui.Motion tracking with fast adaptive background subtraction [J].Wuhan University Journal of Natural Sciences,2003,8(1):35-40.
[10] Nam T,Venkatesh S,West G.Multiple camera coordination in a surveillance system [J].Acta Automatica Sinica,2003,29(3):408-422.
[11] Simmons R.The inter-process communication system [EB/OL].[2007-10].http://www-2.cs.cmu.edu/afs/cs/project/TCA/www/ipc/ipc.html.
[12] Javed O,Shaf I K,Shah M.Appearance modeling for tracking in multiple non-overlapping cameras [C] //Proceeding of the IEEE Int Conf on Computer Vision and Pattern Recognition.San Diego,2005:26-33.
[13] Coman I D,Ramesh V,Meer P.Real-time tracking of non-rigid objects using mean shift[C] //Proceeding of the IEEE Int Conf on Computer Vision and Pattern Recognition.Hilton Head Island,SC,2000:142-151.

备注/Memo

备注/Memo:
作者简介: 梁志伟(1980—),男,博士生; 马旭东(联系人),男,教授,xdma@seu.edu.cn.
基金项目: 国家高技术研究发展计划(863计划)资助项目(2006AA040202, 2007AA041703).
引文格式: 梁志伟,马旭东,戴先中.融合人运动模式分析的服务机器人和谐导航[J].东南大学学报:自然科学版,2008,38(3):401-406.
更新日期/Last Update: 2008-05-20