基于“原型”的机器人开放式室内场所感知实验研究

朱博, 戴先中, 李新德, 杨伟, 陈芳园

朱博, 戴先中, 李新德, 杨伟, 陈芳园. 基于“原型”的机器人开放式室内场所感知实验研究[J]. 机器人, 2013, 35(4): 491-499,512. DOI: 10.3724/SP.J.1218.2013.00491
引用本文: 朱博, 戴先中, 李新德, 杨伟, 陈芳园. 基于“原型”的机器人开放式室内场所感知实验研究[J]. 机器人, 2013, 35(4): 491-499,512. DOI: 10.3724/SP.J.1218.2013.00491
ZHU Bo, DAI Xianzhong, LI Xinde, YANG Wei, CHEN Fangyuan. Experimental Study on Open Interior-Places Perception of Robot Based on “Prototype”[J]. ROBOT, 2013, 35(4): 491-499,512. DOI: 10.3724/SP.J.1218.2013.00491
Citation: ZHU Bo, DAI Xianzhong, LI Xinde, YANG Wei, CHEN Fangyuan. Experimental Study on Open Interior-Places Perception of Robot Based on “Prototype”[J]. ROBOT, 2013, 35(4): 491-499,512. DOI: 10.3724/SP.J.1218.2013.00491
朱博, 戴先中, 李新德, 杨伟, 陈芳园. 基于“原型”的机器人开放式室内场所感知实验研究[J]. 机器人, 2013, 35(4): 491-499,512. CSTR: 32165.14.robot.2013.00491
引用本文: 朱博, 戴先中, 李新德, 杨伟, 陈芳园. 基于“原型”的机器人开放式室内场所感知实验研究[J]. 机器人, 2013, 35(4): 491-499,512. CSTR: 32165.14.robot.2013.00491
ZHU Bo, DAI Xianzhong, LI Xinde, YANG Wei, CHEN Fangyuan. Experimental Study on Open Interior-Places Perception of Robot Based on “Prototype”[J]. ROBOT, 2013, 35(4): 491-499,512. CSTR: 32165.14.robot.2013.00491
Citation: ZHU Bo, DAI Xianzhong, LI Xinde, YANG Wei, CHEN Fangyuan. Experimental Study on Open Interior-Places Perception of Robot Based on “Prototype”[J]. ROBOT, 2013, 35(4): 491-499,512. CSTR: 32165.14.robot.2013.00491

基于“原型”的机器人开放式室内场所感知实验研究

详细信息
    作者简介:

    朱 博(1981-),男,博士生.研究领域:空间定性推理,机器人交互与导航,语义地图创建.
    戴先中(1954-),男,博士,教授.研究领域:复杂控制理论,机器人控制,电力系统控制,测量与信号处理.
    李新德(1975-),男,博士,副教授.研究领域:智能机器人,机器感知,信息融合,不确定推理和机器视觉.

    通信作者:

    朱博, zhuboseu@163.com

  • 中图分类号: TP242

Experimental Study on Open Interior-Places Perception of Robot Based on “Prototype”

  • 摘要: 在基于“原型”的场所感知算法基础上构建了一种场所感知实验平台.其中,硬件系统主要以双目立体相机作为环境感知传感器,以CPU-GPU(中央处理器-图形处理器)协同计算单元作为多种任务、 复杂逻辑和密集数据的处理单元;而软件系统基于微软Robotics Developer Studio平台构建,双目视觉服务和场所感知服务为其中两大核心服务, 前者利用RANSAC(随机采样一致性)和GPU版本ASIFT(仿射尺度不变特征变换)等算法在宽视角范围内实现物品识别和位姿估算,适用于拥挤室内环境, 后者基于双目视觉结果和已有场所感知算法完成场所分类及区域感知并构建2D语义地图.在无人工标注的真实室内环境中开展实验,实验结果表明, 基于本文实验平台的机器人能够在线鲁棒地感知活动空间中的开放式场所,实验也在一定程度上验证了已有场所感知算法的可实现性、有效性和实用性.
    Abstract: A place-perception experimental platform is proposed on the basis of the prototype based place perception algorithm. In the hardware system, a binocular rig is used as environment perception sensor, and CPU (central processing unit) and GPU (graphic processing unit) coordinated computing unit is used to process multiple tasks, complex logic, intensive data, and so on. The software system is constructed based on Microsoft Robotics Developer Studio platform. Binocular vision service and place perception service are two core services in it. The former is fit for clustered indoor environment, and realizes object recognition and pose estimation simultaneously in wide viewing angle by using RANSAC (RANdom SAmple Consensus), ASIFT (affine scale-invariant feature transform) -GPU and other algorithms. The latter realizes place categorization and region perception and constructs 2D semantic map based on the results of binocular vision and the existing place perception algorithm. The experiments are conducted in a real interior environment in which no artificial label is used. The experiment results show that the robot can robustly perceive open places in its action space online based on the experimental platform, and realizability, effectiveness and practicability of the existing place perception algorithm are verified to a certain extent.
  • [1] Vasudevan S, Siegwart R. Bayesian space conceptualization and place classification for semantic maps in mobile robotics[J]. Robotics and Autonomous Systems, 2008, 56(6): 522-537.  
    [2] Pronobis A, Jensfelt P. Hierarchical multi-modal place categorization[C/OL]//5th European Conference on Mobile Robots. [2012-08-25]. http://cogx.eu/data/cogx/publications/ PronobisECMR2011.pdf
    [3] Swadzba A, Wachsmuth S. Indoor scene classification using combined 3D and gist features[C]//The 10th Asian Conference on Computer Vision (ACCV 2010). Berlin, Germany: Springer-Verlag, 2011: 201-215.
    [4] Pronobis A. Semantic mapping with mobile robots[D]. Stockholm, Sweden: KTH Royal Institute of Technology, 2011.
    [5] Pronobis A, Sjoo K, Aydemir A, et al. A framework for robust cognitive spatial mapping[C]//14th International Conference on Advanced Robotics. Piscataway, NJ, USA: IEEE, 2009: 1-8.
    [6] Pronobis A, Martinez Mozos O, Caputo B, et al. Multi-modal semantic place classification[J]. International Journal of Robotics Research, 2010, 29(2/3): 298-320.
    [7] Zivkovic Z, Booij O, Krose B. From images to rooms[J]. Robotics and Autonomous Systems, 2007, 55(5): 411-418.  
    [8] Valgren C, Lilienthal A. Incremental spectral clustering and seasons: Appearance-based localization in outdoor environments [C]//IEEE International Conference on Robotics and Automation. Piscataway, NJ, USA: IEEE, 2008: 1856-1861.
    [9] 吴皓,田国会,陈西博,等.基于机器人服务任务导向的室内未知环境地图构建[J].机器人,2010,32(2):196-203. Wu H, Tian G H, Chen X B, et al. Map building of indoor unknown environment based on robot service mission direction[J]. Robot, 2010, 32(2): 196-203.
    [10] Klenk M, Hawes N, Lockwood K. Representing and reasoning about spatial regions defined by context[C/OL]//2011 AAAI Fall Symposium. El Segundo, CA, USA: AI Access Foundation, 2011: 154-161. [2012-08-25]. https://www.aaai.org/ocs/ index.php/FSS/FSS11/paper/download/4143/4543.
    [11] Hawes N, Klenk M, Lockwood K, et al. Towards a cognitive system that can recognize spatial regions based on context[C/OL]//26th AAAI Conference on Artificial Intelligence. El Segundo, CA, USA: AI Access Foundation, 2012: 200-206. [2012-08-25]. http://www.aaai.org/ocs/index.php/AAAI/ AAAI12/paper/download/5061/5139.
    [12] 朱博,戴先中,李新德.基于“原型”的机器人开放式室内场所感知算法[J].模式识别与人工智能,2012,25(1):1-10. Zhu B, Dai X Z, Li X D. Open interior-places perception algorithm of robot based on prototype[J]. Pattern Recognition and Artificial Intelligence. 2012, 25(1): 1-10.
    [13] 朱博,戴先中,李新德.一种基于物联网技术的场所感知系统初探[J].计算机科学,2012,39(2):216-221.Zhu B, Dai X Z, Li X D. Preliminary study on a kind of placeperception system based on IOT technology[J]. Computer Science,2012, 39(2): 216-221.
    [14] Morel J-M, Yu G S. ASIFT: A new framework for fully affineinvariant image comparison[J]. SIAM Journal on Imaging Sciences,2009, 2(2): 438-469.  
    [15] MIT Media Lab. Lifelong Kindergarten[OL]. [2012-08-25].http://llk.media.mit.edu/projects.php?id=135.
    [16] Microsoft Robotics. Microsoft Robotics Developer Studio[OL].
    [2012-08-25]. http://www.microsoft.com/robotics/#About.
    [17] Bodurov V. Using Microsoft Robotics Developer Studio withLego Mindstorms NXT Robot[OL]. (2010-08-10) [2012-08-25]. http://www.simple-talk.com/dotnet/.net-framework/usingmicrosoft-robotics-developer-studio-with-lego-mindstormsnxt-robot/.
    [18] Fischler M A, Bolles R C. Random sample consensus: Aparadigm for model fitting with applications to image analysisand automated cartography[J]. Communications of the ACM,1981, 24(6): 381-395.  
    [19] Zhu B, Dai X Z, Li X D, et al. Place concept teaching throughsketch map for robot place perception based on prototypemechanism[C]//6th International Conference on Intelligent Systemsand Knowledge Engineering: vol.124. Berlin, Germany:Springer-Verlag, 2011: 79-89.
计量
  • 文章访问数:  25
  • HTML全文浏览量:  1154
  • PDF下载量:  688
  • 被引次数: 0
出版历程
  • 收稿日期:  2012-09-13

目录

    /

    返回文章
    返回
    x 关闭 永久关闭