A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Volume 8 Issue 8
Aug.  2021

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 6.171, Top 11% (SCI Q1)
    CiteScore: 11.2, Top 5% (Q1)
    Google Scholar h5-index: 51, TOP 8
Turn off MathJax
Article Contents
He Zhang, Lingqiu Jin and Cang Ye, "An RGB-D Camera Based Visual Positioning System for Assistive Navigation by a Robotic Navigation Aid," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1389-1400, Aug. 2021. doi: 10.1109/JAS.2021.1004084
Citation: He Zhang, Lingqiu Jin and Cang Ye, "An RGB-D Camera Based Visual Positioning System for Assistive Navigation by a Robotic Navigation Aid," IEEE/CAA J. Autom. Sinica, vol. 8, no. 8, pp. 1389-1400, Aug. 2021. doi: 10.1109/JAS.2021.1004084

An RGB-D Camera Based Visual Positioning System for Assistive Navigation by a Robotic Navigation Aid

doi: 10.1109/JAS.2021.1004084
Funds:  This work was supported by the NIBIB and the NEI of the National Institutes of Health (R01EB018117). The content is solely the responsibility of the authors and does not necessarily represent the official views of the funding agencies
More Information
  • There are about 253 million people with visual impairment worldwide. Many of them use a white cane and/or a guide dog as the mobility tool for daily travel. Despite decades of efforts, electronic navigation aid that can replace white cane is still research in progress. In this paper, we propose an RGB-D camera based visual positioning system (VPS) for real-time localization of a robotic navigation aid (RNA) in an architectural floor plan for assistive navigation. The core of the system is the combination of a new 6-DOF depth-enhanced visual-inertial odometry (DVIO) method and a particle filter localization (PFL) method. DVIO estimates RNA’s pose by using the data from an RGB-D camera and an inertial measurement unit (IMU). It extracts the floor plane from the camera’s depth data and tightly couples the floor plane, the visual features (with and without depth data), and the IMU’s inertial data in a graph optimization framework to estimate the device’s 6-DOF pose. Due to the use of the floor plane and depth data from the RGB-D camera, DVIO has a better pose estimation accuracy than the conventional VIO method. To reduce the accumulated pose error of DVIO for navigation in a large indoor space, we developed the PFL method to locate RNA in the floor plan. PFL leverages geometric information of the architectural CAD drawing of an indoor space to further reduce the error of the DVIO-estimated pose. Based on VPS, an assistive navigation system is developed for the RNA prototype to assist a visually impaired person in navigating a large indoor space. Experimental results demonstrate that: 1) DVIO method achieves better pose estimation accuracy than the state-of-the-art VIO method and performs real-time pose estimation (18 Hz pose update rate) on a UP Board computer; 2) PFL reduces the DVIO-accrued pose error by 82.5% on average and allows for accurate wayfinding (endpoint position error ≤ 45 cm) in large indoor spaces.

     

  • loading
  • [1]
    R. R A Bourne, S. R. Flaxman, T. Braithwaite, M.V. Cicinelli, et al., “Magnitude, temporal trends, and projections of the global prevalence of blindness and distance and near vision impairment: A systematic review and meta-analysis,” Lancet Glob Healthm, vol. 5, no. 9, pp. 888–897, 2017. doi: 10.1016/S2214-109X(17)30293-0
    [2]
    J. M. Saez, F. Escolano, and A. Penalver, “First steps towards stereo-based 6-DOF SLAM for the visually impaired,” in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition Workshops, 2005.
    [3]
    V. Pradeep, G. Medioni, and J. Weiland, “Robot vision for the visually impaired,” in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition Workshops, 2010, pp. 15–22.
    [4]
    Y. H. Lee and G. Medioni, “RGB-D camera based navigation for the visually impaired,” in Proc. RSS Workshop on RGB-D: Advanced Reasoning With Depth Cameras, 2011, pp. 1–6.
    [5]
    C. Ye, S. Hong, X. Qian, and W. Wu, “Co-robotic cane: A new robotic navigation aid for the visually impaired,” IEEE Systems,Man,and Cybernetics Magazine, vol. 2, no. 2, pp. 33–42, 2016. doi: 10.1109/MSMC.2015.2501167
    [6]
    H. Zhang and C.Ye, “An Indoor navigation aid for the visualy impaired,” in Proc. IEEE Int. Conf. Robotics and Biomimetics, 2016, pp. 467–472.
    [7]
    B. Li, J.P. Munoz, X. Rong, Q. Chen, et al., “Vision-based mobile indoor assistive navigation aid for blind people,” IEEE Trans. Mobile Computing, vol. 18, no. 3, pp. 702–714, 2018.
    [8]
    H. Zhang, L. Jin, and C. Ye, “A depth-enhanced visual inertial odometry for a robotic navigation aid for blind people,” in Proc. Visual-Inertial Navigation: Challenges and Applications Workshop at 2019 IEEE/RSJ Int. Conf. Intelligent Robots and Systems.
    [9]
    C. Ye, S. Hong, and A. Tamjidi, “6-DOF pose estimation of a robotic navigation aid by tracking visual and geometric features,” IEEE Trans. Automation Science and Engineering, vol. 12, no. 4, pp. 1169–1180, 2015. doi: 10.1109/TASE.2015.2469726
    [10]
    S. Treuillet, E. Royer, T. Chateau, M. Dhome, et al., “Body mounted vision system for visually impaired outdoor and indoor wayfinding assistance,” in Proc. Conf. Assistive Technologies for People with Vision and Hearing Impairments, 2007.
    [11]
    K. Wang, W. Wang, and Y. Zhuang, “A map approach for vision-based self-localization of mobile robot,” Acta Automatica Sinica, vol. 34, no. 2, pp. 159–166, 2008.
    [12]
    D. Ahmetovic, C. Gleason, C. Ruan, K. Kitani, et al., “NavCog: A navigational cognitive assistant for the blind,” in Proc. 18th Int. Conf. Human-Computer Interaction with Mobile Devices and Services, 2016.
    [13]
    A. Ganz, J. M. Schafer, S. Gandhi, E. Puleo, et al., “PERCEPT indoor navigation system for the blind and visually impaired: Architecture and experimentation,” Int. J. Telemedicine and Applications, 2012. DOI: 10.1155/2012/894869
    [14]
    A. Ganz, J. M. Schafer, Y. Tao, C. Wilson, et al., “PERCEPT-II: Smartphone based indoor navigation system for the blind,” in Proc. 36th Annu. Int. Conf. IEEE Engineering in Medicine and Biology Society, 2014, pp. 3662–3665.
    [15]
    H. Zhang, L. Jin, H. Zhang, and C. Ye, “A comparative analysis of visual-inertial SLAM for assisted wayfinding of the visually impaired,” in Proc. IEEE Winter Conf. Applications of Computer Vision, 2019, pp. 210–217.
    [16]
    S. Leutenegger, S. Lynen, M. Bosse, R. Siegwart, et al., “Keyframe-based visual-inertial SLAM using nonlinear optimization,” Int. J. Robotics Research, vol. 34, no. 3, pp. 314–334, 2015. doi: 10.1177/0278364914554813
    [17]
    T. Qin, P. Li, and S. Shen, “VINS-MONO: A robust and versatile monocular visual-inertial state estimator,” IEEE Trans. Robotics, vol. 34, no. 4, pp. 1004–1020, 2018. doi: 10.1109/TRO.2018.2853729
    [18]
    R. Mur-Artal and J. D. Tardós, “Visual-inertial monocular SLAM with map reuse,” IEEE Robotics and Automation Letters, vol. 2.2, pp. 796–803, 2017.
    [19]
    S. Weiss, M. W. Achtelik, S. Lynen, M. Chli, et al., “Real-time onboard visual-inertial state estimation and self-calibration of MAVs in unknown environments,” in Proc. IEEE Int. Conf. Robotics and Automation, 2012, pp. 957–964.
    [20]
    V. Indelman, S. Williams, M. Kaess, and F. Dellaert, “Information fusion in navigation systems via factor graph based incremental smoothing,” Robotics and Autonomous Systems, vol. 61, no. 8, pp. 721–738, 2013. doi: 10.1016/j.robot.2013.05.001
    [21]
    W. Zheng, F. Zhou, and Z. Wang, “Robust and accurate monocular visual navigation combining IMU for a quadrotor,” IEEE/CAA J. Autom. Sinica, vol. 2, no. 1, pp. 33–44, 2015.
    [22]
    A. I. Mourikis and S. I. Roumeliotis, “A multi-state constraint Kalman filter for vision-aided inertial navigation,” in Proc. IEEE Int. Conf. Robotics and Automation, 2007.
    [23]
    C. Campos, R. Elvira, J. J. G. Rodriguez, J. M. Montiel, et al., “ORB-SLAM3: An accurate open-source library for visual, visual-inertial and multi-map SLAM,” arXiv preprint arXiv: 2007.11898, 2020.
    [24]
    C. Campos, J. M. Montiel, and J. D. Tardós, “Inertial-only optimization for visual-inertial initialization,” arXiv preprint arXiv: 2003.05766, 2020.
    [25]
    T. Qin and S. Shen, “Robust initialization of monocular visual-inertial estimation on aerial robots,” in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, 2017.
    [26]
    J. Delmerico and D. Scaramuzza, “A benchmark comparison of monocular visual-inertial odometry algorithms for flying robots,” in Proc. IEEE Int. Conf. Robotics and Automation, 2018.
    [27]
    K. Sun, K. Mohta, B. Pfrommer, M. Watterson, et al., “Robust stereo visual inertial odometry for fast autonomous flight,” IEEE Robotics and Automation Letters, vol. 3, no. 2, pp. 965–972, 2018.
    [28]
    N. Brunetto, S. Salti, N. Fioraio, T. Cavallari, et al., “Fusion of inertial and visual measurements for RGB-D SLAM on mobile devices,” in Proc. IEEE Int. Conf. Computer Vision Workshops, 2015, pp. 1–9.
    [29]
    Y. Ling, H. Liu, X. Zhu, J. Jiang, et al., “RGB-D inertial odometry for indoor robot via keyframe-based nonlinear optimization,” in Proc. IEEE Int. Conf. Mechatronics and Automation, 2018, pp. 973–979.
    [30]
    Z. Shan, R. Li, and S. Schwertfeger, “RGBD-inertial trajectory estimation and mapping for ground robots,” Sensors, vol. 19, no. 10, Article No. 2251, 2019. doi: 10.3390/s19102251
    [31]
    J. Shi, “Good features to track,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1994, pp. 593–600.
    [32]
    V. Lepetit, F. Moreno-Noguer, and P. Fua, “EPnP: An accurate O(n) solution to the PnP problem,” Int. J. Computer Vision, vol. 81, no. 2, Article No. 155, 2009. doi: 10.1007/s11263-008-0152-6
    [33]
    F. Boniardi, T. Caselitz, R. Kummerle, and W. Burgard, “Robust LiDAR-based localization in architectural floor plans,” in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, 2017, pp. 3318–3324.
    [34]
    F. Boniardi, T. Caselitz, R. Kummerle, and W. Burgard, “A pose graph-based localization system for long-term navigation in CAD floor plans,” Robotics and Autonomous Systems, vol. 112, pp. 84–97, 2019. doi: 10.1016/j.robot.2018.11.003
    [35]
    Y. Watanabe, K. R. Amaro, B. llhan, T. Kinoshita, et al., “Robust localization with architectural floor plans and depth camera,” in Proc. IEEE/SICE Int. Symp. System Integration, 2020.
    [36]
    A. Segal, D. Hhnel, and S. Thrun, “Generalized-ICP,” in Proc. Robotics: Science and Systems, 2009.
    [37]
    S. Seifzadeh, B. Khaleghi, and F. Karray, “Distributed soft-data-constrained multi-model particle filter,” IEEE Trans. Cybernetics, vol. 45, no. 3, pp. 384–394, 2014.
    [38]
    W. Winterhalter, F. Fleckenstein, B. Steder, L. Spinello, et al., “Accurate indoor localization for RGB-D smartphones and tablets given 2D floor plans,” in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, 2015, pp. 3138–3143.
    [39]
    UP Bridge the Gap. [Online]. Available: http://www.up-board.org/up
    [40]
    H. Zhang and C. Ye, “Human-robot interaction for assisted wayfinding of a robotic navigation aid for the blind,” in Proc. IEEE Int. Conf. Human System Interaction, 2019, pp. 137–142.
    [41]
    R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, New York, 2004.
    [42]
    B. Lucas and T. Kanade, “An iterative image registration technique with an application to stereo vision,” in Proc. Imaging Understanding Workshop, 1981, pp. 121–130.
    [43]
    Z. Zhang, “A flexible new technique for camera calibration,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp. 1330–1334, 2000. doi: 10.1109/34.888718
    [44]
    H. Zhang and C. Ye, “Plane-aided visual-inertial odometry for 6-DOF pose estimation of a robotic navigation aid,” IEEE Access, vol. 8, pp. 90042–90051, 2020. doi: 10.1109/ACCESS.2020.2994299
    [45]
    H. Zhang and C. Ye, “An indoor wayfinding system based on geometric features aided graph SLAM for the visually impaired,” IEEE Trans. Neural Systems and Rehabilitation Engineering, vol. 25, no. 9, pp. 1592–1604, 2017. doi: 10.1109/TNSRE.2017.2682265
    [46]
    C. Ye, “T-transformation: A new traversability analysis method for terrain navigation,” in Proc. SPIE Defense and Security Symp., 2004.
    [47]
    C. Ye, “A method for mobile robot obstacle negotiation,” Int. J. Intelligent Control and Systems, vol. 10, no. 3, pp. 188–200, 2005.
    [48]
    O. Wulf, K. O. Arras, H. I. Christensen, and B. Wagner, “2D mapping of cluttered indoor environments by means of 3D perception,” in Proc. IEEE Int. Conf. Robotics and Automation, 2004.
    [49]
    G. Giorgio, C. Stachniss, and W. Burgard, “Improved techniques for grid mapping with rao-blackwellized particle filters,” IEEE Trans. Robotics, vol. 23, no. 1, pp. 34–46, 2007. doi: 10.1109/TRO.2006.889486

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(9)  / Tables(5)

    Article Metrics

    Article views (1323) PDF downloads(58) Cited by()

    Highlights

    • An RGB-D camera based visual positioning system (VPS) for real-time localization of a robotic navigation aid (RNA) for assistive navigation.
    • A new depth-enhanced visual-inertial odometry method that tightly couples the visual features, geometric feature, and inertial data in a graph optimization framework to estimate the RNA’s 6-DOF pose.
    • A particle filter localization method that uses the geometric information of an indoor space’s architectural CAD drawing to reduce the accumulative error of the DVIO-estimated pose.
    • An RNA prototype consists of VPS and other essential software modules, including path planning, obstacle avoidance, and active rolling tip (ART) control, for assistive navigation.

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return