基於機器人的純熟技術下，載具之同步定位與地圖建構技術(Simultaneous Localization and Mapping, SLAM)近年來也備受關注。根據SLAM的感知技術研究，主要是藉由配帶多樣傳感器，使其身處未知環境中，仍可透過移動過程中進行資訊收集比對，鑑別環境特徵，完成未知環境下之探勘任務。
為了考量低成本與運算效率，本研究僅選用了光學雷達作為單一傳感器，執行未知環境中的空間量測。因此，點雲(point cloud)量測資料的穩定性、可靠度與資訊豐富度，將形成本研究的一大挑戰。過少或不正確的量測資訊，亦將導致載具位置之錯估。另外，考量到定位之運算效率即時性，萃取點雲中的特徵點，使其進入最近點迭代(Iterative Closest Point, ICP)演算法，將會是一個較佳的解決方向。
基於相關SLAM的研究架構下，本研究提出具權重機制之平行估測演算法(Weighted Parallel ICP, WP-ICP)，來解決前述問題。研究中，針對掃描點雲擷取了角點與直線特徵分群，使點雲資料量大幅降低，同時賦予其特徵資訊，可有效提高運算效率以及避免ICP匹配錯誤，再搭配低通濾波器來提高載具姿態估測穩定性。最後，透過對於角點與直線之特徵匹配權重機制，完成載具姿態的估測與融合。在此基礎下，可達成環境物件分類，使載具對於周邊物件具備認知與鑑別能力。本研究的定位準確性與文獻方法相比，能於計算速度與估測精度上達到權衡。根據實驗結果顯示，在不失室內定位應用需求下，可大幅提升運算效率。
本研究所提出的演算法均在不同的場景進行測試，以確保不同環境之適用性與可靠度，並對於WP-ICP定位之準確性和運算效率進行相關比較與討論。最後，本研究所提出之方法，於5公尺×6公尺之室內空間，以及15公尺×40公尺之室外環境，均完成實際測試，也驗證了WP-ICP之可行性。

In this paper, lidar is considered as the only sensor for detecting and identifying surroundings. To reduce computation effort for real-time pose estimate, feature points extracted from scanning points are used for ICP algorithm. This paper proposed a novel method of feature extraction, different scan matching method and a WP-ICP algorithm to improve the robustness of the pose estimate. It is obviously that the results of our proposed method are more correspond to actual traveling path of the vehicle and the developed method is with higher robustness against to external environment uncertainty. Finally, experiments are considered to verify the feasibility and efficiency of the proposed method.

[1] Lowe, D. G. (1999). Object recognition from local scale-invariant features. In Computer vision, 1999. The proceedings of the seventh IEEE international conference on (Vol. 2, pp. 1150-1157). Ieee.
[2] Bay, H., Ess, A., Tuytelaars, T., & Van Gool, L. (2008). Speeded-up robust features (SURF). Computer vision and image understanding, 110(3), 346-359.
[3] Besl, P. J., & McKay, N. D. (1992, April). Method for registration of 3-D shapes. In Robotics-DL tentative (pp. 586-606). International Society for Optics and Photonics.
[4] Thrun, S., Burgard, W., & Fox, D. (2005). Probabilistic robotics. MIT press.
[5] Hess, W., Kohler, D., Rapp, H., & Andor, D. (2016, May). Real-time loop closure in 2D LIDAR SLAM. In Robotics and Automation (ICRA), 2016 IEEE International Conference on (pp. 1271-1278). IEEE.
[6] Ho, K. L., & Newman, P. (2007). Detecting loop closure with scene sequences. International Journal of Computer Vision, 74(3), 261-286.
[7] Angeli, A., Filliat, D., Doncieux, S., & Meyer, J. A. (2008). Fast and incremental method for loop-closure detection using bags of visual words. IEEE Transactions on Robotics, 24(5), 1027-1037.
[8] Nguyen, V., Martinelli, A., Tomatis, N., & Siegwart, R. (2005, August). A comparison of line extraction algorithms using 2D laser rangefinder for indoor mobile robotics. In Intelligent Robots and Systems, 2005.(IROS 2005). 2005 IEEE/RSJ International Conference on (pp. 1929-1934). IEEE.
[9] Pavlidis, T., & Horowitz, S. L. (1974). Segmentation of plane curves. IEEE transactions on Computers, 100(8), 860-870.
[10] Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of basic Engineering, 82(1), 35-45.
[11] Nützi, G., Weiss, S., Scaramuzza, D., & Siegwart, R. (2011). Fusion of IMU and vision for absolute scale estimation in monocular SLAM. Journal of intelligent & robotic systems, 61(1), 287-299.
[12] Jensfelt, P., & Christensen, H. (1998, May). Laser based position acquisition and tracking in an indoor environment. In International Symposium on Robotics and Automation-ISRA (Vol. 98).
[13] Armesto, L., & Tornero, J. (2004). SLAM based on Kalman filter for multi-rate fusion of laser and encoder measurements. In Intelligent Robots and Systems, 2004.(IROS 2004). Proceedings. 2004 IEEE/RSJ International Conference on(Vol. 2, pp. 1860-1865). IEEE.
[14] Scanning Rangefinder Distance Data Output/UST-10/20LX Product Details | HOKUYO AUTOMATIC CO., LTD.. (2017). Hokuyo-aut.jp. Retrieved 8 July 2017, from https://www.hokuyo-aut.jp/search/single.php?serial=167
[15] Lv, J., Kobayashi, Y., Ravankar, A. A., & Emaru, T. (2014). Straight line segments extraction and ekf-slam in indoor environment. Journal of Automation and Control Engineering Vol, 2(3).
[16] Wang, Y. K., Huo, J., & Wang, X. S. (2014, July). A real-time robotic indoor 3D mapping system using duel 2D laser range finders. In Control Conference (CCC), 2014 33rd Chinese (pp. 8542-8546). IEEE.
[17] Premebida, C., & Nunes, U. (2005). Segmentation and geometric primitives extraction from 2d laser range data for mobile robot applications. Robotica, 2005, 17-25.
[18] Nunez, P., Vazquez-Martin, R., del Toro, J. C., Bandera, A., & Sandoval, F. (2006, May). Feature extraction from laser scan data based on curvature estimation for mobile robotics. In Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006. (pp. 1167-1172). IEEE.
[19] Borges, G. A., & Aldon, M. J. (2004). Line extraction in 2D range images for mobile robotics. Journal of Intelligent and Robotic Systems, 40(3), 267-297.