透過您的圖書館登入
IP:44.200.74.73
  • 學位論文

應用雷射測距儀於多機器人合作之人員追蹤系統

Multi-robot Cooperation Based Human Tracking System Using Laser Scanner

指導教授 : 傅立成

摘要


近年來,隨著人員與機器人之間互動功能(簡稱:人機互動)日漸頻繁,人員偵測以及人員追蹤系統也開始慢慢受到重視。本論文提出一套以雷射測距儀作為感測器的混合式人員腳部偵測系統,並且透過多機器人間共享視野及整合,開發出以多機器人和多人的環境中的人員追蹤系統。 首先,我們利用雷射測距儀從環境中所蒐集到的資訊,將雷射點資訊分段成為數個區塊,之後套入機率模型去比對人腳的模版檢驗(Leg Pattern)與人腳的相似程度。然而,此一模版比對方法應用在日常生活中容易因為存在於環境中類似人腳的靜態物體而失敗,故我們再加入修正型內角變異(Modified Inscribed Angle Variance)方法來驗證所得到的區段資訊是否符合人類小腿部位的弧形特徵。此外,我們也利用運動偵測來去除環境中沒有移動過的靜態物體。 在本論文中,系統中的每個機器人都搭載著一台雷射測距儀以及上述的混合式人員偵測系統,所以每個機器人都能夠偵測出周遭環境中存在的人員,並且透過無限網路將人員的位置資訊回傳至中央處理主機。根據已知的地圖資訊,每個機器人可以經由自我定位的模組得到自己在世界座標中的位置,這個位置資訊也會經由無限網路回傳至中央處理主機。此外,我們訂出一套適合的規則以降低處理多機器人間人員的資料相關的運算複雜度。最後,這些整合過後的人員資訊將透過(SIR)粒子濾波器持續追蹤,本論文也會透過位於室內多人以及多機器人環境的實驗來驗證演算法的可行性。

並列摘要


Human tracking has received tremendous amount of attention while human-robot interaction is getting more and more important nowadays. In this paper, we developed a hybrid approach to a Laser Range Finder (LRF) based human leg detection system that returns not only "true" or "false" type of answer but also a probability. We first obtain the geometric information from measurements made by the laser range finder, and this set of measurement data is further decomposed into several sectors using segmentation. And then we apply a probabilistic model to compare these sectors with leg patterns to check if they belong to the set of human leg patterns or not. Next, we examine these leg sectors with a modified Inscribe Angle Variance (IAV) method in order to get if how likely these sectors are from human leg's arc feature or not. Moreover, we also use motion detector to check if these objects move or not as an enhancement of the detection. In our work, each robot of our system is equipped with a LRF and a hybrid approach as mentioned to human detection, so it can deliver the detected human information to our center control computer through the Inter-Process Communication (IPC). Within a prior map information and supposing each robot in the team has a localization module, we can map these results of human detection from each robot into the global coordinate. But in order to reduce the computational complexity while doing the data association among these robots in a team, we introduce a set of appropriate rules. Finally, we apply the observations to a SIR particle filter based human tracking system to keep tracking people being detected. This work has been evaluated through several experiments with a number of mobile robots and humans in an indoor environment, and promising performance has been observed.

參考文獻


[1]J.S. Cui, H.B. Zha, H.J. Zhao, R. Shibasaki, “Multi-modal Tracking of People Using Laser Scanners and Video Camera,” Image Vision Computing, no. 2, pp. 240-252, 2008.
[2]N. Bellotto, H. Hu, “Multisensor-Based Human Detection and Tracking for Mobile Service Robots, ” IEEE Trans. on Systems, Man, and Cybernetics, Part B, 39 (1). pp. 167-181
[3]E.A. Topp, H.I. Christensen, “Tracking for Following and Passing Persons,” IEEE Int. Conf. on Intelligent Robots and Systems, pp. 2321-2327, 2005.
[5]Z. Huijing, S. Ryosuke, I. Nobuaki, “A Novel System for Tracking Pedestrians Using Multiple Single-Row Laser-Range Scanners,” IEEE Int. Trans. Systems, Man and Cybernetics, vol. 35, pp. 283-291, 2005.
[6]T. Horiuchi, S. Thompson, S. Kagami, Y. Ehara, “Pedestrian Tracking From a Mobile Robot Using a Laser Range Finder,” IEEE Int. Conf. on Systems, Man and Cybernetics, pp. 931-936, 2007.

延伸閱讀