題目：Intelligent Robot Localization using Unconventional Sensors
報告人： Simon X. Yang教授，加拿大Guelph大學
時間：2014.12.11, 13:30
地點：信息工程學院（新校）信息樓329
Simon X. Yang(楊先一)，本科畢業于北京大學、碩士畢業于美國休斯頓大學、博士畢業于加拿大阿爾伯塔大學(University of Alberta)。現為加拿大Guelph大學高級機器人與智能系統實驗室主任，終身教授，博士生導師。
主要研究領域：移動機器人路徑規劃與控制、多傳感器信息融合、無線傳感器網絡、智能計算與優化等。國際雜志《IEEE Transactions On Neural Networks》、《IEEE Transactions On Cybernetics》、《International Journal of Robotics and Automation》、《Control and Intelligent Systems》副主編; 國際雜志《International Journal of Computational Intelligence and Applications》、《International Journal of Automation and Systems Engineering》、《Journal of Robotics》、《International Journal of Computing and Information Technology》、《International Journal of Information Acquisition》編委.
報告內容簡介：
Localization without prior knowledge of the environment is considered to be one of the most challenging problems in the field of robotics. This talk explores the problem of Simultaneous Localization and Mapping (SLAM) with a focus on combining different sensors to build a more robust, accurate, and reliable localization framework.? A high level sensor fusion solution is developed, which enables simple integration of unconventional sensors not typically used for robot localization.? A capacitive sensor for sensing floor joists directly under the robot is proposed as an example of an unconventional sensor.? A neural network is implemented to combine multiple measurements and build a model of likely joist locations in unexplored regions. Two different sensor fusion approaches are demonstrated.? The first solution explores robot localization with a-priori map knowledge.? Prior map knowledge removes the requirement for map learning and focuses the problem on fusion of the different sensor maps.? With this focus high-level scalable sensor fusion architecture is implemented. Results show an improvement when using this algorithm to incorporate new sensors into the robot localization configuration.? The approach also solves the solution where the map is known but the starting location is not. The second fusion approach develops a complete multi-SLAM solution by removing the requirement of a-priori map knowledge.? The capacitive sensor is incorporated into the algorithm to demonstrate the scalability of the approach. After incorporating multiple sensors into the solution the peak error and average error of the estimated robot position are both reduced; while simultaneously enabling greater robustness through redundant sensors.
