题目：Intelligent Multi-Robot Cooperation for Target Searching and Foraging in Completely Unknown Environments
报告人： Simon X. Yang (杨先一) 教授，加拿大Guelph大学
时间：2013.5.4, 上午10:30
地点：信息工程学院（新校）信息楼330
主讲人简介：
Simon X. Yang(杨先一)，本科毕业于北京大学、硕士毕业于美国休斯顿大学（University of Huston）、博士毕业于加拿大阿尔伯塔大学(University of Alberta)。现为加拿大Guelph大学高级机器人与智能系统实验室主任，终身教授，博士生导师。
主要研究领域：移动机器人路径规划与控制、多传感器信息融合、无线传感器网络、智能计算与优化、多机器人系统等。国际杂志《IEEE Transactions On Neural Networks》、《IEEE Transactions On Systems, Man, And Cybernetics, Part B》、《International Journal of Robotics and Automation》、《Control and Intelligent Systems》副主编; 国际杂志《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》编委.
报告内容简介：
Multi-robot cooperation can significantly improve work efficiency and provide with better robustness and adaptability than a single robot. This research focuses on the effective cooperation strategy for multi-robot systems. Target searching in completely unknown environments is a challenging topic in multi-robot exploration. The multi-robot system has no information about the environments except the total number of targets, and a target searching task is accomplished when all the targets are acquired. Autonomous and reasonable exploration is expected. In this research, a combined Option and MAXQ hierarchical reinforcement learning algorithm is firstly developed to promote the learning ability to handle tasks in new unknown environments. Though it can work in some situations, the indispensable learning process prevents it from efficiently dealing with dynamic tasks in unknown environments. A potential field-based particle swarm optimization (PPSO) approach is presented. A novel potential field-based fitness function is developed for the PSO algorithm structure to provide the exploration priority evaluation for undetected areas. The potential function is based on some designed cooperation rules. Furthermore, an improved PPSO approach with dynamic parameter tuning is applied to handle tasks in complex environments. As an extension, cooperative foraging tasks are investigated. In addition, fuzzy obstacle avoidance is integrated to improve the smoothness of the robot trajectory. The scheme is tested under different scenarios in simulation experiments to validate the flexibility and effectiveness. In simulation studies, scenarios with obstacles and uncertainties are considered to demonstrate the robustness and adaptability.
