摘要
In this research work,a hierarchical controller has been designed for an autonomous navigation robot to avoid unexpected moving obstacles where the state and action spaces are continuous.The proposed scheme consists of two parts:1)a controller with a high-level approximate reinforcement learning(ARL)technique for choosing an optimal trajectory in autonomous navigation;and 2)a low-level,appearance-based visual servoing(ABVS)controller which controls and execute the motion of the robot.A novel approach for path planning and visual servoing has been proposed by the combined system framework.The characteristics of the on-board camera which is equipped on the robot is naturally suitable for conducting the reinforcement learning algorithm.Regarding the ARL controller,the computational overhead is quite low thanks to the fact that a knowledge of obstacle motion is not necessary.The developed scheme has been implemented and validated in a simulation system of obstacle avoidance.It is noted that findings of the proposed method are successfully verified by obtaining an optimal robotic plan motion strategy.
基金
supported by research grants from the Natural Sciences and Engineering Research Council(NSERC)of Canada
the British Columbia Knowledge Development Fund(BCKDF)
the Canada Foundation for Innovation(CFI)
the Canada Research Chair in Mechatronics and Industrial Automation held by C.W.de Silva
作者简介
Yunfei ZHANG,received his B.S.degree in Automation from Qingdao University of Science and Technology in 2006,and MS degree in Automotive Engineering from Shanghai Jiao Tong University,China,in 2010.He finished his Ph.D.degree the Department of Mechanical Engineering at the University of British Columbia,Canada in 2015.He is currently working on robotic technologies for caring elderly people,as an ambitious start up entrepreneur.His main research interests include deep reinforcement learning and control,decision making,robotics,and autonomous driving;Yanjun WANG obtained his PhD degree in the Department of Mechanical Engineering,The University of British Columbia,Vancouver,Canada in 2014.He received his Master's degree in Automotive Engineering from Shanghai Jiao Tong University,Shanghai,China in 2009,and his Bachelor's degree in Automotive Engineering from Nanjing University of Aeronautics&Astronautics,Nanjing,Jiangsu,China in 2006.Presently he works on compliance control of robotics in ViWiSTAR Technologies Ltd.His research interests are in robot dynamics modelling and control,system identification,automotive powertrain system modeling,control and optimization,and soft computing;Haoxiang LANG received his M.Sc.and Ph.D.degrees from the Department of Mechanical Engineering,The University of British Columbia,Vancouver,Canada in 2008 and 2012,respectively,and the Bachelor's degree from Ningbo University in 2003.He worked in the Motorola Cellular Equipment Company as a software engineering from January 2004 to September 2005.He was with the Industrial Automation Laboratory as a postdoctoral research fellow and the Lab Manager from November 2012 to December 2014.Haoxiang Lang is currently an Assistant Professor of Mechanical Engineering and the Director of the GRASP(General Robotics and Autonomous Systems and Processes)at University of Ontario Institute of Technology(UOIT).His research and development areas are Mechatron-ics,Robotics,and Artificial Intelligence;Ying WANG received his Ph.D.degree in Robotics and Mechatronics from The University of British Columbia(UBC),Vancouver,BC,Canada in 2008.He also received his Master's degree(1999)and the Bachelor's degree(1991)from Shanghai Jiao Tong University,China.He is now an Associate Professor in the Department of Mechatronics Engineering at Kennesaw State University,Marietta,Georgia,30060,USA.Dr.Wang's research interests are in the areas of robotics,controls,mechatronics and machine learning;Clarence W.de Silva received Ph.D.degrees from Massachusetts Institute of Technology,Cambridge,USA.,in 1978,and the University of Cambridge,Cambridge,U.K.,in 1998,the Honorary D/Eng,degree from the University of Waterloo,Waterloo,ON,Canada,in 2008,and the higher doctorate(Sc.D.)from the University of Cambridge(2020).He has been a Professor of Mechanical Engineering and NSERC-BC Packers Chair in Industrial Automation at the University of British Columbia,Vancouver,BC,Canada,since 1988,and the Senior Canada Research Chair in Mechatronics and Industrial Automation.He has authored 25 books and more than 550 papers,approximately half of which are in journals.His recent books published by Taylor&Francis/CRC arej Modeling of Dynamic Systems—with Engineering Applications(.2018),Sensor Systems(2017),Sensors and Actuators—Engineering System Instrumentation,2nd edition(2016),Mechanics of Materials(2014),Mechatronics—A Foundation Coui'se(2010),Modeling and Control of Engineering Systems(2009),Sensors and Actuators—Control System Instrumentation(2007),VIBRATION—Fundamentals and Practice(2nd ecL,2007),Mechatronics—An Integrated Approach(2005)and by Addison Wesley:Soft Computing and Intelligent Systems Design Theory,Tools,and Applications(with F.Karray,2004),Prof,de Silva is a Fellow of:The Institute of Electrical and Electronics Engineers(IEEE),American Society of Mechanical Engineers(ASME),the Canadian Academy of Engineering,and the Royal Society of Canada.
