1. 毕业设计（论文）的内容和要求

内容：机器人避障有着广泛的应用，本课题使用深度双Q强化强化学习开展研究，理解其数学原理，设计仿真程序。

要求：程序结构清楚，美观

2. 参考文献

[1] Gao Xin,Jia Qingxuan,Sun Hanxu,Chen Gang . Real-time dynamic system to path tracking and collision avoidance for redundant robotic arms[J].《The Journal of China Universities of Posts and Telecommunications》.2016 [2] Shih-An Li . Dynamic Obstacles Avoidance Based on Potential Field Implement on Mobile Robot[A]. 中国自动化学会控制理论专业委员会、The Society of Instrument and Control Engineers (SICE).Proceedings of the Society of Instrument and Control Engineers Annual Conference 2015[C]. [3] Y.C.Lei . Research on Obstacle Avoidance of Fire-Fighting Robot Based On Fuzzy Control[A]. Science and Engineering Research Center.Proceedings of 2015 International Conference on Computer Information Systems and Industrial Applications(CISIA2015)[C].Science and Engineering Research Center.2015 [4] Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Playing Atari with Deep Reinforcement Learning. [5] Sivaranjini Srikanthakumar. Optimisation-based Verification Process of Obstacle Avoidance Systems for Unicycle-like Mobile Robots[J]. International Journal of Automation Computing.2011 [6] A.Filipescu. Fuzzy Control and Bubble Rebound Obstacle Avoidance of a Mobile Platform Used as Robotic Assistant[A]. 中国自动化学会控制理论专业委员会(Technical Committee on Control Theory,Chinese Association of Automation).第二十九届中国控制会议论文集[C].中国自动化学会控制理论专业委员会(Technical Committee on Control Theory,Chinese Association of Automation). 2010 [7] 薛晗,马宏绪. Swarm intelligence based dynamic obstacle avoidance for mobile robots under unknown environment using WSN[J] .《Journal of Central South University of Technology》.2008 [8] Formation Control of Mobile Robots with Active Obstacle Avoidance[J]. 《自动化学报》.2007 [9] Kai Arulkumaran,Nat Dilokthanakul,Murray Shanahan,Classifying Options for Deep Reinforcement Learning,《Statistics》 2016 [10] X.Q.Guan. A Redundant DOFs Manipulator Motion Obstacle Avoidance Algorithm[A]. Advanced Science and Industry Research Center.Proceedings of 2015 International Conference on Automation,Mechanical and Electrical Engineering(AMEE 2015)[C].Advanced Science and Industry Research Center.2015 [11]Y.C.Lei. Research on Obstacle Avoidance of Fire-Fighting Robot Based On Fuzzy Control[A]. Science and Engineering Research Center.Proceedings of 2015 International Conference on Computer Information Systems and Industrial Applications(CISIA2015)[C].Science and Engineering Research Center.2015 [12] S Mahadevan，J Connell, Automatic programming of behavior-based robots using reinforcement learning, 《Artificial Intelligence》, 1992, 55(2#8211;3):311-365 [13] P Piggott，A Sattar ,Reinforcement learning of iterative behaviour with multiple sensors, 《Applied Intelligence》, 1994, 4(4):351-365 [14] 乔俊飞，侯占军，阮晓钢,基于神经网络的强化学习在避障中的应用, 中国过程控制会议, 2008 [15] 陈春林 陈宗海 卓睿 周光明，基于分层式强化学习的移动机器人导航控制，南京航空航天大学学报，2006, 38(1) ，TP24 TP18 [16] 赵冬斌 邵坤 朱圆恒 李栋 陈亚冉 王海涛 刘德荣 周彤 王成红，深度强化学习综述：兼论计算机围棋的发展，《控制理论与应用》2016年 第6期 [17] 唐鹏，李小坚，强化学习在移动机器人避障上的应用，《科学家》2016年第5期 [18] 陈兴国 俞扬 南京邮电大学计算机学院/软件学院，强化学习及其在电脑围棋中的应用，《自动化学报》2016年 第5期 [19] 史忠植，突破通过机器进行学习的极限，《科学通报》2016年 第33期 [20]IEEE Transactions on Neural Networks and Learning Systems special section on deep reinforcement learning and adaptive dynamic programming,《IEEE Transactions on Neural Networks and Learning Systems》 2017

3. 毕业设计（论文）进程安排

20170116-20170303 撰写开题报告 20170304-20170415 程序原型设计 20170416-20170430 各模块完善 20170501-20170515 系统测试 20170516-20170530 撰写论文 20170601 交论文初稿 20170605-20170612 修改论文 20170615 答辩