Abstract：The omnidirectional mobile robot with 3-degree-of-freedom in the plane has high flexibility and can be also applied in crowded and narrow environment. The BP (backpropagation) neural network method is used to solve the problems of the vibration phenomena and trajectory error of the MY2 wheel developed in the laboratory during movement. According to the structure and movement characteristics of the robot, the BP neural network model is established and the parameters of the BP neural network are optimized. Trajectory simulation experiments based on the BP neural network model are conducted. The impact of initial values, different speeds and different trajectories on model are analyzed. The consequence shows that the method based on the suitable BP neural network can keep the trajectory error within the range of 3 mm and the deflection angle error less than 3°, so the BP neural network can decrease the robot vibration and improve the trajectory accuracy. The universal applicability of the BP neural network model is verified by inputting different motion trajectories, and the correctness of simulation results are validated by experiments in the end.
 赵冬斌,易建强,邓旭玥.全方位移动机器人结构和运动分析[J].机器人,2003,25(5):394-398. Zhao D B, Yi J Q, Deng X Y. Structure and kinematic analysisof omni-directional mobile robots[J]. Robot, 2003, 25(5):394-398.  赵冬斌,易建强.全方位移动机器人导论[M].北京:科学出版社,2010:3-11. Zhao D B, Yi J Q. Introduction to omni-directional mobile robot[M]. Beijing:Science Press, 2010:3-11.  Ren C, Ma S G. Trajectory tracking control of an omnidirectional mobile robot with friction compensation[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE, 2016:5361-5366.  Byun K S, Song J B. Design and construction of continuous alternate wheels for an omnidirectional mobile robot[J]. Journal of Field Robotics, 2010, 20(9):569-579.  Bae J J, Kang N. Design optimization of a Mecanum wheel to reduce vertical vibrations by the consideration of equivalent stiffness[J]. Shock and Vibration, 2016. DOI:10.1155/2016/5892784.  Fernández C A P, Cerqueira J F, Lima A M N. Control of wheeled mobile robots singularly perturbed by using the slipping and skidding variations:Curvilinear coordinates approach (Part I)[J]. IFAC Papersonline, 2015, 48(19):94-99.  Conceicao A. Modeling of a three wheeled omnidirectional robot including friction models[J]. IFAC Papersonline, 2012, 45(22):7-12.  Ren C, Ma S G. Analysis and control of an omnidirectional mobile robot[C]//44th IEEE International Symposium on Robotics. Piscataway, USA:IEEE, 2013:1-6.  叶长龙,马书根,回丽.一种全方位移动机器人[J].中国科学:信息科学,2011,41(2):181-189.Ye C L, Ma S G, Hui L. An omnidirectional mobile robot[J]. Science China:Information Sciences, 2011, 41(2):181-189.  Muir P F, Neuman C P. Kinematic modeling of wheeled mobile robots[J]. Journal of Robotic Systems, 1987, 4(2):281-340.  Pin F G, Killough S M. A new family of omnidirectional and holonomic wheeled platforms for mobile robots[J]. IEEE Transactions on Robotics and Automation, 1994, 10(4):480-489.  杨世强,傅卫平,张鹏飞.四轮全方位轮式移动机器人的运动学模型研究[J].机械科学与技术,2009,28(3):412-415.Yang S Q, Fu W P, Zhang P F. A study of the kinematics model of a mobile robot with four omnidirectional wheels[J]. Mechanical Science and Technology, 2009, 28(3):412-415.  叶长龙,李怀勇,马书根,等.具有MY轮的全方位移动机器人运动学研究[J].机器人,2012,34(2):144-151.Ye C L, Li H Y, Ma S G, et al. Kinematics study on an omnidirectional mobile robot with MY wheels[J]. Robot, 2012, 34(2):144-151.  Ye C L, Zhao D, Yu S Y, et al. Stability improvement of mobile robot with mutative driving axial distance omni-directional wheels[C]//IEEE International Conference on Real-time Computing and Robotics. Piscataway, USA:IEEE, 2018:325-330.  刘金琨.机器人控制系统的设计与MATLAB仿真[M].北京:清华大学出版社,2008:1-29.Liu J K. Design and MATLAB simulation of robot control system[M]. Beijing:Tsinghua University Press, 2008:1-29.  王小川.MATLAB神经网络43个案列分析[M].北京:北京航空航天大学出版社,2013:1-30.Wang X C. 43 case analysis of MATLAB neural network[M]. Beijing:Beihang University Press, 2013:1-30.  魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社,2005:36-37.Wei H K. The theory and method of neural network structure design[M]. Beijing:National Defense Industry, 2005:36-37.