The soccer robot system is a dynamic environment with multiple obstacles . it is a problem of high complexity to perform path planning in such environments . the traditional methods are not efficient in such complex environments . in this paper , a self - learning method of robot navigation is proposed based on the reinforcement learning method and artificial potential field method 本论文将增强式学习算法和人工势场法相结合，提出状态评价函数和势场的对应关系，以及控制策略和势场力方向的对应关系，通过机器人的自适应学习，来形成优化的人工势场，使机器人能够以最短路径绕过障碍，到达目标。
The significant characteristics of the new afm include : ( i ) it has a horizontally designed probe unit , and the direction of cantilever ' s weight was perpendicular to the atomic force , thus the effect of cantilever ' s weight on the imaging quality can be effectively avoided ; ( ii ) it owns a particular path of optical beam deflection method for the measurement of cantilever ' s displacement 卧式afm探头系统的显著特色是，微悬臂重力与原子力方向相互垂直，有效地避免了重力对微悬臂及成像质量的影响，从而在设计方法上保证了afm的性能。本文在方法上的另一创新是，发展了独特的微悬臂偏转量的光束偏转法检测系统。
