论文部分内容阅读
针对未知环境下移动机器人路径规划问题,以操作条件反射学习机制为基础,根据模糊推理系统和学习自动机的原理,提出一种应用于移动机器人导航的混合学习策略.运用仿生的自组织学习方法,通过不断与外界未知环境交互从而使机器人具有自学习和自适应的功能.仿真结果表明,该方法能使机器人学会避障和目标导航任务,与传统的人工势场法相比,能有效地克服局部极小和振荡情况.
Aiming at the problem of mobile robot path planning in unknown environment and based on the operating condition reflection learning mechanism, a hybrid learning strategy applied in mobile robot navigation is proposed according to the principle of fuzzy inference system and learning automaton. By using the bionic self-organizing learning method , Which can make the robot self-learning and self-adaptive by constantly interacting with the unknown environment.The simulation results show that this method can make the robot learn obstacle avoidance and target navigation tasks, compared with the traditional artificial potential field method can effectively overcome Local minima and oscillation.