Abstract: This paper has resolved obstacle avoidance problem in game using unsupervised Neural Networks.This unsupervised mechanism is made by Genetic Algorithm，which has improved the weights of the Neural Networks through optimizing the fitness，finally，the Neural Networks can get the outputs with best fitness.Sensors are simulated by 5 line segments that radiate outward from the agent body，the agent can sense the game environment by the 5 sensors.After iterating for 768 times，average fitness and best fitness of the population have been improved quickly，the ratio of avoiding successfully has been improved from 12.5% to 85%.

Key words: obstacle avoidance, Neural Networks, Genetic Algorithm, sensor

摘要： 使用无监督神经网络解决了游戏中的障碍物绕行问题（obstacle avoidance）。使用遗传算法实现了无监督机制，该方法通过最优化适应度来改进神经网络的权值，使得神经网络得到最佳的输出值；利用以智能体（Agent）中心为出发点的5条射线模拟传感器（Sensor），通过检测5条射线与障碍物边界的相交情况来感知环境。经过768代的进化，遗传算法种群最优适应度和平均适应度都有了明显提高，同时绕行成功率从12.5%上升到85%。

关键词: 障碍物绕行, 神经网络, 遗传算法, 传感器