两级传感器信息融合的移动机器人避障研究

针对移动机器人的避障问题,以AS-R移动机器人为研究平台,提出了一种将神经网络和模糊神经网络相结合的两级融合方法。采用BP神经网络对多超声波传感器信息进行融合,以减少传感器信息的不确定,提高对障碍物识别的准确率;采用模糊神经网络实现移动机器人的避障决策控制,使之更适合系统的避障要求。该方法使移动机器人在避障中具有较好的灵活性和鲁棒性。机器人避障实验验证了所提方法的有效性。

Obstacle avoidance study for mobile robot based on two-level sensor information fusion

To the problem of obstacle avoidance for mobile robot,with the platform of AS-R mobile robot,a novel approach of multi-sensor information fusion based on neural networks and fuzzy neural networks is presented.A BP neural network is used to fuse information from multi ultrasonic sensors so that the uncertainty of the sensors' information can be decreased and high accuracy of obstacle identification can be obtained.In order to realize decision control,a fuzzy neural network is used for obstacle avoidence.With the two-level information fusion method high performance of robust and flexible for obstacle avoidance can be achieved.Experiment results verified the effectiveness of the proposed approach.