论文部分内容阅读
为了提高自主移动机器人的动态避障能力,提出了一种基于视觉信息的拟人动态避障方法.以视觉信息为决策依据,利用神经网络对障碍物的屏幕坐标和实际相对坐标进行非线性映射,在避障过程中只考虑障碍物相对于机器人的运动及可能的碰撞方式,无需考虑机器人和障碍物的运动速度和运动方向.仿真试验证明这种方法是可行而有效的.
In order to improve the dynamic obstacle avoidance capability of autonomous mobile robot, a dynamic person avoidance method based on visual information is proposed.With visual information as the decision-making basis, the screen coordinates of the obstacle and the actual relative coordinates are nonlinearly mapped by neural network, In obstacle avoidance process, only the movement of obstacle relative to the robot and possible collision modes are considered, without considering the moving speed and moving direction of the robot and obstacles. Simulation results show that this method is feasible and effective.