安全屏障机制下基于SAC算法的机器人导航系统

Robot navigation system based on SAC with security barrier mechanism

为了提高移动机器人自主导航系统的智能化水平和安全性,设计了安全屏障机制下基于SAC(Soft Actor-Critic)算法的自主导航系统,并构建了依赖于机器人与最近障碍物距离、目标点距离以及偏航角的回报函数.在Gazebo仿真平台中,搭建载有激光雷达的移动机器人以及周围环境.实验结果表明,安全屏障机制在一定程度上降低了机器人撞击障碍物的概率,提高了导航的成功率,并使得基于SAC算法的移动机器人自主导航系统具有更高的泛化能力.在更改起终点甚至将静态环境改为动态时,系统仍具有自主导航的能力.

An autonomous navigation system was proposed based on Soft Actor-Critic under the security barrier mechanism to improve the intelligence and security of mobile robot autonomous navigation system.The return function was designed based on distance between the robot and the nearest obstacle,the distance from the target point,and the yaw angle.On the Gazebo simulation platform,a mobile robot with lidar and its surrounding environment were built.Experiments showed that the security barrier mechanism reduced the probability of collision with obstacles to a certain extent,improved the success rate of navigation,and made the SAC-based mobile robot autonomous navigation system have high generalization ability.The system still had the ability of autonomous navigation when changing the origin and destination or even changing the environment from static to dynamic.