Path Planning Of Mobile Robots Based On ROS

In the wake of developments in science and technology,robots have been applied to the fields of industrial production,life services,space exploration,etc.As a key technology to achieve autonomous movement,path planning has become the focus of research in the field of robotics.The improvement of navigation efficiency and obstacle avoidance performance of robots in complex environments has become a research hotspot.It is of great theoretical significance and application value to study path planning in indoor environments.The robot experimental platform is built.The robot operating system is selected as the software platform.The Turtlebot2 is used as the hardware platform and the Kinect camera is used as environmental information acquisition device.A two-dimensional map is constructed on the experimental platform using the Gmapping algorithm.Aiming at the defects of low sampling efficiency and poor path quality of RRT global path planning algorithm,the target bias strategy and the odor diffusion method are introduced in the original algorithm framework to optimize the node expansion method,so that the random tree grows to the target point.A path smoothing method on cubic B-spline curve is proposed to optimize the path.The experimental results demonstrate that the path generated by the proposed algorithm is around 22.1% shorter than that of basic RRT algorithm and the searching efficiency is higher as well.The improved method has the best performance in complex environments.An improved local path planning algorithm is proposed to meet the obstacle avoidance requirements of mobile robots in complex scenarios.The proposed method fuses dynamic window approach and improved RRT algorithm.An objective function following the global optimal path is designed.DWA can output the local path based on the global path planned by the improved RRT algorithm and the real-time information of the environment,which can avoid dynamic obstacles in the environment.The experimental results demonstrate that the average speed is around 10.7% faster than that of A*-DWA algorithm and has higher navigation efficiency in indoor environments.It has high reliability and practicability.