A Path Planning Algorithm for Mobile Robots Based on DGABI-RRT

As we know, mobile robots have been widely used in daily life, and path planning has also become a hot topic for many scholars. Due to excellent performance of the fast search speed and independent of the environment model, Rapidly-exploring Random Tree (RRT) algorithm is used broadly in mobile robots' path planning. However, it also has some problems, the randomness is very important among all the problems, because it makes the planned path deviate from the optimal path. To solve the problems above, this paper presents a double sampling points and gravitational adaptive step size bidirectional RRT (DGABI-RRT) algorithm for mobile robots. In this algorithm, better sampling point strategy and gravity adaptive step size strategy are used to make the mobile robot's motion have goal bias and avoid obstacles. Besides, to get a better path, path optimization strategies are used to shorten and smooth paths so that the mobile robot can move smoothly in the workspace. To verify the performance of the proposed algorithm, simulation compared with other three algorithms is carried out in this paper. The numerical comparison of simulation results proves that the DGABI-RRT algorithm is better than the other three improved algorithms in terms of path planning time, number of expansion nodes, number of path points and path length. The simulation results in two working environments of mobile robots show that the improved algorithm can better solve the path planning and obstacle avoidance problem of the mobile robots.