Research On Hybrid Path Planning In Indoor Environment Of Autonomous Navigation Robot

Path planning is a key technology for robots to achieve autonomous navigation.Due to the complex and ever-changing application scenarios of indoor robots,a single path planning method cannot make robots adapt well to changing environments.In this paper,a hybrid path planning combined with global path planning and local path planning is proposed for indoor environment with known global environment and emergent obstacles.The main research contents are as follows:Firstly,the high-precision map required for path planning is constructed.To solve the problem of particle degradation and diversity reduction in the RBPF m apping algorithm,an RBPF algorithm based on annealing optimization and genetic resampling is proposed.On the one hand,the observation information is introduced into the proposed distribution;on the other hand,the adaptive mutation crossover operation is introduced to the particles during the resampling process.Simulation experiments verify that the improved RBPF algorithm can build a high-precision grid map with fewer particles.Secondly,the particle swarm optimization algorithm is used to study the global path planning.In view of the problems that the particle swarm optimization algorithm is prone to premature convergence and local traps,the simulated annealing algorithm with strong global search ability is introduced.Experiments show that the global search capability can jump out of the local optimal solution,resulting in better path quality.Aiming at the abrupt obstacles encountered during the robot's driving,the dynamic window method is adopted for local planning.In order to improve the disadvantage that the robot will deviate from the target point when it is close to the target point,the target distance is introduced into the evaluation function to improve the speed control ability of the robot when it is close to the target point.Meanwhile,the laser sensor is used to sense the environmental information,predict the movement trajectory of the detected obstacle,and take corresponding obstacle avoidance measures according to different collision types.The simulation results show that the robot can avoid the dynamic and static obstacles in the course of driving.Finally,for the complex and changing indoor environment,the simulated annealing particle swarm algorithm is combined with the improved dynamic window method.First,the simulated annealing particle swarm is used to plan the global optimal path.The robot adopts the dynamic window method for emerging obstacles along its driving process Carry out obstacle avoidance,return to the global optimal path after obstacle avoidance,and continue driving.The Turtlebot2 robot is used to build an experimental platform based on ROS.The algorithm of this paper is introduced and the experiment is carried out.Through simulation experiments and actual verification,it is proved that the robot can effectively avoid the emerging dynamic and static obstacles and complete the path planning when driving along the optimal path.