Research On Path Planning Of Humanoid Robot NAO

Robot path study has become a national high-tech field of strategic research objective.In recent years,the study of humanoid path planning has become a hotspot in the field of automatic control and artificial intelligence.Its development has a great influence on national defense,industry,economy,and science and technology.The research of this paper includes the following aspects:First,we describe the status and trends of domestic and foreign humanoid robot path planning and development,point out the important meaning for path planning study of humanoid robot and NAO robot.Secondly,according to the characteristics of the NAO robot monocular vision,this paper presents an artificial landmark localization method.Based on NAO robot,the principle of camera positioning is analyzed,and the important research on robot target recognition and localization are completed.Third,this paper introduces the artificial potential field algorithm application in obstacle avoidance,and points out the limitations of the traditional artificial potential field algorithm in practical application.Using the geometric method so as to avoid the artificial potential field algorithm is the local minimum problem,ensuring the machine can successfully reach the target point in the path planning.Through the comparison of simulation results before and after,we can see that the artificial potential field algorithm provides a good method for the research of robot path planning.Last,this paper introduces the implementation of particle swarm algorithm in global path planning for a humanoid robot,and puts forward an improved particle swarm optimization algorithm,proving that the proposed method can avoid particle swarm into local optimal value.At the same time,combined with the improved artificial potential field algorithm and particle swarm optimization algorithm,hybrid research on path planning of NAO robot was completed.Experimental results show that the scheme shortens the length of path planning,planning a real-time and fast and strong optimum path.