Researches On Motion Planning Of Mobile Manipulator

The mobile manipulator is a complex nonlinear system consisting of a mobile base and an operable manipulator.Multi-degree of freedom manipulator and mobile platform make mobile manipulator both mobile and flexible,making it a wide range of applications in the areas of home services,intelligent warehousing and industrial production.The research on the theory and application of mobile manipulator is of great importance to improve the quality of life and promote the development of productive forces.It has become a hotspot in the field of robotics recent years.In this paper,some problems in the kinematics of mobile manipulator are studied.The main contents are as follows: the path planning problems of the mobile base,the inverse kinematics problem of the six degree of freedom manipulator and optimization of obstacle avoidance trajectory planning for manipulator.(1)The path planning problem of the mobile base of manipulator can be classified as the path planning of the robot,which is the basis of many robot operations.In this paper,an improved artificial potential field method based on tangent vector and particle swarm optimization,PSO-TVAPF,is proposed to avoid local minima problem and improve path planning efficiency for classical artificial potential field(APF).First,PSO-TVAPF calculates tangent vector of the obstacles between current position and the goal,and selects the optimal tangent vector by a certain screening strategy.Then,tangent vector is combined with the attraction and repulsion of APF according to a certain proportion to format the driving force of robot path planning.Tangent vector has a significant role in improving the quality of path planning and avoiding the local minimum problem.Finally,in order to further improve the robustness of the algorithm and the quality of the path,particle swarm optimization algorithm was used to optimize the tangent vector based artificial potential field(TVAPF).Simulation and experiment results show that the artificial potential field method based on tangent vector and particle swarm optimization can effectively avoid the local minimum problems and greatly shorten the final path length.(2)This paper presents an intelligent algorithm with extreme learning machine and sequential mutated genetic algorithm,ELM-SGA,for inverse kinematics solution of a 6-DOF robotic manipulator.The proposed algorithm mainly focuses on minimizing computational time while keep a high accuracy of the end effector.Firstly,the preliminary inverse solution is calculated by extreme learning machine,and then it optimized by improved genetic algorithm based on sequential mutation.Extreme learning machine randomly initialize input layer weights and hidden nodes bias which can greatly improve its training speed.Different from classical genetic algorithm,sequential mutated genetic algorithm changes gene code in order from high to low,which reduces randomness of mutation operation and enhances local search capability.As a result,the convergence speed at the end of evolution improved.Simulation and experiment results indicate that the proposed algorithm can greatly improve time efficiency with high end effector accuracy.(3)Aiming at the problem of obstacle avoidance trajectory planning of manipulator,an improved artificial potential field method is proposed.Then,inverse kinematic algorithm ELM-SGA is used to calculate the inverse kinematic solution on the trajectory equidistantly.The pose of manipulator is updating and collision detection is proceeding constantly until a safe trajectory has been found.Finally,particle swarm optimization algorithm is used to optimize the trajectory by both trajectory length and energy consumption.The simulation results show that the improved artificial field method can effectively shorten length of trajectory and reduce the energy consumption of the manipulator.