Development of an Improved Genetic Algorithm for Resolving Inverse Kinematics of Virtual Human’s Upper Limb Kinematics Chain

Inverse kinematics is the key technique in virtual human motion control and it is difficult to obtain the solutions by using geometric, algebraic, or iterative algorithms. In this chapter, an Improved Genetic Algorithm (IGA) is proposed to resolve the inverse kinematics problem in upper limb kinematics chain (ULKC). First, the joint-units of ULKC and its mathematical models are constructed by using D–H method; then population diversity and population initialization are accomplished by simulating human population, and the adaptive operators for mutation are designed. The simulation results show that compared with the Standard Genetic Algorithm (SGA), the IGA can provide higher precise solutions in searching process and avoid “premature” stop or inefficient searching in later stage with high probability.

[1]  Carlos Kavka,et al.  Robot arm fuzzy control by a neuro-genetic algorithm , 1998 .

[2]  Lin Jing.  Adaptive genetic annealing algorithm of solving 0/1 knapsack , 2013 .

[3]  Yaduvir Singh,et al.  Simulation of Robotic Arm using Genetic Algorithm and AHP , 2007 .

[4]  William W. Melek,et al.  A Genetic Algorithm Approach to solve for Multiple Solutions of Inverse Kinematics using Adaptive Niching and Clustering , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[5]  Lifeng Sun,et al.  Breakout prediction for continuous casting using genetic algorithm-based back propagation neural network model , 2012, Int. J. Model. Identif. Control..

[6]  Jin Qiurui.  Optimum Base Station Frequency Allocation Based on Hierarchical Genetic Algorithms , 2013 .

[7]  Santosh Kumar Nanda,et al.  A Novel Application of Artificial Neural Network for the Solution of Inverse Kinematics Controls of Robotic Manipulators , 2012 .

[8]  Hu Xiaoguang.  Method of relay routing based on genetic adaptive ant colony system algorithm , 2013 .

[9]  M. K. Mayer,et al.  A network parallel genetic algorithm for the one machine sequencing problem , 1999 .

[10]  J. Sziveri,et al.  Parallel processing neural networks and genetic algorithms , 1998 .

[11]  Kenji Onaga,et al.  A Parallel and Distributed Genetic Algorithm on Loosely-Coupled Multiprocessor Systems(Special Section on Concurrent Systems Technology) , 1998 .

[12]  Bassam Daya,et al.  Applying Neural Network Architecture for Inverse Kinematics Problem in Robotics , 2010, J. Softw. Eng. Appl..

[13]  Kalyanmoy Deb,et al.  Messy Genetic Algorithms: Motivation, Analysis, and First Results , 1989, Complex Syst..

[14]  Zhao Jin-chang.  Neural networks based on the genetic algorithm and its application in mechanical engineering , 2008 .

[15]  Lu Liu,et al.  A Geometrical Method for Inverse Kinematics of a Kind of Humanoid Manipulator , 2012 .

[16]  Wang Zhaoqi,et al.  A Survey of Physics-Based Human Motion Simulation , 2010 .

[17]  Chai Chun-lei.  An Overview of 3D Human Motion Editing and Synthesis , 2009 .

[18]  Xiaobang Liu,et al.  A brief fuzzy controller for an intelligent tracking system , 2013, Int. J. Model. Identif. Control..

[19]  Amar Goléa,et al.  Neural network-based adaptive sliding mode control for uncertain non-linear MIMO systems , 2012, Int. J. Model. Identif. Control..