An Intelligent Human-like Motion Planner for Anthropomorphic Arms Based on Diversified Arm Motion Models

In this paper, the human-like motion issue for anthropomorphic arms is further discussed. An Intelligent Human-like Motion Planner (IHMP) consisting of Movement Primitive (MP), Bayesian Network (BN) and Coupling Neural (CPNN) proposed to help robot generate arm movements. Firstly, model decoupled in aspects structure process, respectively. former aspect, into different simple models through Primitive. A Hierarchical Planning Strategy (HPS) decouple a complete process sub-processes. Based on diversified models, used choose suitable among these models. Then, according features obtain inverse kinematic (IK) solutions. This network can integrate single reflect by changing structure. Being major contribution specific focus improvement accuracy independent consciousness robots. Finally, availability IHMP verified experiments humanoid Pepper.