A comparison of human trajectory planning models for implementation on humanoid robot

The human locomotion is a complex motor task that coordinates the activity of many different muscles and joints across each step. In terms of general behavior, this complexity can be modeled using simple rules due to the high redundancy presented by the motor system. This work presents a detailed analysis on recent neuroscientific models for the trajectory formation during locomotion task. With the aim to implement one of the presented approaches in a humanoid platform, these models have been applied on human data and compared. The trajectory error has been computed with respect to the resulted fitting. The advantages and disadvantages of each model have been highlighted and discussed.