Development of a neuromorphic control system for a lightweight humanoid robot

International Conference on Information Technology and Digital Applications

计算机科学

Folgheraiter, Michele^1 ; Keldibek, Amina^1 ; Aubakir, Bauyrzhan^1 ; Salakchinov, Shyngys^1 ; Gini, Giuseppina^2 ; Franchi, Alessio Mauro^2 ; Bana, Matteo^2

School of Science and Technology, Robotics and Mechatronics Department, Nazarbayev University, Kazakhstan^1

DEIB, Politecnico di Milano, piazza L. da Vinci 32, Milano, Italy^2

关键词: Complex-periodic;    Control architecture;    Dynamic neurons;    Humanoid robot;    Linear combinations;    Normalized signals;    Recurrent neural network (RNN);    Target trajectory;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/185/1/012021/pdf
DOI  :  10.1088/1757-899X/185/1/012021

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

A neuromorphic control system for a lightweight middle size humanoid biped robot built using 3D printing techniques is proposed. The control architecture consists of different modules capable to learn and autonomously reproduce complex periodic trajectories. Each module is represented by a chaotic Recurrent Neural Network (RNN) with a core of dynamic neurons randomly and sparsely connected with fixed synapses. A set of read-out units with adaptable synapses realize a linear combination of the neurons output in order to reproduce the target signals. Different experiments were conducted to find out the optimal initialization for the RNN's parameters. From simulation results, using normalized signals obtained from the robot model, it was proven that all the instances of the control module can learn and reproduce the target trajectories with an average RMS error of 1.63 and variance 0.74.