Padoan Junior Antonio Carlos, De A Barreto Guilherme, Araújo Aluizio F R
Departamento de Engenharia Elétrica, Universidade de São Paulo, Av. Trabalhador Sancarlense, 400, São Carlos, São Paulo, CEP 13566-590, Brasil.
Int J Neural Syst. 2003 Apr;13(2):119-27. doi: 10.1142/S0129065703001510.
In this paper we proposed an unsupervised neural architecture, called Temporal Parametrized Self Organizing Map (TEPSOM), capable of learning and reproducing complex robot trajectories and interpolating new states between the learned ones. The TEPSOM combines the Self-Organizing NARX (SONARX) network, responsible for coding the temporal associations of the robotic trajectory, with the Parametrized Self-Organizing (PSOM) network, responsible for an efficient interpolation mechanism acting on the SONARX neurons. The TEPSOM network is used to model the inverse kinematics of the PUMA 560 robot during the execution of trajectories with repeated states. Simulation results show that the TEPSOM is more accurate than the SONARX in the reproduction of the learned trajectories.
在本文中，我们提出了一种无监督神经架构，称为时间参数化自组织映射（TEPSOM），它能够学习和再现复杂的机器人轨迹，并在所学轨迹之间插入新状态。TEPSOM将负责编码机器人轨迹时间关联的自组织NARX（SONARX）网络与负责对SONARX神经元进行有效插值机制的参数化自组织（PSOM）网络相结合。TEPSOM网络用于在执行具有重复状态的轨迹期间对PUMA 560机器人的逆运动学进行建模。仿真结果表明，在再现所学轨迹方面，TEPSOM比SONARX更准确。
