Back close

Comparing Robotic Control using a Spiking Model of Cerebellar Network and a Gain Adapting Forward Inverse Model

Publication Type : Conference Proceedings

Thematic Areas : Medical Sciences, Biotech

Publisher : International Conference on Advances in Computing, Communications and Informatics

Source : Proceedings of the Sixth International Conference on Advances in Computing, Communications and Informatics (ICACCI-2017), Manipal University, Karnataka, India, Sept 13-16, 2017.

Url : https://ieeexplore.ieee.org/document/8125900/(link is external)

Keywords : 6 DOF robotic arm, Adaptation models, adaptive learning process, anthropomorphic manipulators, Artificial Neural Network, bioinspired models, body movements, Brain modeling, cerebellar network, cerebellum, computational modeling, fast movement based tasks, forward inverse model, forward-inverse model, internal models, Inverse kinematics, kinematic motor control, learning (artificial intelligence), learning rules, low cost robotic arm, manipulator kinematics, mathematical model, Mobile robots, neural network accounts, neurocontrollers, optimal control, optimal control model, rat cerebellum, real-world information, Robot sensing systems, Robotic Arm, robotic control, spatial information, spiking model, spiking neural network, temporal information

Campus : Amritapuri

School : School of Biotechnology

Center : Amrita Mind Brain Center, Biotechnology, Computational Neuroscience and Neurophysiology

Department : Computational Neuroscience Laboratory, biotechnology

Year : 2017

Abstract : Internal models inspired from the functioning of cerebellum are being increasingly used to predict and control movements of anthropomorphic manipulators. A major function of cerebellum is to fine tune the body movements with precision and are comparative to capabilities of artificial neural network. Several studies have focused on encoding the real-world information to neuronal responses but temporal information was not given due importance. Spiking neural network accounts to conversion of temporal information into the adaptive learning process. In this study, cerebellum like network was reconstructed which encodes spatial information to kinematic parameters, self-optimized by learning patterns as seen in rat cerebellum. Learning rules were incorporated into our model. Performance of the model was compared to an optimal control model and have evaluated the role of bioinspired models in representing inverse kinematics through applications to a low cost robotic arm developed at the lab. Artificial neural network of Kawato was used to compare with our existing model because of their similarity to biological circuit as seen in a real brain. Kawato's paired forward inverse model has used to train for fast movement based tasks which resembles human based motor tasks. Result suggest kinematics of a 6 DOF robotic arm was internally represented and this may have potential application in neuroprosthesis.

Cite this Research Publication : Asha Vijayan, Vivek Gopan, Dr. Bipin G. Nair, and Dr. Shyam Diwakar, “Comparing robotic control using a spiking model of cerebellar network and a gain adapting forward-inverse model”, in Proceedings of the Sixth International Conference on Advances in Computing, Communications and Informatics (ICACCI-2017), Manipal University, Karnataka, India, Sept 13-16, 2017.

Admissions Apply Now