ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Inverse Kinematics Analysis of Cassie Robot using Radial Basis Function Networks

Mitra, M and Raj, S and Kolathaya, S (2021) Inverse Kinematics Analysis of Cassie Robot using Radial Basis Function Networks. In: 2021 International Symposium of Asian Control Association on Intelligent Robotics and Industrial Automation, IRIA 2021, 20-22 Sep 2021, Goa, pp. 351-356.

[img] PDF
IRIA_2021.pdf - Published Version
Restricted to Registered users only

Download (825kB) | Request a copy
Official URL: https://doi.org/10.1109/IRIA53009.2021.9588698

Abstract

Inverse Kinematics of bipedal humanoid robots remains a challenging problem in the domain of robotics and computation, due to high order non-linearity and computation involved in Inverse Kinematics solutions. Also, there are many constraints involved with the various joint parameters which makes their analysis even more complex. Through this paper, we attempt to solve the Inverse Kinematics problem of a bipedal humanoid robot, Cassie, using Radial Basis Function (RBF) Networks. Our method can also be applied to other higher degrees of freedom serial manipulators. Our simulation analyses the results based on size of datasets, data distribution and network parameters. We have considered datasets of size �300k and �1 million, single and multiple hidden layers, equal and random data distribution, different number of neurons in layers and different training functions. We achieve our target of limiting the Mean Squared Error (MSE) calculated using the trained model below 0.1° for each joint angle, which is under acceptable limits for practical implementation. The configurations obtained from the RBF network are simulated and compared with the original input configuration. This is compared visually in MATLAB and the resulting pose of end-effector are similar for both the cases, complementing the performance that we get for the networks. © 2021 IEEE.

Item Type: Conference Paper
Publication: 2021 International Symposium of Asian Control Association on Intelligent Robotics and Industrial Automation, IRIA 2021
Publisher: Institute of Electrical and Electronics Engineers Inc.
Additional Information: The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords: Anthropomorphic robots; Degrees of freedom (mechanics); Functions; Heat conduction; Inverse kinematics; Inverse problems; Manipulators; MATLAB; Mean square error, Bipedal robot; Cassie; Data distribution; Forward kinematics; High-order; Higher-order; Humanoid robot; Inverse kinematic analysis; Inverse kinematic solutions; Joints's parameters, Radial basis function networks
Department/Centre: Division of Electrical Sciences > Computer Science & Automation
Division of Interdisciplinary Sciences > Computational and Data Sciences
Division of Mechanical Sciences > Centre for Product Design & Manufacturing
Date Deposited: 03 Dec 2021 08:48
Last Modified: 03 Dec 2021 08:48
URI: http://eprints.iisc.ac.in/id/eprint/70627

Actions (login required)

View Item View Item