Exploration of a data-driven walking controller for a large-scale bipedal robot with structural deformation

Biped robots hold a great potential in advancing multiple industries, from healthcare to disaster relief to entertainment and personal assistance. These robots have the ability to navigate complex environments, interact more efficiently with people, and perform tasks that require balance and dexterity. However, accomplishing those tasks depends on heavily on being able to represent the kinematics of the robot, which can be heavily altered due to structural deformation and motors backlash. This thesis develops a data- driven approach to address the kinematics issues for a large-scale biped robot using Hybird-Leg as well as develop a simple controller for its locomotion. In order to evaluate the proposed approach, two sets of tests are proposed. First, a test is performed to compare between the performance produced when only using the existing kinematics model versus when using the kine- matics model along with an Artificial Neural Network (ANN) model, which showed that the developed approach improved the tracking. The next set of tests develops and validates a simple walking controller using simulation. Then, the generated walking trajectory is inputted into the ANN model in order to be implemented on the hardware. The outputted trajectory by the ANN model was not feasible or safe for hardware implementation, therefore hardware implementation of the walking trajectory was not completed. The contribution of this work is highlighted in providing a skeleton for developing a data-driven approach in order to limit the effects of structural deformation in the development of successfully walking bipeds. This work provides a detailed approach to a possible method in order to limit the effects of inaccurate kinematic modeling.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Mechanical Engineering

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2023

Author dc:creator

• Darwish, Omar

Contributors dc:contributor

• Kim, Joohyung

• Robotics
• Data-driven Controller
• Bipedal Robots

Statement dc:rights

• Copyright 2023 Omar Darwish

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/120463

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F120463