Design and imitation learning study on Bumpybot robot

Access full-text files

Date

2023-05-04

Authors

Jaiswal, Mehar Shaileshkumar

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

We are in an era where robotics research is rapidly growing. The robotics industry is booming and more and more people are open to living with robots in and around their spaces of work, and leisure. People are expecting robots to provide more than one service. For this reason, the Bumpybot robot is designed for domestic or indoor use around people of many ages while. It becomes our duty then to make sure the designs and deployments of these robots are safe and reliable. During the course of this thesis, I studied the design of outer shells for Bumpybot using multiple iterations and various prototyping methods. As a second part of my thesis, I used an imitation learning algorithm to train and then deploy the simulated robot to track trajectories. The combined study on design and imitation learning was done to enhance safety, reliability, and navigation in human environments.

Description

LCSH Subject Headings

Citation