MARC details
| 000 -LEADER |
|---|
| fixed length control field |
03130nam a22003377a 4500 |
| 003 - CONTROL NUMBER IDENTIFIER |
|---|
| control field |
OSt |
| 005 - DATE AND TIME OF LATEST TRANSACTION |
|---|
| control field |
20250718165629.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
250718b |||||||| |||| 00| 0 eng d |
| 040 ## - CATALOGING SOURCE |
|---|
| Original cataloging agency |
TUPM |
| Language of cataloging |
English |
| Transcribing agency |
TUPM |
| Modifying agency |
TUPM |
| Description conventions |
rda |
| 050 ## - LIBRARY OF CONGRESS CALL NUMBER |
|---|
| Classification number |
BTH TK 870 |
| Item number |
B86 2025 |
| 100 ## - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Bumagat, Kyle Mhiron P. |
| Relator term |
author |
| 245 ## - TITLE STATEMENT |
|---|
| Title |
Multi-simulated deep reinforcement learning based conversational robot arm/ |
| Statement of responsibility, etc. |
Kyle Mhiron P. Bumagat, Arianne Joy D. Evangelista, John Louis D. Lagramada, Jhon Mark G. Remollo, Nicamae G. Tamundong, and Althea R. Villanueva.-- |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. |
|---|
| Place of publication, distribution, etc. |
Manila: |
| Name of publisher, distributor, etc. |
Technological University of the Philippines, |
| Date of publication, distribution, etc. |
2025. |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
x, 90pages: |
| Dimensions |
29cm. |
| 336 ## - CONTENT TYPE |
|---|
| Source |
rdacontent |
| 337 ## - MEDIA TYPE |
|---|
| Source |
rdamedia |
| 338 ## - CARRIER TYPE |
|---|
| Source |
rdacarrier |
| 500 ## - GENERAL NOTE |
|---|
| General note |
Bachelor's thesis<br/> |
| 502 ## - DISSERTATION NOTE |
|---|
| Dissertation note |
College Of Engineering.--<br/> |
| Degree type |
Bachelor of science in electronics engineering: |
| Name of granting institution |
Technological University of the Philippines, <br/> |
| Year degree granted |
2025. |
| 504 ## - BIBLIOGRAPHY, ETC. NOTE |
|---|
| Bibliography, etc. note |
Includes bibliographic references and index. |
| 520 ## - SUMMARY, ETC. |
|---|
| Summary, etc. |
Adaptive control that dynamically responds to perturbations is a difficult problem<br/>to solve using classical techniques in robot manipulation. This raises a critical issue in<br/>creating a fully collaborative robotic system. In this study, deep reinforcement learning<br/>was used to train a robot arm in reaching a specific 3D point in space using 4096 parallel<br/>environments. The rewards were shaped to minimize action rate and velocity under a<br/>curriculum with domain randomization. This study simulated, gain-tuned, and trained the<br/>agents using the Isaac Lab framework. Within 6.24 minutes, a performant model arrived,<br/>essentially compressing months of training to minutes. Proxima policy optimization (PPO)<br/>was used with a multi-layer perceptron (MLP) neural network backbone. A modular ROS<br/>2 package was also presented for bridging natural language understanding to physical<br/><br/>systems. The package employs both cloud and edge computing of state-of-the-art speech-<br/>to-text, text-to-speech, and large language models. The developed system was evaluated<br/><br/>for its educational impact using a structured learning module. Results showed significant<br/>improvements between the pre-test and post-test, with a t-value of -19.329 and p < .001.<br/>The mean scores for the evaluated factors: Attention, Relevance, Confidence, and<br/>Satisfaction ranged from approximately 3.9 to 4.3, with Cronbach’s alpha values indicating<br/>high reliability. The Structural Equation Model (SEM) indicated a good fit, SRMR = 0.071.<br/>Future enhancements should focus on increasing sample size, adding beginner-friendly<br/>resources, and expanding advanced ROS 2 topics. Further development of the<br/>conversational robot arm with interactive features can also improve student engagement<br/>and learning. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Robot manipulation |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Adaptive control |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Deep learning |
| 700 ## - ADDED ENTRY--PERSONAL NAME |
|---|
| Personal name |
Evangelista, Arianne Joy D. |
| Relator term |
author |
| 700 ## - ADDED ENTRY--PERSONAL NAME |
|---|
| Personal name |
Lagramada, John Louis D. |
| Relator term |
author |
| 700 ## - ADDED ENTRY--PERSONAL NAME |
|---|
| Personal name |
Remollo, Jhon Mark G. |
| Relator term |
author |
| 700 ## - ADDED ENTRY--PERSONAL NAME |
|---|
| Personal name |
Tamundong, Nicamae G. |
| Relator term |
author |
| 700 ## - ADDED ENTRY--PERSONAL NAME |
|---|
| Personal name |
Villanueva, Althea R. |
| Relator term |
author |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
Library of Congress Classification |
| Koha item type |
Bachelor's Thesis COE |
| Suppress in OPAC |
No |