2026-09-23T12:14:24Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/122269 2024-03-02 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Mehr, Negar 2023-12 application/pdf en text Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2025-12-01 The student, Amogh Pandey, accepted the attached license on 2023-12-05 at 15:44. The student, Amogh Pandey, submitted this Thesis for approval on 2023-12-05 at 15:56. This Thesis was approved for publication on 2023-12-06 at 11:21. DSpace SAF Submission Ingestion Package generated from Vireo submission #20148 on 2024-03-01 at 13:57:23 TranDynaMo: A comparative study of transformer and GRU performance in modeling dynamical systems Pandey, Amogh Transformers, Large Language Models Chatgpt Gpt Llm Dynamics Learning Dynamics Modeling Rnn Gru Control System Dynamics Dynamical Models 2023-12-06 Dynamics modeling is critical to many robotics and control tasks and applications, such as motion planning and trajectory optimization. However, obtaining a model through current methods is difficult and expensive, so instead, there have been many efforts to come up with data-driven methods to learn dynamics models. With the popularity and success of Large Language Models (LLMs) such as ChatGPT, we were inspired to find a way to leverage transformers, the building blocks of ChatGPT, to solve the dynamics learning problem. In this thesis, we study the viability of utilizing transformers for dynamics modeling. We do this by first introducing transformers and posing dynamics learning as a sequence-to-sequence modeling task. We then create a GPT2-based dynamics learning framework called TranDynaMo and test its dynamics modeling performance for various dynamical systems, such as chaotic systems and systems with limit cycles, by giving it an initial condition and seeing how well it can predict the trajectory. We then compare TranDynaMo against a GRU-based framework. We find that when the dynamics learning framework is required to predict parts of a trajectory significantly beyond the horizon of the training trajectories it was given, TranDynaMo beats the GRU-based framework; however, if the training and testing trajectories are of almost the same horizon, both perform satisfactorily, but the GRU-based framework outperforms TranDynaMo, thus indicating that the generalization of transformers is better. Text eng https://hdl.handle.net/2142/122269 Copyright 2023 Amogh Pandey M.S. Thesis Electrical & Computer Engr University of Illinois at Urbana-Champaign Electrical & Computer Eng