Transition Control of a Double-Inverted Pendulum System Using Sim2Real Reinforcement Learning
This study presents a sim2real reinforcement learning-based controller for transition control in a double-inverted pendulum system, addressing the limitations of traditional control methods that rely on precomputed trajectories and lack adaptability to strong external disturbances. By introducing th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/13/3/186 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850279501408239616 |
|---|---|
| author | Taegun Lee Doyoon Ju Young Sam Lee |
| author_facet | Taegun Lee Doyoon Ju Young Sam Lee |
| author_sort | Taegun Lee |
| collection | DOAJ |
| description | This study presents a sim2real reinforcement learning-based controller for transition control in a double-inverted pendulum system, addressing the limitations of traditional control methods that rely on precomputed trajectories and lack adaptability to strong external disturbances. By introducing the novel concept of ‘transition control’, this research expands the scope of inverted pendulum studies to tackle the challenging task of navigating between multiple equilibrium points. To overcome the reality gap—a persistent challenge in sim2real transfer—a hardware-centered approach was employed, aligning the physical system’s mechanical design with high-fidelity dynamic equations derived from the Euler–Lagrange equation. This design eliminates the need for software-based corrections, ensuring consistent and robust system performance across simulated and real-world environments. Experimental validation demonstrates the controller’s ability to reliably execute all 12 transition scenarios within the double-inverted pendulum system. Additionally, it exhibits recovery characteristics, enabling the system to stabilize and return to equilibrium point even under severe disturbances. |
| format | Article |
| id | doaj-art-1480d4e01b4545ddba49c8829aedd840 |
| institution | OA Journals |
| issn | 2075-1702 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj-art-1480d4e01b4545ddba49c8829aedd8402025-08-20T01:49:04ZengMDPI AGMachines2075-17022025-02-0113318610.3390/machines13030186Transition Control of a Double-Inverted Pendulum System Using Sim2Real Reinforcement LearningTaegun Lee0Doyoon Ju1Young Sam Lee2Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of KoreaDepartment of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of KoreaDepartment of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of KoreaThis study presents a sim2real reinforcement learning-based controller for transition control in a double-inverted pendulum system, addressing the limitations of traditional control methods that rely on precomputed trajectories and lack adaptability to strong external disturbances. By introducing the novel concept of ‘transition control’, this research expands the scope of inverted pendulum studies to tackle the challenging task of navigating between multiple equilibrium points. To overcome the reality gap—a persistent challenge in sim2real transfer—a hardware-centered approach was employed, aligning the physical system’s mechanical design with high-fidelity dynamic equations derived from the Euler–Lagrange equation. This design eliminates the need for software-based corrections, ensuring consistent and robust system performance across simulated and real-world environments. Experimental validation demonstrates the controller’s ability to reliably execute all 12 transition scenarios within the double-inverted pendulum system. Additionally, it exhibits recovery characteristics, enabling the system to stabilize and return to equilibrium point even under severe disturbances.https://www.mdpi.com/2075-1702/13/3/186reinforcement learningdouble-inverted pendulumsim2real transfertransition control |
| spellingShingle | Taegun Lee Doyoon Ju Young Sam Lee Transition Control of a Double-Inverted Pendulum System Using Sim2Real Reinforcement Learning Machines reinforcement learning double-inverted pendulum sim2real transfer transition control |
| title | Transition Control of a Double-Inverted Pendulum System Using Sim2Real Reinforcement Learning |
| title_full | Transition Control of a Double-Inverted Pendulum System Using Sim2Real Reinforcement Learning |
| title_fullStr | Transition Control of a Double-Inverted Pendulum System Using Sim2Real Reinforcement Learning |
| title_full_unstemmed | Transition Control of a Double-Inverted Pendulum System Using Sim2Real Reinforcement Learning |
| title_short | Transition Control of a Double-Inverted Pendulum System Using Sim2Real Reinforcement Learning |
| title_sort | transition control of a double inverted pendulum system using sim2real reinforcement learning |
| topic | reinforcement learning double-inverted pendulum sim2real transfer transition control |
| url | https://www.mdpi.com/2075-1702/13/3/186 |
| work_keys_str_mv | AT taegunlee transitioncontrolofadoubleinvertedpendulumsystemusingsim2realreinforcementlearning AT doyoonju transitioncontrolofadoubleinvertedpendulumsystemusingsim2realreinforcementlearning AT youngsamlee transitioncontrolofadoubleinvertedpendulumsystemusingsim2realreinforcementlearning |