Global Multi-Phase Path Planning Through High-Level Reinforcement Learning
In this paper, we introduce the <italic>Global Multi-Phase Path Planning</italic> (<monospace><inline-formula><tex-math notation="LaTeX">$GMP^{3}$</tex-math></inline-formula></monospace>) algorithm in planner problems, which computes fast and...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Control Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10613437/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554062967832576 |
|---|---|
| author | Babak Salamat Sebastian-Sven Olzem Gerhard Elsbacher Andrea M. Tonello |
| author_facet | Babak Salamat Sebastian-Sven Olzem Gerhard Elsbacher Andrea M. Tonello |
| author_sort | Babak Salamat |
| collection | DOAJ |
| description | In this paper, we introduce the <italic>Global Multi-Phase Path Planning</italic> (<monospace><inline-formula><tex-math notation="LaTeX">$GMP^{3}$</tex-math></inline-formula></monospace>) algorithm in planner problems, which computes fast and feasible trajectories in environments with obstacles, considering physical and kinematic constraints. Our approach utilizes a Markov Decision Process (MDP) framework and high-level reinforcement learning techniques to ensure trajectory smoothness, continuity, and compliance with constraints. Through extensive simulations, we demonstrate the algorithm's effectiveness and efficiency across various scenarios. We highlight existing path planning challenges, particularly in integrating dynamic adaptability and computational efficiency. The results validate our method's convergence guarantees using Lyapunov’s stability theorem and underscore its computational advantages. |
| format | Article |
| id | doaj-art-c0c4148da18b4ae6a48f855a7c4a1404 |
| institution | Kabale University |
| issn | 2694-085X |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Control Systems |
| spelling | doaj-art-c0c4148da18b4ae6a48f855a7c4a14042025-01-09T00:03:12ZengIEEEIEEE Open Journal of Control Systems2694-085X2024-01-01340541510.1109/OJCSYS.2024.343508010613437Global Multi-Phase Path Planning Through High-Level Reinforcement LearningBabak Salamat0https://orcid.org/0000-0001-7262-3264Sebastian-Sven Olzem1https://orcid.org/0009-0001-8995-7209Gerhard Elsbacher2https://orcid.org/0000-0002-8297-5033Andrea M. Tonello3https://orcid.org/0000-0002-9873-2407AImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, GermanyAImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, GermanyAImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, GermanyInstitute of Networked and Embedded Systems, Alpen-Adria University Klagenfurt, Klagenfurt, AustriaIn this paper, we introduce the <italic>Global Multi-Phase Path Planning</italic> (<monospace><inline-formula><tex-math notation="LaTeX">$GMP^{3}$</tex-math></inline-formula></monospace>) algorithm in planner problems, which computes fast and feasible trajectories in environments with obstacles, considering physical and kinematic constraints. Our approach utilizes a Markov Decision Process (MDP) framework and high-level reinforcement learning techniques to ensure trajectory smoothness, continuity, and compliance with constraints. Through extensive simulations, we demonstrate the algorithm's effectiveness and efficiency across various scenarios. We highlight existing path planning challenges, particularly in integrating dynamic adaptability and computational efficiency. The results validate our method's convergence guarantees using Lyapunov’s stability theorem and underscore its computational advantages.https://ieeexplore.ieee.org/document/10613437/High level reinforcement learningmulti-phase path planning |
| spellingShingle | Babak Salamat Sebastian-Sven Olzem Gerhard Elsbacher Andrea M. Tonello Global Multi-Phase Path Planning Through High-Level Reinforcement Learning IEEE Open Journal of Control Systems High level reinforcement learning multi-phase path planning |
| title | Global Multi-Phase Path Planning Through High-Level Reinforcement Learning |
| title_full | Global Multi-Phase Path Planning Through High-Level Reinforcement Learning |
| title_fullStr | Global Multi-Phase Path Planning Through High-Level Reinforcement Learning |
| title_full_unstemmed | Global Multi-Phase Path Planning Through High-Level Reinforcement Learning |
| title_short | Global Multi-Phase Path Planning Through High-Level Reinforcement Learning |
| title_sort | global multi phase path planning through high level reinforcement learning |
| topic | High level reinforcement learning multi-phase path planning |
| url | https://ieeexplore.ieee.org/document/10613437/ |
| work_keys_str_mv | AT babaksalamat globalmultiphasepathplanningthroughhighlevelreinforcementlearning AT sebastiansvenolzem globalmultiphasepathplanningthroughhighlevelreinforcementlearning AT gerhardelsbacher globalmultiphasepathplanningthroughhighlevelreinforcementlearning AT andreamtonello globalmultiphasepathplanningthroughhighlevelreinforcementlearning |