Adaptive trajectory controller design for unmanned surface vehicles based on SAC-PID
n adaptive proportional integral derivative (PID) controller based on the soft actor-critic (SAC) algorithm for trajectory control of unmanned surface vehicles (USV) is proposed in this paper. The gains of the PID controller need to be manually adjusted based on experience in the original formulatio...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Mechanical Engineering and Naval Architecture
2025-01-01
|
| Series: | Brodogradnja |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/476944 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850117840703586304 |
|---|---|
| author | Wei Guan Zhaoyong Xi Zhewen Cui Xianku Zhang |
| author_facet | Wei Guan Zhaoyong Xi Zhewen Cui Xianku Zhang |
| author_sort | Wei Guan |
| collection | DOAJ |
| description | n adaptive proportional integral derivative (PID) controller based on the soft actor-critic (SAC) algorithm for trajectory control of unmanned surface vehicles (USV) is proposed in this paper. The gains of the PID controller need to be manually adjusted based on experience in the original formulation. Furthermore, once tuned, these gains remain fixed and making further modifications becomes time-consuming and labor-intensive. To address these limitations, the SAC algorithm is introduced, enabling online tuning of PID gains through agent-environment interaction. Additionally, the strategy of combining SAC algorithm with PID controller mitigates concerns regarding interpretability and security often associated with DRL. In this study, stability analysis of the adaptive trajectory controller based on the SAC-PID algorithm is conducted. This paper horizontally compares the proposed method with traditional PID tuning methods, genetic algorithms (GA), and deep deterministic policy gradient (DDPG) algorithm to highlight the superiority of the SAC-PID approach. Finally, experiments in different scenarios are performed to compare generalization capabilities between DDPG and SAC algorithms. Results demonstrate that the proposed SAC-PID algorithm exhibits excellent stability properties, fast convergence speed, and strong generalization ability. |
| format | Article |
| id | doaj-art-8ec3c4f0496546898e07784fae0d486c |
| institution | OA Journals |
| issn | 0007-215X 1845-5859 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Faculty of Mechanical Engineering and Naval Architecture |
| record_format | Article |
| series | Brodogradnja |
| spelling | doaj-art-8ec3c4f0496546898e07784fae0d486c2025-08-20T02:36:00ZengFaculty of Mechanical Engineering and Naval ArchitectureBrodogradnja0007-215X1845-58592025-01-0176212210.21278/brod76206Adaptive trajectory controller design for unmanned surface vehicles based on SAC-PIDWei Guan0Zhaoyong Xi1Zhewen Cui2Xianku Zhang3Navigation College, Dalian Maritime University, Dalian, ChinaNavigation College, Dalian Maritime University, Dalian, ChinaNavigation College, Dalian Maritime University, Dalian, ChinaNavigation College, Dalian Maritime University, Dalian, Chinan adaptive proportional integral derivative (PID) controller based on the soft actor-critic (SAC) algorithm for trajectory control of unmanned surface vehicles (USV) is proposed in this paper. The gains of the PID controller need to be manually adjusted based on experience in the original formulation. Furthermore, once tuned, these gains remain fixed and making further modifications becomes time-consuming and labor-intensive. To address these limitations, the SAC algorithm is introduced, enabling online tuning of PID gains through agent-environment interaction. Additionally, the strategy of combining SAC algorithm with PID controller mitigates concerns regarding interpretability and security often associated with DRL. In this study, stability analysis of the adaptive trajectory controller based on the SAC-PID algorithm is conducted. This paper horizontally compares the proposed method with traditional PID tuning methods, genetic algorithms (GA), and deep deterministic policy gradient (DDPG) algorithm to highlight the superiority of the SAC-PID approach. Finally, experiments in different scenarios are performed to compare generalization capabilities between DDPG and SAC algorithms. Results demonstrate that the proposed SAC-PID algorithm exhibits excellent stability properties, fast convergence speed, and strong generalization ability.https://hrcak.srce.hr/file/476944deep reinforcement learningunmanned surface vehiclesoft actor criticpid tuning |
| spellingShingle | Wei Guan Zhaoyong Xi Zhewen Cui Xianku Zhang Adaptive trajectory controller design for unmanned surface vehicles based on SAC-PID Brodogradnja deep reinforcement learning unmanned surface vehicle soft actor critic pid tuning |
| title | Adaptive trajectory controller design for unmanned surface vehicles based on SAC-PID |
| title_full | Adaptive trajectory controller design for unmanned surface vehicles based on SAC-PID |
| title_fullStr | Adaptive trajectory controller design for unmanned surface vehicles based on SAC-PID |
| title_full_unstemmed | Adaptive trajectory controller design for unmanned surface vehicles based on SAC-PID |
| title_short | Adaptive trajectory controller design for unmanned surface vehicles based on SAC-PID |
| title_sort | adaptive trajectory controller design for unmanned surface vehicles based on sac pid |
| topic | deep reinforcement learning unmanned surface vehicle soft actor critic pid tuning |
| url | https://hrcak.srce.hr/file/476944 |
| work_keys_str_mv | AT weiguan adaptivetrajectorycontrollerdesignforunmannedsurfacevehiclesbasedonsacpid AT zhaoyongxi adaptivetrajectorycontrollerdesignforunmannedsurfacevehiclesbasedonsacpid AT zhewencui adaptivetrajectorycontrollerdesignforunmannedsurfacevehiclesbasedonsacpid AT xiankuzhang adaptivetrajectorycontrollerdesignforunmannedsurfacevehiclesbasedonsacpid |