Soft Actor-Critic Based Deep Reinforcement Learning Strategy for Tracking Control of Unmanned Aerial Vehicles.
Saved in:
| Title: | Soft Actor-Critic Based Deep Reinforcement Learning Strategy for Tracking Control of Unmanned Aerial Vehicles. |
|---|---|
| Authors: | Chen, Bo1 njit_airobot@126.com, Song, Chengcheng2 schengcheng@126.com, Zhou, Baoyu1 y00452505136@njit.edu.cn, Wu, Hao1 y00452505127@njit.edu.cn, Shang, Yanling3 hnnhsyl@126.com, Li, Guipu4 ligp@njit.edu.cn, Gao, Fangzheng5 gaofz@126.com |
| Source: | Engineering Letters. Sep2026, Vol. 34 Issue 9, p3917-3925. 9p. |
| Subjects: | Reinforcement learning, Tracking control systems, Model validation, Markov processes, Maximum entropy method, Drone aircraft, Robust control |
| Abstract: | To enhance the autonomous target tracking and control performance of unmanned aerial vehicles (UAVs) in complex and dynamic environments, this paper proposes a deep reinforcement learning-based UAV tracking control method. First, the UAV target tracking problem is formulated as a Markov Decision Process (MDP), with carefully designed state space, action space, and reward function. On this basis, the Soft Actor-Critic (SAC) algorithm is introduced to construct the UAV control policy. By leveraging the maximum entropy reinforcement learning framework, the proposed approach improves exploration capability and training stability. Finally, the effectiveness of the method is validated in a simulation environment. Experimental results demonstrate that the proposed method can achieve stable target tracking under various initial conditions and target motion patterns, while exhibiting strong robustness and generalization performance. [ABSTRACT FROM AUTHOR] |
| Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 196712816 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Soft Actor-Critic Based Deep Reinforcement Learning Strategy for Tracking Control of Unmanned Aerial Vehicles. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Chen%2C+Bo%22">Chen, Bo</searchLink><relatesTo>1</relatesTo><i> njit_airobot@126.com</i><br /><searchLink fieldCode="AR" term="%22Song%2C+Chengcheng%22">Song, Chengcheng</searchLink><relatesTo>2</relatesTo><i> schengcheng@126.com</i><br /><searchLink fieldCode="AR" term="%22Zhou%2C+Baoyu%22">Zhou, Baoyu</searchLink><relatesTo>1</relatesTo><i> y00452505136@njit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wu%2C+Hao%22">Wu, Hao</searchLink><relatesTo>1</relatesTo><i> y00452505127@njit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Shang%2C+Yanling%22">Shang, Yanling</searchLink><relatesTo>3</relatesTo><i> hnnhsyl@126.com</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Guipu%22">Li, Guipu</searchLink><relatesTo>4</relatesTo><i> ligp@njit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Gao%2C+Fangzheng%22">Gao, Fangzheng</searchLink><relatesTo>5</relatesTo><i> gaofz@126.com</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Engineering+Letters%22">Engineering Letters</searchLink>. Sep2026, Vol. 34 Issue 9, p3917-3925. 9p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Reinforcement+learning%22">Reinforcement learning</searchLink><br /><searchLink fieldCode="DE" term="%22Tracking+control+systems%22">Tracking control systems</searchLink><br /><searchLink fieldCode="DE" term="%22Model+validation%22">Model validation</searchLink><br /><searchLink fieldCode="DE" term="%22Markov+processes%22">Markov processes</searchLink><br /><searchLink fieldCode="DE" term="%22Maximum+entropy+method%22">Maximum entropy method</searchLink><br /><searchLink fieldCode="DE" term="%22Drone+aircraft%22">Drone aircraft</searchLink><br /><searchLink fieldCode="DE" term="%22Robust+control%22">Robust control</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: To enhance the autonomous target tracking and control performance of unmanned aerial vehicles (UAVs) in complex and dynamic environments, this paper proposes a deep reinforcement learning-based UAV tracking control method. First, the UAV target tracking problem is formulated as a Markov Decision Process (MDP), with carefully designed state space, action space, and reward function. On this basis, the Soft Actor-Critic (SAC) algorithm is introduced to construct the UAV control policy. By leveraging the maximum entropy reinforcement learning framework, the proposed approach improves exploration capability and training stability. Finally, the effectiveness of the method is validated in a simulation environment. Experimental results demonstrate that the proposed method can achieve stable target tracking under various initial conditions and target motion patterns, while exhibiting strong robustness and generalization performance. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=196712816 |
| RecordInfo | BibRecord: BibEntity: Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 9 StartPage: 3917 Subjects: – SubjectFull: Reinforcement learning Type: general – SubjectFull: Tracking control systems Type: general – SubjectFull: Model validation Type: general – SubjectFull: Markov processes Type: general – SubjectFull: Maximum entropy method Type: general – SubjectFull: Drone aircraft Type: general – SubjectFull: Robust control Type: general Titles: – TitleFull: Soft Actor-Critic Based Deep Reinforcement Learning Strategy for Tracking Control of Unmanned Aerial Vehicles. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Chen, Bo – PersonEntity: Name: NameFull: Song, Chengcheng – PersonEntity: Name: NameFull: Zhou, Baoyu – PersonEntity: Name: NameFull: Wu, Hao – PersonEntity: Name: NameFull: Shang, Yanling – PersonEntity: Name: NameFull: Li, Guipu – PersonEntity: Name: NameFull: Gao, Fangzheng IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 09 Text: Sep2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 1816093X Numbering: – Type: volume Value: 34 – Type: issue Value: 9 Titles: – TitleFull: Engineering Letters Type: main |
| ResultId | 1 |
