Evolutionary Computational Intelligence-Based Multi-Objective Sensor Management for Multi-Target Tracking
In multi-sensor systems (MSSs), sensor selection is a critical technique for obtaining high-quality sensing data. However, when the number of sensors to be selected is unknown in advance, sensor selection is essentially non-deterministic polynomial-hard (NP-hard), and finding the optimal solution is...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Sprog: | English |
| Udgivet: |
MDPI AG
2022-07-01
|
| Serier: | Remote Sensing |
| Fag: | |
| Online adgang: | https://www.mdpi.com/2072-4292/14/15/3624 |
| _version_ | 1827624646861651968 |
|---|---|
| author | Shuang Liang Yun Zhu Hao Li Junkun Yan |
| author_facet | Shuang Liang Yun Zhu Hao Li Junkun Yan |
| author_sort | Shuang Liang |
| collection | DOAJ |
| description | In multi-sensor systems (MSSs), sensor selection is a critical technique for obtaining high-quality sensing data. However, when the number of sensors to be selected is unknown in advance, sensor selection is essentially non-deterministic polynomial-hard (NP-hard), and finding the optimal solution is computationally unacceptable. To alleviate these issues, we propose a novel sensor selection approach based on evolutionary computational intelligence for tracking multiple targets in the MSSs. The sensor selection problem is formulated in a partially observed Markov decision process framework by modeling multi-target states as labeled multi-Bernoulli random finite sets. Two conflicting task-driven objectives are considered: minimization of the uncertainty in posterior cardinality estimates and minimization of the number of selected sensors. By modeling sensor selection as a multi-objective optimization problem, we develop a binary constrained evolutionary multi-objective algorithm based on non-dominating sorting and dynamically select a subset of sensors at each time step. Numerical studies are used to evaluate the performance of the proposed approach, where the MSS tracks multiple moving targets with nonlinear/linear dynamic models and nonlinear measurements. The results show that our method not only significantly reduces the number of selected sensors but also provides superior tracking accuracy compared to generic sensor selection methods. |
| first_indexed | 2024-03-09T12:13:42Z |
| format | Article |
| id | doaj.art-43535549f970427f8f10050d07b34ebb |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T12:13:42Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-43535549f970427f8f10050d07b34ebb2023-11-30T22:48:36ZengMDPI AGRemote Sensing2072-42922022-07-011415362410.3390/rs14153624Evolutionary Computational Intelligence-Based Multi-Objective Sensor Management for Multi-Target TrackingShuang Liang0Yun Zhu1Hao Li2Junkun Yan3Academy of Advanced Interdisciplinary Research, Xidian University, Xi’an 710071, ChinaSchool of Computer Science, Shaanxi Normal University, Xi’an 710119, ChinaSchool of Electronic Engineering, Xidian University, Xi’an 710071, ChinaNational Laboratory of Radar Signal Processing, Xidian University, Xi’an 710071, ChinaIn multi-sensor systems (MSSs), sensor selection is a critical technique for obtaining high-quality sensing data. However, when the number of sensors to be selected is unknown in advance, sensor selection is essentially non-deterministic polynomial-hard (NP-hard), and finding the optimal solution is computationally unacceptable. To alleviate these issues, we propose a novel sensor selection approach based on evolutionary computational intelligence for tracking multiple targets in the MSSs. The sensor selection problem is formulated in a partially observed Markov decision process framework by modeling multi-target states as labeled multi-Bernoulli random finite sets. Two conflicting task-driven objectives are considered: minimization of the uncertainty in posterior cardinality estimates and minimization of the number of selected sensors. By modeling sensor selection as a multi-objective optimization problem, we develop a binary constrained evolutionary multi-objective algorithm based on non-dominating sorting and dynamically select a subset of sensors at each time step. Numerical studies are used to evaluate the performance of the proposed approach, where the MSS tracks multiple moving targets with nonlinear/linear dynamic models and nonlinear measurements. The results show that our method not only significantly reduces the number of selected sensors but also provides superior tracking accuracy compared to generic sensor selection methods.https://www.mdpi.com/2072-4292/14/15/3624computational intelligenceintelligent sensing techniquemulti-sensor systemsmulti-target trackingrandom finite setsensor selection |
| spellingShingle | Shuang Liang Yun Zhu Hao Li Junkun Yan Evolutionary Computational Intelligence-Based Multi-Objective Sensor Management for Multi-Target Tracking Remote Sensing computational intelligence intelligent sensing technique multi-sensor systems multi-target tracking random finite set sensor selection |
| title | Evolutionary Computational Intelligence-Based Multi-Objective Sensor Management for Multi-Target Tracking |
| title_full | Evolutionary Computational Intelligence-Based Multi-Objective Sensor Management for Multi-Target Tracking |
| title_fullStr | Evolutionary Computational Intelligence-Based Multi-Objective Sensor Management for Multi-Target Tracking |
| title_full_unstemmed | Evolutionary Computational Intelligence-Based Multi-Objective Sensor Management for Multi-Target Tracking |
| title_short | Evolutionary Computational Intelligence-Based Multi-Objective Sensor Management for Multi-Target Tracking |
| title_sort | evolutionary computational intelligence based multi objective sensor management for multi target tracking |
| topic | computational intelligence intelligent sensing technique multi-sensor systems multi-target tracking random finite set sensor selection |
| url | https://www.mdpi.com/2072-4292/14/15/3624 |
| work_keys_str_mv | AT shuangliang evolutionarycomputationalintelligencebasedmultiobjectivesensormanagementformultitargettracking AT yunzhu evolutionarycomputationalintelligencebasedmultiobjectivesensormanagementformultitargettracking AT haoli evolutionarycomputationalintelligencebasedmultiobjectivesensormanagementformultitargettracking AT junkunyan evolutionarycomputationalintelligencebasedmultiobjectivesensormanagementformultitargettracking |