Related Experiment Video
Updated: May 24, 2025
11:53
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
Published on: October 14, 2017
11.5K
Neural-network-based practical specified-time resilient formation maneuver control for second-order nonlinear
Chuanhai Yang1, Jingyi Huang2, Shuang Wu2
1School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China.
Summary
This study introduces a resilient formation control for multi-robot systems against false data injection attacks. The method ensures specified-time convergence and enhances robustness using a hierarchical framework and neural networks.
Area of Science:
- Robotics
- Control Systems
- Cybersecurity
Background:
- Multi-robot systems face vulnerabilities to false data injection (FDI) attacks.
- Existing formation control lacks resilience and specified-time convergence under adversarial conditions.
- Distributed relative localization accuracy is crucial for coordinated robot maneuvers.
Purpose of the Study:
- To develop a specified-time resilient formation maneuver control approach for second-order nonlinear multi-robot systems.
- To enhance robustness against false data injection (FDI) attacks.
- To improve distributed relative localization accuracy and achieve specified-time convergence.
Main Methods:
- A hierarchical topology framework based on (d+1)-reachability theory for downward decoupling.
- Restricting follower information flow to enhance resilience.
- Employing an offline radial basis function neural network (RBFNN) to mitigate nonlinearities and FDI attacks.
Main Results:
- The proposed approach achieves specified-time convergence for formation maneuvers.
- Enhanced resilience and robustness against FDI attacks demonstrated through simulations.
- Reduced system errors compared to traditional finite-time and fixed-time control methods.
Conclusions:
- The specified-time resilient formation maneuver control approach is effective for multi-robot systems under FDI attacks.
- The hierarchical framework and RBFNN significantly improve system robustness and localization accuracy.
- The method offers a promising solution for secure and efficient multi-robot coordination.
