Related Experiment Video
Updated: Aug 6, 2026
06:52
Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats
Published on: April 3, 2026
Distributed predefined-time optimal allocation for multi-target tracking using constrained kWTA networks
Xiaoxuan Wang1, Shaofu Yang2, Zhenyuan Guo3
1School of Automation, Nanjing University of Information Science and Technology, Nanjing, 210044, China.
Summary
This study introduces a novel approach for optimal task allocation in distributed multi-target tracking. It ensures agents efficiently track targets in dynamic environments, minimizing conflicts and untracked targets.
Area of Science:
- Robotics and Control Systems
- Artificial Intelligence
- Sensor Networks
Background:
- Distributed task allocation is critical for multi-target tracking in complex environments.
- Existing methods face challenges in dynamic, large-scale scenarios.
Purpose of the Study:
- To investigate the optimal task allocation problem (TAP) for distributed multi-target tracking.
- To develop a robust solution for assigning agents to targets while avoiding conflicts.
Main Methods:
- Formulated TAP as a constrained k-winners-take-all (kWTA) problem using target-agent distance.
- Developed a distributed kWTA network for consistent cases.
- Designed a distributed perturbation mechanism for inconsistent cases.
Main Results:
- Achieved predefined-time convergence to optimal task allocation in consistent scenarios.
- Successfully eliminated inconsistency while preserving optimality in inconsistent scenarios.
- Demonstrated effectiveness and scalability through numerical simulations.
Conclusions:
- The proposed networks offer a practical and scalable solution for dynamic multi-target tracking.
- The approach effectively addresses challenges in large-scale, real-world tracking applications.
