UAV-UGV-UMV Multi-Swarms for Cooperative Surveillance

Area of Science:

• Robotics and Control Systems
• Artificial Intelligence
• Surveillance Technology

Background:

• Traditional surveillance systems struggle with early detection of evasive targets in complex environments.
• Controlling heterogeneous swarms of unmanned vehicles (aerial, ground, marine) presents significant challenges in coordination and trajectory planning.

Purpose of the Study:

• To develop and evaluate a novel surveillance system for the early detection of escapers from restricted areas.
• To introduce a new swarming mobility model, CROMM-MS, for controlling heterogeneous multi-swarms of unmanned vehicles.
• To optimize system parameters using a Competitive Coevolutionary Genetic Algorithm (CompCGA) within a predator-prey framework.

Main Methods:

• Development of the Chaotic Rössler Mobility Model for Multi-Swarms (CROMM-MS) to manage heterogeneous unmanned vehicle swarms.
• Implementation of a Competitive Coevolutionary Genetic Algorithm (CompCGA) for optimizing vehicle parameters and evasion abilities.
• Utilizing a predator-prey approach to simulate and test the surveillance and evasion dynamics.

Main Results:

• The CROMM-MS model demonstrates viability for effective surveillance tasks.
• The proposed system achieves competitive performance compared to existing state-of-the-art surveillance approaches.
• Optimization through CompCGA significantly enhances early detection capabilities and overall success rates.

Conclusions:

• The CROMM-MS based surveillance system offers a promising advancement in early detection of escapers.
• The integration of CompCGA provides an effective method for optimizing swarm behavior in surveillance scenarios.
• This research validates the effectiveness and competitiveness of the novel swarming mobility model for security applications.