A pack hunting strategy for heterogeneous robots in rescue operations

Area of Science:

• Robotics
• Artificial Intelligence
• Swarm Intelligence

Background:

• Coordinating heterogeneous robots (UAVs, UGVs) is crucial for complex tasks like rescue operations.
• Existing methods often rely on static roles, limiting adaptability in dynamic environments.

Purpose of the Study:

• To develop a novel framework for improved coordination in heterogeneous robot teams.
• To enhance the effectiveness of rescue operations through adaptive robot behavior.

Main Methods:

• Inspired by natural pack-hunting strategies, a framework combining hierarchical decision-making with decentralized control was developed.
• Dynamic target assignment and real-time task allocation using a multi-factor scoring function (distance, energy, communication).
• Implementation of adaptive 'Chaser' and 'Flanker' roles allowing robots to switch based on real-time data.

Main Results:

• The proposed framework demonstrated superior coordination and decision-making capabilities.
• Robots autonomously adjusted their roles to optimize mission outcomes.
• Improved responsiveness and efficient resource utilization in simulated rescue scenarios.

Conclusions:

• Combining hierarchical structures with decentralized control significantly enhances robot team performance.
• The adaptive role-switching mechanism improves adaptability in complex, changing environments.
• The framework shows strong potential for real-world applications, particularly in autonomous rescue operations.