UAV Swarm Mission Planning in Dynamic Environment Using Consensus-Based Bundle Algorithm.

Area of Science:

• Robotics and Automation
• Artificial Intelligence
• Aerospace Engineering

Background:

• Mission planning for multiple heterogeneous Unmanned Aerial Vehicles (UAVs) in dynamic environments presents significant computational and real-time challenges.
• Existing algorithms often struggle with constraints such as task timing, limited UAV resources, diverse task types, and dynamic task additions.

Purpose of the Study:

• To develop a novel approach for real-time complex mission planning for multiple heterogeneous UAVs.
• To adapt and enhance the Consensus-Based Bundle Algorithms (CBBA) to address dynamic environments and stringent operational constraints.

Main Methods:

• Introduced a dynamic task generation mechanism to satisfy task timing constraints.
• Simplified multi-UAV cooperative tasks into single-UAV sub-tasks.
• Implemented an asynchronous task allocation mechanism to reduce computational complexity and communication time.
• Utilized a partial task redistribution mechanism for dynamic task allocation.

Main Results:

• The adapted CBBA effectively handles task timing, resource limitations, diverse tasks, and dynamic task additions.
• The asynchronous and partial redistribution mechanisms significantly reduce computational load and communication overhead.
• The algorithm ensures real-time performance while maintaining optimal mission planning results.

Conclusions:

• The proposed enhanced CBBA provides a feasible and real-time solution for complex mission planning problems involving multiple heterogeneous UAVs.
• Dynamic simulation experiments validated the algorithm's effectiveness and real-time performance in dynamic environments.