Planning and control of three-dimensional multi-agent formations

This paper provides a practicable framework for planning and control of three-dimensional multi-agent formations. The formation path planning is performed by using the A* search algorithm coupled with an optimizing algorithm to generate a collision-free and deadlock-free feasible path. For the formation motion control, we propose a set of decentralized control laws for the cohesive motion of three-dimensional multi-agent formations with a point-agent system model. Based on these control laws, the shape of the formation is maintained during continuous motion, which can efficiently avoid inter-agent collision. Rigorous proofs regarding the stability and convergence of proposed control laws are given by using Lyapunov theory and some geometric relations between agents. The effectiveness of the proposed framework is demonstrated via simulation results.