Dynamic Path Planning and Cooperative Collision Avoidance for Multi-UAV Systems Using Independent Proximal Policy Optimization

Path planning enables Unmanned Aerial Vehicles (UAVs) to generate safe and efficient trajectories toward mission goals, minimizing flight time and energy consumption, while cooperative collision avoidance ensures reliable operation of UAV swarms in dense and dynamic environments. Introducing these two functions together is crucial for enhancing both the autonomy and robustness of UAV systems. This paper presents a novel dynamic path planning and collision avoidance algorithm for multi-UAV systems, known as the Independent Proximal Policy Optimization with Cooperative Collision Avoidance (IPPO-CCA) algorithm. The proposed algorithm integrates Independent Proximal Policy Optimization (IPPO) with Optimal Reciprocal Collision Avoidance (ORCA) and Region-Guided Collision Avoidance (RGCA) to improve navigation efficiency and flight safety in complex environments. Using a shared policy network and a bidirectional gated recurrent unit model, IPPO-CCA enables each UAV to independently learn optimal action strategies, achieving collision-free flight paths and flexible route adjustments. Simulation results across various scenarios confirm that IPPO-CCA significantly improves the overall safety, adaptability, and efficiency of multi-UAV missions. In quantitative terms, IPPO-CCA outperforms MASAC-CCA and MADDPG-CCA in average final reward by 13.66% and 21.70%, respectively. The source code is available at https://github.com/Shihong-Yin/IPPO-CCA.