This work presents a novel, inference-based approach to the distributed and cooperative flocking control of aerial robot swarms. The proposed method stems from the Unmanned Aerial Vehicle (UAV) dynamics by limiting the latent set to the robots' feasible action space, thus preventing any unattainable control inputs from being produced and leading to smooth flocking behavior. By modeling the inter-agent relationships using a pairwise energy function, we show that interacting robot swarms constitute a Markov Random Field. Our algorithm builds on the Mean-Field Approximation and incorporates the collective behavioral rules: cohesion, separation, and velocity alignment. We follow a distributed control scheme and show that our method can control a swarm of UAVs to a formation and velocity consensus with real-time collision avoidance. We validate the proposed method with physical UAVs and high-fidelity simulation experiments.

翻译：本工作提出了一种新颖的基于推理的分布式协作无人机群编队控制方法。该方法从无人机动力学出发，将潜在集限制在机器人的可行动作空间内，从而避免产生任何不可达的控制输入，并实现平滑的编队行为。通过使用成对能量函数对智能体间关系进行建模，我们证明交互的机器人集群构成了马尔可夫随机场。我们的算法基于平均场近似，并融合了集体行为规则：内聚、分离和速度对齐。我们采用分布式控制方案，证明该方法能够控制无人机群实现编队和速度一致性，同时具备实时避障能力。我们通过物理无人机和高保真仿真实验验证了所提方法的有效性。