In this paper, we develop and present a novel strategy for safe coordination of a large-scale multi-agent team with ``\textit{local deformation}" capabilities. Multi-agent coordination is defined by our proposed method as a multi-layer deformation problem specified as a Deep Neural Network (DNN) optimization problem. The proposed DNN consists of $p$ hidden layers, each of which contains artificial neurons representing unique agents. Furthermore, based on the desired positions of the agents of hidden layer $k$ ($k=1,\cdots,p-1$), the desired deformation of the agents of hidden layer $k + 1$ is planned. In contrast to the available neural network learning problems, our proposed neural network optimization receives time-invariant reference positions of the boundary agents as inputs and trains the weights based on the desired trajectory of the agent team configuration, where the weights are constrained by certain lower and upper bounds to ensure inter-agent collision avoidance. We simulate and provide the results of a large-scale quadcopter team coordination tracking a desired elliptical trajectory to validate the proposed approach.
翻译:在本文中,我们开发并提出了一种安全协调大规模多智能体团队的新策略,这些团队具有“局部形变”能力。我们的建议将多智能体协调定义为多层形变问题,这是指定为深度神经网络(DNN)优化问题的问题。所提出的DNN由p个隐藏层组成,每个隐藏层包含表示独特智能体的人工神经元。此外,基于隐藏层k的智能体的期望位置(k = 1,...,p-1),计划隐藏层k + 1的智能体的期望变形。与可用的神经网络学习问题相比,我们提出的神经网络优化接收边缘代理的时不变参考位置作为输入,并根据代理团队配置的期望轨迹训练权重,其中权重受到一定的下限和上限的限制,以确保智能体间避免碰撞。我们通过对大规模无人机团队协调跟踪期望椭圆轨迹的仿真和结果,验证了所提出的方法。