In decentralized multiagent trajectory planners, agents need to communicate and exchange their positions to generate collision-free trajectories. However, due to localization errors/uncertainties, trajectory deconfliction can fail even if trajectories are perfectly shared between agents. To address this issue, we first present PARM and PARM*, perception-aware, decentralized, asynchronous multiagent trajectory planners that enable a team of agents to navigate uncertain environments while deconflicting trajectories and avoiding obstacles using perception information. PARM* differs from PARM as it is less conservative, using more computation to find closer-to-optimal solutions. While these methods achieve state-of-the-art performance, they suffer from high computational costs as they need to solve large optimization problems onboard, making it difficult for agents to replan at high rates. To overcome this challenge, we present our second key contribution, PRIMER, a learning-based planner trained with imitation learning (IL) using PARM* as the expert demonstrator. PRIMER leverages the low computational requirements at deployment of neural networks and achieves a computation speed up to 5500 times faster than optimization-based approaches.

翻译：在去中心化的多智能体轨迹规划器中，智能体需要进行通信并交换其位置信息以生成无碰撞轨迹。然而，由于定位误差/不确定性，即使轨迹在智能体之间被完美共享，轨迹解冲突仍可能失败。为解决这一问题，我们首先提出了PARM和PARM*，这两种感知感知的、去中心化的、异步的多智能体轨迹规划器，使得智能体团队能够在不确定环境中导航，同时利用感知信息进行轨迹解冲突并避开障碍物。PARM*与PARM的不同之处在于其保守性较低，通过更多的计算来寻找更接近最优的解决方案。尽管这些方法实现了最先进的性能，但它们存在计算成本高的问题，因为需要在机载设备上求解大规模优化问题，这使得智能体难以以高速率进行重新规划。为克服这一挑战，我们提出了第二个关键贡献——PRIMER，这是一种基于学习的规划器，使用PARM*作为专家演示器，通过模仿学习（IL）进行训练。PRIMER利用了神经网络在部署时较低的计算需求，其计算速度比基于优化的方法快达5500倍。