几何模型预测路径积分用于敏捷无人机控制与在线避障
Geometric Model Predictive Path Integral for Agile UAV Control with Online Collision Avoidance
AI总结：
本文提出几何模型预测路径积分（GMPPI）用于无人机敏捷控制与在线避障，通过几何SE(3)控制和定制代价函数提升避障与跟踪性能。
摘要：
在本文中，我们介绍了几何模型预测路径积分（GMPPI），一种基于采样的控制器，能够跟踪敏捷轨迹并避障。在每次迭代中，GMPPI生成大量候选滚动轨迹，然后通过平均生成一个名义控制，供受控无人机执行。经典模型预测路径积分（MPPI）面临跟踪精度与避障之间的权衡；高噪声随机滚动在跟踪上效率低下，但对避障是必要的。为此，我们提出利用几何SE(3)控制生成GMPPI滚动的一部分。为了最大化其效益，我们引入了针对无人机的代价函数，平衡跟踪性能与避障。所有生成的滚动都投影到深度图像中以实现避障，据我们所知，这是首次在无人机MPPI循环中直接利用深度数据的方法。仿真显示GMPPI的跟踪误差与无障碍物的几何控制器相当，同时超过现有最先进规划器和基于学习的控制器的避障能力。现实世界实验显示以高达17米/秒的速度飞行，并能实现高达10米/秒的避障能力。
英文摘要：
In this letter, we introduce Geometric Model Predictive Path Integral (GMPPI), a sampling-based controller capable of tracking agile trajectories while avoiding obstacles. In each iteration, GMPPI generates a large number of candidate rollout trajectories and then averages them to create a nominal control to be followed by the controlled Unmanned Aerial Vehicle (UAV). Classical Model Predictive Path Integral (MPPI) faces a trade-off between tracking precision and obstacle avoidance; high-noise random rollouts are inefficient for tracking but necessary for collision avoidance. To this end, we propose leveraging geometric SE(3) control to generate a portion of GMPPI rollouts. To maximize their benefit, we introduce a UAV-tailored cost function balancing tracking performance with obstacle avoidance. All generated rollouts are projected onto depth images for collision avoidance, representing, to our knowledge, the first method utilizing depth data directly in a UAV MPPI loop. Simulations show GMPPI matches the tracking error of an obstacle-blind geometric controller while exceeding the avoidance capabilities of state-of-the-art planners and learning-based controllers. Real-world experiments demonstrate flight at speeds up to 17 m/s and obstacle avoidance up to 10 m/s.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
