论文标题
在倾斜的表面上用四肢旋转的稳健活动视觉栖息
Robust Active Visual Perching with Quadrotors on Inclined Surfaces
论文作者
论文摘要
自动微型航空车被部署用于各种任务，包括监视和监视。栖息和凝视使车辆可以监视目标而无需飞行，节省电池电量并增加整体任务时间，而无需频繁替换电池。本文解决了主动视觉栖息（AVP）控制问题，以自主在倾斜的表面上自主栖息，最高$ 90^\ circ $。我们的方法生成动态可行的轨迹，以在所需的目标位置在所需的目标位置进行导航和栖息，同时考虑到执行器和视野（FOV）约束。通过在飞行中进行重新掌握，我们利用了更准确的目标定位，从而增加了旋转动作的稳健性，以靶向定位或控制误差。我们利用Karush-Kuhn-Tucker（KKT）条件来确定计划目标过程中计划目标与视觉传感约束之间的兼容性。此外，我们在实验上确定了相应的边界条件，这些条件可在栖息器操作过程中最大化时空目标可见性。所提出的方法实时在板载下工作，并具有很大的计算限制，仅依赖于摄像机和惯性测量单元（IMU）。 Experimental results validate the proposed approach and shows the higher success rate as well as increased target interception precision and accuracy with respect to a one-shot planning approach, while still retaining aggressive capabilities with flight envelopes that include large excursions from the hover position on inclined surfaces up to 90$^\circ$, angular speeds up to 750~deg/s, and accelerations up to 10~m/s$^2$.
Autonomous Micro Aerial Vehicles are deployed for a variety tasks including surveillance and monitoring. Perching and staring allow the vehicle to monitor targets without flying, saving battery power and increasing the overall mission time without the need to frequently replace batteries. This paper addresses the Active Visual Perching (AVP) control problem to autonomously perch on inclined surfaces up to $90^\circ$. Our approach generates dynamically feasible trajectories to navigate and perch on a desired target location, while taking into account actuator and Field of View (FoV) constraints. By replanning in mid-flight, we take advantage of more accurate target localization increasing the perching maneuver's robustness to target localization or control errors. We leverage the Karush-Kuhn-Tucker (KKT) conditions to identify the compatibility between planning objectives and the visual sensing constraint during the planned maneuver. Furthermore, we experimentally identify the corresponding boundary conditions that maximizes the spatio-temporal target visibility during the perching maneuver. The proposed approach works on-board in real-time with significant computational constraints relying exclusively on cameras and an Inertial Measurement Unit (IMU). Experimental results validate the proposed approach and shows the higher success rate as well as increased target interception precision and accuracy with respect to a one-shot planning approach, while still retaining aggressive capabilities with flight envelopes that include large excursions from the hover position on inclined surfaces up to 90$^\circ$, angular speeds up to 750~deg/s, and accelerations up to 10~m/s$^2$.
