论文标题
在非结构化或限制环境中的束缚空中视觉助手的风险感知路径和运动计划
Risk-aware Path and Motion Planning for a Tethered Aerial Visual Assistant in Unstructured or Confined Environments
论文作者
论文摘要
这项研究旨在为束缚的无人驾驶汽车（UAV）开发路径和运动计划算法，以在非结构化或限制的环境中视觉上为遥控的主要机器人提供帮助。核操作，炸弹小队，灾难机器人和其他具有新任务或高度遮挡的环境的实践的新兴状态是使用两个机器人，一个机器人，这是一个视觉助手，可以通过提供外部观点来克服传感器的感知局限性。 However, the benefits of using an assistant have been limited for at least three reasons: (1) users tend to choose suboptimal viewpoints, (2) only ground robot assistants are considered, ignoring the rapid evolution of small unmanned aerial systems for indoor flying, (3) introducing a whole crew for the second teleoperated robot is not cost effective, may introduce further teamwork demands, and therefore could lead to miscommunication.本文提出了使用自主的束缚空中视觉助手来代替二级机器人及其操作人员。除了基于负担能力的观点质量理论，本论文旨在定义和代表非结构化或受限环境中的机器人运动风险。基于这些理论，开发了一种新颖的高级路径计划算法来实现风险感知计划，该计划平衡了观点质量和运动风险之间的权衡，以提供安全且值得信赖的视觉援助飞行。然后，计划的飞行轨迹将在束缚的无人机平台上实现。量身定制的感知和致动量以低水平运动套件的形式量身定制，包括一个基于绑扎的新型本地化模型，具有可忽略的计算开销，基于位置和速度控制的束缚飞机的运动原始模型，以及两个不同
This research aims at developing path and motion planning algorithms for a tethered Unmanned Aerial Vehicle (UAV) to visually assist a teleoperated primary robot in unstructured or confined environments. The emerging state of the practice for nuclear operations, bomb squad, disaster robots, and other domains with novel tasks or highly occluded environments is to use two robots, a primary and a secondary that acts as a visual assistant to overcome the perceptual limitations of the sensors by providing an external viewpoint. However, the benefits of using an assistant have been limited for at least three reasons: (1) users tend to choose suboptimal viewpoints, (2) only ground robot assistants are considered, ignoring the rapid evolution of small unmanned aerial systems for indoor flying, (3) introducing a whole crew for the second teleoperated robot is not cost effective, may introduce further teamwork demands, and therefore could lead to miscommunication. This dissertation proposes to use an autonomous tethered aerial visual assistant to replace the secondary robot and its operating crew. Along with a pre-established theory of viewpoint quality based on affordances, this dissertation aims at defining and representing robot motion risk in unstructured or confined environments. Based on those theories, a novel high level path planning algorithm is developed to enable risk-aware planning, which balances the tradeoff between viewpoint quality and motion risk in order to provide safe and trustworthy visual assistance flight. The planned flight trajectory is then realized on a tethered UAV platform. The perception and actuation are tailored to fit the tethered agent in the form of a low level motion suite, including a novel tether-based localization model with negligible computational overhead, motion primitives for the tethered airframe based on position and velocity control, and two different
