Borrowed Eyes: Markerless Nano-UAV Flight with an Active Quadruped Observer

Key points

• Nano unmanned aerial vehicles (nano-UAVs) can navigate confined spaces that larger robots cannot, but their payload capacity severely limits the sensors and compute available for self-localization in global navigation satellite system (GNSS)-denied environments.1
• To ensure continuous tracking, we developed a perception-aware nonlinear Model Predictive Controller (NMPC) that dynamically adjusts the quadruped's body and arm to maximize the drone's visibility, treating observation reliability as a primary control objective.1
• Relying solely on this external estimate, the nano-UAV executed predefined trajectories from takeoff to landing with a median 3D localization error of 59 mm.1
• Ultimately, this framework allows a quadruped to offload the localization burden of a nano-UAV, enabling inspection of complex spaces that neither robot could navigate alone.1

Sources (1)

• [1]Borrowed Eyes: Markerless Nano-UAV Flight with an Active Quadruped Observer
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 12:38 PM

  We present a vision-based system that localizes a nano-UAV from a quadruped robot with an arm-mounted camera.

  Nano unmanned aerial vehicles (nano-UAVs) can navigate confined spaces that larger robots cannot, but their payload capacity severely limits the sensors and compute available for self-localization in global navigation satellite system (GNSS)-denied environments.

Extractive summary: sentences quoted from the sources.