Vision and Learning for Deliberative Monocular Cluttered Flight
Debadeepta Deya✉, Kumar Shaurya Shankara, Sam Zenga, Rupesh Mehtab, M. Talha Agcayazic, Christopher Eriksend, Shreyansh Daftrya, Martial Heberta, James Andrew Bagnella
- aThe Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA
- bNVIDIA Corporation, Santa Clara, CA, USA
- cGeorge Mason University, Fairfax, VA, USA
- dHarvey Mudd College, Claremont, CA, USA
- ✉Corresponding author
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Cameras provide a rich source of information while being passive, cheap and lightweight for small Unmanned Aerial Vehicles (UAVs). In this work we present the first implementation of receding horizon control, which is widely used in ground vehicles, with monocular vision as the only sensing mode for autonomous UAV flight in dense clutter. Two key contributions make this possible: novel coupling of perception and control via relevant and diverse, multiple interpretations of the scene around the robot, leveraging recent advances in machine learning to showcase anytime budgeted cost-sensitive feature selection, and fast non-linear regression for monocular depth prediction. We empirically demonstrate the efficacy of our novel pipeline via real world experiments of more than 2 kms through dense trees with an off-the-shelf quadrotor. Moreover our pipeline is designed to combine information from other modalities like stereo and lidar.
TL;DRThis work presents the first implementation of receding horizon control, which is widely used in ground vehicles, with monocular vision as the only sensing mode for autonomous UAV flight in dense clutter. (Semantic Scholar)