# Learning Transferable UAV for Forest Visual Perception

arXiv: https://arxiv.org/abs/1806.03626 · HTML: https://mlsanity.com/paper/1806.03626/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2018.

## Built on by (most cited first, 3 of 3)

- [Aerial Vision-and-Dialog Navigation](https://mlsanity.com/paper/2205.12219/) (2022)
- [Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving](https://mlsanity.com/paper/1907.06838/) (2019)
- [Learn by Observation: Imitation Learning for Drone Patrolling from Videos of A Human Navigator](https://mlsanity.com/paper/2008.13193/) (2020)

## Abstract (arXiv)

In this paper, we propose a new pipeline of training a monocular UAV to fly a collision-free trajectory along the dense forest trail. As gathering high-precision images in the real world is expensive and the off-the-shelf dataset has some deficiencies, we collect a new dense forest trail dataset in a variety of simulated environment in Unreal Engine. Then we formulate visual perception of forests as a classification problem. A ResNet-18 model is trained to decide the moving direction frame by frame. To transfer the learned strategy to the real world, we construct a ResNet-18 adaptation model via multi-kernel maximum mean discrepancies to leverage the relevant labelled data and alleviate the discrepancy between simulated and real environment. Simulation and real-world flight with a variety of appearance and environment changes are both tested. The ResNet-18 adaptation and its variant model achieve the best result of 84.08% accuracy in reality.