# Where to Perch in a Tree: Vision-Guidance for Tree-Grasping Drones

arXiv: https://arxiv.org/abs/2605.15430 · HTML: https://mlsanity.com/paper/2605.15430/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 36 references that are in the map.
- First posted on arXiv 14 May 2026.

## Builds on (most cited first, 7 of 7)

- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [Semantic Segmentation for Partially Occluded Apple Trees Based on Deep Learning](https://mlsanity.com/paper/2010.06879/) (2020)
- [Aerial Tensile Perching and Disentangling Mechanism for Long-Term Environmental Monitoring](https://mlsanity.com/paper/2403.01890/) (2024)
- [ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue](https://mlsanity.com/paper/2504.01261/) (2025)
- [How ornithopters can perch autonomously on a branch](https://mlsanity.com/paper/2207.07489/) (2022)
- [Exploring the Potential of Multi-modal Sensing Framework for Forest Ecology](https://mlsanity.com/paper/2410.23033/) (2024)
- [Tendon-driven Grasper Design for Aerial Robot Perching on Tree Branches](https://mlsanity.com/paper/2503.00214/) (2025)

## Abstract (arXiv)

This study demonstrates a method to locate an ideal perch location on a tree for vision-guided autonomous tree-perching drones. Various image processing algorithms, including those used for machine learning, image segmentation and binary image morphology, are implemented to assess the shape and structure of a tree. Rather than identifying the closest available branch, this study builds on vision methods by evaluating the potential of each branch, determining its suitability for perching based on factors such as branch width, slope (angle to the horizontal) and curvature. For a given tree-perching drone and a dataset of more than 10,000 urban tree images taken from February to October in a subtropical and temperate monsoon climate, the proposed method successfully produces a result for 76% of feasible targets. A feasible target defined as a tree where the branch diameters are sufficiently thick and where the available perching space is at least equal to the width of a tendon-driven grasping claw. These successful preliminary results create a foundation from which a number of identified improvements and additional features can be developed to create a generalised method; this will involve the incorporation of supplementary data from depth perception and attitude sensors to enhance the branch assessment.