# PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion

arXiv: https://arxiv.org/abs/2606.03441 · HTML: https://mlsanity.com/paper/2606.03441/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Builds on (most cited first, 16 of 16)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains](https://mlsanity.com/paper/2007.13866/) (2020)
- [A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flight](https://mlsanity.com/paper/2202.10796/) (2022)
- [OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control](https://mlsanity.com/paper/2309.12825/) (2023)
- [Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight](https://mlsanity.com/paper/2403.12203/) (2024)
- [Whole-Body Control Through Narrow Gaps From Pixels To Action](https://mlsanity.com/paper/2409.00895/) (2024)
- [What Matters in Learning A Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study](https://mlsanity.com/paper/2412.11764/) (2024)
- [Inclined Quadrotor Landing using Deep Reinforcement Learning](https://mlsanity.com/paper/2103.09043/) (2021)
- [Robust Active Visual Perching with Quadrotors on Inclined Surfaces](https://mlsanity.com/paper/2204.02458/) (2022)
- [DynamicPose: Real-time and Robust 6D Object Pose Tracking for Fast-Moving Cameras and Objects](https://mlsanity.com/paper/2508.11950/) (2025)
- [Aggressive Visual Perching with Quadrotors on Inclined Surfaces](https://mlsanity.com/paper/2107.11171/) (2021)
- [Reinforcement Learning based Autonomous Multi-Rotor Landing on Moving Platforms](https://mlsanity.com/paper/2302.13192/) (2023)
- [Adaptive Tracking and Perching for Quadrotor in Dynamic Scenarios](https://mlsanity.com/paper/2312.11866/) (2023)
- [Real-Time Trajectory Planning for Aerial Perching](https://mlsanity.com/paper/2203.01061/) (2022)
- [EAGERx: Graph-Based Framework for Sim2real Robot Learning](https://mlsanity.com/paper/2407.04328/) (2024)

## Abstract (arXiv)

Autonomous vision-based perching of quadrotors on moving inclined platforms is critical for air-ground collaboration but remains challenging due to the limited field of view (FOV). In this paper, we propose PerchRL, a reinforcement learning (RL) framework for vision-based agile perching on inclined platforms under rapid and irregular motion. Specifically, we employ a two-stage learning strategy consisting of state-based pre-training followed by vision-based fine-tuning. To improve generalization across diverse platform motions, we employ randomized platform trajectories to prevent overfitting and temporal augmentation methods to capture latent motion patterns from historical observations. During vision-based fine-tuning, a hybrid learning framework consisting of visibility-aware state augmentation and active perception rewards is presented to improve robustness under intermittent visual loss. Extensive simulation and real-world experiments demonstrate the feasibility, stability, and real-time performance of PerchRL, while successful deployment across distinct quadrotor platforms further validates its adaptability. The source code will be released to benefit the community.