PerchRL: Vision-Based Agile Perching on Inclined Platforms under Rapid and Irregular Motion
This work addresses the challenging problem of vision-based perching on moving inclined platforms for quadrotors, which is critical for air-ground collaboration but previously unsolved due to limited field of view and motion complexity.
PerchRL enables quadrotors to autonomously perch on moving inclined platforms using vision, achieving high success rates in both simulation and real-world tests with robustness to intermittent visual loss and rapid platform motion.
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.