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

ArXi:2606.03441v1 Announce Type: cross 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-