Ask to Land: Learning a Mask-Conditioned Open-Vocabulary Landing Policy via Differentiable Physics
- 1 December 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14292-14299
Abstract
No abstract availableFunding Information
- National Science Foundation of China (62073214)
This publication has 20 references indexed in Scilit:
- PEACE: Prompt Engineering Automation for CLIPSeg Enhancement for Safe-Landing Zone Segmentation2025
- Learning vision-based agile flight via differentiable physicsNature Machine Intelligence, 2025
- Learning Quadrotor Control from Visual Features Using Differentiable Simulation2025
- VisFly: An Efficient and Versatile Simulator for Training Vision-Based Flight2025
- YOLO-World: Real-Time Open-Vocabulary Object Detection2024
- Segment Anything2023
- A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flight2022
- Inclined Quadrotor Landing using Deep Reinforcement Learning2021
- A Deep Reinforcement Learning Technique for Vision-Based Autonomous Multirotor Landing on a Moving Platform2018
- Vision-Based Landing of a Simulated Unmanned Aerial Vehicle with Fast Reinforcement Learning2010