Terrain-aware Low Altitude Path Planning

2025/05/11 by Jia, Yixuan, Tagliabue, Andrea, Thomas, Annika +2
#FOS: Computer and information sciences #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2505.07141

Abstract

In this paper, we study the problem of generating low-altitude path plans for nap-of-the-earth (NOE) flight in real time with only RGB images from onboard cameras and the vehicle pose. We propose a novel training method that combines behavior cloning and self-supervised learning, where the self-supervision component allows the learned policy to refine the paths generated by the expert planner. Simulation studies show 24.7% reduction in average path elevation compared to the standard behavior cloning approach.

Citations

• iKap: Kinematics-aware Planning with Imperative Learning
• Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion
• Safe Low-Altitude Navigation in Steep Terrain with Fixed-Wing Aerial Vehicles
• ViPlanner: Visual Semantic Imperative Learning for Local Navigation
• Efficient Deep Learning of Robust Policies from MPC using Imitation and Tube-Guided Data Augmentation
• DINOv2: Learning Robust Visual Features without Supervision
• iPlanner: Imperative Path Planning
• How to train your robot with deep reinforcement learning: lessons we have learned
• Fast Policy Learning through Imitation and Reinforcement
• Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry\n and Semantics
• Feature Pyramid Networks for Object Detection
• Deep Residual Learning for Image Recognition
• Adam: A Method for Stochastic Optimization
• Sampling-based Algorithms for Optimal Motion Planning

Related

• Safe Low-Altitude Navigation in Steep Terrain with Fixed-Wing Aerial Vehicles
• Learning to Drive Off Road on Smooth Terrain in Unstructured\n Environments Using an On-Board Camera and Sparse Aerial Images
• Neural Elevation Models for Terrain Mapping and Path Planning
• Pathfinder for Low-altitude Aircraft with Binary Neural Network
• RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigation