Off-Road Drivable Area Extraction Using 3D LiDAR Data
This addresses the challenge of ambiguous terrain detection for autonomous vehicles in off-road settings, though it appears incremental in its approach.
The paper tackles the problem of extracting drivable areas in off-road environments using 3D LiDAR data for autonomous driving, achieving better performance with fewer human annotations through weakly and semi-supervised methods.
We propose a method for off-road drivable area extraction using 3D LiDAR data with the goal of autonomous driving application. A specific deep learning framework is designed to deal with the ambiguous area, which is one of the main challenges in the off-road environment. To reduce the considerable demand for human-annotated data for network training, we utilize the information from vast quantities of vehicle paths and auto-generated obstacle labels. Using these autogenerated annotations, the proposed network can be trained using weakly supervised or semi-supervised methods, which can achieve better performance with fewer human annotations. The experiments on our dataset illustrate the reasonability of our framework and the validity of our weakly and semi-supervised methods.