Learning for Active 3D Mapping
This work addresses efficient 3D mapping for robotics or autonomous systems using emerging sensors, but it appears incremental as it builds on existing active mapping and learning approaches.
The paper tackles the problem of active 3D mapping with controllable depth sensors by proposing a method that learns to reconstruct dense 3D maps from sparse measurements and optimizes ray control, resulting in significant improvement in map accuracy on a subset of the KITTI dataset.
We propose an active 3D mapping method for depth sensors, which allow individual control of depth-measuring rays, such as the newly emerging solid-state lidars. The method simultaneously (i) learns to reconstruct a dense 3D occupancy map from sparse depth measurements, and (ii) optimizes the reactive control of depth-measuring rays. To make the first step towards the online control optimization, we propose a fast prioritized greedy algorithm, which needs to update its cost function in only a small fraction of pos- sible rays. The approximation ratio of the greedy algorithm is derived. An experimental evaluation on the subset of the KITTI dataset demonstrates significant improve- ment in the 3D map accuracy when learning-to-reconstruct from sparse measurements is coupled with the optimization of depth-measuring rays.