Photometric LiDAR and RGB-D Bundle Adjustment
This work addresses the challenge of global refinement for high-resolution LiDAR and RGB-D sensors in SLAM systems, offering a unified approach that is incremental but improves trajectory estimates for robotics and autonomous navigation applications.
The paper tackles the problem of jointly optimizing sensor trajectories and 3D maps in SLAM by introducing a novel photometric bundle adjustment method that unifies RGB-D and LiDAR data, achieving performance on par or better than state-of-the-art methods without requiring data association or environmental assumptions.
The joint optimization of the sensor trajectory and 3D map is a crucial characteristic of Simultaneous Localization and Mapping (SLAM) systems. To achieve this, the gold standard is Bundle Adjustment (BA). Modern 3D LiDARs now retain higher resolutions that enable the creation of point cloud images resembling those taken by conventional cameras. Nevertheless, the typical effective global refinement techniques employed for RGB-D sensors are not widely applied to LiDARs. This paper presents a novel BA photometric strategy that accounts for both RGB-D and LiDAR in the same way. Our work can be used on top of any SLAM/GNSS estimate to improve and refine the initial trajectory. We conducted different experiments using these two depth sensors on public benchmarks. Our results show that our system performs on par or better compared to other state-of-the-art ad-hoc SLAM/BA strategies, free from data association and without making assumptions about the environment. In addition, we present the benefit of jointly using RGB-D and LiDAR within our unified method. We finally release an open-source CUDA/C++ implementation.