Gaussian Semantic Field for One-shot LiDAR Global Localization
This work addresses a domain-specific problem for robotics and autonomous systems by improving localization accuracy through semantic disambiguation, representing an incremental advancement over existing landmark-based methods.
The paper tackles the problem of repetitive and misleading landmarks in one-shot LiDAR global localization by proposing a tri-layered scene graph with continuous semantic distributions learned from Gaussian processes, achieving superior performance against state-of-the-art methods on public datasets.
We present a one-shot LiDAR global localization algorithm featuring semantic disambiguation ability based on a lightweight tri-layered scene graph. While landmark semantic registration-based methods have shown promising performance improvements in global localization compared with geometric-only methods, landmarks can be repetitive and misleading for correspondence establishment. We propose to mitigate this problem by modeling semantic distributions with continuous functions learned from a population of Gaussian processes. Compared with discrete semantic labels, the continuous functions capture finer-grained geo-semantic information and also provide more detailed metric information for correspondence establishment. We insert this continuous function as the middle layer between the object layer and the metric-semantic layer, forming a tri-layered 3D scene graph, serving as a light-weight yet performant backend for one-shot localization. We term our global localization pipeline Outram-GSF (Gaussian semantic field) and conduct a wide range of experiments on publicly available data sets, validating the superior performance against the current state-of-the-art.