A Simulation-based End-to-End Learning Framework for Evidential Occupancy Grid Mapping
This work addresses a domain-specific problem for automated vehicles, offering an incremental improvement in handling uncertainty and data efficiency.
The paper tackles the problem of limited performance and uncertainty quantification in evidential occupancy grid mapping for automated vehicles by proposing a deep learning-based framework that does not rely on manually labeled data, achieving superiority over other approaches on synthetic and real-world data.
Evidential occupancy grid maps (OGMs) are a popular representation of the environment of automated vehicles. Inverse sensor models (ISMs) are used to compute OGMs from sensor data such as lidar point clouds. Geometric ISMs show a limited performance when estimating states in unobserved but inferable areas and have difficulties dealing with ambiguous input. Deep learning-based ISMs face the challenge of limited training data and they often cannot handle uncertainty quantification yet. We propose a deep learning-based framework for learning an OGM algorithm which is both capable of quantifying first- and second-order uncertainty and which does not rely on manually labeled data. Results on synthetic and on real-world data show superiority over other approaches. Source code and datasets are available at https://github.com/ika-rwth-aachen/EviLOG