Deep Bayesian Future Fusion for Self-Supervised, High-Resolution, Off-Road Mapping
This work addresses the need for long-range, high-resolution mapping in off-road robotics, enabling safer navigation over varied surfaces, though it appears incremental by combining existing methods.
The paper tackles the problem of generating high-resolution maps for off-road navigation from sparse sensing data, achieving dense maps at 2cm resolution from 30m forward sensing, which outperforms conventional baselines and improves downstream navigation.
High-speed off-road navigation requires long-range, high-resolution maps to enable robots to safely navigate over different surfaces while avoiding dangerous obstacles. However, due to limited computational power and sensing noise, most approaches to off-road mapping focus on producing coarse (20-40cm) maps of the environment. In this paper, we propose Future Fusion, a framework capable of generating dense, high-resolution maps from sparse sensing data (30m forward at 2cm). This is accomplished by - (1) the efficient realization of the well-known Bayes filtering within the standard deep learning models that explicitly accounts for the sparsity pattern in stereo and LiDAR depth data, and (2) leveraging perceptual losses common in generative image completion. The proposed methodology outperforms the conventional baselines. Moreover, the learned features and the completed dense maps lead to improvements in the downstream navigation task.