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.
@article{arxiv.2403.11876,
title = {Deep Bayesian Future Fusion for Self-Supervised, High-Resolution, Off-Road Mapping},
author = {Shubhra Aich and Wenshan Wang and Parv Maheshwari and Matthew Sivaprakasam and Samuel Triest and Cherie Ho and Jason M. Gregory and John G. Rogers and Sebastian Scherer},
journal= {arXiv preprint arXiv:2403.11876},
year = {2024}
}