Robustness of Embodied Point Navigation Agents
Abstract
We make a step towards robust embodied AI by analyzing the performance of two successful Habitat Challenge 2021 agents under different visual corruptions (low lighting, blur, noise, etc.) and robot dynamics corruptions (noisy egomotion). The agents had underperformed overall. However, one of the agents managed to handle multiple corruptions with ease, as the authors deliberately tackled robustness in their model. For specific corruptions, we concur with observations from literature that there is still a long way to go to recover the performance loss caused by corruptions, warranting more research on the robustness of embodied AI. Code available at m43.github.io/projects/embodied-ai-robustness .
Cite
Text
Rajic. "Robustness of Embodied Point Navigation Agents." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25075-0_15Markdown
[Rajic. "Robustness of Embodied Point Navigation Agents." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/rajic2022eccvw-robustness/) doi:10.1007/978-3-031-25075-0_15BibTeX
@inproceedings{rajic2022eccvw-robustness,
title = {{Robustness of Embodied Point Navigation Agents}},
author = {Rajic, Frano},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {193-204},
doi = {10.1007/978-3-031-25075-0_15},
url = {https://mlanthology.org/eccvw/2022/rajic2022eccvw-robustness/}
}