A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL. The file type is application/pdf
.
Filters
Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning [article]
2024 arXiv pre-print
Towards Byzantine-robust federated embodied agent learning, in this paper, we study the attack and defense for the task of vision-and-language navigation (VLN), where the agent is required to follow natural ... First, we introduce a simple but effective attack strategy, Navigation as Wish (NAW), in which the malicious client manipulates local trajectory data to implant a backdoor into the global model. ... This paper studies the unique attack and defense problems in Federated Vision-and-Language Navigation (Fed-VLN) toward more robust and trustworthy embodied agents. ...
arXiv:2211.14769v4 fatcat:6cqso4tqsvckbkalimktmx62wi
CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation [article]
2024 arXiv pre-print
To evaluate the effectiveness and generalization of navigation agents in a zero-shot multi-task setting, we create a benchmark called NavBench. ... However, the majority of existing vision-and-language navigation (VLN) methods primarily operate in less realistic simulator settings and do not incorporate environmental feedback into their decision-making ... Acknowledgements This work was supported in part by CAAI-Huawei MindSpore Open Fund. We also thank MindSpore for the partial support of this work, which is a new deep learning computing framework. ...
arXiv:2306.10322v3 fatcat:5ofofvgwrfagpcnkxfaqtwkdru
Benchmarking Robustness in Neural Radiance Fields [article]
2023 arXiv pre-print
In this work, we provide the first comprehensive analysis of the robustness of NeRF-based novel view synthesis algorithms in the presence of different types of corruptions. ... We hope that our findings will attract more researchers to study the robustness of NeRF-based approaches and help to improve their performance in the real world. ... Researchers have also examined benchmarks beyond image classification. RobustNav [4] quantifies the performance of embodied navigation agents when exposed to both visual and dynamic corruptions. ...
arXiv:2301.04075v1 fatcat:35b7w4f7q5evbcfyiytfxcwmo4