analiza aiqbench
This research addresses the critical safety gap in vision-based robot navigation by fine-tuning transformer policies to explicitly encode obstacle boundaries and free-space structures. The proposed method significantly reduces collisions and improves goal arrival rates across multiple platforms, demonstrating that integrating geometric priors directly into the policy yields superior generalization in dynamic environments.
SAFER-Nav: Enhancing Safety for Visual Robot Navigation via Segmentation-Aware Fine-Tuning
arXiv:2606.11636v2 Announce Type: replace Abstract: Vision-based navigation models, particularly foundation models, generate viable trajectories from RGB observations alone. However, even state-of-the-art transformer- and diffusion-based policies struggle to generalize in unfamiliar deployment environments containing unseen obstacles or shifted conditions. The resulting trajectories often remain goal-directed but unsafe. Existing efforts improve safety through external trajectory correction or internal geometric priors, yet the resulting policies are not trained to explicitly represent obstacle boundaries or traversable free-space structure. To address this, we propose a navigation model that incorporates these structures directly into the policy via fine-tuning and is designed for transformer-based RGB navigation policies. Across three robot platforms, two indoor environments, and static and dynamic obstacle scenarios, our method reduces collisions per run from 1.76 to 0.20 and raises the goal arrival rate from 42% to 93% relative to ViNT, with consistent gains over NoMaD and their CARE-augmented variants. Project page: https://paper-demo.github.io/SAFER_Nav/
Abstract:Vision-based navigation models, particularly foundation models, generate viable trajectories from RGB observations alone. However, even state-of-the-art transformer- and diffusion-based policies struggle to generalize in unfamiliar deployment environments containing unseen obstacles or shifted conditions. The resulting trajectories often remain goal-directed but unsafe. Existing efforts improve safety through external trajectory correction or internal geometric priors, yet the resulting policies are not trained to explicitly represent obstacle boundaries or traversable free-space structure. To address this, we propose a navigation model that incorporates these structures directly into the policy via fine-tuning and is designed for transformer-based RGB navigation policies. Across three robot platforms, two indoor environments, and static and dynamic obstacle scenarios, our method reduces collisions per run from 1.76 to 0.20 and raises the goal arrival rate from 42% to 93% relative to ViNT, with consistent gains over NoMaD and their CARE-augmented variants. Project page: this https URL
Robotics (cs.RO)
arXiv:2606.11636 [cs.RO]
(or arXiv:2606.11636v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.11636 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 236 cuvinte
Subiecte conexe
SAFER-Nav: Enhancing Safety for Visual Robot Navigation via Segmentation-Aware Fine-Tuning
arXiv · 11 iun. 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · 18 sept. 2026
Onboard Lightweight LLM Reasoning for Human-Aware Safe UAV Navigation
arXiv · 16 oct. 2026
UP-Fuse: Uncertainty-guided LiDAR-Camera Fusion for 3D Panoptic Segmentation
arXiv · 28 iul. 2026