analiza aiqbench
ODG-NoMaD advances robot navigation by integrating global overhead camera data into a diffusion policy without requiring retraining, significantly improving exploration efficiency in unknown environments. This approach effectively bridges the gap between unguided wandering and directed movement, offering a robust solution for autonomous agents operating without prior topological maps. The method demonstrates superior collision-free performance and reduced residual distance compared to existing point-goal guidance techniques.
ODG-NoMaD: Overhead-Camera Direction-Guided NoMaD
arXiv:2608.21395v1 Announce Type: cross Abstract: NoMaD [31] is a learned vision-navigation policy that unifies goal-conditioned navigation and exploration in a single goal-masked diffusion policy. In an unseen environment, however - where neither a goal image nor a topological map is available - it can only explore undirectedly, wandering without global awareness. We present ODG-NoMaD, which gives NoMaD's exploration mode a global sense of where to proceed, without retraining the policy. An overhead depth camera is used once on deployment to build an occupancy map and plan a global path, which is segmented to yield a desired heading; a per-frame traversability map from the robot's onboard depth then refines this into a collision-free direction. The gradient of a cosine direction cost is injected into the final denoising steps, rotating sampled trajectories toward this direction while preserving the multimodality of exploration. In simulated office environments with and without random obstacles, ODG-NoMaD reduces the residual distance to the target by up to an order of magnitude over unguided exploration, outperforms the point-goal cost guidance of NaviDiffusor [37], and is the only configuration that remains collision-free on every trial.
Abstract:NoMaD [31] is a learned vision-navigation policy that unifies goal-conditioned navigation and exploration in a single goal-masked diffusion policy. In an unseen environment, however - where neither a goal image nor a topological map is available - it can only explore undirectedly, wandering without global awareness. We present ODG-NoMaD, which gives NoMaD's exploration mode a global sense of where to proceed, without retraining the policy. An overhead depth camera is used once on deployment to build an occupancy map and plan a global path, which is segmented to yield a desired heading; a per-frame traversability map from the robot's onboard depth then refines this into a collision-free direction. The gradient of a cosine direction cost is injected into the final denoising steps, rotating sampled trajectories toward this direction while preserving the multimodality of exploration. In simulated office environments with and without random obstacles, ODG-NoMaD reduces the residual distance to the target by up to an order of magnitude over unguided exploration, outperforms the point-goal cost guidance of NaviDiffusor [37], and is the only configuration that remains collision-free on every trial.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2608.21395 [cs.RO]
(or arXiv:2608.21395v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2608.21395 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 · 274 cuvinte
Subiecte conexe
Coming of a New Sun
LessWrong · 3 aug. 2026
Accelerating BEV Pooling on NVIDIA GPUs for Physical AI Applications
NVIDIA · 24 iun. 2026
The Machines that Make the Machines
NVIDIA · 7 oct. 2026
VANDERER: Map-Free Exploration using Future-Aware and Visual-Curiosity-Guided Diffusion Policy
arXiv · 16 iun. 2026