OWLS: Open-world Language-conditioned Speed Fields for Zero-Shot Rover
Overview
OWLS uses dense feature maps from open-vocabulary vision-language models to generate speed fields for rover navigation. It adapts semantic terrain descriptions into a minimum-time planner, enabling navigation without task-specific training, terrain annotation, or exteroceptive sensors beyond a single camera.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Evidence dependency changes (3)
- 2026-10-30T20:07:07.508Z · evidence updated · source revision 2. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T20:06:49.559Z · evidence updated · source revision 2. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-30T16:28:40.135Z · evidence updated · source revision 2. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalOWLS: Open-world Language-conditioned Speed Fields for Zero-Shot Rover Navigation
OWLS uses dense feature maps from open-vocabulary vision-language models to generate speed fields for rover navigation. It adapts semantic terrain descriptions into a minimum-time planner, enabling navigation without task-specific training, terrain annotation, or exteroceptive sensors beyond a single camera.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).