Skip to content

Event

Paper on the WildOS Open-Vocabulary Object Search System Published

1 reports · 1 sources

Hardik Shah and other authors published a paper on arXiv cs.RO proposing WildOS, an open-vocabulary object search system for wild environments. The system combines safe geometric exploration with semantic visual reasoning, uses a sparse navigation graph to maintain spatial memory, and has a vision module based on foundation models, ExploRFM, score the frontier nodes of the graph while predicting traversability, visual frontiers, and object similarity, enabling real-time onboard semantic navigation. The authors report that in closed-loop field experiments conducted at various off-road and urban sites, WildOS navigates reliably and is clearly superior to pure-geometry and pure-vision baselines in both efficiency and autonomy. These conclusions come from the paper authors' experimental reports.

Report timeline

  1. WildOS: An Open-Vocabulary Object Search System for the Wild

    WildOS is a unified system for long-range, open-vocabulary object search that combines safe geometric exploration with semantic visual reasoning for complex outdoor environments without prior maps and with limited depth sensing. The system builds a sparse navigation graph to maintain spatial memory and uses a foundation-model-based vision module, ExploRFM, to score the graph's frontier nodes, simultaneously predicting traversability, visual frontiers, and object similarity to enable real-time onboard semantic navigation.

    arXiv cs.RO ·

Related topics

Perception and localizationPlanning and decision makingRobot models and learningResearch papers

Interest trend

Current
3
Peak
4Nov 4 01:00
Past 24 hours
–

The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.