Air-Ground Collaborative Navigation: Uncertainty-Triggered Aerial Refinement
What happened
Pranay Samineni and other authors propose an air-ground collaborative navigation method driven by planner-conditioned triggers: it first evaluates how uncertain map information affects the unmanned ground vehicle's (UGV) current MPPI trajectory; when navigation continuously degrades, it re-scores the same set of trajectories under resolved map hypotheses, selects the aerial measurement corresponding to the map layer request that yields the greatest improvement, and fuses it for replanning. The authors report that the method was tested in 180 simulation trials across three off-road routes and achieved uncertainty resolution and navigation recovery in approximately 2 km of field UGV operation. These results come from the paper's report and await independent verification.
AI 根据报道生成 · 6 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- arXiv cs.ROUncertainty-Triggered Aerial Refinement for Off-Road Navigation
The paper proposes a planner-conditioned air-ground assistance method that evaluates how map uncertainty affects the UGV's current MPPI rollouts. When navigation remains degraded, it re-scores the same rollouts under resolved map hypotheses, selects the map layer whose request yields the largest improvement, requests the corresponding aerial measurement, and fuses it to replan.
Activity for this event
- Current
- 3
- Peak
- 10Nov 5 14:00
- Past 24 hours
- -49%
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.