Work

Uncertainty-Calibrated System-2 MLLM Deliberation and System-1 VLA Control with Selective Abstention for Autonomous Earth Observation

Year: 2026
Type: preprint
Abstract: Autonomous Earth observation requires reliable aerial navigation under environmental degradation and distribution shift. We propose U-S2A-VLA, an uncertainty-calibrated dual-system framework that combines deliberative planning, reactive control, and selective abstention. Its asynchronous spatiotemporal context engine maintains a causal graph and issues subgoals at 1 Hz, while an edge policy uses abnormal-aware distillation to control flight at 15 Hz. A conformal uncertainty gate separates aleatoric and epistemic uncertainty to guide execution, safe hovering, or re-scouting. Experiments across AerialVLN, FloodNet, and RS-Agent show a 47.85% navigation success rate, 4.25 percentage points above the previous state of the art, and a 3.45% expected calibration error, with 18.4 ms edge execution latency.
Language: English
Open Access status: green
OpenAlex ID: W7226017928
Cites:
Cited by:
Related to: 10