Confidence-Gated Vision-Only Heading Alignment for UAV-UGV Cooperative Systems

2026-07-21

AI Summary

This work addresses the unreliability of control commands in vision-only UAV-UGV cooperative heading prediction when perception confidence is low, which often leads to blind and erroneous execution. To mitigate this issue, the authors propose a lightweight confidence-gated framework that leverages two interpretable proxy metrics—bounding box area and short-term heading variation—to assess perception reliability. During low-confidence intervals, the framework conservatively updates control commands using either a freeze strategy or a novel bounded fusion fallback mechanism. This study is the first to integrate interpretable reliability proxies with a decision-aware command issuance policy, revealing the limitations of freezing strategies under sparse execution and demonstrating that bounded fusion significantly enhances command-level stability. Experiments on real-world datasets show that the approach effectively balances execution rate, accuracy, and smoothness, with bounded fusion substantially reducing stale-command errors in low-confidence scenarios.

Abstract

Vision-based heading prediction is useful for UAV--UGV cooperation, but accurate prediction alone does not guarantee that every predicted heading should be issued directly as a control command. This paper investigates the decision problem of when and how a fixed vision-based heading predictor should be trusted for command issuance. A lightweight confidence-gated framework is proposed in which execution decisions are made using two interpretable reliability proxies derived from the perception stream: bounding-box area as a visibility-related proxy and short-window variation in predicted heading as a stability-related proxy. During low-confidence intervals, the framework compares the baseline freeze-HOLD policy with a bounded-blend fallback that updates the issued command conservatively. The method is evaluated on a real UAV--UGV dataset under clean and perturbed conditions. The results show that confidence gating creates a clear trade-off among execution rate, executed-frame accuracy, issued-command accuracy, and smoothness. The results further show that sparse execution can cause severe stale-command error under the baseline freeze-HOLD policy, whereas the bounded-blend fallback substantially improves command-level behavior under the same gate decisions. These findings highlight that reliable perception-driven autonomy depends not only on prediction accuracy, but also on decision-aware command issuance during low-confidence

Problem

• heading prediction
• confidence gating
• UAV-UGV cooperation
• command issuance
• perception reliability

Innovation

• confidence-gated control
• vision-only heading prediction
• reliability proxies
• bounded-blend fallback
• UAV-UGV cooperation