Synthesizing the Kill Chain: A Zero-Shot Framework for Target Verification and Tactical Reasoning on the Edge

TL;DR

This paper presents a hierarchical zero-shot framework combining lightweight object detection and vision-language models for autonomous edge robotics in military environments, enabling target verification and tactical reasoning with high accuracy and low latency.

Contribution

It introduces a novel hierarchical zero-shot approach using compact VLMs and a new diagnostic methodology for assessing model suitability in safety-critical edge applications.

Findings

Achieved up to 100% false-positive filtering accuracy.

Extended pipeline into an autonomous Scout-Commander with 100% correct asset deployment.

Validated hierarchical zero-shot architecture for edge autonomy in military scenarios.

Abstract

Deploying autonomous edge robotics in dynamic military environments is constrained by both scarce domain-specific training data and the computational limits of edge hardware. This paper introduces a hierarchical, zero-shot framework that cascades lightweight object detection with compact Vision-Language Models (VLMs) from the Qwen and Gemma families (4B-12B parameters). Grounding DINO serves as a high-recall, text-promptable region proposer, and frames with high detection confidence are passed to edge-class VLMs for semantic verification. We evaluate this pipeline on 55 high-fidelity synthetic videos from Battlefield 6 across three tasks: false-positive filtering (up to 100% accuracy), damage assessment (up to 97.5%), and fine-grained vehicle classification (55-90%). We further extend the pipeline into an agentic Scout-Commander workflow, achieving 100% correct asset deployment and a 9.8/10 reasoning score (graded by GPT-4o) with sub-75-second latency. A novel "Controlled Input" methodology decouples perception from reasoning, revealing distinct failure phenotypes: Gemma3-12B excels at tactical logic but fails in visual perception, while Gemma3-4B exhibits reasoning collapse even with accurate inputs. These findings validate hierarchical zero-shot architectures for edge autonomy and provide a diagnostic framework for certifying VLM suitability in safety-critical applications.