# Interpretable Fuzzy Inference for UAV Target Tracking Using Bounding-Box Geometry

arXiv: https://arxiv.org/abs/2608.04121 · HTML: https://mlsanity.com/paper/2608.04121/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 26 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 3 of 3)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Visual Heading Prediction for Autonomous Aerial Vehicles](https://mlsanity.com/paper/2512.09898/) (2025)

## Abstract (arXiv)

Vision-based guidance of unmanned aerial vehicles (UAVs) toward unmanned ground vehicles (UGVs) supports cooperative aerial--ground robotics, but reliable continuous yaw estimation from onboard vision remains challenging because of sensing uncertainty, limited computation, and the need for interpretable control. Existing deep-learning and geometric-reconstruction approaches often require large datasets, external localization, or complex modeling assumptions, reducing transparency and deployment suitability on resource-constrained platforms. We present an interpretable fuzzy-inference framework that generates continuous yaw commands from low-dimensional features extracted from YOLO boxes: target centroid location, area, and aspect ratio. No explicit geometric modeling is required. A Mamdani fuzzy system serves as an interpretable baseline using a shoulder--triangle--shoulder input partition. It is followed by a first-order Takagi--Sugeno model with three antecedent membership terms per input, whose parameters are derived from training-set quantiles, yielding a compact 27-rule structure. Evaluation uses 6,169 labeled samples from a VICON motion-capture environment. Across five randomized train--test splits, the Takagi--Sugeno model achieves a test-set mean absolute error of 0.140^circ ± 0.003^circ, a root mean squared error of 0.200^circ ± 0.008^circ, and a maximum absolute error of 1.254^circ ± 0.121^circ. Within-threshold accuracies are 99.676% ± 0.270% for ±1^circ and 100.000% ± 0.000% for both ±3^circ and ±5^circ. Directional consistency between image-plane horizontal displacement and predicted yaw sign reaches 90.254% ± 0.612%. These results show that the framework is transparent, data-efficient, computationally lightweight, and suitable for real-time vision-based UAV guidance toward mobile ground targets.