# PAANI : On Device Visual Evidence Fusion and Explainable Guidance for River Robot Simulation

arXiv: https://arxiv.org/abs/2609.22353 · HTML: https://mlsanity.com/paper/2609.22353/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Builds on (most cited first, 19 of 19)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Simple Online and Realtime Tracking](https://mlsanity.com/paper/1602.00763/) (2016)
- [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022)
- [SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water](https://mlsanity.com/paper/2105.01922/) (2021)
- [WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfaces](https://mlsanity.com/paper/2307.06505/) (2023)
- [MODS -- A USV-oriented object detection and obstacle segmentation benchmark](https://mlsanity.com/paper/2105.02359/) (2021)
- [LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmark](https://mlsanity.com/paper/2308.09618/) (2023)
- [Explainable Autonomous Robots: A Survey and Perspective](https://mlsanity.com/paper/2105.02658/) (2021)
- [Survey of Deep Learning for Autonomous Surface Vehicles in the Marine Environment](https://mlsanity.com/paper/2210.08487/) (2022)
- [Temporal Context for Robust Maritime Obstacle Detection](https://mlsanity.com/paper/2203.05352/) (2022)
- [Learning Maritime Obstacle Detection from Weak Annotations by Scaffolding](https://mlsanity.com/paper/2108.00564/) (2021)
- [The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024](https://mlsanity.com/paper/2311.14762/) (2023)
- [A water-obstacle separation and refinement network for unmanned surface vehicles](https://mlsanity.com/paper/2001.01921/) (2020)
- [eWaSR -- an embedded-compute-ready maritime obstacle detection network](https://mlsanity.com/paper/2304.11249/) (2023)

## Abstract (arXiv)

Mobile river monitoring robots must interpret obstacles and water boundaries that geographic waypoints alone cannot describe. On resource constrained platforms, converting imperfect visual predictions into timely and inspectable guidance is a distinct challenge. An object label or steering command does not explain which evidence supports a decision or when that evidence is unreliable. We present PAANI, an on-device perception to guidance architecture that combines a project trained YOLO11n detector and a custom MobileNetV3 Small semantic segmenter with timestamp aligned evidence fusion on Arduino UNO Q. Bounded tracking supplies object persistence, while an explicit corridor policy combines surface labels, accepted detections, urgency and mask uncertainty. Each final advisory exposes its contributing evidence and policy reasons. ROS 2 interfaces connect the local AI pipeline to a separate Gazebo vessel, localization and control testbed. Training uses 10,000 WaterScenes images for four-class detection and 1,127 MaSTr1325 images for segmentation, including 198 segmentation validation images. The selected FP32 ONNX models occupy 14.817 MB. Detector checkpoint test mAP at 0.5 IoU is 0.7388, while the separately evaluated rectangular ONNX export achieves validation mAP at 0.5 IoU of 0.7367. Segmentation ONNX validation mIoU is 0.9750. A five-minute UNO Q recording produced median and 95th percentile pipeline latencies of 467.8 ms and 580.3 ms at a configured 0.5 Hz cadence. The evaluation also identifies black input misclassification and a sampling rate mismatch that prevents the diagnostic apparent motion estimator from collecting sufficient evidence. These results support an inspectable and reusable edge robotics foundation while clearly distinguishing model accuracy and on-board execution from validated on-water collision avoidance.