UltraLight Luma: A Novel Edge-Deployable Perception Network for Crop-Row Segmentation in Agricultural Robotics

Dhanushka Balasingham; Shamod Ginigaddarage; Hanojhan Rajahrajasingh; Nuwan Kodagoda; Rajitha de Silva

cs.ROOct 8, 2026

UltraLight Luma: A Novel Edge-Deployable Perception Network for Crop-Row Segmentation in Agricultural Robotics

Authors: Dhanushka Balasingham, Shamod Ginigaddarage, Hanojhan Rajahrajasingh, Nuwan Kodagoda, Rajitha de Silva

Organizations: Faculty of Computing, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka · Lincoln Centre for Autonomous Systems (L-CAS), University of Lincoln, UK

Abstract

Reliable crop-row perception is essential for autonomous agricultural robots, but low-cost deployment is constrained by computation, memory, power, and inference time. This paper addresses crop-row detection and navigation-line extraction using UltraLight Luma, a compact encoder-decoder segmentation network with a progressive learning strategy and only 13.1k trainable parameters. The predicted crop-row masks are processed using a post-processing algorithm to estimate row alignment for downstream visual servoing. UltraLight Luma improves parameter efficiency over U-Net, YOLOv8, and YOLOv26 while maintaining reliable crop-row detection performance. The model required only 25.23 mJ per inference, demonstrating its suitability for resource-constrained agricultural robots.

Explore similar work

Nano-U: Efficient Terrain Segmentation for Tiny Robot Navigation
May 11, 2026Federico Pizzolato, Francesco Pasti, Nicola BellottoRobot Navigation Semantic Segmentation
Dept of Information Engineering, University of Padua, Italy
LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields
Jun 30, 2026Felipe Tommaselli, Francisco Affonso, Arthur Pompeu +4Robot Navigation Agricultural Robotics
Mobile Robotics Group, Center for Robotics (CRob), São Carlos School of Engineering (EESC), University of São Paulo, São Carlos, SP, Brazil · DASLab, Department of Computer Science, University of Illinois Urbana-Champaign, Champaign, IL, USA
Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices
Apr 25, 2026Linyuan Wang, Haibo Yao, Te-Ming Tseng +4Agricultural Remote Sensing Weed Detection
Department of Agricultural and Biological Engineering, Mississippi State University, Mississippi State, MS, USA · USDA-ARS, Genetics and Sustainable Agriculture Research Unit, Mississippi State, MS, USA · Department of Plant and Soil Sciences, Mississippi State University, Mississippi State, MS, USA +2

May 11, 2026, cs.ROJ/K move · Enter open · S save

Nano-U: Efficient Terrain Segmentation for Tiny Robot Navigation

Federico Pizzolato, Francesco Pasti, Nicola Bellotto

Dept of Information Engineering, University of Padua, Italy

Robot Navigation Semantic Segmentation Neural Network Quantization

Open paper AskPDF arXiv

Terrain segmentation is a fundamental capability for autonomous mobile robots operating in unstructured outdoor environments. However, state-of-the-art models are incompatible with the memory and compute constraints typical of microcontrollers, limiting scalable deployment in small robotics platforms. To address this gap, we develop a complete framework for robust binary terrain segmentation on a low-cost microcontroller. At the core of our approach we design Nano-U, a highly compact binary segmentation network with a few thousand parameters. To compensate for the network's minimal capacity, we train Nano-U via Quantization-Aware Distillation (QAD), combining knowledge distillation and quantization-aware training. This allows the final quantized model to achieve excellent results on the Botanic Garden dataset and to perform very well on TinyAgri, a custom agricultural field dataset with more challenging scenes. We deploy the quantized Nano-U on a commodity microcontroller by extending MicroFlow, a compiler-based inference engine for TinyML implemented in Rust. By eliminating interpreter overhead and dynamic memory allocation, the quantized model executes on an ESP32-S3 with a minimal memory footprint and low latency. This compiler-based execution demonstrates a viable and energy-efficient solution for perception on low-cost robotic platforms.

Abstract

Explore similar work

Nano-U: Efficient Terrain Segmentation for Tiny Robot Navigation

LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields

Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices