Nano-U: Efficient Terrain Segmentation for Tiny Robot Navigation

TL;DR

This paper introduces Nano-U, a compact terrain segmentation network optimized for microcontrollers, enabling efficient navigation for tiny robots in outdoor environments.

Contribution

The authors develop Nano-U, a highly compact segmentation model trained with Quantization-Aware Distillation, and deploy it on microcontrollers using a custom compiler, advancing TinyML robotics.

Findings

Nano-U achieves high accuracy on Botanic Garden and TinyAgri datasets.

The model runs efficiently on ESP32-S3 with minimal memory and low latency.

The approach enables scalable, energy-efficient perception for small robotic platforms.

Abstract

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.