TinyNav: End-to-End TinyML for Real-Time Autonomous Navigation on Microcontrollers

Pooria Roy; Nourhan Jadallah. Tomer Lapid; Shahzaib Ahmad; Armita Afroushe; Mete Bayrak

cs.ROMar 10, 2026

TinyNav: End-to-End TinyML for Real-Time Autonomous Navigation on Microcontrollers

Authors: Pooria Roy, Nourhan Jadallah. Tomer Lapid, Shahzaib Ahmad, Armita Afroushe, Mete Bayrak

Organizations: Queen’s University

Abstract

Autonomous navigation typically relies on power-intensive processors, limiting accessibility in low-cost robotics. Although microcontrollers offer a resource-efficient alternative, they impose strict constraints on model complexity. We present TinyNav, an end-to-end TinyML system for real-time autonomous navigation on an ESP32 microcontroller. A custom-trained, quantized 2D convolutional neural network processes a 20-frame sliding window of depth data to predict steering and throttle commands. By avoiding 3D convolutions and recurrent layers, the 23k-parameter model achieves 30 ms inference latency. Correlation analysis and Grad-CAM validation indicate consistent spatial awareness and obstacle avoidance behavior. TinyNav demonstrates that responsive autonomous control can be deployed directly on highly constrained edge devices, reducing reliance on external compute resources.

Figures & tables

Fig. 1: TinyNav Real‑Time Autonomous Navigation Pipeline

Fig. 2: Example: top-down view of a track

Fig. 4: Quantization Correlation Float vs. INT8

Fig. 5: Steering & Throttle correlation graphs

Fig. 6: Ground Truth vs. Prediction Distributions

Robot Navigation

Robot navigation studies how robots perceive, localize, plan, and move safely toward goals in static or changing environments.

See all 554 papers

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
Power-Performance Characterization of TinyML Systems
Aug 21, 2026Yujie Zhang, Dhananjaya Wijerathne, Zhaoying Li +1Tiny ML Energy-Efficient ML
School of Computing, National University of Singapore
Improving Autonomous Nano-drones Performance via Automated End-to-End Optimization and Deployment of DNNs
Jul 14, 2026Vlad Niculescu, Lorenzo Lamberti, Francesco Conti +2Efficient Neural Network Inference Aerial Robotics
Integrated Systems Laboratory - ETH Zürich, Switzerland · Department of Electrical, Electronic and Information Engineering - University of Bologna, Italy · Dalle Molle Institute for Artificial Intelligence - USI-SUPSI, Switzerland

May 11, 2026J/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

Robot Navigation

Explore similar work

Nano-U: Efficient Terrain Segmentation for Tiny Robot Navigation

Power-Performance Characterization of TinyML Systems

Improving Autonomous Nano-drones Performance via Automated End-to-End Optimization and Deployment of DNNs