轻量级模型让微型机器人在户外地形中高效识别路径
Nano-U: Efficient Terrain Segmentation for Tiny Robot Navigation
- 设计仅数千参数的极简二值分割网络Nano-U
- 量化感知蒸馏使模型在两个数据集上表现优异
- 编译器部署实现低内存低延迟，适合低成本机器人
地形分割是自主移动机器人在非结构化户外环境中运行的基础能力。然而，现有先进模型不兼容微控制器常见的内存与计算约束，限制了小型机器人平台的大规模部署。为此，我们开发了一个完整的框架，在低成本微控制器上实现鲁棒的二值地形分割。核心是设计了参数仅数千的极小二值分割网络Nano-U。为弥补网络容量不足，采用量化感知蒸馏（QAD）训练，结合知识蒸馏与量化感知训练。最终量化模型在Botanic Garden数据集和自建的更复杂农田数据集TinyAgri上均表现良好。通过扩展基于Rust的编译器推理引擎MicroFlow，将量化后的Nano-U部署于ESP32-S3微控制器。通过消除解释器开销和动态内存分配，模型以极小内存占用和低延迟运行，验证了编译器执行在低成本机器人感知中的可行性和能效优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。