# TIO-Former：基于流式因果 Transformer 的面向 Nano-UAVs 的超轻量级六方向 ToF-惯性里程计

> 原文链接：https://robotics.hellobike.com/papers/2026-09-15-2609-17198
> 频道：papers | 更新日期：2026-09-15 | 标签：arxiv, cs.RO
> 核心摘要：TIO-FORMER面向SWaP-C受限的nano-UAV自运动估计，融合六向ToF与IMU，并在真实飞行和边缘RISC-V上验证。

# TIO-Former：基于流式因果 Transformer 的面向 Nano-UAVs 的超轻量级六方向 ToF-惯性里程计

::: v-pre
> 原文链接：[TIO-Former: Ultra-Lightweight 6-Directional ToF-Inertial Odometry for Nano-UAVs via a Streaming Causal Transformer](https://arxiv.org/abs/2609.17198)（arXiv 2609.17198 · 发布日期：2026-09-15）

**TIO-Former: Ultra-Lightweight 6-Directional ToF-Inertial Odometry for Nano-UAVs via a Streaming Causal Transformer**

TIO-FORMER面向SWaP-C受限的nano-UAV自运动估计，融合六向ToF与IMU，并在真实飞行和边缘RISC-V上验证。

## 核心要点

- 视觉传感器和LiDAR受载荷限制，纯惯性易漂移，稀疏ToF估计6-DoF具挑战。
- 系统使用六个正交8×8 ToF阵列和IMU，结合双边门控差分与IMU引导交叉注意力。
- 流式因果Transformer结合Local KV与Chunk-FIFO记忆，约束长时推理成本和内存占用。
- 真实飞行中位置误差较光流降54.4%，较学习惯性基线降66.4%-89.1%，代码已开源。

**验证范围与局限**：验证范围包括真实飞行、多环境、严重感知退化测试及边缘RISC-V部署。

## 英文摘要 (Abstract)

Autonomous nano-UAV navigation requires accurate ego-motion estimation under stringent size, weight, power, and computing (SWaP-C) constraints, where visual sensors and LiDARs exceed payload limits, optical flow degrades in low-texture scenes, and inertial-only state estimation is susceptible to accumulated drift. While multi-zone time-of-flight (ToF) arrays provide a lightweight metric complement, 6-DoF estimation from merely 384 ranges per frame is challenged by invalid returns, anisotropic observability, and temporal computational scaling. We propose TIO-FORMER, a camera-free, optical-flow-free, and mapless range-inertial odometry framework driven by an IMU and an ultra-lightweight (15 g) payload of six orthogonal 8 x 8 ToF arrays. Our frontend pairs consecutive range grids with a bilateral gated difference, while IMU-guided cross-attention dynamically routes directional features conditioned on platform kinematics. A Streaming Causal Transformer couples an uncompressed Local KV cache with compressed Chunk-FIFO memory, maintaining bounded inference cost and memory footprint independent of flight duration. In real-flight evaluations, TIO-FORMER reduces open-loop position error by 54.4% compared to nano-UAV optical flow and by 66.4%-89.1% over learned inertial baselines. We also evaluate performance across multiple environments and robustness under severe sensing degradation. Deployed on an edge RISC-V companion computer, TIO-FORMER achieves a P95 latency of 10.466 ms and peak resident memory of 6.324 MiB (less than 5 percent system RAM), demonstrating that sparse range sensing provides practical geometric anchoring for resource-constrained micro-aerial robots. Code is available at https://github.com/Ly041021/TIO-Former.

作者：Yang Liu, Yifan He, Wenhao Zhao, Xiangyu Mo, Yang Xu, Hao Wei, Mingze Ma, Huan Li, Yifan Wu, Fei Gao
:::

## 原始参考来源 (Sources)

- [arXiv 2609.17198：TIO-Former: Ultra-Lightweight 6-Directional ToF-Inertial Odometry for Nano-UAVs via a Streaming Causal Transformer](https://arxiv.org/abs/2609.17198)