发表机构
Zhejiang University; Differential Robotics（浙江大学; 微分机器人）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TIO-Former提出一种基于流式因果Transformer的超轻量ToF-惯性里程计，利用15克六正交ToF阵列，在纳米无人机上实现高精度、低延迟的自我运动估计，显著降低位置误差。
AI 中文摘要
自主纳米无人机导航要求在严格的尺寸、重量、功耗和计算（SWaP-C）约束下进行准确的自我运动估计，其中视觉传感器和激光雷达超出有效载荷限制，光流在低纹理场景中性能下降，而仅依赖惯性的状态估计易受累积漂移影响。虽然多区域飞行时间（ToF）阵列提供了轻量级的度量补充，但仅从每帧384个距离值进行六自由度（6-DoF）估计面临无效返回、各向异性可观测性和时间计算扩展等挑战。我们提出TIO-FORMER，一种无相机、无光流、无地图的距离-惯性里程计框架，由IMU和超轻量（15克）的六个正交8×8 ToF阵列有效载荷驱动。我们的前端将连续距离网格与双边门控差分配对，而IMU引导的交叉注意力根据平台运动学动态路由方向特征。流式因果Transformer将未压缩的局部KV缓存与压缩的Chunk-FIFO内存耦合，保持与飞行时长无关的有界推理成本和内存占用。在真实飞行评估中，与纳米无人机光流相比，TIO-FORMER将开环位置误差降低了54.4%，与学习型惯性基线相比降低了66.4%-89.1%。我们还评估了在多种环境下的性能以及在严重传感退化下的鲁棒性。部署在边缘RISC-V协处理器上，TIO-FORMER实现了P95延迟10.466毫秒和峰值常驻内存6.324 MiB（小于系统RAM的5%），表明稀疏距离传感为资源受限的微型飞行机器人提供了实用的几何锚定。代码可在该https URL获取。
英文摘要
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.
