AI 中文总结
研究提出DINS-IO，直接从原始IMU流学习惯性里程计。利用INS速度递推约束，转化为滑动窗口最小二乘问题求解，以残差为自监督损失。设计高频网络并校准速度，在标准基准测试中，预训练自监督并微调的DINS-IO表现出色。
AI 中文摘要
学习惯性里程计的训练依赖于来自运动捕捉、视觉惯性里程计或同步定位与地图构建（SLAM）的密集、高精度位置真值，获取成本高且难以规模化。我们提出DINS-IO，它能直接从原始惯性测量单元（IMU）数据流中学习惯性里程计，无需位置标签。关键在于捷联惯性导航系统（INS）速度递推是一个强大的、完全可微的一致性先验。我们将此约束转化为具有全局共享偏差的滑动窗口最小二乘问题并闭式求解，用求解器残差作为自监督损失。设计高频网络以提供样本约束，还通过直接监督预测的体坐标系速度并仅调整低秩补丁将其校准到真实度量速度。在标准基准测试中，预训练自监督并使用少量标签微调的DINS-IO与完全监督基线相当或更优。
英文摘要
The training of learned inertial odometry depends on dense, high-precision position ground truth from motion capture, visual-inertial odometry or SLAM, which is costly and hard to acquire at scale. We propose DINS-IO, which learns inertial odometry directly from raw IMU streams without position labels. Our key insight is that the strapdown INS velocity recursion is a strong, fully differentiable consistency prior: the predicted velocity, rotated into the navigation frame, must agree with the integrated specific force up to an unknown initial velocity and a constant accelerometer bias. We cast this constraint as a sliding-window least-squares problem with a globally shared bias, solve it in closed form, and use the solver residual as a self-supervised loss whose gradient flows back to the network through the analytic solution. To supply this per-sample constraint, we design a high-frequency network that emits dense body-frame velocity at the IMU rate. Since the self-supervised network learns consistent motion but its velocity is not yet metrically calibrated, we calibrate it to true metric velocity from a few labeled trajectories by directly supervising the predicted body-frame velocity and adapting only low-rank (LoRA) patches. On standard benchmarks, DINS-IO pretrained self-supervised and fine-tuned with a small fraction of labels matches or surpasses fully supervised baselines.
