Detects 6-DoF degeneracy of feature-based LiDAR odometry in tunnels from the covariance of the rotation and translation blocks, and fuses a SuperPoint and LightGlue visual-inertial odometry only along the degenerate directions through a conditional EKF.

技術屬性

欄位內容為文獻擷取紀錄的原文用語(英文),以原文為據;「未查證」表示本研究尚未讀到該資訊,不代表該方法不具備此能力。

Deep feature-enhanced LVIO (tunnel) 的技術屬性
感測輸入3D LiDAR (mechanical spinning model assumed in the LO derivation; Velodyne on KMCT, Livox on WHU-Helmet)、camera (Intel RealSense D455 RGB-D on KMCT; helmet cameras on WHU-Helmet)、IMU (preintegrated in the VIO)
原文測試平台no own platform; offline evaluation on public datasets recorded by Clearpath Jackal ground robots (KMCT) and a helmet-mounted rig (WHU-Helmet)
狀態估計Conditional EKF: LiDAR odometry runs continuously; when covariance-based detection flags degenerate rotation or translation directions, a selection matrix keeps only the visual-inertial information along those directions and the state is updated with a FAST-LIO style Kalman gain; the VIO itself has no back-end optimization (Secs. 3.2, 3.3)
資料關聯LiDAR: curvature from five horizontal neighbours on each side separates edge and planar points, matched point-to-line and point-to-plane to global feature maps and solved by Gauss-Newton; degeneracy from eigen-decomposition of the rotation and translation blocks of the inverted information matrix against empirical thresholds; visual: SuperPoint features with an adaptive score threshold and LightGlue matching inside an ORB-SLAM3 style tracking thread (Secs. 3.1 to 3.2)
時間表示discrete scan poses; constant-velocity camera prediction; IMU preintegration between frames with high-rate IMU propagation of the output pose (Secs. 3.1.1, 3.2)
去畸變linear interpolation of the inter-scan transform across the sweep by point index (Eq. 3, Sec. 3.1.1)
迴圈閉合none; the authors argue loop closure is often infeasible in tunnels and choose an odometry design (Secs. 2.3, 3.3.1)
全域最佳化none (no factor graph or bundle adjustment)
地圖表示point cloud map built by accumulating registered scans, with global edge and planar feature maps used for matching (Secs. 3, 3.1.1)
先驗資訊none (official pre-trained SuperPoint and LightGlue models; no prior map)
可輸出幾何dense LiDAR point cloud map evaluated by Mean Map Entropy (local consistency only) and, on one KMCT sequence, by voxel error against the ground-truth map (Secs. 4.2.2, 4.3, Fig. 9)
計算需求Intel i9-12900H CPU, NVIDIA 3070 Ti GPU, 32 GB RAM, Ubuntu 20.04 with CUDA, cuDNN and ONNX inference: 25.4 to 29.0 ms per frame in total (VIO about 20 to 23 ms, LO about 5 to 6 ms, EKF about 0.1 ms) versus 28.8 to 35.8 ms for R3LIVE++ and 49.7 to 67.6 ms for LVI-SAM (Table 5)

使用設備

原文使用的感測器、運算硬體與載具(equipment)。型號保留原文寫法,連結到設備頁中同一型號的歸併名稱;角色依原文用途分為方法輸入、資料集感測器、執行運算平台、參考或真值量測(reference or ground truth)與比較對象設備。

原文使用的設備
類別型號(原文寫法)角色資料集原文規格出處
LiDARVelodyne LiDAR (model 原文未報告)資料集感測器Kimera-Multi Campus-Tunnel (KMCT)原文未報告(Yan et al., 2026a, Sec. 4.1)
LiDARLIVOX LiDAR (model 原文未報告)資料集感測器WHU-Helmet (WHUH)原文未報告(Yan et al., 2026a, Sec. 4.1)
慣性量測單元(IMU)IMU (model 原文未報告)歸入:IMU (model not reported)資料集感測器WHU-Helmet (WHUH)原文未報告(Yan et al., 2026a, Sec. 4.1)
GNSS 接收器GNSS receiver (model 原文未報告)歸入:GNSS (receiver model not reported)資料集感測器WHU-Helmet (WHUH)原文未報告(Yan et al., 2026a, Sec. 4.1)
相機cameras (models 原文未報告)資料集感測器WHU-Helmet (WHUH)Tunnel sequence 12,304 images in 1403 s; Subway 15,685 images in 1580 s(Yan et al., 2026a, Sec. 4.1)
RGB-D 相機Intel RealSense D455資料集感測器Kimera-Multi Campus-Tunnel (KMCT)RGB-D camera on each robot(Yan et al., 2026a, Sec. 4.1)
載具平台Clearpath Jackal mobile robots (eight)資料集感測器Kimera-Multi Campus-Tunnel (KMCT)collectively travelled 6753 m in about 30 min in the MIT campus tunnel(Yan et al., 2026a, Sec. 4.1)
載具平台helmet (per the dataset name and the title of ref. [21])資料集感測器WHU-Helmet (WHUH)Wuhan University helmet-based multisensor dataset(Yan et al., 2026a, Sec. 4.1, ref. [21])
運算硬體Intel i9-12900H CPU with NVIDIA 3070 Ti執行運算平台未標示32 GB RAM, Ubuntu 20.04, CUDA 11.3, cuDNN 8.9.6, ONNX 1.16.3(Yan et al., 2026a, Sec. 4.1)

作者報告的優勢與限制

優勢

限制

營建工程相關證據

論文以隧道營運維護與機器人巡檢為應用情境(摘要與引言明確提及營運維護),刊於本文目標期刊。驗證資料為 MIT 校園地下隧道(KMCT,八台 Clearpath Jackal 機器人,總長 6753 m)與 WHU-Helmet 的 Tunnel(790.32 m)與 Subway(854.24 m)序列,並非施工中隧道;作者未自行蒐集資料,軌跡真值由資料集提供,參考量測方式未在文中說明。

原文驗證環境:地下或隧道、公開基準

報告的性能數據

以下是原文作者報告的性能數值(author-reported results),不是本研究重新量測的結果。每張圖只並列同一個比較組(comparison group,同一張表、同一組實驗設定)內的方法;不同比較組之間的數值不可直接比較,也不構成排名。

本方法共出現在 8 個比較組,合計 35 筆紀錄。以下列出本方法紀錄最多的 4 組,其餘 4 組列在最後,並連到性能比較頁。

Yan et al., 2026a · Table 1 本方法 9 筆

表格設定(擷取紀錄原文):ATE (RMSE, m) on KMCT; each ROS bag run five times and the best trial reported; 'Failed' = failure to run (Yan et al., 2026a, Table 1)

ATE (m), RMSE of global absolute trajectory error,Kimera-Multi Campus-Tunnel (KMCT) · 07_ac2-005

只並列這張表在相同設定下報告的方法;以「本方法:」開頭者為本頁方法。失敗、未執行與未報告以標記呈現,不是 0。

  • 失敗

按 Tab 進入圖表後,用上下方向鍵逐一瀏覽各類別,Esc 關閉提示框;也可開啟表格檢視閱讀全部數值。

這些是 Yan et al., 2026a 在此表設定下報告的數值(author-reported results),只能在同一個比較組內對照,不代表方法在其他資料或設定下的表現。

統計量:均方根誤差(RMSE);對齊方式:原文未報告;單位:m;場景:MIT campus subterranean tunnel, long and uniform (Kimera-Multi Campus-Tunnel; eight Clearpath Jackal robots, 6753 m in about 30 min)

資料來源作者報告值(Yan et al., 2026a, Table 1)

數值與出處
方法(原文寫法)報告值出處
ORB-SLAM3無數值失敗註記(擷取紀錄):failed(Yan et al., 2026a, Table 1)
VINS-Mono3.96 m(Yan et al., 2026a, Table 1)
LeGO-LOAM3.63 m(Yan et al., 2026a, Table 1)
LIO-SAM3.41 m(Yan et al., 2026a, Table 1)
Fast-LIO22.7 m(Yan et al., 2026a, Table 1)
LVI-SAM2.77 m(Yan et al., 2026a, Table 1)
COIN-LIO2.71 m(Yan et al., 2026a, Table 1)
VINS-FEN3.05 m(Yan et al., 2026a, Table 1)
Proposed本方法原文提出2.89 m(Yan et al., 2026a, Table 1)

Yan et al., 2026a · Table 5 本方法 9 筆

指標Time consumption (ms)

表格設定(擷取紀錄原文):Time consumption per frame; proposed method component times (VIO, LO, EKF) not extracted, only their sum (Yan et al., 2026a, Table 5)

Time consumption (ms),Kimera-Multi Campus-Tunnel (KMCT) · ac2-005

只並列這張表在相同設定下報告的方法;以「本方法:」開頭者為本頁方法。失敗、未執行與未報告以標記呈現,不是 0。

按 Tab 進入圖表後,用上下方向鍵逐一瀏覽各類別,Esc 關閉提示框;也可開啟表格檢視閱讀全部數值。

這些是 Yan et al., 2026a 在此表設定下報告的數值(author-reported results),只能在同一個比較組內對照,不代表方法在其他資料或設定下的表現。

統計量:平均值(mean);對齊方式:不適用;單位:ms

資料來源作者報告值(Yan et al., 2026a, Table 5)

數值與出處
方法(原文寫法)報告值出處
This work (Sum of VIO, LO and EKF)本方法原文提出硬體:Intel i9-12900H CPU, NVIDIA 3070 Ti, 32 GB RAM, Ubuntu 20.0427.51 ms(Yan et al., 2026a, Table 5)
LVI-SAM硬體:Intel i9-12900H CPU, NVIDIA 3070 Ti, 32 GB RAM, Ubuntu 20.0451.36 ms(Yan et al., 2026a, Table 5)
R3LIVE++硬體:Intel i9-12900H CPU, NVIDIA 3070 Ti, 32 GB RAM, Ubuntu 20.0430.53 ms(Yan et al., 2026a, Table 5)

Yan et al., 2026a · Table 6 本方法 6 筆

資料集與序列Kimera-Multi Campus-Tunnel (KMCT) · Average (3 sequences)

表格設定(擷取紀錄原文):Ablation of deep-feature VIO and CEKF; averages over KMCT 07_api-003, 07_sob-002 and 07_spl-007; per-sequence rows not extracted (Yan et al., 2026a, Table 6)

Average ATE (m),Kimera-Multi Campus-Tunnel (KMCT) · Average (3 sequences)

只並列這張表在相同設定下報告的方法;以「本方法:」開頭者為本頁方法。失敗、未執行與未報告以標記呈現,不是 0。

按 Tab 進入圖表後,用上下方向鍵逐一瀏覽各類別,Esc 關閉提示框;也可開啟表格檢視閱讀全部數值。

這些是 Yan et al., 2026a 在此表設定下報告的數值(author-reported results),只能在同一個比較組內對照,不代表方法在其他資料或設定下的表現。

統計量:均方根誤差(RMSE);對齊方式:原文未報告;單位:m;場景:MIT campus subterranean tunnel, long and uniform (Kimera-Multi Campus-Tunnel; eight Clearpath Jackal robots, 6753 m in about 30 min)

資料來源作者報告值(Yan et al., 2026a, Table 6)

數值與出處
方法(原文寫法)報告值出處
Standard VIO + Base (VINS-Mono front end)本方法1.84 m(Yan et al., 2026a, Table 6)
Base + EKF (standard EKF without selection)本方法1.59 m(Yan et al., 2026a, Table 6)
Proposed method本方法原文提出1.24 m(Yan et al., 2026a, Table 6)

Yan et al., 2026a · Table 2 本方法 4 筆

表格設定(擷取紀錄原文):ATE (RMSE, m) on WHU-Helmet with dataset ground-truth trajectory; LiDAR baselines use variants adapted to the Livox configuration; 'Failed' = failure to run (Yan et al., 2026a, Table 2)

ATE (m),WHU-Helmet (WHUH) · Tunnel

只並列這張表在相同設定下報告的方法;以「本方法:」開頭者為本頁方法。失敗、未執行與未報告以標記呈現,不是 0。

  • 失敗

按 Tab 進入圖表後,用上下方向鍵逐一瀏覽各類別,Esc 關閉提示框;也可開啟表格檢視閱讀全部數值。

這些是 Yan et al., 2026a 在此表設定下報告的數值(author-reported results),只能在同一個比較組內對照,不代表方法在其他資料或設定下的表現。

統計量:均方根誤差(RMSE);對齊方式:原文未報告;單位:m;場景:WHU-Helmet Tunnel sequence, 790.32 m, 1403 s

資料來源作者報告值(Yan et al., 2026a, Table 2)

數值與出處
方法(原文寫法)報告值出處
ORB-SLAM35.92 m(Yan et al., 2026a, Table 2)
VINS-Mono無數值失敗註記(擷取紀錄):failed(Yan et al., 2026a, Table 2)
LOAM無數值失敗註記(擷取紀錄):failed(Yan et al., 2026a, Table 2)
BALM4.53 m(Yan et al., 2026a, Table 2)
LIO-Mapping5.95 m(Yan et al., 2026a, Table 2)
Fast-LIO24.21 m(Yan et al., 2026a, Table 2)
R3live++5.3 m(Yan et al., 2026a, Table 2)
COIN-LIO4.05 m(Yan et al., 2026a, Table 2)
VINS-FEN4.39 m(Yan et al., 2026a, Table 2)
This work本方法原文提出4.04 m(Yan et al., 2026a, Table 2)

其他比較組

列出其餘 4 個比較組

來源

  • Yan et al., 2026a

    Yi Yan, Limao Zhang, Qingqing Ye, Zhaoxiang Zhang, Minghui Sun(2026)Deep feature-enhanced LiDAR-visual-inertial odometry for robust mapping in tunnel environmentAutomation in Construction, 184: 106825

    同儕審查已出版已讀全文近十年查證後修正

回到方法圖鑑

選擇開啟Esc關閉