A self-supervised LiDAR odometry network trained with point-to-plane and plane-to-plane losses on 3D nearest-neighbour correspondences, needing no ground-truth poses, and tested on legged, tracked and wheeled platforms.

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。

DeLORA 的技術屬性
感測輸入Velodyne VLP-16 Puck Lite (ANYmal, Sec. IV-A)、Ouster OS1-64 (DARPA SubT Urban, Sec. IV-B)、KITTI odometry LiDAR (sensor model not named in the paper, Sec. IV-C)
原文測試平台legged (ANYmal)、tracked UGV (iRobot PackBot Explorer, DARPA SubT Urban Circuit dataset)、vehicle (KITTI)
狀態估計self-supervised CNN (ResNet-like blocks) regressing relative 6-DoF pose (translation + quaternion) from two spherical range images; poses optionally passed to the LOAM mapping module (Sec. III-B, IV-A)
資料關聯training only: 3D nearest-neighbour correspondences via KD-tree, with point-to-plane and plane-to-plane losses on PCA normals precomputed offline; inference uses the range image (x, y, z, range) only (Sec. III-C, III-D)
時間表示discrete poses (scan-to-scan)
去畸變原文未報告
迴圈閉合none
全域最佳化none
地圖表示none inside the method; maps in the experiments are built by the LOAM mapping module fed with DeLORA poses (Sec. IV-A, IV-B)
先驗資訊none at inference; training needs unlabelled scans from the target sensor or domain, no ground-truth poses (abstract, Sec. III)
可輸出幾何6-DoF relative poses; point-cloud maps only when combined with LOAM mapping (Figs. 3-4)
計算需求about 48 ms per prediction on an i7-8565U laptop CPU and 13 ms on a GeForce MX250 laptop GPU, with about 32,000 points, H = 16, W = 720 (Sec. IV-A)

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 VLP-16 Puck Lite歸入:Velodyne VLP-16方法輸入未標示mounted upright for the training missions and upside down for the test mission; range image H = 16, W = 720, about 32,000 points per scan(Nubert et al., 2021, Sec. IV-A)
LiDAROuster OS1-64資料集感測器DARPA SubT Challenge Urban Circuitcarried by a tracked robot at Satsop Business Park; Alpha course used for training, Beta course for testing(Nubert et al., 2021, Sec. IV-B)
載具平台ANYmal quadrupedal robot方法輸入未標示learning-based locomotion controller; autonomous exploration missions of about 250 m on average in the ETH Zurich CLA basement(Nubert et al., 2021, Sec. IV-A; Fig. 1)
載具平台iRobot PackBot Explorer (tracked robot)資料集感測器DARPA SubT Challenge Urban Circuittracked robot capable of fast in-spot yaw rotations(Nubert et al., 2021, Sec. IV-B)
運算硬體i7-8565U low-power laptop CPU執行運算平台未標示about 48 ms per prediction(Nubert et al., 2021, Sec. IV-A)
運算硬體GeForce MX250 laptop GPU執行運算平台未標示about 13 ms per prediction(Nubert et al., 2021, Sec. IV-A)

作者報告的優勢與限制

優勢

限制

營建工程相關證據

在 ETH Zürich 建物地下室的長廊(類隧道)以 ANYmal 足式機器人測試,並使用 DARPA SubT Urban Circuit 資料(Satsop Business Park 的核電廠設施);後者有地圖真值,但比較只作定性呈現。未在營建工地測試,也沒有以獨立量測評估點雲幾何精度。

原文驗證環境:已完工建築、基礎設施、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 44 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。

Nubert et al., 2021 · Table I 本方法 12 筆

表格設定(擷取紀錄原文):ANYmal test mission (LiDAR mounted upside down); relative pose deviation of DeLORA poses combined with the LOAM mapping module against the open-source LOAM implementation, which serves as reference because no external ground truth was available (Nubert et al., 2021, Table I)

t_rel [%] relative translation deviation vs LOAM,ANYmal CLA basement (own data) · test mission, segment length 5 m

這張表在此指標與資料序列只列出本方法一筆,沒有可並列的其他方法,因此不畫圖,數值與出處見下表。這是 Nubert et al., 2021 在此表設定下報告的數值(author-reported results),不代表方法在其他資料或設定下的表現。

統計量:原文未報告;對齊方式:原文未報告;單位:%;場景:indoor building basement with long tunnel-like corridors

數值與出處
方法(原文寫法)報告值出處
Ours with mapping (DeLORA + LOAM mapping module)本方法原文提出0.345%(Nubert et al., 2021, Table I)

Nubert et al., 2021 · Table II 本方法 12 筆

表格設定(擷取紀錄原文):KITTI odometry, errors over all subsequences of 100 to 800 m; DeLORA trained self-supervised on 00-08, tested on 09 and 10; only the 00-08 mean of LO-Net and Velas et al. was adapted by the authors because those were trained on 00-06 (Nubert et al., 2021, Table II)

t_rel [%],KITTI odometry · Training 00-08 (mean)

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 Nubert et al., 2021 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:未對齊;單位:%;場景:outdoor urban driving (car)

資料來源作者報告值(Nubert et al., 2021, Table II)

數值與出處
方法(原文寫法)報告值出處
Ours本方法原文提出3%(Nubert et al., 2021, Table II)
Ours+Map (LOAM scan-to-map refinement)本方法原文提出1.78%(Nubert et al., 2021, Table II)
DeepLO [24]3.68%(Nubert et al., 2021, Table II)
LO-Net [21]1.27%(Nubert et al., 2021, Table II)
Velas et al. [20]2.94%(Nubert et al., 2021, Table II)
UnDeepVO [8]4.54%(Nubert et al., 2021, Table II)
SfMLearner [22]28.52%(Nubert et al., 2021, Table II)
Zhu et al. [23]5.72%(Nubert et al., 2021, Table II)
LO-Net+Map0.81%(Nubert et al., 2021, Table II)
SUMA [13]3.06%(Nubert et al., 2021, Table II)
LOAM [3]1.26%(Nubert et al., 2021, Table II)

Nubert et al., 2021 · Table III 本方法 8 筆

表格設定(擷取紀錄原文):Loss ablation on KITTI, networks trained from scratch on 00-06 and tested on 07-10 (Nubert et al., 2021, Table III)

t_rel [%],KITTI odometry · Training 00-06

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 Nubert et al., 2021 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:未對齊;單位:%;場景:outdoor urban driving (car)

資料來源作者報告值(Nubert et al., 2021, Table III)

數值與出處
方法(原文寫法)報告值出處
DeLORA loss variant: p2pl + pl2pl本方法原文提出3.41%(Nubert et al., 2021, Table III)
DeLORA loss variant: p2pl本方法原文提出6.47%(Nubert et al., 2021, Table III)

Deng et al., 2023 · Table 3 本方法 4 筆

指標RMSE of ATE (SE(3) alignment)

表格設定(擷取紀錄原文):Odometry ATE RMSE with SE(3) alignment (Sec. 5.1); '-' means failed; unit not stated; DeLORA and PWC-LONet are pre-trained on KITTI (Deng et al., 2023, Table 3)

RMSE of ATE (SE(3) alignment),MaiCity · Mai00

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 Deng et al., 2023 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:SE(3) 剛體對齊;單位:not stated;場景:synthetic urban street (simulated 64-beam LiDAR)

資料來源作者報告值(Deng et al., 2023, Table 3)

數值與出處
方法(原文寫法)報告值出處
ICP [3] (point-to-point)1.9(Deng et al., 2023, Table 3)
GICP [31]1.24(Deng et al., 2023, Table 3)
Puma [36]0.25(Deng et al., 2023, Table 3)
SuMA [2]2.01(Deng et al., 2023, Table 3)
DeLORA [26]本方法57.57(Deng et al., 2023, Table 3)
PWC-LONet [39]3.28(Deng et al., 2023, Table 3)
Ours原文提出1.27(Deng et al., 2023, Table 3)

其他比較組

列出其餘 4 個比較組

來源

  • Nubert et al., 2021

    Julian Nubert, Shehryar Khattak, Marco Hutter(2021)Self-supervised Learning of LiDAR Odometry for Robotic Applications2021 IEEE International Conference on Robotics and Automation (ICRA), Xi'an, China, pp. 9601-9607

    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