Pith. sign in

REVIEW 3 major objections 4 minor 13 cited by

GrandTour is the largest public legged-robot dataset to date, pairing 49 missions with survey-grade ground truth and a 52-method benchmark.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · deepseek-v4-flash

2026-08-02 21:59 UTC pith:EDLAMBM7

load-bearing objection GrandTour is the legged-SLAM dataset the community needs, but the ground-truth validation on GNSS-denied missions is self-consistency, not absolute accuracy, so the benchmark rankings on ARC-2/ARC-7 inherit unquantified drift. the 3 major comments →

arxiv 2602.18164 v3 pith:EDLAMBM7 submitted 2026-02-20 cs.RO

GrandTour: A Legged Robotics Dataset in the Wild for Multi-Modal Perception and State Estimation

Turcan Tuna , Jonas Frey , Frank Fu , Katharine Patterson , Tianao Xu , Maurice Fallon , Cesar Cadena , Marco Hutter This is my paper
classification cs.RO
keywords legged roboticsmulti-modal datasetstate estimationSLAM benchmarkmulti-sensor fusionLiDAR-inertial odometryvisual-inertial odometryground truth
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

GrandTour sets out to give legged-robotics research what large earlier datasets gave driving and aerial vehicles: a shared, open collection of real-world, time-synchronized sensor data plus reference trajectories accurate enough to benchmark state-estimation methods. The paper claims it is the largest legged-robot dataset to date—49 missions, more than ten kilometers of walking, and over five hours of data, spanning alpine, forest, urban, industrial, indoor, and underground environments. The dataset pairs multiple LiDARs, ten cameras, depth cameras, eight IMUs, and full joint/proprioceptive feedback with ground truth from a robotic total station and RTK-GNSS, fused to millimeter-level accuracy. On six representative missions the authors evaluate 52 open-source odometry and SLAM pipelines, reporting per-mission ATE/RTE, ranks, and failures. If the claim holds, this becomes a reference benchmark for legged state estimation, multi-modal fusion, and perception in hard outdoor and indoor conditions.

Core claim

The central claim is that GrandTour is the largest, most comprehensively instrumented public legged-robot dataset to date, and that its survey-grade reference trajectories make it a trustworthy benchmark. The supporting discovery is that centimeter-to-millimeter-level ground truth can be produced under real-field legged locomotion by combining total-station prism tracking, post-processed GNSS/INS, and a high-grade IMU in a factor-graph fusion, and that this reference is good enough to separate 52 open-source odometry/SLAM systems into meaningful rankings with clear failure cases.

What carries the argument

The load-bearing mechanism is the sensor payload plus its calibration and time-synchronization chain: all sensors share a common time source (sub-millisecond for most streams), extrinsics are calibrated to 0.05 mm mechanical tolerance and validated by point-cloud-to-image overlays, and ground-truth poses are generated by factor-graph fusion of total-station 20 Hz positions, post-processed GNSS/INS poses, and IMU measurements—producing a 20 Hz reference trajectory that follows the total station when line of sight exists and bridges occlusions with inertial/GNSS propagation.

Load-bearing premise

The reference trajectories are assumed to remain accurate in the portions of a mission where the total station loses line of sight and GNSS is absent, because those gaps are bridged by inertial/GNSS dead-reckoning; if that drift is larger than the few-centimeter gaps between competing methods, the benchmark's rankings on those segments are not reliable.

What would settle it

Take the missions with no GNSS and less than half total-station coverage, re-derive the reference trajectory using only the raw total-station fixes with no inertial propagation, and recompute ATE/RTE for the top-ranked methods; if the rank order changes materially beyond a few centimeters, the ground-truth accuracy and the resulting rankings on those missions are falsified.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Odometry and SLAM researchers get a common legged-robot test bed with 52 pre-run baselines, per-mission ATE/RTE ranks, and documented failure cases, so new methods can be compared without re-tuning every competitor.
  • Multi-modal fusion can be studied under real legged dynamics—foot contacts, slipping, body orientation changes—with synchronized LiDAR, camera, depth, IMU, and joint-encoder data on a single platform.
  • The benchmark's finding that no method dominates across missions, while visual-inertial systems fail most often on dark or featureless sequences, argues for evaluation protocols that emphasize robustness and recovery rather than mean error alone.
  • Intermediate outputs such as motion-compensated point clouds, leg odometry, terrain maps, and occupancy maps lower the entry barrier for perception, locomotion, and navigation research that does not want to build a full SLAM front end.
  • Survey-grade total-station ground truth, synchronized to sub-millisecond accuracy, makes it possible to test whether claimed improvements of a few centimeters are real or within reference noise.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If GrandTour is adopted the way earlier large datasets were, it could become the default comparison point for legged state estimation, shifting the field's focus from single-metric gains toward cross-mission robustness, initialization, and failure recovery.
  • The millimeter-level ground-truth claim is only as strong as the reference in GNSS-denied, line-of-sight-blocked segments; an independent check there, such as loop-closure-based map consistency or total-station-only interpolation, would show whether the published rankings survive.
  • Because the suite includes cross-view images and dense geometry from a moving quadruped, it is a natural testbed for learned depth, relocalization, and neural scene representation, going beyond the paper's own state-estimation benchmark.
  • A direct stress test would be to run the same benchmark on the lowest-coverage missions with a reference re-derived without dead-reckoning; if method rankings change drastically, the dataset's ranking protocol should be refined.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

3 major / 4 minor

Summary. This paper introduces GrandTour, a 49-mission legged-robotics dataset collected with an ANYmal-D quadruped carrying the Boxi sensor payload. The dataset provides synchronized multi-modal data (three LiDARs, ten cameras, seven IMUs, depth cameras, proprioception, GNSS/INS) and ground-truth trajectories derived from dual-antenna RTK-GNSS with Inertial Explorer post-processing, a Leica MS60 total station, and Holistic Fusion factor-graph integration. The authors also present a localization benchmark on six missions in which 52 open-source odometry/SLAM pipelines are evaluated with ATE/RTE metrics and per-mission ranks. The central claims are that GrandTour is the largest legged-robot dataset to date, that it achieves millimeter-level ground-truth accuracy with sub-millisecond synchronization, and that the accompanying benchmark provides a rigorous cross-method comparison.

Significance. The dataset is potentially a major community resource: it combines a rich sensor suite, substantial environmental diversity, a detailed calibration chain with concrete validation artifacts (3 mm cross-camera prism consistency, LiDAR-camera overlays in Fig. 5), and an unusually detailed evaluation protocol. The open release in both Zarr and ROS formats, with derived outputs and conversion tools, is a genuine strength. If the ground-truth accuracy on low-coverage segments can be rigorously established, this would be a KITTI-class benchmark for quadruped state estimation and perception. However, the current validation of the ground-truth generation is self-referential on exactly the segments where benchmark rankings are decided, which tempers the 'millimeter-level' and '52-method benchmark' claims until the issue is addressed.

major comments (3)
  1. [Sec. 4.2, Eq. (1), Tables 3–4, 8–11, Fig. 10] The ground-truth validation is self-referential on the segments that matter most. TPS positions are factors in the Holistic Fusion graph (Eq. 1), so the reported 0.0028 m mean ATE against raw TPS measures self-consistency, not absolute accuracy between fixes. When the MS60 line of sight is lost, the graph retains Inertial Explorer unary poses and the HG4930 IMU, i.e., dead-reckoning; the text states that this 'lead[s] to drift accumulation,' and Table 4 gives 0.11 m horizontal position RMS for a 60 s GNSS outage. On benchmark missions ARC-2 (27.3% MS60 coverage), ARC-7 (35.8%, no GNSS), and CON-4 (67.1%, no GNSS), TPS gaps of tens of seconds are the norm due to the re-lock procedure (Fig. 10), so GT on those arcs can plausibly drift to the decimeter level. Since ATE/RTE separations among top LIO/LIVO methods on ARC-2/ARC-7 are about 1–8 cm (Table 9), the per-mission ranks and any 'millim
  2. [Abstract, Sec. 2.3, Sec. 9] The 'millimeter-level accuracy' claim is overgeneralized. The 2.8 mm validation is shown only on the SPX-2 sequence of Fig. 9; the text does not state whether the aggregate numbers cover all missions or a single representative one. No per-mission validation against an independent reference is provided for the 49 missions, many of which have far lower MS60 coverage (e.g., 18.8%, 20.3%, 23.6%, 27.3%). Please replace the global claim with a quantified statement of GT accuracy as a function of coverage, or restrict it to segments where it is actually supported.
  3. [Sec. 7.1.2, Tables 8–11, Eqs. (2)–(3)] The ordinal benchmark claims would benefit from uncertainty quantification. The text itself notes that many methods are separated by 'a few millimeters to about a centimeter in RTE and a few centimeters in ATE, often comparable to the reported standard deviations,' yet summary ranks (Eq. 3) and statements such as 'Coco-LIC and FAST-LIVO2 obtain the best average ranks' are reported without confidence intervals or significance tests. Given the GT uncertainty on low-coverage missions identified above, rank instability is a real risk. Please provide error bars, bootstrap/permutation intervals, or a sensitivity analysis with respect to GT perturbations.
minor comments (4)
  1. [Sec. 7.1 intro] The list reads '1) State Estimation and localization (Sec. 7.1), 1) Perception (Sec. 7.2), and 3) Locomotion & Navigation'; the second '1)' should be '2)'.
  2. [Table 2, Sec. 7.1.2] Typo: 'Intertial Explorer' in Table 2; also 'HF4930 IMU' in Sec. 7.1.2 should be 'HG4930 IMU'.
  3. [Table 3 / Fig. 7] The GNSS column uses 'Yes/No/Partially' but Fig. 7 only distinguishes Yes/No. Please define 'Partially' and explain how it is counted in the figure.
  4. [Sec. 4.2] Terminology is inconsistent: 'dual RTK-GPS' (Sec. 2.3), 'dual-antenna RTK GNSS' (Sec. 3.1), and 'NovAtel SPAN CPT7' should be unified to avoid confusion about the GNSS receiver/INS.

Circularity Check

1 steps flagged

Circular GT validation: Holistic Fusion is evaluated against the same TPS positions it consumes as factor-graph inputs, so the 2.8 mm ATE is a fit residual, not independent evidence of millimeter-level ground truth.

specific steps
  1. fitted input called prediction [Sec. 4.2, 'Holistic Fusion Ground Truth', Eq. (1) and validation paragraph]
    "Holistic Fusion ... enables the fusion of TPS position measurements, Inertial Explorer post-processed poses, and HG4930 IMU measurements. ... When compared against the raw TPS position measurements, ATE for Holistic Fusion is a mean of 0.0028 m with standard deviation (σ) of 0.0020 m and RMSE 0.0034 m, whereas the Inertial Explorer tightly coupled solution yields a mean ATE of 0.132 m with σ=0.0721 m and RMSE 0.1504 m."

    The MAP estimate X* = arg max p(X|Z) in Eq. (1) uses the TPS position measurements as input factors, along with IE unary poses and IMU data. Reporting ATE/RMSE of Holistic Fusion against those same raw TPS positions therefore measures how well the graph fit its own factors, not absolute trajectory accuracy. The graph also estimates alignment-transform context variables, which can absorb static frame errors, further reducing the residual. The quoted 2.8 mm ATE / 3.4 mm RMSE is thus a self-consistency residual, yet it is used to support the paper's 'millimeter-level accuracy' ground-truth claim. The comparison to Inertial Explorer is not independent either, since IE post-processed poses are also inputs to the same graph. No independent bound is provided for the GNSS-denied / TPS-occluded seg

full rationale

The single concrete circular step is in Sec. 4.2: Holistic Fusion consumes TPS position measurements as factors in its factor graph, and the paper then validates Holistic Fusion against those same raw TPS measurements, reporting a mean ATE of 0.0028 m. This is a fit residual, not an external accuracy check, so it cannot independently support the abstract/Sec. 2.3 claim of 'millimeter-level accuracy.' The paper itself acknowledges that periods without both MS60 and Inertial Explorer unary poses require 'IMU-only dead-reckoning, leading to drift accumulation,' and Table 4 allows 0.11 m position error over a 60 s GNSS outage. On benchmark missions such as ARC-2 and ARC-7, where MS60 coverage is only 27.3% and 35.8%, Table 9 ranks methods separated by roughly 1–8 cm ATE; a 5–10 cm GT drift over multi-second-to-minute TPS outages is at the scale of those rankings. The stated GT restriction to segments with 'Inertial Explorer pose availability or MS60 measurements' is not a meaningful quality gate because IE emits poses continuously, including during GNSS-denied coasting. This is a partial circularity affecting the central GT-accuracy evidence. The dataset release, calibration chain, and 52-method benchmark are nevertheless substantial and mostly independent, so the overall score is 6 rather than higher.

Axiom & Free-Parameter Ledger

4 free parameters · 5 axioms · 0 invented entities

The paper's central value is empirical. Everything load-bearing is either instrument accuracy taken on vendor authority, fusion weights inherited from the authors' prior library, or evaluation thresholds chosen by hand. These are reasonable for a dataset paper, but they mean the 'millimeter-level' and 'comprehensive benchmark' claims are not fully self-contained. No new physical entities are postulated; Boxi, Kleinkram, and the AP20-IMU are engineered hardware/software artifacts documented elsewhere, not new forces, particles, or conserved quantities.

free parameters (4)
  • Holistic Fusion factor-graph weights and covariances = not disclosed (inherited from Nubert et al., 2025)
    The 2.8 mm ATE ground-truth quality claim depends on how TPS, Inertial Explorer, and IMU factors are weighted in Eq. (1); the values are not given in this paper and are set by the authors' own prior work.
  • Trajectory association threshold t_max_diff = 0.5 × median(Δt_dense) ≈ 0.025 s for a 20 Hz reference
    Hand-set in Sec. 7.1; changes which estimate/reference pairs are compared and thus affects all benchmark numbers.
  • RTE path-length increment Δ = 0.5 m
    Hand-set based on quadruped motion characteristics; directly scales the reported relative trajectory error values.
  • Umeyama single-transform alignment = one rigid 4×4 transform per trajectory
    Modeling choice the authors explicitly flag as an assumption; if a trajectory needs multiple frames, all ATE numbers shift.
axioms (5)
  • domain assumption Leica MS60/AP20 accuracy specifications (1.5 mm range, ±2 mm static, 20 Hz) hold as stated
    Anchors the mm-level GT claim; sourced from the vendor, not independently verified in this paper (Sec. 4.2).
  • domain assumption Inertial Explorer tightly-coupled performance matches Table 4 vendor specs (e.g., 0.01-0.02 m position RMS over 10 s GNSS outages)
    Used to claim GT remains bounded during GNSS outages; stated as 'within 2σ variation' per spec sheet (Sec. 4.2).
  • domain assumption Sub-ms time-synchronization accuracy holds across all sensors except the ZED2i
    Verified by a custom alignment tool whose methodology is not detailed; all fusion and calibration overlay claims depend on it (Sec. 3.2.1).
  • standard math Factor-graph MAP estimation and Umeyama least-squares are valid standard tools
    Eq. (1) and the evaluation protocol rely on standard estimation mathematics (Sec. 4.2, Sec. 7.1).
  • domain assumption Benchmark comparisons are valid on restricted GT spans (segments with Inertial Explorer or MS60 data)
    The paper truncates GT to well-supported segments; the tables do not mark which portions of each mission were dropped, so per-mission comparability assumes the restriction affects all methods equally (Sec. 4.2).

pith-pipeline@v1.3.0-alltime-deepseek · 44696 in / 18331 out tokens · 149875 ms · 2026-08-02T21:59:52.130277+00:00 · methodology

0 comments
read the original abstract

Accurate state estimation and multi-modal perception are prerequisites for autonomous legged robots in complex, large-scale environments. To date, no large-scale public legged-robot dataset captures the real-world conditions needed to develop and benchmark algorithms for legged-robot state estimation, perception, and navigation. To address this, we introduce the GrandTour dataset, a multi-modal legged-robotics dataset collected across challenging outdoor and indoor environments, featuring an ANYbotics ANYmal-D quadruped equipped with the Boxi multi-modal sensor payload. GrandTour spans a broad range of environments and operational scenarios across distinct test sites, ranging from alpine scenery and forests to demolished buildings and urban areas, and covers a wide variation in scale, complexity, illumination, and weather conditions. The dataset provides time-synchronized sensor data from spinning LiDARs, multiple RGB cameras with complementary characteristics, proprioceptive sensors, and stereo depth cameras. Moreover, it includes high-precision ground-truth trajectories from satellite-based RTK-GNSS and a Leica Geosystems total station. This dataset supports research in SLAM, high-precision state estimation, and multi-modal learning, enabling rigorous evaluation and development of new approaches to sensor fusion in legged robotic systems. With its extensive scope, GrandTour represents the largest open-access legged-robotics dataset to date. The dataset is available at https://grand-tour.leggedrobotics.com on HuggingFace (ROS-independent), and in ROS formats, along with tools and demo resources.

Figures

Figures reproduced from arXiv: 2602.18164 by Cesar Cadena, Frank Fu, Jonas Frey, Katharine Patterson, Marco Hutter, Maurice Fallon, Tianao Xu, Turcan Tuna.

Figure 1
Figure 1. Figure 1: GrandTour dataset preview. Top: views of ANYmal traversing diverse environments during GrandTour, inset summarizes sensor suite and dataset scale (49 missions, >10 km, >5 h). Bottom: aerial imagery alongside on-board RGB views from a subset of the cameras for six missions of GrandTour (ETH-1, PIL-1, EIG-1, SPX-2, HEAP-1, ARC-2). The path color indicates the frequency with which the robot is at that locatio… view at source ↗
Figure 2
Figure 2. Figure 2: Sensor placement visualization of the entire GrandTour sensor suite. A) Shows the spatial relationships of the sensors on the Boxi payload, and B) shows the sensors of the ANYmal base platform components. Each colored axis represents a sensor or joint frame. For brevity, repeated sensors are not shown (e.g., 6× Intel RealSense D435i depth cameras). stereo, and multi-view imaging. The suite further contains… view at source ↗
Figure 3
Figure 3. Figure 3: System architecture and sensor interfaces of the combined Boxi–ANYmal platform. All compute units (Jetson AGX Orin, Intel NUC, Raspberry Pi) are connected to the UbiSwitch Ethernet device, and the sensors are connected to their respective compute platforms via various interfaces, such as USB 3.1, GMSL2, RJ45, and I²C. Name Description Time Synchronization† LiDARs (Livox) Livox Mid-360 vFoV: 59◦ , Range: 0.… view at source ↗
Figure 4
Figure 4. Figure 4: Top-down projection of range observations around the robot in GrandTour (scale bar: 3 m), illustrating the complementary coverage of the sensor suite. A) Combined view with color-coding: Hesai LiDAR (red), Livox LiDAR (blue), VLP16 (green), and ANYmal-Depth cameras (yellow). B)–D) For clarity, the sensor(s) of interest are shown in color while all other measurements are shown in gray. B) Hesai LiDAR. C) Li… view at source ↗
Figure 5
Figure 5. Figure 5: The calibration provided with the GrandTour dataset is validated through the overlay of point clouds from different LiDARs onto all available RGB images of GrandTour. As shown, the point clouds align with the correct visual features in the image. Points are colorized by their depth along the camera axis; red indicates closer points, and blue indicates farther points. downloading & uploading multiple files … view at source ↗
Figure 6
Figure 6. Figure 6: A colorized point cloud map of the HAUS-1 sequence is shown to highlight the accuracy of the sensor calibration. A) and B) shows the front-center colored CoreResearch camera from different moments during the sequence, whereas C) shows the colorized point cloud map generated by FAST-LIVO2 (Zheng et al., 2025) using Hesai LiDAR and the front-center colored CoreResearch camera. D) shows a view rendered within… view at source ↗
Figure 7
Figure 7. Figure 7: GNSS coverage and semantic diversity of the dataset. A) Number of sequences recorded with and without GNSS. B) The most common intersections of semantic labels across all missions, illustrating how weather, environment, terrain, and hazard conditions co-occur. C) Number of sequences per high-level label class, where each class aggregates the underlying labels listed below the plot. compared against the raw… view at source ↗
Figure 9
Figure 9. Figure 9: Holistic Fusion-based 6-DoF ground truth generation is shown for the SPX-2 sequence of GrandTour. As expected, when the MS60 line-of-sight is obstructed, the standard deviation of the estimate increases. • SPX-2: On the Jungfraujoch research station, dynamic initialization is needed. Consists of thin structures and moving objects. Presents a loop-closure. • SNOW-2: Fast walking on fully snow-covered terrai… view at source ↗
Figure 8
Figure 8. Figure 8: Data format overview. A) Zarr layout on HuggingFace. Topics are stored as multi-arrays; for instance, the hdr_front contains a timestamp and sequence_id. For images, the sequence_id can be used to retrieve the corresponding .jpeg file. Metadata, including intrinsics, extrinsics, and descriptions, is provided both within the Zarr attributes and the YAML file in the metadata folder. Post-processed assets (Ga… view at source ↗
Figure 10
Figure 10. Figure 10: Data collection methodology for the GrandTour dataset. The ANYmal robot equipped with the Boxi sensor payload traverses environments with varying GNSS availability (red circle indicates denied regions) and total station visibility constraints (yellow circle). The deployment requires two operators: a Leica MS60 total positioning station (TPS) operator and a robot teleoperator. The TPS operator is responsib… view at source ↗
Figure 11
Figure 11. Figure 11: GrandTour dataset example from ANYmal showing synchronized proprioceptive signals over a 5 s window (15 s to 20 s from bag start). From top to bottom: LF_HFE joint position (state-estimator output, SEA-measured position, and commanded/target position), binary foot contact states (LF/RF/LH/RH), corresponding contact force magnitudes ∥f∥ (N), and IMU measurements (ωx in rad s−1 , ax in g from /anymal/imu. F… view at source ↗
Figure 12
Figure 12. Figure 12: Overview of GrandTour applications for perception, locomotion, and navigation. (A) Online mesh generation with SLAMesh (Ruan et al., 2023). (B) Prediction of friction parameters from RGB images using training data collected via proprioceptive terrain interaction (Chen et al., 2024a). (C) Integration with Elevation Mapping Cupy (Miki et al., 2022b), enabling the assessment of foothold placement scores. (D)… view at source ↗

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts

    cs.RO 2026-07 conditional novelty 7.0

    Exact symplectic learning extends to open robotic systems via an algebraic structured canonical lift, improving OOD autoregressive prediction on pendulum, quadrotor, and quadruped with parameter-efficient SympNets.

  2. ForEnt: A Multi-Modal Dataset for Characterizing Quadruped Robot Entrapments in Forest Environments

    cs.RO 2026-06 unverdicted novelty 7.0

    ForEnt is a new dataset of time-synchronized RGB-D, LiDAR, proprioceptive and third-person video recordings from 69 labeled forest entrapment events collected across eight sites with a quadruped robot.

  3. FARM: Find Anything using Relational Spatial Memory

    cs.RO 2026-06 unverdicted novelty 7.0

    FARM creates an open-vocabulary relational spatial memory that improves object retrieval recall by 164-224% over prior methods on 44k language queries across 67 scenes while running at 5-10 Hz.

  4. G-PROBE: Cross-FOV Place Recognition and Certainty-Coupled Localization for 3D Point Clouds

    cs.RO 2026-07 conditional novelty 6.0

    A learning-free cross-FOV ensemble plus certainty-coupled GICP keeps place recognition and 6-DoF localization usable under extreme FOV asymmetry and wide-to-narrow cross-sensor pairing where prior methods collapse.

  5. FARM: Find Anything using Relational Spatial Memory

    cs.RO 2026-06 conditional novelty 6.0

    A real-time relational spatial memory that parses object queries into spatial predicates, scores them against per-object 3D Gaussians, and retrieves object instances with substantially higher top-K recall than prior s...

  6. Green for Go, Red for No: Visual Grounding via Semantic Segmentation for VLA Navigation Policies

    cs.CV 2026-07 conditional novelty 5.5

    Real-time SegFormer green/red overlays reduce OmniVLA far-waypoint error 27-44% on Grand Tour language goals mainly by shortening trajectories, with little help for image goals.

  7. Chalito: An Extensible Library for Filtering-Based State Estimation in Quadruped Robots

    cs.RO 2026-07 conditional novelty 5.0

    Chalito is the first open-source library dedicated to benchmarking filter-based state estimators for quadruped robots across robots and datasets via URDF-driven, filter-agnostic interfaces.

  8. CaLiSym: Learning Symplectic Dynamics of Real-World Systems through Structured Canonical Lifts

    cs.RO 2026-07 conditional novelty 5.0

    Lifting non-conservative, actuated, and contact-constrained robot dynamics into an exactly symplectic phase-space map yields state-of-the-art out-of-distribution autoregressive rollout error at low parameter and FLOP cost.

  9. Sensor Configuration Matters: A Systematic Evaluation of Multimodal SLAM on Quadruped Robots

    cs.RO 2026-06 unverdicted novelty 5.0

    Systematic evaluation on an ANYmal D quadruped shows stereo global-shutter cameras outperform monocular, RGB-D, and rolling-shutter setups, while standard inertial integration can degrade vision-based SLAM under legge...

  10. Iterated Invariant EKF for Quadruped Robot Odometry

    cs.RO 2026-04 unverdicted novelty 5.0

    An IterIEKF algorithm for quadruped odometry, relying on proprioceptive kinematic constraints, outperforms vanilla IEKF and SO(3) Kalman filters in accuracy and consistency on simulations and real datasets.

  11. Ultra-Fusion: A Resilient Tightly-Coupled Multi-Sensor Fusion SLAM Framework under Sensor Degradation and Spatiotemporal Perturbation for Intelligent Transportation Systems

    cs.RO 2026-06 unverdicted novelty 4.0

    Ultra-Fusion presents a unified sliding-window estimator for multi-sensor fusion SLAM supporting WIO/VIO/LIO/LVIO with observability-aware initialization, factor-wise reliability scheduling, and online spatiotemporal ...

  12. Multimodal embodiment-aware navigation transformer

    cs.RO 2026-04 unverdicted novelty 4.0

    ViLiNT improves goal-conditioned navigation success rates by 166% on average over vision-only baselines across simulations and real rover tests by combining multimodal sensing with embodiment-conditioned diffusion tra...

  13. A Proprioceptive-Only Benchmark for Quadruped State Estimation: ATE, RPE, and Runtime Trade-offs Between Filters and Smoothers

    cs.RO 2026-05 unverdicted novelty 3.0

    Benchmark of MUSE, IEKF, and IS on CYN-1 sequence shows similar RPEs, lower ATE for IEKF and IS, and accuracy-latency trade-offs with open-source evaluation code.

Reference graph

Works this paper leans on

124 extracted references · 4 canonical work pages · cited by 11 Pith papers

  1. [1]

    IEEE Robotics and Automation Letters 7(2): 4861--4868

    Bai C, Xiao T, Chen Y, Wang H, Zhang F and Gao X (2022) Faster-lio: Lightweight tightly coupled lidar-inertial odometry using parallel sparse incremental voxels. IEEE Robotics and Automation Letters 7(2): 4861--4868. doi:10.1109/LRA.2022.3152830

    arXiv 2022

  2. [2]

    Bloesch M, Burri M, Omari S, Hutter M and Siegwart R (2017) Iterated extended kalman filter based visual-inertial odometry using direct photometric feedback. Intl. J. of Robotics Research 36(10): 1053--1072

    2017

  3. [3]

    In: Robotics: Science and Systems (RSS)

    Bloesch M, Hutter M, Hoepflinger M, Leutenegger S, Gehring C, Remy CD and Siegwart R (2012) State estimation for legged robots - consistent fusion of leg kinematics and IMU . In: Robotics: Science and Systems (RSS). Sydney, Australia, pp. 3--11. doi:10.15607/RSS.2012.VIII.003

    doi:10.15607/rss.2012.viii.003 2012

  4. [4]

    ://github.com/ori-drs/allan_variance_ros

    Buchanan R (2021) Allan variance ros. ://github.com/ori-drs/allan_variance_ros

    2021

  5. [5]

    In: Conference on robot learning

    Buchanan R, Camurri M, Dellaert F and Fallon M (2022) Learning inertial odometry for dynamic legged robot state estimation. In: Conference on robot learning. PMLR, pp. 1575--1584

    2022

  6. [6]

    The International Journal of Robotics Research 42(1-2): 33--42

    Burnett K, Yoon DJ, Wu Y, Li AZ, Zhang H, Lu S, Qian J, Tseng WK, Lambert A, Leung KY, Schoellig AP and Barfoot TD (2023) Boreas: A multi-season autonomous driving dataset. The International Journal of Robotics Research 42(1-2): 33--42. doi:10.1177/02783649231160195. ://doi.org/10.1177/02783649231160195

    doi:10.1177/02783649231160195 2023

  7. [7]

    Burri M, Nikolic J, Gohl P, Schneider T, Rehder J, Omari S, Achtelik MW and Siegwart R (2016) The euroc micro aerial vehicle datasets. Intl. J. of Robotics Research 35(10): 1157--1163

    2016

  8. [8]

    IEEE Robotics and Automation Letters 10(10): 10666--10673

    Cao Z, Talbot W and Li K (2025) Resple: Recursive spline estimation for lidar-based odometry. IEEE Robotics and Automation Letters 10(10): 10666--10673

    2025

  9. [9]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops

    Chaney K, Cladera F, Wang Z, Bisulco A, Hsieh MA, Korpela C, Kumar V, Taylor CJ and Daniilidis K (2023) M3ed: Multi-robot, multi-sensor, multi-environment event dataset. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. pp. 4015--4022

    2023

  10. [10]

    IEEE Robotics and Automation Letters

    Chen J, Frey J, Zhou R, Miki T, Martius G and Hutter M (2024 a ) Identifying terrain physical parameters from vision-towards physical-parameter-aware locomotion and navigation. IEEE Robotics and Automation Letters

    2024

  11. [11]

    IEEE Robotics and Automation Letters 7(2): 2000--2007

    Chen K, Lopez BT, Agha-mohammadi Aa and Mehta A (2022) Direct lidar odometry: Fast localization with dense point clouds. IEEE Robotics and Automation Letters 7(2): 2000--2007. doi:10.1109/LRA.2022.3142739

    arXiv 2022

  12. [13]

    IEEE Robotics and Automation Letters 10(12): 12636--12643

    Chen Z, Le Gentil C, Lin F, Lu M, Qiao Q, Xu B, Qi Y and Lu P (2025) Breaking the static assumption: A dynamic-aware lio framework via spatio-temporal normal analysis. IEEE Robotics and Automation Letters 10(12): 12636--12643. doi:10.1109/LRA.2025.3623436

    arXiv 2025

  13. [14]

    IEEE Robotics and Automation Letters 9(2): 1883--1890

    Chen Z, Xu Y, Yuan S and Xie L (2024 b ) ig-lio: An incremental gicp-based tightly-coupled lidar-inertial odometry. IEEE Robotics and Automation Letters 9(2): 1883--1890. doi:10.1109/LRA.2024.3349915

    arXiv 2024

  14. [15]

    IEEE Robotics and Automation Letters 10(3): 2998--3005

    Choi S and Kim TW (2025) Probabilistic kernel optimization for robust state estimation. IEEE Robotics and Automation Letters 10(3): 2998--3005. doi:10.1109/LRA.2025.3536294

    arXiv 2025

  15. [16]

    ://arxiv.org/abs/2510.01648

    Choi S, Park D, Hwang SY and Kim TW (2025) Statistical uncertainty learning for robust visual-inertial state estimation. ://arxiv.org/abs/2510.01648

    arXiv 2025

  16. [17]

    IEEE Robotics and Automation Letters 9(11): 9375--9382

    Chung D and Kim J (2024) Nv-liom: Lidar-inertial odometry and mapping using normal vectors towards robust slam in multifloor environments. IEEE Robotics and Automation Letters 9(11): 9375--9382. doi:10.1109/LRA.2024.3457373

    arXiv 2024

  17. [18]

    Georgia Institute of Technology, Tech

    Dellaert F (2012) Factor graphs and gtsam: A hands-on introduction. Georgia Institute of Technology, Tech. Rep 2(4)

    2012

  18. [19]

    In: IEEE/RSJ Intl

    Erni G, Frey J, Miki T, Mattamala M and Hutter M (2023) Mem: Multi-modal elevation mapping for robotics and learning. In: IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS). IEEE, pp. 11011--11018

    2023

  19. [20]

    ://arxiv.org/abs/2510.15352

    Escontrela A, Kerr J, Allshire A, Frey J, Duan R, Sferrazza C and Abbeel P (2025) Gaussgym: An open-source real-to-sim framework for learning locomotion from pixels. ://arxiv.org/abs/2510.15352

    arXiv 2025

  20. [21]

    In: Proc

    Fan Y, Zhao T and Wang G (2024) Schurvins: Schur complement-based lightweight visual inertial navigation system. In: Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition . pp. 17964--17973

    2024

  21. [22]

    IEEE Transactions on Intelligent Transportation Systems 22(3): 1341--1360

    Feng D, Haase-Schütz C, Rosenbaum L, Hertlein H, Gläser C, Timm F, Wiesbeck W and Dietmayer K (2021) Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges. IEEE Transactions on Intelligent Transportation Systems 22(3): 1341--1360. doi:10.1109/TITS.2020.2972974

    arXiv 2021

  22. [23]

    IEEE Trans

    Feng F, Braun J, Titus A, McGill SG, Ott L, Siegwart R and Nieto J (2023) Scale-aware visual-inertial localization over large areas in real-time on a legged robot. IEEE Trans. Robotics 39(4): 2512--2530

    2023

  23. [24]

    IEEE Robotics and Automation Letters 9(11): 9175--9182

    Ferrari S, Giammarino LD, Brizi L and Grisetti G (2024) Mad-icp: It is all about matching data – robust and informed lidar odometry. IEEE Robotics and Automation Letters 9(11): 9175--9182. doi:10.1109/LRA.2024.3456509

    arXiv 2024

  24. [25]

    Firoozi R, Tucker J, Tian S, Majumdar A, Sun J, Liu W, Zhu Y, Song S, Kapoor A, Hausman K, Ichter B, Driess D, Wu J, Lu C and Schwager M (2025) Foundation models in robotics: Applications, challenges, and the future. Intl. J. of Robotics Research 44(5): 701--739. doi:10.1177/02783649241281508

    doi:10.1177/02783649241281508 2025

  25. [26]

    In: Robotics: Science and Systems (RSS)

    Frey J, Mattamala M, Chebrolu N, Cadena C, Fallon M and Hutter M (2023) Fast Traversability Estimation for Wild Visual Navigation . In: Robotics: Science and Systems (RSS). Daegu, Republic of Korea, pp. 54--70. doi:10.15607/RSS.2023.XIX.054. ://roboticsproceedings.org/rss19/p054.html

    work page doi:10.15607/rss.2023.xix.054 2023

  26. [27]

    In: Robotics: Science and Systems (RSS)

    Frey J, Tuna T, Fu LFT, Weibel C, Patterson K, Krummenacher B, M \"u ller M, Nubert J, Fallon M, Cadena C and Hutter M (2025) Boxi : Design decisions in the context of algorithmic performance for robotics. In: Robotics: Science and Systems (RSS). Los Angeles, United States, pp. 1--9

    2025

  27. [28]

    In: IEEE/RSJ Intl

    Fu LFT, Chebrolu N and Fallon M (2023) Extrinsic calibration of camera to lidar using a differentiable checkerboard model. In: IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS). pp. 1825--1831. doi:10.1109/IROS55552.2023.10341781

    arXiv 2023

  28. [29]

    In: IEEE/RSJ Intl

    Furgale P, Rehder J and Siegwart R (2013) Unified temporal and spatial calibration for multi-sensor systems. In: IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS). IEEE, pp. 1280--1286

    2013

  29. [30]

    Geiger A, Lenz P, Stiller C and Urtasun R (2013) Vision meets robotics: The kitti dataset. Intl. J. of Robotics Research 32(11): 1231--1237

    2013

  30. [31]

    In: Intl

    Gelfand N, Ikemoto L, Rusinkiewicz S and Levoy M (2003) Geometrically stable sampling for the icp algorithm. In: Intl. Conf. on 3-D Digital Imaging and Modeling (3DIM). pp. 260--267. doi:10.1109/IM.2003.1240258

    Pith/arXiv arXiv 2003

  31. [32]

    In: IEEE Intl

    Geneva P, Eckenhoff K, Lee W, Yang Y and Huang G (2020) Openvins: A research platform for visual-inertial estimation. In: IEEE Intl. Conf. on Robotics and Automation (ICRA). pp. 4666--4672. doi:10.1109/ICRA40945.2020.9196524

    arXiv 2020

  32. [33]

    https://github.com/MichaelGrupp/evo

    Grupp M (2017) evo: Python package for the evaluation of odometry and slam. https://github.com/MichaelGrupp/evo

    2017

  33. [34]

    IEEE Robotics and Automation Letters 9(12): 11234--11241

    Hatleskog J and Alexis K (2024) Probabilistic degeneracy detection for point-to-plane error minimization. IEEE Robotics and Automation Letters 9(12): 11234--11241. doi:10.1109/LRA.2024.3484153

    arXiv 2024

  34. [35]

    Advanced Intelligent Systems 5(7): 2200459

    He D, Xu W, Chen N, Kong F, Yuan C and Zhang F (2023) Point-lio: robust high-bandwidth light detection and ranging inertial odometry. Advanced Intelligent Systems 5(7): 2200459

    2023

  35. [36]

    IEEE Robotics and Automation Letters 7(3): 7518--7525

    Helmberger M, Morin K, Berner B, Kumar N, Cioffi G and Scaramuzza D (2022) The hilti slam challenge dataset. IEEE Robotics and Automation Letters 7(3): 7518--7525

    2022

  36. [37]

    ://arxiv.org/abs/2509.06285

    Hu X, Chen X, Jia M, Wu J, Tan P and Waslander SL (2025) Dcreg: Decoupled characterization for efficient degenerate lidar registration. ://arxiv.org/abs/2509.06285

    arXiv 2025

  37. [38]

    IEEE Trans

    Huai Z and Huang G (2024) A consistent parallel estimation framework for visual-inertial slam. IEEE Trans. Robotics 40: 3734--3755. doi:10.1109/TRO.2024.3433868

    arXiv 2024

  38. [39]

    In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

    Hutter M, Gehring C, Jud D, Lauber A, Bellicoso CD, Tsounis V, Hwangbo J, Bodie K, Fankhauser P, Bloesch M, Diethelm R, Bachmann S, Melzer A and Hoepflinger M (2016) Anymal - a highly mobile and dynamic quadrupedal robot. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 38--44. doi:10.1109/IROS.2016.7758092

    arXiv 2016

  39. [40]

    ://arxiv.org/abs/2601.17815

    Inglin Y, Frey J, Chen C and Hutter M (2026) Less is more: Scalable visual navigation from limited data. ://arxiv.org/abs/2601.17815

    arXiv 2026

  40. [41]

    IEEE Sensors Letters 8(3): 1--4

    Jeong S, Kim H and Cho Y (2024) Diter: Diverse terrain and multimodal dataset for field robot navigation in outdoor environments. IEEE Sensors Letters 8(3): 1--4

    2024

  41. [42]

    In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

    Jiao J, Wei H, Hu T, Hu X, Zhu Y, He Z, Wu J, Yu J, Xie X, Huang H, Geng R, Wang L and Liu M (2022) Fusionportable: A multi-sensor campus-scene dataset for evaluation of localization and mapping accuracy on diverse platforms. In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 3851--3856. doi:10.1109/IROS47612.2022.9982119

    arXiv 2022

  42. [43]

    IEEE Trans

    Jung JH, Choe Y and Park CG (2022) Photometric visual-inertial navigation with uncertainty-aware ensembles. IEEE Trans. Robotics 38(4): 2039--2052. doi:10.1109/TRO.2021.3139964

    arXiv 2022

  43. [44]

    IEEE Robotics and Automation Letters 8(7): 4211--4218

    Jung M, Jung S and Kim A (2023) Asynchronous multiple lidar-inertial odometry using point-wise inter-lidar uncertainty propagation. IEEE Robotics and Automation Letters 8(7): 4211--4218. doi:10.1109/LRA.2023.3281264

    arXiv 2023

  44. [45]

    IEEE Trans

    Kannala J and Brandt S (2006) A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses. IEEE Trans. Pattern Anal. Machine Intell. 28: 1335--40. doi:10.1109/TPAMI.2006.153

    work page doi:10.1109/tpami.2006.153 2006

  45. [46]

    IEEE Robotics and Automation Letters 6(2): 2971--2978

    Kim D, Gu Y and Fearing RS (2021 a ) Legged robot state estimation using invariant kalman filtering and learned contact events. IEEE Robotics and Automation Letters 6(2): 2971--2978

    2021

  46. [47]

    IEEE Trans

    Kim G, Choi S and Kim A (2021 b ) Scan context++: Structural place recognition robust to rotation and lateral variations in urban environments. IEEE Trans. Robotics 38(3): 1856--1874

    2021

  47. [48]

    In: IEEE Intl

    Kim G, Park YS, Cho Y, Jeong J and Kim A (2020) Mulran: Multimodal range dataset for urban place recognition. In: IEEE Intl. Conf. on Robotics and Automation (ICRA). IEEE, pp. 6246--6253

    2020

  48. [49]

    ://arxiv.org/abs/2412.05839

    Kim J, Kim H, Jeong S, Shin Y and Cho Y (2024) Diter++: Diverse terrain and multi-modal dataset for multi-robot slam in multi-session environments. ://arxiv.org/abs/2412.05839

    Pith/arXiv arXiv 2024

  49. [50]

    Journal of Robotics and Autonomous Systems 179: 104750

    Koide K, Yokozuka M, Oishi S and Banno A (2024) Glim: 3d range-inertial localization and mapping with gpu-accelerated scan matching factors. Journal of Robotics and Autonomous Systems 179: 104750. doi:https://doi.org/10.1016/j.robot.2024.104750. ://www.sciencedirect.com/science/article/pii/S0921889024001349

    arXiv 2024

  50. [51]

    IEEE Robotics and Automation Letters 7(2): 2585--2592

    Korthals T, Kragh M, Christiansen P and Karstoft H (2022) Multi-modal semantic slam for complex dynamic environments. IEEE Robotics and Automation Letters 7(2): 2585--2592

    2022

  51. [52]

    arXiv preprint arXiv:2107.04034

    Kumar A, Fu Z, Pathak D and Malik J (2021) Rma: Rapid motor adaptation for legged robots. arXiv preprint arXiv:2107.04034

    Pith/arXiv arXiv 2021

  52. [53]

    IEEE Robotics and Automation Letters 8(11): 7074--7081

    Lang X, Chen C, Tang K, Ma Y, Lv J, Liu Y and Zuo X (2023) Coco-lic: Continuous-time tightly-coupled lidar-inertial-camera odometry using non-uniform b-spline. IEEE Robotics and Automation Letters 8(11): 7074--7081. doi:10.1109/LRA.2023.3315542

    arXiv 2023

  53. [54]

    IEEE Robotics and Automation Letters 10(1): 152--159

    Lee D, Lim H and Han S (2025 a ) GenZ-ICP: Generalizable and Degeneracy-Robust LiDAR Odometry Using an Adaptive Weighting . IEEE Robotics and Automation Letters 10(1): 152--159. doi:10.1109/LRA.2024.3498779

    arXiv 2025

  54. [55]

    IEEE Trans

    Lee MA, Zhu Y, Srinivasan K, Shah P, Savarese S, Fei-Fei L, Garg A and Bohg J (2020) Making sense of vision and touch: Self-supervised learning of multimodal representations for contact-rich tasks. IEEE Trans. Robotics 36(3): 582--596

    2020

  55. [56]

    Lee W, Geneva P, Chen C and Huang G (2025 b ) Mins: Efficient and robust multisensor-aided inertial navigation system. J. of Field Robotics 42(7): 3252--3284

    2025

  56. [57]

    arXiv preprint arXiv:2202.09199

    Leutenegger S (2022) OKVIS2 : Realtime scalable visual‑inertial slam with loop closure. arXiv preprint arXiv:2202.09199

    Pith/arXiv arXiv 2022

  57. [58]

    ://arxiv.org/abs/2501.10100

    Li C, Krause A and Hutter M (2025) Robotic world model: A neural network simulator for robust policy optimization in robotics. ://arxiv.org/abs/2501.10100

    arXiv 2025

  58. [59]

    In: IEEE Intl

    Liang J, Song D, Shuvo MNH, Durrani M, Taranath K, Penskiy I, Manocha D and Xiao X (2025) Gnd: Global navigation dataset with multi-modal perception and multi-category traversability in outdoor campus environments. In: IEEE Intl. Conf. on Robotics and Automation (ICRA). IEEE, pp. 11345--11352

    2025

  59. [60]

    IEEE Trans

    Lin J, Yuan C, Cai Y, Li H, Ren Y, Zou Y, Hong X and Zhang F (2023) Immesh: An immediate lidar localization and meshing framework. IEEE Trans. Robotics 39(6): 4312--4331. doi:10.1109/TRO.2023.3321227

    arXiv 2023

  60. [61]

    IEEE Robotics and Automation Letters 8(3): 1523--1530

    Liu X, Liu Z, Kong F and Zhang F (2023) Large-scale lidar consistent mapping using hierarchical lidar bundle adjustment. IEEE Robotics and Automation Letters 8(3): 1523--1530

    2023

  61. [62]

    ://arxiv.org/abs/2410.08935

    Liu Z, Li H, Yuan C, Liu X, Lin J, Li R, Zheng C, Zhou B, Liu W and Zhang F (2024) Voxel-slam: A complete, accurate, and versatile lidar-inertial slam system. ://arxiv.org/abs/2410.08935

    Pith/arXiv arXiv 2024

  62. [63]

    IEEE/ASME Trans

    Lv J, Lang X, Xu J, Wang M, Liu Y and Zuo X (2023) Continuous-time fixed-lag smoothing for lidar-inertial-camera slam. IEEE/ASME Trans. Mechatron. 28(4): 2259--2270. doi:10.1109/TMECH.2023.3241398

    arXiv 2023

  63. [64]

    Maddern W, Pascoe G, Linegar C and Newman P (2017) 1\,000 km of autonomy: The oxford robotcar dataset. Intl. J. of Robotics Research 36(1): 3--15. doi:10.1177/0278364916679498

    doi:10.1177/0278364916679498 2017

  64. [65]

    arXiv preprint arXiv:2509.06593

    Malladi M, Guadagnino T, Lobefaro L and Stachniss C (2025) A robust approach for lidar-inertial odometry without sensor-specific modeling. arXiv preprint arXiv:2509.06593. ://arxiv.org/pdf/2509.06593

    Pith/arXiv arXiv 2025

  65. [66]

    IEEE Access 11: 144918--144927

    Meng K, Sun H, Qi J and Wang H (2023) Section-lio: A high accuracy lidar-inertial odometry using undistorted sectional point. IEEE Access 11: 144918--144927. doi:10.1109/ACCESS.2023.3344037

    arXiv 2023

  66. [67]

    Science robotics 7(62): eabk2822

    Miki T, Lee J, Hwangbo J, Wellhausen L, Koltun V and Hutter M (2022 a ) Learning robust perceptive locomotion for quadrupedal robots in the wild. Science robotics 7(62): eabk2822

    2022

  67. [68]

    In: IEEE Intl

    Miki T, Lee J, Wellhausen L and Hutter M (2024) Learning to walk in confined spaces using 3d representation. In: IEEE Intl. Conf. on Robotics and Automation (ICRA). IEEE, pp. 8649--8656

    2024

  68. [69]

    In: IEEE/RSJ Intl

    Miki T, Wellhausen L, Grandia R, Jenelten F, Homberger T and Hutter M (2022 b ) Elevation mapping for locomotion and navigation using gpu. In: IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS). IEEE, pp. 2273--2280

    2022

  69. [70]

    IEEE Robotics and Automation Letters 9(6): 5330--5337

    Nguyen TM, Xu X, Jin T, Yang Y, Li J, Yuan S and Xie L (2024 a ) Eigen is all you need: Efficient lidar-inertial continuous-time odometry with internal association. IEEE Robotics and Automation Letters 9(6): 5330--5337. doi:10.1109/LRA.2024.3391049

    arXiv 2024

  70. [71]

    In: Proc

    Nguyen TM, Yuan S, Nguyen TH, Yin P, Cao H, Xie L, Wozniak M, Jensfelt P, Thiel M, Ziegenbein J and Blunder N (2024 b ) Mcd: Diverse large-scale multi-campus dataset for robot perception. In: Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition . pp. 22304--22313

    2024

  71. [72]

    ://arxiv.org/abs/2504.06479

    Nubert J, Tuna T, Frey J, Cadena C, Kuchenbecker KJ, Khattak S and Hutter M (2025) Holistic fusion: Task- and setup-agnostic robot localization and state estimation with factor graphs. ://arxiv.org/abs/2504.06479

    Pith/arXiv arXiv 2025

  72. [73]

    ://arxiv.org/abs/2410.22200

    Nwankwo L, Ellensohn B, Dave V, Hofer P, Forstner J, Villneuve M, Galler R and Rueckert E (2025) Envodat: A large-scale multisensory dataset for robotic spatial awareness and semantic reasoning in heterogeneous environments. ://arxiv.org/abs/2410.22200

    arXiv 2025

  73. [74]

    In: IEEE Intl

    Olson E (2011) Apriltag: A robust and flexible visual fiducial system. In: IEEE Intl. Conf. on Robotics and Automation (ICRA). pp. 3400--3407. doi:10.1109/ICRA.2011.5979561

    arXiv 2011

  74. [75]

    ://arxiv.org/abs/2601.18923

    Patel M, Frey J, Mittal M, Yang F, Hansson A, Bar A, Cadena C and Hutter M (2026) Defm: Learning foundation representations from depth for robotics. ://arxiv.org/abs/2601.18923

    arXiv 2026

  75. [76]

    IEEE Trans

    Peng Y, Chen C, Wu K and Huang G (2025) vins : Robust and ultrafast square-root filter-based 3d motion tracking. IEEE Trans. Robotics 41: 6570--6589. doi:10.1109/TRO.2025.3626607

    arXiv 2025

  76. [77]

    IEEE Robotics and Automation Letters 9(6): 5230--5237

    Petracek P, Alexis K and Saska M (2024) Rms: Redundancy-minimizing point cloud sampling for real-time pose estimation. IEEE Robotics and Automation Letters 9(6): 5230--5237. doi:10.1109/LRA.2024.3389820

    arXiv 2024

  77. [78]

    ://arxiv.org/abs/2511.20492

    P \"u ntener C, Schwabe J, Garmier D, Frey J and Hutter M (2025) Kleinkram: Open robotic data management. ://arxiv.org/abs/2511.20492

    arXiv 2025

  78. [79]

    ://arxiv.org/abs/2512.19567

    Pérez-Ruiz C and Solà J (2026) Limoncello: Iterated error-state kalman filter on the sgal(3) manifold for fast lidar-inertial odometry. ://arxiv.org/abs/2512.19567

    arXiv 2026

  79. [80]

    IEEE Trans

    Qin T, Li P and Shen S (2018) Vins-mono: A robust and versatile monocular visual-inertial state estimator. IEEE Trans. Robotics 34(4): 1004--1020. doi:10.1109/TRO.2018.2853729

    arXiv 2018

  80. [81]

    In: IEEE/RSJ Intl

    Qin T and Shen S (2018) Online temporal calibration for monocular visual-inertial systems. In: IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS). pp. 3662--3669. doi:10.1109/IROS.2018.8593603

    arXiv 2018

Showing first 80 references.