pith. sign in

arxiv: 2511.18525 · v2 · submitted 2025-11-23 · 💻 cs.RO · cs.CV

Splatblox: Traversability-Aware Gaussian Splatting for Outdoor Robot Navigation

Samarth Chopra , Jing Liang , Gershom Seneviratne , Yonghan Lee , Jaehoon Choi , Jianyu An , Stephen Cheng , Dinesh Manocha This is my paper

Pith reviewed 2026-05-17 05:59 UTC · model grok-4.3

classification 💻 cs.RO cs.CV
keywords Gaussian SplattingtraversabilityESDFoutdoor navigationvegetationLiDAR fusionsemantic mappingrobot navigation
0
0 comments X

The pith

Splatblox fuses segmented RGB images and LiDAR through Gaussian Splatting to build a traversability-aware ESDF that lets robots navigate dense vegetation.

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

The paper presents Splatblox as a real-time system for autonomous robot navigation in outdoor areas containing dense vegetation, irregular obstacles, and varied terrain. It fuses semantic labels extracted from RGB camera images with geometric measurements from LiDAR point clouds inside a Gaussian Splatting representation. The result is an online-updated Euclidean Signed Distance Field that carries both geometric distances and semantic distinctions, marking tall grass as passable while treating tree trunks and rocks as barriers. Field experiments on a quadruped robot and a wheeled platform demonstrate clear gains over prior approaches in completing missions without getting stuck. The system maintains usable maps for planning distances as long as 100 meters ahead.

Core claim

Splatblox fuses segmented RGB images and LiDAR point clouds using Gaussian Splatting to construct a traversability-aware Euclidean Signed Distance Field (ESDF) that jointly encodes geometry and semantics. Updated online, this field enables semantic reasoning to distinguish traversable vegetation from rigid obstacles, while LiDAR ensures 360-degree geometric coverage for extended planning horizons.

What carries the argument

The traversability-aware Euclidean Signed Distance Field constructed by Gaussian Splatting fusion of semantic RGB segmentation and LiDAR geometry.

Load-bearing premise

Semantic segmentation of RGB images can reliably label traversable vegetation separately from rigid obstacles under changing outdoor light, with LiDAR supplying enough geometry to fix any segmentation mistakes in real time.

What would settle it

A field run in which the segmentation model mislabels grass as an obstacle or a tree as passable under strong shadows or glare, causing the robot either to freeze or to drive into a collision.

Figures

Figures reproduced from arXiv: 2511.18525 by Dinesh Manocha, Gershom Seneviratne, Jaehoon Choi, Jianyu An, Jing Liang, Samarth Chopra, Stephen Cheng, Yonghan Lee.

Figure 1
Figure 1. Figure 1: Navigation trajectory of our method Splatblox (red) compared to baselines (Nvblox [19], DWA [20], MIM [21], VERN [4], GA-Nav [11]). Our method achieves the lowest normalized trajectory length (NTL) and highest success rate by about 3% and 60% respectively, compared to the second-best method, when navigating through the narrow corridor between bushes (see Table I for quantitative results). The top-right ins… view at source ↗
Figure 2
Figure 2. Figure 2: Splatblox architecture: RGB frames are processed by a segmentation module to assign traversability costs to image pixels, which are then associated with LiDAR points projected into the camera frame. These costs and 3D points are used for spawning new Gaussian primitives, forming a traversability￾aware volumetric field. The Gaussian Splatting module incrementally updates this field online, maintaining a com… view at source ↗
Figure 3
Figure 3. Figure 3: ESDF fusion strategy. Top: Robot’s camera view (left) and fusion strategy (right), where the frontal region is covered by GSplat ESDF (red) and 360° coverage is provided by LiDAR ESDF (green). Bottom: GSplat ESDF (left) encodes fine-grained traversability detail, LiDAR ESDF (middle) provides global geometric consistency, and their fusion (right) combines both to produce collision-free, traversability-aware… view at source ↗
Figure 4
Figure 4. Figure 4: Top: Navigation trajectories of our method Splatblox (red) compared with baselines (Nvblox [19], DWA [20], MIM [21], VERN [4], GA-Nav [11]) across four outdoor scenarios with diverse terrains, including paved areas, vegetation, and uneven ground. In each case, Splatblox achieves successful traversal with the shortest normalized trajectory length (NTL) through narrow passages and cluttered regions, while se… view at source ↗
Figure 5
Figure 5. Figure 5: Top: Splatblox (red) is the only method that successfully completes this scenario. The trajectory begins from the pavement into the grass (left image) and transitions to the vines and shrubs (right image). Our method is the only one able to navigate through the dense vegetation to reach the goal. Bottom: All methods succeed in a simpler scenario, where the trajectory begins on pavement (left image) and tra… view at source ↗
read the original abstract

We present Splatblox, a real-time system for autonomous navigation in outdoor environments with dense vegetation, irregular obstacles, and complex terrain. Our method fuses segmented RGB images and LiDAR point clouds using Gaussian Splatting to construct a traversability-aware Euclidean Signed Distance Field (ESDF) that jointly encodes geometry and semantics. Updated online, this field enables semantic reasoning to distinguish traversable vegetation (e.g., tall grass) from rigid obstacles (e.g., trees), while LiDAR ensures 360-degree geometric coverage for extended planning horizons. We validate Splatblox on a quadruped robot and demonstrate transfer to a wheeled platform. In field trials across vegetation-rich scenarios, it outperforms state-of-the-art methods with over 50% higher success rate, 40% fewer freezing incidents, 5% shorter paths, and up to 13% faster time to goal, while supporting long-range missions up to 100 meters. Experiment videos and more details can be found on our project page: https://splatblox.github.io

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper presents Splatblox, a real-time system for autonomous outdoor robot navigation in vegetation-rich environments. It fuses segmented RGB images with LiDAR point clouds via Gaussian Splatting to build an online traversability-aware Euclidean Signed Distance Field (ESDF) that encodes both geometry and semantics, enabling distinction between traversable vegetation and rigid obstacles. The method is demonstrated on a quadruped robot with transfer to a wheeled platform, claiming in field trials over 50% higher success rates, 40% fewer freezing incidents, 5% shorter paths, up to 13% faster time-to-goal, and support for missions up to 100 meters compared to state-of-the-art approaches.

Significance. If the reported performance gains hold under rigorous validation, the work would be significant for outdoor robotics by demonstrating a practical fusion of semantic and geometric information in a unified, updatable representation that supports long-horizon planning through unstructured terrain. The real-robot experiments, cross-platform transfer, and explicit handling of vegetation as traversable are strengths that address a persistent gap in prior geometric-only methods.

major comments (2)
  1. [Experimental Results] Experimental section (field trials): The headline claims of >50% higher success rate, 40% fewer freezes, and other metrics rest on comparisons whose baselines and environment selection are not fully detailed in the available description; without ablations isolating the semantic ESDF contribution from planner tuning or scene choice, it remains unclear whether the gains are attributable to the core representation or to other factors.
  2. [Methods] Methods (semantic fusion): The central assumption that RGB semantic segmentation reliably labels traversable vegetation under varying outdoor lighting, with LiDAR correcting errors in real time, is load-bearing for the claimed advantage over pure-geometry baselines; quantitative segmentation accuracy metrics across illumination conditions are needed to confirm the ESDF does not revert to geometry-only behavior.
minor comments (1)
  1. [Abstract] The abstract would be strengthened by a one-sentence description of how Gaussian Splatting enables the joint geometry-semantics encoding.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback and for recognizing the potential significance of Splatblox. We address the two major comments point by point below, providing clarifications from the manuscript and indicating planned revisions.

read point-by-point responses

  1. Referee: [Experimental Results] Experimental section (field trials): The headline claims of >50% higher success rate, 40% fewer freezes, and other metrics rest on comparisons whose baselines and environment selection are not fully detailed in the available description; without ablations isolating the semantic ESDF contribution from planner tuning or scene choice, it remains unclear whether the gains are attributable to the core representation or to other factors.

    Authors: We agree that expanded details on the experimental protocol would improve clarity. In the revised manuscript we will add: explicit descriptions of each baseline implementation and parameter settings; characteristics of the vegetation-rich field sites (density, terrain slope, approximate area); and new ablation experiments that hold the planner and test scenes fixed while toggling the semantic component of the ESDF. These changes will make the attribution of performance gains to the traversability-aware representation explicit. revision: yes

  2. Referee: [Methods] Methods (semantic fusion): The central assumption that RGB semantic segmentation reliably labels traversable vegetation under varying outdoor lighting, with LiDAR correcting errors in real time, is load-bearing for the claimed advantage over pure-geometry baselines; quantitative segmentation accuracy metrics across illumination conditions are needed to confirm the ESDF does not revert to geometry-only behavior.

    Authors: We acknowledge the value of direct evidence for segmentation reliability. The revised manuscript will include quantitative segmentation metrics (precision, recall, and IoU for the traversable-vegetation class) evaluated on a held-out image set captured under multiple illumination conditions (bright sun, overcast, and dusk). We will also add a short analysis showing how the online LiDAR update mitigates occasional segmentation errors, confirming that the ESDF retains semantic benefit beyond pure geometry. revision: yes

Circularity Check

0 steps flagged

No circularity detected in derivation or evaluation chain

full rationale

The manuscript describes a Gaussian Splatting pipeline that fuses RGB semantics with LiDAR to produce a traversability-aware ESDF, followed by online updates and robot field trials. No equations, parameter fits, or self-citations are shown that reduce any claimed performance metric (success rate, path length, etc.) to quantities defined by the authors' own inputs or prior work. The reported gains rest on external physical experiments rather than self-referential definitions or fitted predictions, satisfying the criteria for a self-contained, non-circular result.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on the assumption that semantic segmentation outputs can be trusted to label vegetation as traversable and that LiDAR geometry reliably corrects any mislabels; no explicit free parameters or invented entities are named in the abstract.

axioms (2)
  • domain assumption RGB semantic segmentation reliably distinguishes traversable vegetation from rigid obstacles under outdoor conditions
    Invoked when the method fuses segmented images into the splat representation to encode traversability.
  • domain assumption LiDAR provides sufficient 360-degree geometric coverage to support long-range planning
    Stated as enabling extended planning horizons beyond camera field of view.

pith-pipeline@v0.9.0 · 5509 in / 1449 out tokens · 54650 ms · 2026-05-17T05:59:50.556185+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

58 extracted references · 58 canonical work pages

  1. [1]

    Precision agriculture robot for seeding function,

    N. S. Naik, V . V . Shete, and S. R. Danve, “Precision agriculture robot for seeding function,” in2016 international conference on inventive computation technologies (ICICT), vol. 2. IEEE, 2016, pp. 1–3

    work page 2016

  2. [2]

    Use of unmanned vehicles in search and rescue operations in forest fires: Advantages and limitations observed in a field trial,

    S. Karma, E. Zorba, G. Pallis, G. Statheropoulos, I. Balta, K. Mikedi, J. Vamvakari, A. Pappa, M. Chalaris, G. Xanthopouloset al., “Use of unmanned vehicles in search and rescue operations in forest fires: Advantages and limitations observed in a field trial,”International journal of disaster risk reduction, vol. 13, pp. 307–312, 2015

    work page 2015

  3. [3]

    A survey on terrain traversability analysis for autonomous ground vehicles: Methods, sensors, and challenges,

    P. V . Borges, T. Peynot, S. Liang, B. Arain, M. Wildie, M. G. Minareci, S. Lichman, G. Samvedi, I. Sa, N. Hudsonet al., “A survey on terrain traversability analysis for autonomous ground vehicles: Methods, sensors, and challenges,”Field Robotics, vol. 2, pp. 1567– 1627, 2022

    work page 2022

  4. [4]

    Vern: Vegetation-aware robot navigation in dense unstructured outdoor environments,

    A. J. Sathyamoorthy, K. Weerakoon, T. Guan, M. Russell, D. Conover, J. Pusey, and D. Manocha, “Vern: Vegetation-aware robot navigation in dense unstructured outdoor environments,” in2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2023, pp. 11 233–11 240

    work page 2023

  5. [5]

    Mosu: Autonomous long-range robot navigation with multi-modal scene understanding,

    J. Liang, K. Weerakoon, D. Song, S. Kirubaharan, X. Xiao, and D. Manocha, “Mosu: Autonomous long-range robot navigation with multi-modal scene understanding,”arXiv preprint arXiv:2507.04686, 2025

    work page arXiv 2025

  6. [6]

    Wild visual navigation: fast traversability learning via pre-trained models and online self-supervision,

    M. Mattamala, J. Frey, P. Libera, N. Chebrolu, G. Martius, C. Cadena, M. Hutter, and M. Fallon, “Wild visual navigation: fast traversability learning via pre-trained models and online self-supervision,”Au- tonomous Robots, vol. 49, no. 3, pp. 1–18, 2025

    work page 2025

  7. [7]

    On terrain traversabil- ity analysis in unstructured environments: recent advances in forest applications,

    A. E Carvalho, D. Portugal, and P. Peixoto, “On terrain traversabil- ity analysis in unstructured environments: recent advances in forest applications,”Intelligent Service Robotics, pp. 1–19, 2025

    work page 2025

  8. [8]

    Terrain traversability prediction through self- supervised learning and unsupervised domain adaptation on synthetic data,

    G. Vecchio, S. Palazzo, D. C. Guastella, D. Giordano, G. Muscato, and C. Spampinato, “Terrain traversability prediction through self- supervised learning and unsupervised domain adaptation on synthetic data,”Autonomous Robots, vol. 48, no. 2, p. 4, 2024

    work page 2024

  9. [9]

    Traverse the non-traversable: Estimating traversability for wheeled mobility on vertically challenging terrain,

    C. Pan, A. Datar, A. Pokhrel, M. Choulas, M. Nazeri, and X. Xiao, “Traverse the non-traversable: Estimating traversability for wheeled mobility on vertically challenging terrain,”arXiv preprint arXiv:2409.17479, 2024

    work page arXiv 2024

  10. [10]

    Characterization and traversal of pliable vegetation for robot navigation,

    C. Ordonez, R. Alicea, B. Rothrock, K. Ladyko, J. Nash, R. Thakker, S. Daftry, M. Harper, E. Collins, and L. Matthies, “Characterization and traversal of pliable vegetation for robot navigation,” inInterna- tional Symposium on Experimental Robotics. Springer, 2018, pp. 293–304

    work page 2018

  11. [11]

    Ga-nav: Efficient terrain segmenta- tion for robot navigation in unstructured outdoor environments,

    T. Guan, D. Kothandaraman, R. Chandra, A. J. Sathyamoorthy, K. Weerakoon, and D. Manocha, “Ga-nav: Efficient terrain segmenta- tion for robot navigation in unstructured outdoor environments,”IEEE Robotics and Automation Letters, vol. 7, no. 3, pp. 8138–8145, 2022

    work page 2022

  12. [12]

    Roadrunner-learning traversabil- ity estimation for autonomous off-road driving,

    J. Frey, M. Patel, D. Atha, J. Nubert, D. Fan, A. Agha, C. Padgett, P. Spieler, M. Hutter, and S. Khattak, “Roadrunner-learning traversabil- ity estimation for autonomous off-road driving,”IEEE Transactions on Field Robotics, 2024

    work page 2024

  13. [13]

    Where should i walk? predicting terrain properties from images via self-supervised learning,

    L. Wellhausen, A. Dosovitskiy, R. Ranftl, K. Walas, C. Cadena, and M. Hutter, “Where should i walk? predicting terrain properties from images via self-supervised learning,”IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 1509–1516, 2019

    work page 2019

  14. [14]

    Vapor: Legged robot navigation in outdoor vegetation using offline reinforcement learning,

    K. Weerakoon, A. J. Sathyamoorthy, M. Elnoor, and D. Manocha, “Vapor: Legged robot navigation in outdoor vegetation using offline reinforcement learning,”arXiv preprint arXiv:2309.07832, 2023

    work page arXiv 2023

  15. [15]

    Amco: adaptive multimodal coupling of vision and proprioception for quadruped robot navigation in outdoor envi- ronments,

    M. Elnoor, K. Weerakoon, A. J. Sathyamoorthy, T. Guan, V . Rajagopal, and D. Manocha, “Amco: adaptive multimodal coupling of vision and proprioception for quadruped robot navigation in outdoor envi- ronments,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2024, pp. 7687–7694

    work page 2024

  16. [16]

    Terrain classification for the spot quadrupedal mobile robot using only proprioceptive sensing,

    S. Villemure, J. Silveira, and J. A. Marshall, “Terrain classification for the spot quadrupedal mobile robot using only proprioceptive sensing,” in2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE). IEEE, 2024, pp. 448–452

    work page 2024

  17. [17]

    Cross-gait: Cross- attention-based multimodal representation fusion for parametric gait adaptation in complex terrains,

    G. Seneviratne, K. Weerakoon, M. Elnoor, V . Rajgopal, H. Varathara- jan, M. K. M. Jaffar, J. Pusey, and D. Manocha, “Cross-gait: Cross- attention-based multimodal representation fusion for parametric gait adaptation in complex terrains,”arXiv preprint arXiv:2409.17262, 2024

    work page arXiv 2024

  18. [18]

    Behav: Behavioral rule guided autonomy using vlms for robot navigation in outdoor scenes,

    K. Weerakoon, M. Elnoor, G. Seneviratne, V . Rajagopal, S. H. Arul, J. Liang, M. K. M. Jaffar, and D. Manocha, “Behav: Behavioral rule guided autonomy using vlms for robot navigation in outdoor scenes,” arXiv preprint arXiv:2409.16484, 2024

    work page arXiv 2024

  19. [19]

    nvblox: Gpu-accelerated incremental signed distance field mapping,

    A. Millane, H. Oleynikova, E. Wirbel, R. Steiner, V . Ramasamy, D. Tingdahl, and R. Siegwart, “nvblox: Gpu-accelerated incremental signed distance field mapping,” in2024 IEEE International Confer- ence on Robotics and Automation (ICRA). IEEE, 2024, pp. 2698– 2705

    work page 2024

  20. [20]

    The dynamic window approach to collision avoidance,

    D. Fox, W. Burgard, and S. Thrun, “The dynamic window approach to collision avoidance,”IEEE robotics & automation magazine, vol. 4, no. 1, pp. 23–33, 2002

    work page 2002

  21. [21]

    Mim: Indoor and outdoor navigation in complex environments using multi-layer intensity maps,

    A. J. Sathyamoorthy, K. Weerakoon, M. Elnoor, M. Russell, J. Pusey, and D. Manocha, “Mim: Indoor and outdoor navigation in complex environments using multi-layer intensity maps,” in2024 IEEE Interna- tional Conference on Robotics and Automation (ICRA). IEEE, 2024, pp. 10 917–10 924

    work page 2024

  22. [22]

    Mem: Multi- modal elevation mapping for robotics and learning,

    G. Erni, J. Frey, T. Miki, M. Mattamala, and M. Hutter, “Mem: Multi- modal elevation mapping for robotics and learning,” in2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2023, pp. 11 011–11 018

    work page 2023

  23. [23]

    Using occupancy grids for mobile robot perception and navigation,

    A. Elfes, “Using occupancy grids for mobile robot perception and navigation,”Computer, vol. 22, no. 6, pp. 46–57, 2002

    work page 2002

  24. [24]

    Surface reconstruction by wrapping finite sets in space,

    H. Edelsbrunner, “Surface reconstruction by wrapping finite sets in space,” inDiscrete and computational geometry: the Goodman-Pollack Festschrift. Springer, 2003, pp. 379–404

    work page 2003

  25. [25]

    Slam-driven robotic mapping and registration of 3d point clouds,

    P. Kim, J. Chen, and Y . K. Cho, “Slam-driven robotic mapping and registration of 3d point clouds,”Automation in Construction, vol. 89, pp. 38–48, 2018

    work page 2018

  26. [26]

    Nerf: Representing scenes as neural radiance fields for view synthesis,

    B. Mildenhall, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoor- thi, and R. Ng, “Nerf: Representing scenes as neural radiance fields for view synthesis,”Communications of the ACM, vol. 65, no. 1, pp. 99–106, 2021

    work page 2021

  27. [27]

    3d gaussian splatting for real-time radiance field rendering

    B. Kerbl, G. Kopanas, T. Leimkühler, and G. Drettakis, “3d gaussian splatting for real-time radiance field rendering.”ACM Trans. Graph., vol. 42, no. 4, pp. 139–1, 2023

    work page 2023

  28. [28]

    On-the- fly reconstruction for large-scale novel view synthesis from unposed images,

    A. Meuleman, I. Shah, A. Lanvin, B. Kerbl, and G. Drettakis, “On-the- fly reconstruction for large-scale novel view synthesis from unposed images,”ACM Transactions on Graphics (TOG), vol. 44, no. 4, pp. 1–14, 2025

    work page 2025

  29. [29]

    Taming 3dgs: High-quality radiance fields with limited resources,

    S. S. Mallick, R. Goel, B. Kerbl, M. Steinberger, F. V . Carrasco, and F. De La Torre, “Taming 3dgs: High-quality radiance fields with limited resources,” inSIGGRAPH Asia 2024 Conference Papers, 2024, pp. 1–11

    work page 2024

  30. [30]

    Splat-nav: Safe real-time robot navi- gation in gaussian splatting maps,

    T. Chen, O. Shorinwa, J. Bruno, A. Swann, J. Yu, W. Zeng, K. Nagami, P. Dames, and M. Schwager, “Splat-nav: Safe real-time robot navi- gation in gaussian splatting maps,”IEEE Transactions on Robotics, 2025

    work page 2025

  31. [31]

    Safer-splat: A control barrier function for safe navigation with online gaussian splatting maps,

    T. Chen, A. Swann, J. Yu, O. Shorinwa, R. Murai, M. Kennedy III, and M. Schwager, “Safer-splat: A control barrier function for safe navigation with online gaussian splatting maps,”arXiv preprint arXiv:2409.09868, 2024

    work page arXiv 2024

  32. [32]

    Gaussian splatting slam,

    H. Matsuki, R. Murai, P. H. Kelly, and A. J. Davison, “Gaussian splatting slam,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 18 039–18 048

    work page 2024

  33. [33]

    Splatam: Splat track & map 3d gaussians for dense rgb-d slam,

    N. Keetha, J. Karhade, K. M. Jatavallabhula, G. Yang, S. Scherer, D. Ramanan, and J. Luiten, “Splatam: Splat track & map 3d gaussians for dense rgb-d slam,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 21 357–21 366

    work page 2024

  34. [34]

    Gsfusion: Online rgb-d mapping where gaussian splatting meets tsdf fusion,

    J. Wei and S. Leutenegger, “Gsfusion: Online rgb-d mapping where gaussian splatting meets tsdf fusion,”IEEE Robotics and Automation Letters, 2024

    work page 2024

  35. [35]

    Gaussian-lic: Real-time photo-realistic slam with gaussian splatting and lidar-inertial-camera fusion,

    X. Lang, L. Li, C. Wu, C. Zhao, L. Liu, Y . Liu, J. Lv, and X. Zuo, “Gaussian-lic: Real-time photo-realistic slam with gaussian splatting and lidar-inertial-camera fusion,”arXiv preprint arXiv:2404.06926, 2024

    work page arXiv 2024

  36. [36]

    3d gaussian splatting in robotics: A survey

    S. Zhu, G. Wang, X. Kong, D. Kong, and H. Wang, “3d gaussian splatting in robotics: A survey,”arXiv preprint arXiv:2410.12262, 2024

    work page arXiv 2024

  37. [37]

    Gaussnav: Gaussian splatting for visual navigation,

    X. Lei, M. Wang, W. Zhou, and H. Li, “Gaussnav: Gaussian splatting for visual navigation,”IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

    work page 2025

  38. [38]

    Efficient temporal consistency for streaming video scene analysis,

    O. Miksik, D. Munoz, J. A. Bagnell, and M. Hebert, “Efficient temporal consistency for streaming video scene analysis,” in2013 IEEE International Conference on Robotics and Automation. IEEE, 2013, pp. 133–139

    work page 2013

  39. [39]

    Octomap: An efficient probabilistic 3d mapping framework based on octrees,

    A. Hornung, K. M. Wurm, M. Bennewitz, C. Stachniss, and W. Bur- gard, “Octomap: An efficient probabilistic 3d mapping framework based on octrees,”Autonomous robots, vol. 34, no. 3, pp. 189–206, 2013

    work page 2013

  40. [40]

    V oxblox: Incremental 3d euclidean signed distance fields for on- board mav planning,

    H. Oleynikova, Z. Taylor, M. Fehr, R. Siegwart, and J. Nieto, “V oxblox: Incremental 3d euclidean signed distance fields for on- board mav planning,” in2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2017, pp. 1366–1373

    work page 2017

  41. [41]

    Terrapn: Unstructured terrain navigation using online self-supervised learning,

    A. J. Sathyamoorthy, K. Weerakoon, T. Guan, J. Liang, and D. Manocha, “Terrapn: Unstructured terrain navigation using online self-supervised learning,” in2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2022, pp. 7197– 7204

    work page 2022

  42. [42]

    Mtg: Mapless trajectory generator with traversabil- ity coverage for outdoor navigation,

    J. Liang, P. Gao, X. Xiao, A. J. Sathyamoorthy, M. Elnoor, M. C. Lin, and D. Manocha, “Mtg: Mapless trajectory generator with traversabil- ity coverage for outdoor navigation,” in2024 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2024, pp. 2396–2402

    work page 2024

  43. [43]

    Dtg: Diffusion-based trajectory generation for mapless global navigation,

    J. Liang, A. Payandeh, D. Song, X. Xiao, and D. Manocha, “Dtg: Diffusion-based trajectory generation for mapless global navigation,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2024, pp. 5340–5347

    work page 2024

  44. [44]

    Convoi: Context-aware navigation using vision language models in outdoor and indoor envi- ronments,

    A. J. Sathyamoorthy, K. Weerakoon, M. Elnoor, A. Zore, B. Ichter, F. Xia, J. Tan, W. Yu, and D. Manocha, “Convoi: Context-aware navigation using vision language models in outdoor and indoor envi- ronments,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2024, pp. 13 837–13 844

    work page 2024

  45. [45]

    Robot navigation using phys- ically grounded vision-language models in outdoor environments,

    M. Elnoor, K. Weerakoon, G. Seneviratne, R. Xian, T. Guan, M. K. M. Jaffar, V . Rajagopal, and D. Manocha, “Robot navigation using phys- ically grounded vision-language models in outdoor environments,” arXiv preprint arXiv:2409.20445, 2024

    work page arXiv 2024

  46. [46]

    Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action,

    D. Shah, B. Osi ´nski, S. Levineet al., “Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action,” in Conference on robot learning. PMLR, 2023, pp. 492–504

    work page 2023

  47. [47]

    ViNT: A foundation model for visual navigation,

    D. Shah, A. Sridhar, N. Dashora, K. Stachowicz, K. Black, N. Hirose, and S. Levine, “Vint: A foundation model for visual navigation,”arXiv preprint arXiv:2306.14846, 2023

    work page arXiv 2023

  48. [48]

    Nomad: Goal masked diffusion policies for navigation and exploration,

    A. Sridhar, D. Shah, C. Glossop, and S. Levine, “Nomad: Goal masked diffusion policies for navigation and exploration,” in2024 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2024, pp. 63–70

    work page 2024

  49. [49]

    Atlas navigator: Active task-driven language-embedded gaussian splatting,

    D. Ong, Y . Tao, V . Murali, I. Spasojevic, V . Kumar, and P. Chaud- hari, “Atlas navigator: Active task-driven language-embedded gaussian splatting,”arXiv preprint arXiv:2502.20386, 2025

    work page arXiv 2025

  50. [50]

    RT-GuIDE: Real- Time Gaussian splatting for Information-Driven Exploration

    Y . Tao, D. Ong, V . Murali, I. Spasojevic, P. Chaudhari, and V . Kumar, “Rt-guide: Real-time gaussian splatting for information-driven explo- ration,”arXiv preprint arXiv:2409.18122, 2024

    work page arXiv 2024

  51. [51]

    Gaussian splatting as a unified representation for autonomy in unstructured environments,

    D. Ong, Y . Tao, V . Murali, I. Spasojevic, V . Kumar, and P. Chaud- hari, “Gaussian splatting as a unified representation for autonomy in unstructured environments,”arXiv preprint arXiv:2505.11794, 2025

    work page arXiv 2025

  52. [52]

    Gaussian-lic2: Lidar-inertial-camera gaussian splatting slam,

    X. Lang, J. Lv, K. Tang, L. Li, J. Huang, L. Liu, Y . Liu, and X. Zuo, “Gaussian-lic2: Lidar-inertial-camera gaussian splatting slam,”arXiv preprint arXiv:2507.04004, 2025

    work page arXiv 2025

  53. [53]

    Image segmentation using text and image prompts,

    T. Lüddecke and A. Ecker, “Image segmentation using text and image prompts,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022, pp. 7086–7096

    work page 2022

  54. [54]

    Chomp: Covariant hamiltonian optimization for motion planning,

    M. Zucker, N. Ratliff, A. D. Dragan, M. Pivtoraiko, M. Klingensmith, C. M. Dellin, J. A. Bagnell, and S. S. Srinivasa, “Chomp: Covariant hamiltonian optimization for motion planning,” inIEEE International Conference on Robotics and Automation (ICRA), 2009

    work page 2009

  55. [55]

    Trajectory optimization for motion planning,

    J. Schulman, Y . Duan, J. Ho, A. Lee, I. Awwal, H. Bradlow, and P. Abbeel, “Trajectory optimization for motion planning,” inIEEE International Conference on Robotics and Automation (ICRA), 2013

    work page 2013

  56. [56]

    Lio-sam: Tightly-coupled lidar inertial odometry via smoothing and mapping,

    T. Shan, B. Englot, D. Meyers, W. Wang, C. Ratti, and D. Rus, “Lio-sam: Tightly-coupled lidar inertial odometry via smoothing and mapping,” in2020 IEEE/RSJ international conference on intelligent robots and systems (IROS). IEEE, 2020, pp. 5135–5142

    work page 2020

  57. [57]

    The marathon 2: A navigation system,

    S. Macenski, F. Martín, R. White, and J. Ginés Clavero, “The marathon 2: A navigation system,” in2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020. [Online]. Available: https://github.com/ros-planning/navigation2

    work page 2020

  58. [58]

    Information theoretic model predictive control: Theory and applications to autonomous driving,

    G. Williams, A. Wagener, B. Goldfain, P. Drews, J. M. Rehg, B. Boots, and E. A. Theodorou, “Information theoretic model predictive control: Theory and applications to autonomous driving,” inIEEE International Conference on Robotics and Automation (ICRA). IEEE, 2017, pp. 3065–3072

    work page 2017