Data in Field Robotics: From State Estimation to Navigation – IROS 2026

1ETH Zürich, 2Stanford University, 3University of Oxford, 4KTH, 5Italian Institute of Technology, 6QUT, 7HNU

Thursday, 1 October 2026 · 1:30 PM – 5:30 PM · Room 317/318 · Half-Day Workshop

Join Online: Video Call
IROS Logo
GrandTour Logo GrandTour Website

Congratulations to Our Winners

Awards were presented during the closing session on 1 October 2026.

Workshop Awards

Best Student Paper

Universal Navigation Interface: Robot-Free Data for Wheeled Robot Navigation

Sarvesh Prajapati, Ananya Trivedi, Lorena Maria Genua, Drake Moore, Taskin Padir

Best Student Poster

CLPV: Dataset of Controlled Co-Located Lighting and Photometric Variation for Robot Vision

Shekoufeh Sadeghi, Yash Turkar, Karthik K Dantu

COMFORT Challenge

Winner

SE(3)-LIVOM: Adaptive Multi-LiDAR-Inertial-Visual Odometry and Mapping

Gunhee Shin

Runner-Up

BIEVR-LIO: Robust LiDAR-Inertial Odometry through Bump-Image-Enhanced Voxel Maps

Patrick Pfreundschuh

3rd Place

EllipseLIO: Adaptive LiDAR Inertial Odometry with an Ellipsoid Representation

Rowan Border

Industry Winner

SLAMLab: Real-Time LiDAR-Inertial SLAM

Philipp Glira

About the Workshop

Mobile robots, including legged robots, humanoids, and drones, are increasingly deployed in unstructured and demanding environments—from scaling rubble and inspecting industrial facilities to navigating disaster zones. These open-ended tasks require robustness to terrain, resilience under degraded sensing, and adaptability to diverse task complexity. On the path to maturity in mobile robotics, data and benchmarks have proven to be the core driving factor, as demonstrated in autonomous driving. There, large-scale datasets and task-specific benchmarks have propelled tasks such as localization, mapping and detection to reach remarkable levels of precision. However, for mobile robots in the field, we are still missing this ecosystem. Unlike passenger vehicles, collecting data in the field with these platforms poses significant challenges. The cost of collecting data is high, and these platforms cannot easily carry the full payload of sensors and ground-truth systems. This raises several key open questions: What kind of datasets will have lasting impact and be most useful for robotics? Which sensors are truly essential to capture the task complexity of these platforms? What level of calibration and ground-truth effort is required to advance research in these tasks? Most importantly: how do we design benchmarks that are apt for the unique tasks and failure modes of these robots beyond navigation on suburban streets? This workshop will bring together researchers from robotics, computer vision, and machine learning to define principles for the next generation of datasets and benchmarks. By rethinking dataset and benchmark design in light of the distinct requirements of embodied intelligence, we aim to accelerate progress not only in localization, but also in perception, mapping, and long-term autonomy in the wild.

A full list of the other workshops and tutorials at IROS 2026 is available on the official IROS 2026 Workshops & Tutorials page.

Speakers

Prof. Lukas Rosenberger Schmid

Rising Star Talk: Frontiers in Robot Data: Examples from 4D Perception

Prof. Lukas Rosenberger Schmid

University of Technology Nuremberg

Webpage Google Scholar Google Scholar
Dr. Cherie Ho

Harnessing Data in the Messy Real World: Organizing Robot Experience and Curating Data at Scale

Dr. Cherie Ho

Stanford University

Webpage Google Scholar Google Scholar
Prof. James Richard Forbes

From Data to Poses Underwater

Prof. James Richard Forbes

McGill University

Webpage Google Scholar Google Scholar
Dr. Youming Qin

Industry Talk

Dr. Youming Qin

CEO, Manifold Tech Limited

Webpage Google Scholar Google Scholar
Dr. Stuart Young

Autonomous Robotic Missions in Complex Environments: The Future of Unmanned Systems

Dr. Stuart Young

Field AI

Webpage
Prof. Tobias Fischer

Data for Field Robotics: Ground Truth, Evaluation and Reproducible Benchmarks

Prof. Tobias Fischer

Associate Professor and ARC Future Fellow

Queensland University of Technology

Webpage Google Scholar Google Scholar

Program

Thursday, October 1, 2026 · 1:30–5:30 PM · Half-Day Workshop
Doors opened at 1:15 PM for arrival and poster setup.

The afternoon program combined invited talks, interactive poster presentations, and hands-on robot demonstrations.

Time Session Details
–13:30 Arrival and Poster Setup Doors open, poster mounting, and robot setup
13:30–13:40 Organizing Committee Welcome and introduction
13:40–14:00 Lukas Rosenberger Schmid · Rising Star Talk Frontiers in Robot Data: Examples from 4D Perception
14:00–14:20 Cherie Ho · Rising Star Talk Harnessing Data in the Messy Real World: Organizing Robot Experience and Curating Data at Scale
14:20–14:40 COMFORT Challenge Spotlight Challenge spotlight and selected results
14:40–15:00 James Richard Forbes · Keynote Talk From Data to Poses Underwater
15:00–15:20 Dr. Youming Qin · Industry Talk Industry Talk
15:20–15:30 Poster Session and Robot Interactions Interactive research presentations and hands-on demonstrations
15:30–16:00 Coffee Break, Extended Poster Session, and Robot Interactions Official IROS afternoon coffee window; live robotic deployments
16:00–16:30 Poster Session and Robot Interactions Interactive research presentations and hands-on demonstrations
16:30–16:50 Stuart Young · Keynote Talk Autonomous Robotic Missions in Complex Environments: The Future of Unmanned Systems
16:50–17:10 Tobias Fischer · Keynote Talk Data for Field Robotics: Ground Truth, Evaluation and Reproducible Benchmarks
17:10–17:30 Best Student Poster, Best Student Paper, and Challenge Awards Awards and closing remarks
Workshop T-shirts, goodies and stickers
17:30 End of Workshop —

COMFORT Challenge

We invite participants to push the boundaries of state estimation by submitting results on the GrandTour Benchmark. For full details on participation, submission guidelines, and evaluation criteria, please visit the COMFORT Challenge website.

Awards

The challenge is evaluated on a sub-task basis, and the full prize ladder below is awarded separately for each sub-task. The total number of sub-tasks depends on the variety of submissions. The organizing committee reserves the right to adjust the prize ladder based on the submissions and the quality of results.

  • 1st Place: 500 USD
  • 2nd Place: 300 USD
  • 3rd Place: 200 USD

Note: To claim an award, winners had to submit a technical report outlining their approach by September 21, 2026.

Workshop Awards

To recognize outstanding contributions by students, the workshop grants two dedicated student awards. Winners are selected by the organizing committee together with the invited speakers and announced during the closing session.

  • Best Student Poster: 250 USD
  • Best Student Paper: 250 USD

Eligibility requires that the presenting author is a student and attends the workshop in person.

Call for Papers

We invite contributions related to data, benchmarking, state estimation, perception, and navigation for robots operating in challenging real-world environments. Relevant topics include, but are not limited to:

Topics of Interest

  • Data for field robotics
  • State estimation, LIO, VIO
  • Benchmarking and evaluation of field robotics
  • Multimodal sensing
  • Navigation and traversability
  • Autonomy stacks
  • Real-world deployment at scale

Submission Types and Review Process

We accept two types of submissions:

  1. Novel work: Submit an anonymous 2–4-page, double-column short paper, with unlimited references and appendices. Papers must follow the IROS 2026 formatting guidelines; we recommend this LaTeX template. Submissions will undergo double-blind peer review. Authors of accepted papers will then prepare a poster for an interactive presentation at the workshop.
  2. Previously published work: Work already published or accepted at IROS or another venue should be submitted as a one-page poster. These submissions will be reviewed only for their relevance to the workshop.

Poster format: Posters should be A0 size; both portrait and landscape are accepted.

Workshop papers are non-archival: they are not part of the official IROS proceedings, so submitting here does not prevent you from publishing the work elsewhere. Submit through the DFR Workshop venue on OpenReview. Additional venue information is available on the OpenReview forum.

Submission Timeline

  • Submission portal: DFR Workshop on OpenReview
  • Submissions: Closed
  • Paper deadline: August 28, 2026 September 4, 2026
  • Benchmark submission deadline: September 14, 2026
  • Notification to authors: September 7, 2026 September 15, 2026, 23:59 AoE
  • Workshop: October 1, 2026 (Thursday), 1:30–5:30 PM (half day)

Accepted Submissions

The following works were accepted to the workshop and will be presented during the poster session.

  1. Wild-World: Action-Conditioned RGB-D-Semantic World Modeling for Field Robotics
    Zihang Wang, Yuhang Chu, Wenkai Zhu, Huateng Wu, Shuyuan Li, Dong Kong
  2. ForEnt: A Multi-Modal Dataset for Characterizing Quadruped Robot Entrapments in Forest Environments
    Natapat Kirdwichai, Danesh Tarapore
  3. Do Airborne-Particle Filters Transfer? The LIAD Cross-Domain Benchmark
    Chethaka Jayasekaramudeli, Yangmengfei Xu, Yiheng Sun, Ying Tan, Denny Oetomo, Jonathan Eden
  4. evalio: Easy, Repeatable Evaluation of Lidar-Inertial Odometry
    Easton Potokar, Michael Kaess
  5. Gaussian Representation for 4D Radar-Inertial Odometry
    Fernando Amodeo, Luis Merino, Fernando Caballero
  6. Tiered-Resolution Volumetric Mapping for Real-Time Simultaneous Planning and Mapping on Natural Outdoor Environments
    Afonso Eloy Carvalho, David Portugal, Paulo Peixoto, George Kantor
  7. CLPV: Dataset of Controlled Co-Located Lighting and Photometric Variation for Robot Vision
    Shekoufeh Sadeghi, Yash Turkar, Karthik K Dantu
  8. G-EDF-Loc: 3D Continuous Gaussian Distance Field for Robust Gradient-Based 6DoF Localization
    José Enrique Maese, Lucía Coto-Elena, Luis Merino, Fernando Caballero
  9. Accelerating Robust State Estimation via Sparse Variable Projection
    Nikolas R. Sanderson, Alan Papalia
  10. FieldMatch: Which Feature Matcher Fits Your Field Robot?
    Hyunwoo Kim, Giseop Kim
  11. Boreas Road Trip: A Multi-Sensor Autonomous Driving Dataset on Challenging Roads
    Daniil Lisus, Katya M. Papais, Cedric Le Gentil, Elliot Preston-Krebs, Andrew Lambert, Keith Y.K. Leung, Timothy Barfoot
  12. TartanDrive 2.5: Scaling Full-Stack Data Across Modalities, Behaviors, and Extreme Environments
    Matthew Sivaprakasam, Micah Nye, Saksham Sharma, Geethika Hemkumar, Samuel Triest, Zhipeng Zhao, Yifei Liu, Parv Maheshwari, Sebastian Scherer, Wenshan Wang
  13. SLAMLab: Real-Time LiDAR-Inertial SLAM on the GrandTour COMFORT Benchmark
    Philipp Glira, Clemens Hofbauer, Kilian Potts, Phillipp Fanta-Jende
  14. Universal Navigation Interface: Robot-Free Data for Wheeled Robot Navigation
    Sarvesh Prajapati, Ananya Trivedi, Lorena Maria Genua, Drake Moore, Taskin Padir
  15. A Multimodal UAV Dataset for Adaptive Agricultural Sensing
    Charuvahan Adhivarahan, Jagadeswara PKV Pothuri, Karthik K Dantu
  16. Super Odometry 1.5: Hessian-Informed Factor Fusion Odometry for Field Robotics
    Tejas Salian, Eungchang Mason Lee, Mohammad Shaheer, T Karan Balakumar, Smrithi Siddagangaiah, Shibo Zhao
  17. MSO: Uncertainty-Aware Multi-Spectral Inertial Odometry for Extreme Environments
    Shibo Zhao, T Karan Balakumar, Avnish Patel, Parv Maheshwari, Tejas Salian, Andrew Jong, Mukai Yu, Wenshan Wang, Sebastian Scherer
  18. ForVis: An In-Field Dataset and Benchmark for VIO Using Under-Canopy UAV Flights in Forests
    Arman Kiani, Masoud Ataei, Elvis Gyaase, Jeffrey Eiyike, Aaron Weiskittel, Prabuddha Chakraborty, Vikas Dhiman

Financial Support

Thanks to the generosity of our sponsors, we were able to offer a limited number of travel grants to help cover the cost of attending IROS 2026 and this workshop. We especially encouraged applications from students, early-career researchers, and participants from underrepresented groups or institutions with limited travel funding.

Applicants were expected to have a contribution to the workshop (an accepted poster, paper, or challenge submission) and to attend in person.

The funds have been allocated.

Organizers

Turcan Tuna

Turcan Tuna

ETH Zürich

Mail
Jonas Frey

Jonas Frey

Stanford University / UC Berkeley

Mail
Frank Fu

Frank Fu

University of Oxford

Mail
Yixi Cai

Yixi Cai

KTH

Mail
Efimia Panagiotaki

Efimia Panagiotaki

University of Oxford

Mail
Ylenia Nisticò

Ylenia Nisticò

IIT

Mail

For questions regarding the workshop, contact: grandtour@leggedrobotics.com

Senior Organizers

Maurice Fallon

Maurice Fallon

University of Oxford

Peyman Moghadam

Peyman Moghadam

CSIRO, QUT

Yi Zhou

Yi Zhou

HNU

Sponsors

We gratefully acknowledge the generous support of Manifold Tech Limited, Leica Geosystems by Hexagon, ANYbotics, and the IEEE RAS Robot Learning Technical Committee, whose contributions have made this event possible.