IROS 2026 Competition · Cross-Platform Inertial Positioning

IMU Odometry Challenge One model. Four embodiments. Raw IMU only.

Estimate 3D body-frame velocity from raw 6-axis IMU with one unified model across car, drone, quadruped, and handheld motion.

Live on Kaggle Four platforms 200 Hz measurements
Compete on Kaggle Register Team Setup Guide

Challenge design

One benchmark across four motion domains.

Training and validation data include platform labels. The anonymized test set does not, requiring a single model to generalize across radically different dynamics without switching between platform-specific experts.

Platforms
4
Windows
~136K
Total Duration
37.9 hrs
Sample Rate
200 Hz

One Unified Model

One submission must handle car, drone, quadruped, and handheld trajectories at once.

Platform-Blind Testing

Test labels and platform-revealing trajectory identifiers remain hidden from participants.

Trajectory-Level Evaluation

Predicted velocities are integrated, aligned with SE(3) Umeyama, and scored equally across platforms.

Open TartanIMU Baseline

Reference checkpoints, training code, and a browser demo provide a reproducible starting point.

Browse Dataset Open Data Explorer TartanIMU Code Run Live Demo

Benchmark coverage

Four embodiments with distinct motion dynamics.

Each platform page provides split statistics, trajectory previews, sensor characteristics, and domain-specific evaluation context.

Car training trajectory preview CarGround vehicle motion Drone training trajectory preview DroneAerial six-degree-of-freedom motion Quadruped training trajectory preview QuadrupedContact-rich legged locomotion Handheld training trajectory preview HandheldHuman-scale free motion

Protocol at a glance

From raw inertial windows to ranked trajectories.

The model interface stays compact while evaluation measures the accumulated motion that matters in deployment.

01

The Task

Input
Raw 6-axis IMU: acceleration in m/s² and angular velocity in rad/s, sampled at 200 Hz.
Context
One-second windows of 200 samples, provided as sequences of 10 consecutive windows.
Output
Per-window 3D body-frame velocity v = (vx, vy, vz) in m/s.
02

Scoring

Primary
Macro-averaged Absolute Trajectory Error (ATE), with all four platforms weighted equally.
Evaluation
Organizers integrate predicted velocities with ground-truth orientation, then align and score each path.
Splits
Train for fitting, validation for selection, and anonymized public/private test trajectories for ranking.
Read the complete setup and evaluation protocol

Organizers and partners

Built by teams working on robust robot perception.

The challenge is organized by CMU AirLab and Amazon FAR in conjunction with the IROS 2026 workshop on interoceptive perception.

CMU AirLab
amazonFAR
Carnegie Mellon University Robotics Institute
Meet the organizers Visit the IROS 2026 workshop

Announcements

Challenge updates.

Platform pages for Car, Drone, Quadruped, and Handheld are published.

The initial IMU Odometry Challenge website and benchmark structure launched.

Research resources

Citation and reference models.

Run the TartanIMU specialist models in the Hugging Face demo. Cite the paper and benchmark when using these resources.

TartanIMU (CVPR 2025)

@inproceedings{zhao2025tartanimu,
  title={Tartan IMU: A Light Foundation Model for Inertial
         Positioning in Robotics},
  author={Zhao, Shibo and Yagnyatinskiy, Maxim and others},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer
             Vision and Pattern Recognition (CVPR)},
  year={2025},
  url={https://openaccess.thecvf.com/content/CVPR2025/papers/
       Zhao_Tartan_IMU_A_Light_Foundation_Model_for_Inertial_
       Positioning_in_CVPR_2025_paper.pdf}
}

IMU Odometry Challenge

@misc{imuchallenge2026,
  title={IMU Odometry Challenge: Cross-Platform Inertial
         Positioning Benchmark},
  author={CMU AirLab and Super Odometry Group},
  year={2026},
  howpublished={\url{https://superodometry.com/imuchallenge/}},
  note={Dataset and benchmark challenge page}
}