Published: May 3, 2022 by

TartanDrive is selected as an outstanding learning paper finalist in ICRA2022

We took an all-terrain vehicle on wild rides through tall grass, loose gravel and mud to gather data about how the ATV interacted with a challenging, off-road environment.

The dataset and the paper are openly available. Read more about it in our linked article below:

We've been featured on @therobotreport with our off-road data-gathering endeavours. Check it out:https://t.co/Q2T6S80jzt
— AirLab (@AirLabCMU) June 1, 2022

Latest Research

UFM: A Simple Path towards Unified Dense Correspondence with Flow

UFM is a simple, end-to-end trained transformer model that directly regresses pixel displacement ...

MAC-VO Selected as ICRA 2025 Best Paper Award Finalist

We are thrilled to announce that our paper “MAC-VO: Metrics-aware Covariance for Learning-based S...

Demonstrating ViSafe: Vision-enabled Safety for High-speed Detect and Avoid

We demonstrate ViSafe, a high-speed vision-only airborne collision avoidance system operating at ...