# TartanDrive 2.0: More Modalities and Better Infrastructure to Further Self-Supervised Learning Research in Off-Road Driving Tasks

arXiv: https://arxiv.org/abs/2402.01913 · HTML: https://mlsanity.com/paper/2402.01913/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Feb 2024.

## Built on by (most cited first, 23 of 23)

- [TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation](https://mlsanity.com/paper/2505.10696/) (2025)
- [Excavating in the Wild: The GOOSE-Ex Dataset for Semantic Segmentation](https://mlsanity.com/paper/2409.18788/) (2024)
- [PhysORD: A Neuro-Symbolic Approach for Physics-infused Motion Prediction in Off-road Driving](https://mlsanity.com/paper/2404.01596/) (2024)
- [VAMOS: A Hierarchical Vision-Language-Action Model for Capability-Modulated and Steerable Navigation](https://mlsanity.com/paper/2510.20818/) (2025)
- [BEVLoc: Cross-View Localization and Matching via Birds-Eye-View Synthesis](https://mlsanity.com/paper/2410.06410/) (2024)
- [ROVER: A Multi-Season Dataset for Visual SLAM](https://mlsanity.com/paper/2412.02506/) (2024)
- [Deep Bayesian Future Fusion for Self-Supervised, High-Resolution, Off-Road Mapping](https://mlsanity.com/paper/2403.11876/) (2024)
- [Survey on Datasets for Perception in Unstructured Outdoor Environments](https://mlsanity.com/paper/2404.18750/) (2024)
- [Spatiotemporal Contrastive Learning for Cross-View Video Localization in Unstructured Off-road Terrains](https://mlsanity.com/paper/2506.05250/) (2025)
- [TOMD: A Trail-based Off-road Multimodal Dataset for Traversable Pathway Segmentation under Challenging Illumination Conditions](https://mlsanity.com/paper/2506.21630/) (2025)
- [CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography](https://mlsanity.com/paper/2605.05014/) (2026)
- [Robust Monocular Visual Odometry using Curriculum Learning](https://mlsanity.com/paper/2411.13438/) (2024)
- [IRisPath: Enhancing Costmap for Off-Road Navigation with Robust IR-RGB Fusion for Improved Day and Night Traversability](https://mlsanity.com/paper/2412.03173/) (2024)
- [3DTTNet: Multimodal Fusion-Based 3D Traversable Terrain Modeling for Off-Road Environments](https://mlsanity.com/paper/2412.08195/) (2024)
- [Visual Loop Closure Detection Through Deep Graph Consensus](https://mlsanity.com/paper/2505.21754/) (2025)
- [BEV-Patch-PF: Particle Filtering with BEV-Aerial Feature Matching for Off-Road Geo-Localization](https://mlsanity.com/paper/2512.15111/) (2025)
- [A Cross-Scale Decoder with Token Refinement for Off-Road Semantic Segmentation](https://mlsanity.com/paper/2603.27931/) (2026)
- [Multimodal embodiment-aware navigation transformer](https://mlsanity.com/paper/2604.19267/) (2026)
- [Towards All-Day Perception for Off-Road Driving: A Large-Scale Multispectral Dataset and Comprehensive Benchmark](https://mlsanity.com/paper/2604.27499/) (2026)
- [OctoSense: Self-Supervised Learning for Multimodal Robot Perception](https://mlsanity.com/paper/2606.27317/) (2026)
- [Feeling Terrain Before Crossing: World Models for Off-Road Navigation](https://mlsanity.com/paper/2609.19863/) (2026)
- [FLINT: Fast Lightweight Inference for Traversability](https://mlsanity.com/paper/2609.26857/) (2026)
- [From Pixels to Executable Physics: Behavior-Grounded World Models for Embodied Action Consequence Prediction](https://mlsanity.com/paper/2610.17630/) (2026)

## Abstract (arXiv)

We present TartanDrive 2.0, a large-scale off-road driving dataset for self-supervised learning tasks. In 2021 we released TartanDrive 1.0, which is one of the largest datasets for off-road terrain. As a follow-up to our original dataset, we collected seven hours of data at speeds of up to 15m/s with the addition of three new LiDAR sensors alongside the original camera, inertial, GPS, and proprioceptive sensors. We also release the tools we use for collecting, processing, and querying the data, including our metadata system designed to further the utility of our data. Custom infrastructure allows end users to reconfigure the data to cater to their own platforms. These tools and infrastructure alongside the dataset are useful for a variety of tasks in the field of off-road autonomy and, by releasing them, we encourage collaborative data aggregation. These resources lower the barrier to entry to utilizing large-scale datasets, thereby helping facilitate the advancement of robotics in areas such as self-supervised learning, multi-modal perception, inverse reinforcement learning, and representation learning. The dataset is available at https://github.com/castacks/tartan drive 2.0.