TartanDrive
TartanDrive is a large-scale real-world off-road driving dataset from CMU's AirLab, built for learning off-road vehicle dynamics models. It contains roughly 200,000 off-road driving interactions (about five hours of data) collected on a modified Yamaha Viking ATV driven across diverse terrain. The authors describe it as the largest real-world multimodal off-road driving dataset both in number of interactions and in number of sensing modalities. It provides seven unique sensing modalities: stereo RGB camera imagery (1024x512 @ 20Hz from a MultiSense S21), bird's-eye-view RGB maps (501x501 @ 20Hz) and heightmaps (501x501 @ 20Hz) derived from the stereo RGB-D mapping pipeline (not LiDAR), IMU (6D @ 200Hz), GPS-derived odometry/state (7D @ 50Hz), and vehicle proprioception including wheel RPM (4D @ 50Hz), shock/suspension position (4D @ 50Hz), and pedal/throttle commands (2D action @ 100Hz). Data are distributed as compressed rosbags (~100GB per compressed folder) that can be converted to PyTorch tensors or NumPy arrays via the provided scripts at github.com/castacks/tartan_drive. The dataset was introduced at ICRA 2022 and benchmarks state-of-the-art model-based RL methods for off-road dynamics prediction, showing that multi-modality improves prediction especially on challenging terrain. A follow-up, TartanDrive 2.0, adds LiDAR (two Velodyne VLP-32 and a Livox Mid-70) and seven hours of data.
- Scale
- 5 hours
- Formats
- custom · rosbag
- License
- CC-BY-4.0
- Published
- 2022-05-03
Decision summary
manual_operation
Metadata requires review against the official source before publication.
Read the dataset manifest and feature schema.
Catalog assessment
Selection evidence
73/100
Provisional · confidence 48 · 4/6 evaluated
Access and governance
Access and license are declared by the source.
Schema and signal coverage
No machine-readable schema has been verified yet.
Policy training readiness
Observation and action/state signals are declared; alignment quality still depends on sample verification.
View 3 more dimensions
World-model readiness
Temporal observations plus geometry or semantic context are declared; sample alignment remains to be audited.
Failure and recovery readiness
No verified failure/recovery annotation evidence is available yet.
Download and processing readiness
Scale is declared; transfer and processing estimates are not measured.
Review unresolved evidence and next checks
Signal gaps
- Language intent / task phase. Not enough evidence is available to classify this signal.
- Feedback / correction / failure. Not enough evidence is available to classify this signal.
Next checks
- Read the dataset manifest and feature schema.
- Run a bounded sample audit before assigning Strong readiness.
Record specifics
Dataset facts
- Source
- CMU AirLab
- Evidence
- secondary claim
- Formats
- custom · rosbag
- hours
- 5
Metadata coverage
Loop signals
5/7 present or partial
No decision-grade evidence captured yet.
unknownNo decision-grade evidence captured yet.
unknownView 5 more signal categories
depth · video · TartanDrive is a large-scale real-world off-road driving dataset from CMU's AirLab, built for learning off-road vehicle dynamics models. It contains roughly 200,000 off-road driving interactions (about five hours of data) collected on a modified Yamaha Viking ATV driven across diverse terrain. The authors describe it as the largest real-world multimodal off-road driving dataset both in number of interactions and in number of sensing modalities. It provides seven unique sensing modalities: stereo RGB camera imagery (1024x512 @ 20Hz from a MultiSense S21), bird's-eye-view RGB maps (501x501 @ 20Hz) and heightmaps (501x501 @ 20Hz) derived from the stereo RGB-D mapping pipeline (not LiDAR), IMU (6D @ 200Hz), GPS-derived odometry/state (7D @ 50Hz), and vehicle proprioception including wheel RPM (4D @ 50Hz), shock/suspension position (4D @ 50Hz), and pedal/throttle commands (2D action @ 100Hz). Data are distributed as compressed rosbags (~100GB per compressed folder) that can be converted to PyTorch tensors or NumPy arrays via the provided scripts at github.com/castacks/tartan_drive. The dataset was introduced at ICRA 2022 and benchmarks state-of-the-art model-based RL methods for off-road dynamics prediction, showing that multi-modality improves prediction especially on challenging terrain. A follow-up, TartanDrive 2.0, adds LiDAR (two Velodyne VLP-32 and a Livox Mid-70) and seven hours of data.
presentTartanDrive is a large-scale real-world off-road driving dataset from CMU's AirLab, built for learning off-road vehicle dynamics models. It contains roughly 200,000 off-road driving interactions (about five hours of data) collected on a modified Yamaha Viking ATV driven across diverse terrain. The authors describe it as the largest real-world multimodal off-road driving dataset both in number of interactions and in number of sensing modalities. It provides seven unique sensing modalities: stereo RGB camera imagery (1024x512 @ 20Hz from a MultiSense S21), bird's-eye-view RGB maps (501x501 @ 20Hz) and heightmaps (501x501 @ 20Hz) derived from the stereo RGB-D mapping pipeline (not LiDAR), IMU (6D @ 200Hz), GPS-derived odometry/state (7D @ 50Hz), and vehicle proprioception including wheel RPM (4D @ 50Hz), shock/suspension position (4D @ 50Hz), and pedal/throttle commands (2D action @ 100Hz). Data are distributed as compressed rosbags (~100GB per compressed folder) that can be converted to PyTorch tensors or NumPy arrays via the provided scripts at github.com/castacks/tartan_drive. The dataset was introduced at ICRA 2022 and benchmarks state-of-the-art model-based RL methods for off-road dynamics prediction, showing that multi-modality improves prediction especially on challenging terrain. A follow-up, TartanDrive 2.0, adds LiDAR (two Velodyne VLP-32 and a Livox Mid-70) and seven hours of data.
presentTartanDrive is a large-scale real-world off-road driving dataset from CMU's AirLab, built for learning off-road vehicle dynamics models. It contains roughly 200,000 off-road driving interactions (about five hours of data) collected on a modified Yamaha Viking ATV driven across diverse terrain. The authors describe it as the largest real-world multimodal off-road driving dataset both in number of interactions and in number of sensing modalities. It provides seven unique sensing modalities: stereo RGB camera imagery (1024x512 @ 20Hz from a MultiSense S21), bird's-eye-view RGB maps (501x501 @ 20Hz) and heightmaps (501x501 @ 20Hz) derived from the stereo RGB-D mapping pipeline (not LiDAR), IMU (6D @ 200Hz), GPS-derived odometry/state (7D @ 50Hz), and vehicle proprioception including wheel RPM (4D @ 50Hz), shock/suspension position (4D @ 50Hz), and pedal/throttle commands (2D action @ 100Hz). Data are distributed as compressed rosbags (~100GB per compressed folder) that can be converted to PyTorch tensors or NumPy arrays via the provided scripts at github.com/castacks/tartan_drive. The dataset was introduced at ICRA 2022 and benchmarks state-of-the-art model-based RL methods for off-road dynamics prediction, showing that multi-modality improves prediction especially on challenging terrain. A follow-up, TartanDrive 2.0, adds LiDAR (two Velodyne VLP-32 and a Livox Mid-70) and seven hours of data.
partialdepth
presentOpen · CC-BY-4.0 · custom · rosbag
partialEvidence details and provenance
Official signal claims
Schema and annotations
No machine-readable schema facts are captured.
Sample verification
Pending. Metadata does not prove sample coverage, alignment, or file integrity.
curated official source
Integration notes
- Metadata requires review against the official source before publication.
Catalog links