DARPA Invisible Headlights: Multi-Sensor Off-Road Navigation Data

Kitware provides a large-scale multi-sensor dataset for autonomous, off-road navigation. It features simultaneously collected imagery from multispectral, hyperspectral, polarimetric, and broadband sensors, spanning wavelengths from visible to long-wave infrared, with aligned LIDAR data for ground-truth shape. Camera calibrations, LiDAR registrations, and traversability annotations are available for a subset.

Use Cases

• Developing sensor fusion models based on simultaneously collected multispectral, hyperspectral, polarimetric, and broadband imagery.
• Training off-road terrain traversability classifiers based on the provided subset of annotations.
• Benchmarking 3D shape reconstruction algorithms based on aligned LIDAR ground-truth data.
• Calibrating and registering multi-sensor systems for autonomous navigation based on the provided camera and LiDAR calibration data.

Strengths

• Features data from multiple sensor modalities collected simultaneously.
• Includes aligned LIDAR data to provide ground-truth shape information.
• Provides camera calibrations, LiDAR registrations, and traversability annotations for a subset.

Limitations

• Row count and total dataset size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Kitware, via the aws_open_data platform.

Collection Method

Simultaneously collected off-road imagery and LIDAR data, annotated for navigation.

Time Range

null

Freshness

Last update date is unknown; freshness unverified.

Geography

null