TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation
This dataset provides a testbed for training and evaluating learning-based tasks in robotics, such as occupancy prediction and SLAM, to improve generalization across diverse environments, though it is incremental as it builds on existing data collection efforts.
The authors introduced TartanGround, a large-scale multi-modal dataset with 1.5 million samples from 910 trajectories across 70 environments, to address the generalization challenges of ground robot perception and navigation, showing that state-of-the-art methods trained on existing datasets struggle in diverse scenes.
We present TartanGround, a large-scale, multi-modal dataset to advance the perception and autonomy of ground robots operating in diverse environments. This dataset, collected in various photorealistic simulation environments includes multiple RGB stereo cameras for 360-degree coverage, along with depth, optical flow, stereo disparity, LiDAR point clouds, ground truth poses, semantic segmented images, and occupancy maps with semantic labels. Data is collected using an integrated automatic pipeline, which generates trajectories mimicking the motion patterns of various ground robot platforms, including wheeled and legged robots. We collect 910 trajectories across 70 environments, resulting in 1.5 million samples. Evaluations on occupancy prediction and SLAM tasks reveal that state-of-the-art methods trained on existing datasets struggle to generalize across diverse scenes. TartanGround can serve as a testbed for training and evaluation of a broad range of learning-based tasks, including occupancy prediction, SLAM, neural scene representation, perception-based navigation, and more, enabling advancements in robotic perception and autonomy towards achieving robust models generalizable to more diverse scenarios. The dataset and codebase are available on the webpage: https://tartanair.org/tartanground