Arena-G1-Static-PickNPlace-Task

Dataset Description: The Arena-G1-Static-PickNPlace-Task dataset is a multimodal collection of trajectories generated in Isaac Lab. It supports humanoid (G1) loco-manipulation task in IsaacLab-Arena environment. Each entry provides the full context (state, vision, language, action) needed to train and evaluate generalist robot policies for an apple pick-and-place task. | Dataset Name | # Trajectories | |---------------------------|----------------| | G1 Static PickNPlace Task | 200 | This dataset is ideal for behavior cloning, policy learning, and generalist robotic manipulation research. It has been for post-training GR00T N1.7 model. This dataset is ready for commercial use. Dataset Owner NVIDIA Corporation Dataset Creation Date: 05/22/2025 License/Terms of Use: This dataset is governed by the Creative Commons Attribution 4.0 International License (CC-BY-4.0). Intended Usage: This dataset is intended for: Training robot manipulation policies using behavior cloning. Research in generalist robotics and task-conditioned agents. Sim-to-real / Sim-to-Sim transfer studies. Dataset Characterization: Data Collection Method Human All 200 demonstrations were manually collected through human teleoperation using a XR headset in Isaac Lab. Each demo was recorded at 50 Hz. Labeling Method Human Dataset Format: We provide a few dataset files, including A manually collected 200-demonstration HDF5 dataset file (`arena_g1_static_apple_dataset_recorded_200_demos.hdf5`) A LeRobot format dataset, converted from the collected HDF5 dataset. Converted dataset is in the `lerobot` directory. Each demo in GR00T-Lerobot datasets consists of a time-indexed sequence of the following modalities: Actions action (FP32): joint desired positions for all body joints (43 DoF) Observations observation.state (FP32): joint positions for all body joints (43 DoF) Task-specific timestamp (FP64): simulation time in seconds of each recorded data entry. annotation.human.task_description (INT64): index referri