{"url":"/dataset/visuomotor-affordance-learning-val-robot","name":"Visuomotor affordance learning (VAL) robot interaction dataset","full_name":null,"description_markdown":"This data contains about 2500 trajectories (with images and actions) of a Sawyer robot interacting with various objects.\r\n\r\nExamples from the dataset are shown in the adjacent video. We provide two versions of the VAL dataset - one with low-res images (1.4 GB) and one with high-res images (162 GB). The data quantity and format is the same between these two versions; the difference is only the image observation quality.\r\n\r\nThe smaller dataset, with 48x48x3 images which can be used for eg. offline RL, is available for direct download: <https://drive.google.com/file/d/1UuWANkVtWLg4egIK2LB_YCKuF87rMQ1H/view?usp=sharing>\r\n\r\nThe larger dataset, with 480x640x3 which might be preferred for eg. representation learning, is available at this Google drive folder:  <https://drive.google.com/drive/folders/1kD9kyP7-RlIrSnuN7rpEASAGWp5qnNov?usp=sharing>\r\n\r\nTo download the larger dataset, we suggest using https://rclone.org/\r\n\r\nThe data is sorted into several folders. There are a total of 300 files and 2500 trajectories.\r\n- fixed_drawer - Human-controlled demonstration data opening and closing drawers. (~10%)\r\n- fixed_pnp - Human-controlled demonstration data picking up objects. (~10%)\r\n- fixed_pot - Human-controlled demonstration data interacting with a pot and a lid. (~10%)\r\n- fixed_tray - Human-controlled demonstration data picking up objects and placing it in a tray. (~10%)\r\n- general - Further human-controlled demonstration data collected with the most diversity and variation. (~40%)\r\n- onpolicy_eval - Evaluation data collected by an RL policy. (~10%)\r\n- onpolicy_expl - Exploration data collected by an RL policy. (~10%)","description_withheld":null,"homepage":"https://sites.google.com/view/val-rl","introduced_date":"2021-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/what-can-i-do-here-learning-new-skills-by","title":"What Can I Do Here? Learning New Skills by Imagining Visual Affordances","first_author":"Alexander Khazatsky","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Actions","url":"/datasets/modality/actions"}],"tasks":[{"name":"Offline RL","url":"/task/offline-rl","datasets_with_task":"/datasets/task/offline-rl"}],"languages":[],"variants":["Visuomotor affordance learning (VAL) robot interaction dataset"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}