{"work":{"id":"1fb6c1b7-913d-4a89-bbad-842fdb5fca1d","openalex_id":null,"doi":null,"arxiv_id":"2203.12601","raw_key":null,"title":"R3M: A Universal Visual Representation for Robot Manipulation","authors":null,"authors_text":"Suraj Nair, Aravind Rajeswaran, Vikash Kumar, Chelsea Finn, Abhinav Gupta","year":2022,"venue":"cs.RO","abstract":"We study how visual representations pre-trained on diverse human video data can enable data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a visual representation using the Ego4D human video dataset using a combination of time-contrastive learning, video-language alignment, and an L1 penalty to encourage sparse and compact representations. The resulting representation, R3M, can be used as a frozen perception module for downstream policy learning. Across a suite of 12 simulated robot manipulation tasks, we find that R3M improves task success by over 20% compared to training from scratch and by over 10% compared to state-of-the-art visual representations like CLIP and MoCo. Furthermore, R3M enables a Franka Emika Panda arm to learn a range of manipulation tasks in a real, cluttered apartment given just 20 demonstrations. Code and pre-trained models are available at https://tinyurl.com/robotr3m.","external_url":"https://arxiv.org/abs/2203.12601","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T03:56:36.999689+00:00","pith_arxiv_id":"2203.12601","created_at":"2026-05-10T03:03:37.469454+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"R3M: A Universal Visual Representation for Robot Manipulation","render_title":"R3M: A Universal Visual Representation for Robot Manipulation"},"hub":{"state":{"work_id":"1fb6c1b7-913d-4a89-bbad-842fdb5fca1d","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":39,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2022-04-04T17:57:11+00:00","last_pith_cited_at":"2026-05-22T17:08:37+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-06T18:11:00.787185+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":13},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":13},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}