{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/making-sense-of-vision-and-touch-self","title":"Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks","arxiv_id":"1810.10191","date":"2018-10-24","proceeding":null,"authors":["Michelle A. Lee","Yuke Zhu","Krishnan Srinivasan","Parth Shah","Silvio Savarese","Li Fei-Fei","Animesh Garg","Jeannette Bohg"],"abstract":"Contact-rich manipulation tasks in unstructured environments often require\nboth haptic and visual feedback. However, it is non-trivial to manually design\na robot controller that combines modalities with very different\ncharacteristics. While deep reinforcement learning has shown success in\nlearning control policies for high-dimensional inputs, these algorithms are\ngenerally intractable to deploy on real robots due to sample complexity. We use\nself-supervision to learn a compact and multimodal representation of our\nsensory inputs, which can then be used to improve the sample efficiency of our\npolicy learning. We evaluate our method on a peg insertion task, generalizing\nover different geometry, configurations, and clearances, while being robust to\nexternal perturbations. Results for simulated and real robot experiments are\npresented.","url_abs":"http://arxiv.org/abs/1810.10191v2","url_pdf":"http://arxiv.org/pdf/1810.10191v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"making-sense-of-vision-and-touch-self","repo_url":"https://github.com/stanford-iprl-lab/multimodal_representation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"making-sense-of-vision-and-touch-self","repo_url":"https://github.com/Henry1iu/ierg5350_rl_course_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contact-rich-manipulation","task_name":"Contact-rich Manipulation"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.10191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.10191"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanford-iprl-lab/multimodal_representation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Henry1iu/ierg5350_rl_course_project","reach":null}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1},"listed":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"dcf160ba03ce4e37","entry":"compute_accuracy","repo":"stanford-iprl-lab/multimodal_representation","repo_kind":"official","path":"multimodal/utils.py","file_url":"https://github.com/stanford-iprl-lab/multimodal_representation/blob/HEAD/multimodal/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dcf160ba03ce4e37"}},{"code_sha256_prefix":"392b3288ca7725c3","entry":"crop_like","repo":"stanford-iprl-lab/multimodal_representation","repo_kind":"official","path":"multimodal/models/base_models/layers.py","file_url":"https://github.com/stanford-iprl-lab/multimodal_representation/blob/HEAD/multimodal/models/base_models/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"392b3288ca7725c3"}},{"code_sha256_prefix":"05aaa6b1fc1c8968","entry":"deconv","repo":"stanford-iprl-lab/multimodal_representation","repo_kind":"official","path":"multimodal/models/base_models/layers.py","file_url":"https://github.com/stanford-iprl-lab/multimodal_representation/blob/HEAD/multimodal/models/base_models/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05aaa6b1fc1c8968"}},{"code_sha256_prefix":"3d8a38f1bf0a035d","entry":"detach_var","repo":"stanford-iprl-lab/multimodal_representation","repo_kind":"official","path":"multimodal/utils.py","file_url":"https://github.com/stanford-iprl-lab/multimodal_representation/blob/HEAD/multimodal/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d8a38f1bf0a035d"}},{"code_sha256_prefix":"e98d143c6058ff0d","entry":"evaluate","repo":"Henry1iu/ierg5350_rl_course_project","repo_kind":"listed","path":"multimodal/train_my_fusion_model.py","file_url":"https://github.com/Henry1iu/ierg5350_rl_course_project/blob/HEAD/multimodal/train_my_fusion_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e98d143c6058ff0d"}},{"code_sha256_prefix":"c18fc9e2821c1a2a","entry":"gaussian_parameters","repo":"stanford-iprl-lab/multimodal_representation","repo_kind":"official","path":"multimodal/models/models_utils.py","file_url":"https://github.com/stanford-iprl-lab/multimodal_representation/blob/HEAD/multimodal/models/models_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c18fc9e2821c1a2a"}},{"code_sha256_prefix":"105d32c87eefda24","entry":"predict_flow","repo":"stanford-iprl-lab/multimodal_representation","repo_kind":"official","path":"multimodal/models/base_models/layers.py","file_url":"https://github.com/stanford-iprl-lab/multimodal_representation/blob/HEAD/multimodal/models/base_models/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"105d32c87eefda24"}},{"code_sha256_prefix":"191ab481350745a3","entry":"product_of_experts","repo":"stanford-iprl-lab/multimodal_representation","repo_kind":"official","path":"multimodal/models/models_utils.py","file_url":"https://github.com/stanford-iprl-lab/multimodal_representation/blob/HEAD/multimodal/models/models_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"191ab481350745a3"}},{"code_sha256_prefix":"8246ecd2d729f5a3","entry":"quaternion_to_euler","repo":"stanford-iprl-lab/multimodal_representation","repo_kind":"official","path":"multimodal/utils.py","file_url":"https://github.com/stanford-iprl-lab/multimodal_representation/blob/HEAD/multimodal/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8246ecd2d729f5a3"}},{"code_sha256_prefix":"c2dce1e9a43381ec","entry":"sample_gaussian","repo":"stanford-iprl-lab/multimodal_representation","repo_kind":"official","path":"multimodal/models/models_utils.py","file_url":"https://github.com/stanford-iprl-lab/multimodal_representation/blob/HEAD/multimodal/models/models_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2dce1e9a43381ec"}},{"code_sha256_prefix":"bf030a9f1859cfda","entry":"train","repo":"Henry1iu/ierg5350_rl_course_project","repo_kind":"listed","path":"multimodal/train_my_fusion_model.py","file_url":"https://github.com/Henry1iu/ierg5350_rl_course_project/blob/HEAD/multimodal/train_my_fusion_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf030a9f1859cfda"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}