{"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/polarnet-3d-point-clouds-for-language-guided","title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","arxiv_id":"2309.15596","date":"2023-09-27","proceeding":null,"authors":["ShiZhe Chen","Ricardo Garcia","Cordelia Schmid","Ivan Laptev"],"abstract":"The ability for robots to comprehend and execute manipulation tasks based on natural language instructions is a long-term goal in robotics. The dominant approaches for language-guided manipulation use 2D image representations, which face difficulties in combining multi-view cameras and inferring precise 3D positions and relationships. To address these limitations, we propose a 3D point cloud based policy called PolarNet for language-guided manipulation. It leverages carefully designed point cloud inputs, efficient point cloud encoders, and multimodal transformers to learn 3D point cloud representations and integrate them with language instructions for action prediction. PolarNet is shown to be effective and data efficient in a variety of experiments conducted on the RLBench benchmark. It outperforms state-of-the-art 2D and 3D approaches in both single-task and multi-task learning. It also achieves promising results on a real robot.","url_abs":"https://arxiv.org/abs/2309.15596v1","url_pdf":"https://arxiv.org/pdf/2309.15596v1.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":"polarnet-3d-point-clouds-for-language-guided","repo_url":"https://github.com/vlc-robot/polarnet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"robot-manipulation","task_name":"Robot Manipulation"},{"task_slug":"robot-manipulation-generalization","task_name":"Robot Manipulation Generalization"}],"methods":[{"method_slug":"polarnet","method_name":"PolarNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/robot-manipulation-on-rlbench","task":"Robot Manipulation","dataset":"RLBench","model":"PolarNet","rank_in_archive_order":12,"of":18,"metrics":{"Input Image Size":"128","Succ. Rate (10 tasks, 100 demos/task)":"89.8","Succ. Rate (18 tasks, 100 demo/task)":"46.4","Succ. Rate (74 tasks, 100 demos/task)":"60.3","Training Time (V100 x 8 x day)":"5"},"uses_additional_data":false},{"leaderboard":"/sota/robot-manipulation-generalization-on-gembench","task":"Robot Manipulation Generalization","dataset":"GEMBench","model":"PolarNet","rank_in_archive_order":5,"of":6,"metrics":{"Average Success Rate":"38.4","Average Success Rate (L1)":"77.7±0.9","Average Success Rate (L2)":"37.1±1.4","Average Success Rate (L3)":"38.5±1.7","Average Success Rate (L4)":"0.1±0.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.15596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15596"}},"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/vlc-robot/polarnet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"838a8eb3bc05bb2f","entry":"get_workspace","repo":"vlc-robot/polarnet","repo_kind":"official","path":"polarnet/config/constants.py","file_url":"https://github.com/vlc-robot/polarnet/blob/HEAD/polarnet/config/constants.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"838a8eb3bc05bb2f"}},{"code_sha256_prefix":"41d28274f234df92","entry":"get_config","repo":"vlc-robot/polarnet","repo_kind":"official","path":"polarnet/config/default.py","file_url":"https://github.com/vlc-robot/polarnet/blob/HEAD/polarnet/config/default.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":"41d28274f234df92"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}