{"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/policy-pre-training-for-end-to-end-autonomous","title":"Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling","arxiv_id":"2301.01006","date":"2023-01-03","proceeding":null,"authors":["Penghao Wu","Li Chen","Hongyang Li","Xiaosong Jia","Junchi Yan","Yu Qiao"],"abstract":"Witnessing the impressive achievements of pre-training techniques on large-scale data in the field of computer vision and natural language processing, we wonder whether this idea could be adapted in a grab-and-go spirit, and mitigate the sample inefficiency problem for visuomotor driving. Given the highly dynamic and variant nature of the input, the visuomotor driving task inherently lacks view and translation invariance, and the visual input contains massive irrelevant information for decision making, resulting in predominant pre-training approaches from general vision less suitable for the autonomous driving task. To this end, we propose PPGeo (Policy Pre-training via Geometric modeling), an intuitive and straightforward fully self-supervised framework curated for the policy pretraining in visuomotor driving. We aim at learning policy representations as a powerful abstraction by modeling 3D geometric scenes on large-scale unlabeled and uncalibrated YouTube driving videos. The proposed PPGeo is performed in two stages to support effective self-supervised training. In the first stage, the geometric modeling framework generates pose and depth predictions simultaneously, with two consecutive frames as input. In the second stage, the visual encoder learns driving policy representation by predicting the future ego-motion and optimizing with the photometric error based on current visual observation only. As such, the pre-trained visual encoder is equipped with rich driving policy related representations and thereby competent for multiple visuomotor driving tasks. Extensive experiments covering a wide span of challenging scenarios have demonstrated the superiority of our proposed approach, where improvements range from 2% to even over 100% with very limited data.","url_abs":"https://arxiv.org/abs/2301.01006v2","url_pdf":"https://arxiv.org/pdf/2301.01006v2.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":"policy-pre-training-for-end-to-end-autonomous","repo_url":"https://github.com/opendrivelab/ppgeo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.01006","atlas_url":"https://app.syntology.ai/?focus=2301.01006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.01006"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/opendrivelab/ppgeo","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":5,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":"2a80220dabcb742a","entry":"conv1x1","repo":"opendrivelab/ppgeo","repo_kind":"official","path":"resnet.py","file_url":"https://github.com/opendrivelab/ppgeo/blob/HEAD/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2a80220dabcb742a"}},{"code_sha256_prefix":"600ff2c45e0de056","entry":"conv3x3","repo":"opendrivelab/ppgeo","repo_kind":"official","path":"resnet.py","file_url":"https://github.com/opendrivelab/ppgeo/blob/HEAD/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"600ff2c45e0de056"}},{"code_sha256_prefix":"62287188376f0ba0","entry":"disp_to_depth","repo":"opendrivelab/ppgeo","repo_kind":"official","path":"layers.py","file_url":"https://github.com/opendrivelab/ppgeo/blob/HEAD/layers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"62287188376f0ba0"}},{"code_sha256_prefix":"955112f5788539a8","entry":"get_translation_matrix","repo":"opendrivelab/ppgeo","repo_kind":"official","path":"layers.py","file_url":"https://github.com/opendrivelab/ppgeo/blob/HEAD/layers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"955112f5788539a8"}},{"code_sha256_prefix":"1df9a5ffd9b38c34","entry":"pil_loader","repo":"opendrivelab/ppgeo","repo_kind":"official","path":"data_ytb.py","file_url":"https://github.com/opendrivelab/ppgeo/blob/HEAD/data_ytb.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1df9a5ffd9b38c34"}},{"code_sha256_prefix":"21846a1e6ae2b8bf","entry":"resnet18","repo":"opendrivelab/ppgeo","repo_kind":"official","path":"resnet.py","file_url":"https://github.com/opendrivelab/ppgeo/blob/HEAD/resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21846a1e6ae2b8bf"}},{"code_sha256_prefix":"ab7c813560099f29","entry":"resnet_multiimage_input","repo":"opendrivelab/ppgeo","repo_kind":"official","path":"networks/resnet_encoder.py","file_url":"https://github.com/opendrivelab/ppgeo/blob/HEAD/networks/resnet_encoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ab7c813560099f29"}},{"code_sha256_prefix":"cdc03d6bfc4d3a34","entry":"transformation_from_parameters","repo":"opendrivelab/ppgeo","repo_kind":"official","path":"layers.py","file_url":"https://github.com/opendrivelab/ppgeo/blob/HEAD/layers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cdc03d6bfc4d3a34"}},{"code_sha256_prefix":"9075e512a7151e61","entry":"resnet18","repo":"opendrivelab/ppgeo","repo_kind":"official","path":"nuscenes_planning/resnet.py","file_url":"https://github.com/opendrivelab/ppgeo/blob/HEAD/nuscenes_planning/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9075e512a7151e61"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}