{"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/geometry-aware-rl-for-manipulation-of-varying","title":"Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects","arxiv_id":"2502.07005","date":"2025-02-10","proceeding":null,"authors":["Tai Hoang","Huy Le","Philipp Becker","Vien Anh Ngo","Gerhard Neumann"],"abstract":"Manipulating objects with varying geometries and deformable objects is a major challenge in robotics. Tasks such as insertion with different objects or cloth hanging require precise control and effective modelling of complex dynamics. In this work, we frame this problem through the lens of a heterogeneous graph that comprises smaller sub-graphs, such as actuators and objects, accompanied by different edge types describing their interactions. This graph representation serves as a unified structure for both rigid and deformable objects tasks, and can be extended further to tasks comprising multiple actuators. To evaluate this setup, we present a novel and challenging reinforcement learning benchmark, including rigid insertion of diverse objects, as well as rope and cloth manipulation with multiple end-effectors. These tasks present a large search space, as both the initial and target configurations are uniformly sampled in 3D space. To address this issue, we propose a novel graph-based policy model, dubbed Heterogeneous Equivariant Policy (HEPi), utilizing $SE(3)$ equivariant message passing networks as the main backbone to exploit the geometric symmetry. In addition, by modeling explicit heterogeneity, HEPi can outperform Transformer-based and non-heterogeneous equivariant policies in terms of average returns, sample efficiency, and generalization to unseen objects. Our project page is available at https://thobotics.github.io/hepi.","url_abs":"https://arxiv.org/abs/2502.07005v6","url_pdf":"https://arxiv.org/pdf/2502.07005v6.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":"geometry-aware-rl-for-manipulation-of-varying","repo_url":"https://github.com/thobotics/geometry_rl","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.07005","atlas_url":"https://app.syntology.ai/?focus=2502.07005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07005"}},"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/thobotics/geometry_rl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"4be4581d86b3faf3","entry":"add_noise","repo":"thobotics/geometry_rl","repo_kind":"official","path":"geometry_rl/modules/pyg_data/utils.py","file_url":"https://github.com/thobotics/geometry_rl/blob/HEAD/geometry_rl/modules/pyg_data/utils.py","link_basis":"harvester_set","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":"4be4581d86b3faf3"}},{"code_sha256_prefix":"10d899539b7452d7","entry":"exponential_weight","repo":"thobotics/geometry_rl","repo_kind":"official","path":"geometry_rl/modules/pyg_data/utils.py","file_url":"https://github.com/thobotics/geometry_rl/blob/HEAD/geometry_rl/modules/pyg_data/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10d899539b7452d7"}},{"code_sha256_prefix":"c1641728823d6467","entry":"noise_like","repo":"thobotics/geometry_rl","repo_kind":"official","path":"geometry_rl/modules/pyg_data/utils.py","file_url":"https://github.com/thobotics/geometry_rl/blob/HEAD/geometry_rl/modules/pyg_data/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c1641728823d6467"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}