Papers › Learning Synergies between Pushing and Grasping with Self-supervised Deep...

Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning

27 Mar 2018arXiv:1803.09956archive 2025-07-28

Andy Zeng, Shuran Song, Stefan Welker, Johnny Lee, Alberto Rodriguez, Thomas Funkhouser

Skilled robotic manipulation benefits from complex synergies between non-prehensile (e.g. pushing) and prehensile (e.g. grasping) actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping can help displace objects to make pushing movements more precise and collision-free. In this work, we demonstrate that it is possible to discover and learn these synergies from scratch through model-free deep reinforcement learning. Our method involves training two fully convolutional networks that map from visual observations to actions: one infers the utility of pushes for a dense pixel-wise sampling of end effector orientations and locations, while the other does the same for grasping. Both networks are trained jointly in a Q-learning framework and are entirely self-supervised by trial and error, where rewards are provided from successful grasps. In this way, our policy learns pushing motions that enable future grasps, while learning grasps that can leverage past pushes. During picking experiments in both simulation and real-world scenarios, we find that our system quickly learns complex behaviors amid challenging cases of clutter, and achieves better grasping success rates and picking efficiencies than baseline alternatives after only a few hours of training. We further demonstrate that our method is capable of generalizing to novel objects. Qualitative results (videos), code, pre-trained models, and simulation environments are available at http://vpg.cs.princeton.edu

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 4 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 7 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

andyzeng/visual-pushing-grasping officialmentioned on GitHubpytorchBSD-2-ClauseSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
cww97/visual-language-grasping mentioned on GitHubpytorchBSD-2-ClauseSyntology: not harvested report
jhu-lcsr/good_robot mentioned on GitHubpytorchBSD-2-ClauseSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
rebekkaorth/robotics_pick_n_place_masterproject mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
2unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

andyzeng/visual-pushing-grasping official repository 4 samples, 3 ran (0 instrument-failed) · 1 unverified
get_heightmap utils.py ran BSD-2-Clause (permissive) · c5da0ddce6880977 · report fixture: signature color_img:ndarray/3/int, depth_img:ndarray/2/float, cam_intrinsics:ndarray/2/float, cam_pose:ndarray/2/float, workspace_limits:ndarray/2/float, heightmap_resolution:float/0/float · returned tuple · level recorded 2026-09-25
get_pointcloud in 6 papers utils.py ran BSD-2-Clause (permissive) · 2008ee658029d65e · report fixture: signature color_img:ndarray/3/int, depth_img:ndarray/2/float, camera_intrinsics:ndarray/2/float · returned tuple · level recorded 2026-09-25
get_rigid_transform calibrate.py ran fingerprinted BSD-2-Clause (permissive) · 66b69e6aec040eec · report fixture: signature A:ndarray/2/float, B:ndarray/2/float · returned tuple · level recorded 2026-09-25
get_affordance_vis utils.py unverified BSD-2-Clause (permissive) · 40580a929888a5e6 · report
jhu-lcsr/good_robot community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
check_success annotate_data.py ran BSD-2-Clause (permissive) · 2f66e33eb753b345 · report fixture: signature data:list/1/list, idx:int/0/int · returned bool · level recorded 2026-09-26
gaussian_augment annotate_data.py ran BSD-2-Clause (permissive) · d13a0b08c052b275 · report fixture: signature pair:ImagePair/0/?, params:tuple/1/float · returned ImagePair · level recorded 2026-09-26
orientation_and_angle_to_push_direction old_robot.py ran BSD-2-Clause (permissive) · cda60434af4d961f · report fixture: signature heightmap_rotation_angle:float/0/float, push_orientation:list/1/float · returned ndarray · level recorded 2026-09-26
tile_vector_as_image_channels_torch models.py ran BSD-2-Clause (permissive) · c3fb49ac0bbf4b2f · report fixture: signature vector_op:Tensor/2/float, image_shape:list/1/int · returned Tensor · level recorded 2026-09-26
trunk_net models.py ran BSD-2-Clause (permissive) · 74eb38f3b409fc2f · report fixture: signature name:str/0/str, fc_channels:int/0/int, second_fc_channels:int/0/int, goal_condition_len:int/0/int, channels_out:int/0/int · returned Sequential · level recorded 2026-09-26
vector_block models.py ran BSD-2-Clause (permissive) · 1d9bce5bd776f699 · report fixture: signature name:str/0/str, channels_in:int/0/int, fc_channels:int/0/int, channels_out:int/0/int · returned Sequential · level recorded 2026-09-26
rotate_pair annotate_data.py unverified BSD-2-Clause (permissive) · b13efc4d8c9255f5 · report

Tasks

Deep Reinforcement LearningQ-LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Q-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections