GraspADMM: Improving Dexterous Grasp Synthesis via ADMM Optimization

Liangwang Ruan; Jiayi Chen; He Wang; Baoquan Chen

cs.ROMar 14, 2026

GraspADMM: Improving Dexterous Grasp Synthesis via ADMM Optimization

Authors: Liangwang Ruan, Jiayi Chen, He Wang, Baoquan Chen

Organizations: School of Computer Science, Peking University. · Galbot. · School of Intelligence Science and Technology, Peking University.

Abstract

Synthesizing high-quality dexterous grasps is a fundamental challenge in robot manipulation, requiring adherence to diversity, kinematic feasibility (valid hand-object contact without penetration), and dynamic stability (secure multi-contact forces). The recent framework Dexonomy successfully ensures broad grasp diversity through dense sampling and improves kinematic feasibility via a simulator-based refinement method that excels at resolving exact collisions. However, its reliance on fixed contact points restricts the hand's reachability and prevents the optimization of grasp metrics for dynamic stability. Conversely, purely gradient-based optimizers can maximize dynamic stability but rely on simplified contact approximations that inevitably cause physical penetrations. To bridge this gap, we propose GraspADMM, a novel grasp synthesis framework that preserves sampling-based diversity while improving kinematic feasibility and dynamic stability. By formulating the refinement stage using the Alternating Direction Method of Multipliers (ADMM), we decouple the target contact points on the object from the actual contact locations on the hand. This decomposition allows the pipeline to alternate between updating the target object points to directly maximize dynamic grasp metrics, and adjusting the hand pose to physically reach these targets while strictly respecting collision boundaries. Extensive experiments demonstrate that GraspADMM significantly outperforms state-of-the-art baselines, achieving a nearly 15% absolute improvement in grasp success rate for type-unaware synthesis and roughly a 100% relative improvement in type-aware synthesis. Furthermore, our approach maintains robust, physically plausible grasp generation even under extreme low-friction conditions.

Figures & tables

Fig. 1 : Overview . From the same initialization, our GraspADMM framework generates robust grasps by optimizing contact points on the hand (red) and the object (yellow), while Dexonomy [ 13 ] simply fixes these points.

Methodology	Diversity	Kinematic Feasibility	Dynamic Stability	Speed
Sampling-based (e.g., GraspIt! [ 4 ] )	$\times$	$\times$	$\sim$	$\times$
Gradient-based (e.g., MALA [ 5 ] )	$\sim$	$\times$	$\checkmark$	$\sim$
Simulator-based (Dexonomy [ 13 ] )	$\checkmark$	$\sim$	$\sim$	$\checkmark$
GraspADMM (Ours)	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$

TABLE I : Comparison of Dexterous Grasp Synthesis Paradigms. We evaluate existing methodologies based on their ability to satisfy the four core requirements of high-quality grasp generation. (

\checkmark

: Fully supports;

\sim

: Partially supports / Some work supports;

\times

: Struggles).

Fig. 2 : ADMM Optimization Pipeline . (a) Update target object contact points $\mathbf{p}^{o}$ via gradient descent to maximize dynamic stability. (b) Update hand pose $\mathbf{q}$ and points $\mathbf{p}^{h}$ via forward-simulated transposed Jacobian control to satisfy kinematic feasibility. (c) Update the dual variable $\lambda$ .

Method	GSR $\uparrow$	OSR $\uparrow$	CDC $\downarrow$	PD $\downarrow$	Div $\downarrow$
DexGraspNet [ 8 ]	12.1	57.0	7.6	4.9	29.0
FRoGGeR [ 10 ]	10.3	55.7	5.0	0.2	27.0
SpringGrasp [ 11 ]	7.8	35.4	23.6	16.6	70.2
BODex [ 12 ]	49.2	96.6	3.0	0.6	32.5
Dexonomy [ 13 ]	60.5	96.5	0.21	0.0	34.2
GraspADMM (Ours)	74.6	97.2	0.17	0.0	25.7

TABLE II : Type-Unaware Grasp Synthesis Comparison. Our method greatly outperforms Dexonomy on grasp success rate and diversity.

Fig. 3 : Visualization of Optimized Grasps. Comparison using the Allegro hand (blue) and Shadow hand (black). Given identical initializations, our method synthesizes more physically stable grasps than Dexonomy. Two representative ADMM convergence curves are also shown here.

Fig. 4 : Performance on the Hard Benchmark. Grasp success rate and object success rate across varying tangential friction coefficients. Our method consistently outperforms Dexonomy.

Grasp Type	GSR (%) $\uparrow$	OSR (%) $\uparrow$	CLN $\uparrow$	Div (%) $\downarrow$
Power	62.8 / 32.9	96.2 / 88.7	12.3 / 9.3	26.4 / 25.2
Intermediate	54.6 / 29.9	96.1 / 89.0	7.4 / 6.4	25.6 / 25.0
Precision	59.2 / 37.5	99.1 / 95.2	5.5 / 4.7	25.1 / 25.0

TABLE III : Type-Aware Grasp Synthesis Comparison. Results are presented as (Ours / Dexonomy [ 13 ] ). We achieve roughly a 100% relative improvement on the grasp success rate.

Fig. 5 : Robustness under Extreme Low Friction ( $\mu=0.1$ ). For each displayed object-template pair, Dexonomy produces only one successful grasp among 100 attempts ( $\text{GSR}=1\%$ ), while GraspADMM produces more successful grasps from the same 100 initializations ( $\text{GSR}>5\%$ ). The aggregate success rates over the full benchmark are reported in Fig. 4.

	GSR $\uparrow$	OSR $\uparrow$	CDC $\downarrow$	PD $\downarrow$
No initialization	27.2	55.1	0.31	0.0
$\rho=0$	17.8	72.6	10.24	4.95
$\rho=10^{2}$	73.5	96.7	0.21	0.0
$\rho=10^{4}$	59.3	96.2	0.29	0.0
$\rho\rightarrow\infty$	62.6	94.7	0.04	0.0
Ours ( $\rho=10^{3}$ )	74.6	97.2	0.17	0.0

TABLE IV : Ablation Study. A good initialization and a moderate

\rho

10^{2}

and

10^{3}

is important.

Fig. 6 : Effect of Dual Variable Annealing. Green: target object contacts $\mathbf{p}^{o}$ . Red: dual-shifted targets $\mathbf{p}^{o}-\lambda$ .

Explore similar work

DexEvolve: Evolutionary Optimization for Robust and Diverse Dexterous Grasp Synthesis
Feb 16, 2026René Zurbrügg, Andrei Cramariuc, Marco HutterRobotic Grasping Dexterous Manipulation
ETH Zürich
Adversarial Game-Theoretic Algorithm for Dexterous Grasp Synthesis
Nov 8, 2025Yu Chen, Botao He, Yuemin Mao +7Robotic Grasping Dexterous Manipulation
Robotics Institute, Carnegie Mellon University, PA 15213 · Department of Computer Science, University of Maryland, MD 20742 · Department of Computer and Information Science, University of Pennsylvania, PA 19104
CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning
Aug 20, 2026Julien Merand, Boris Meden, Liming Chen +1Robotic Grasping Dexterous Manipulation
Université Paris-Saclay, CEA, List, F-91120 Palaiseau, France · Ecole Centrale Lyon, CNRS, LIRIS, UMR5205, Institut Universitaire de France (IUF), F-69130 Ecully, France

Feb 16, 2026J/K move · Enter open · S save

DexEvolve: Evolutionary Optimization for Robust and Diverse Dexterous Grasp Synthesis

René Zurbrügg, Andrei Cramariuc, Marco Hutter

ETH Zürich

Robotic Grasping Dexterous Manipulation Synthetic Data Generation for Robotics Evolutionary Optimization

Open paper AskPDF arXiv

Dexterous grasping is fundamental to robotics, yet data-driven grasp prediction heavily relies on large, diverse datasets that are costly to generate and typically limited to a narrow set of gripper morphologies. Analytical grasp synthesis can be used to scale data collection, but necessary simplifying assumptions often yield physically infeasible grasps that need to be filtered in high-fidelity simulators, significantly reducing the total number of grasps and their diversity. We propose a scalable generate-and-refine pipeline for synthesizing large-scale, diverse, and physically feasible grasps. Instead of using high-fidelity simulators solely for verification and filtering, we leverage them as an optimization stage that continuously improves grasp quality without discarding precomputed candidates. More specifically, we initialize an evolutionary search with a seed set of analytically generated, potentially suboptimal grasps. We then refine these proposals directly in a high-fidelity simulator (Isaac Sim) using an asynchronous, gradient-free evolutionary algorithm, improving stability while maintaining diversity. In addition, this refinement stage can be guided toward human preferences and/or domain-specific quality metrics without requiring a differentiable objective. We further distill the refined grasp distribution into a diffusion model for robust real-world deployment, and highlight the role of diversity for both effective training and during deployment. Experiments on a newly introduced Handles dataset and a DexGraspNet subset demonstrate that our approach achieves over 120 distinct stable grasps per object (a 1.7-6x improvement over unrefined analytical methods) while outperforming diffusion-based alternatives by 46-60% in unique grasp coverage.

Abstract

Explore similar work

DexEvolve: Evolutionary Optimization for Robust and Diverse Dexterous Grasp Synthesis

Adversarial Game-Theoretic Algorithm for Dexterous Grasp Synthesis

CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning