ConGraspXL: Controllable Constraint-Conditioned Dexterous Grasping Motion Synthesis
Not on the map. Why?
Abstract (arXiv)
Dexterous grasping is usually conducted for specific tasks, leading to heterogeneous constraints such as specific approach directions, desired contact regions, specified wrist trajectories, and functional hand poses. Our previous work, GraspXL, achieves scalable grasping motion synthesis for diverse objects and hand morphologies, while lacking controllability for synthesis under such various task-driven constraints. In this paper, we propose ConGraspXL, which extends GraspXL with controllable constraint-conditioned grasp motion synthesis that accommodates diverse task-driven constraints and their combinations. We introduce a hierarchical constraint formulation, enable flexible constraint composition with a masked residual interface, and improve control precision with dynamic hand centers and feed-forward wrist guidance. Without losing the strong generalization capabilities of GraspXL, ConGraspXL enables precise and flexible controllability for various individual constraints and their combinations, providing a plug-and-play low-level grasp controller for downstream applications such as whole-body grasp completion, functional grasping, and human-motion imitation.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 70 of its 88 references that are in the map. First posted on arXiv 14 Sep 2026.
Builds on
70 of 88 references.
References · 70
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
- 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
- 2020GRAB: A Dataset of Whole-Body Human Grasping of Objectscited by 405
- 2019Learning joint reconstruction of hands and manipulated objectscited by 378
- 2023Human Motion Diffusion as a Generative Priorcited by 357
- 2022HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interactioncited by 327
- 2021DexYCB: A Benchmark for Capturing Hand Grasping of Objectscited by 325
- 2022ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulationcited by 312
- 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 254
- 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 238
- 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 223
38 more
- 2023Object Motion Guided Human Motion Synthesiscited by 212
- 2025EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Videocited by 211
- 2020ContactPose: A Dataset of Grasps with Object Contact and Hand Posecited by 183
- 2020Grasping Field: Learning Implicit Representations for Human Graspscited by 179
- 2021Hand-Object Contact Consistency Reasoning for Human Grasps Generationcited by 160
- 2019ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imagingcited by 147
- 2020Reconstructing Hand-Object Interactions in the Wildcited by 144
- 2021GOAL: Generating 4D Whole-Body Motion for Hand-Object Graspingcited by 144
- 2021ContactOpt: Optimizing Contact to Improve Graspscited by 139
- 2023CG-HOI: Contact-Guided 3D Human-Object Interaction Generationcited by 138
- 2022OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interactioncited by 131
- 2018Grounded Human-Object Interaction Hotspots from Videocited by 129
- 2017AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detectioncited by 128
- 2020CPF: Learning a Contact Potential Field to Model the Hand-Object Interactioncited by 128
- 2022IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactionscited by 124
- 2023UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policycited by 124
- 2024MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpaintingcited by 116
- 2021D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactionscited by 113
- 2023Affordance Diffusion: Synthesizing Hand-Object Interactionscited by 110
- 2023UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learningcited by 107
- 2021SAGA: Stochastic Whole-Body Grasping with Contactcited by 91
- 2022DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Videocited by 89
- 2024TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understandingcited by 88
- 2019ContactGrasp: Functional Multi-finger Grasp Synthesis from Contactcited by 87
- 2024Text2HOI: Text-guided 3D Motion Generation for Hand-Object Interactioncited by 86
- 2020Learning Dexterous Grasping with Object-Centric Visual Affordancescited by 85
- 2024OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completioncited by 82
- 2023HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Videocited by 78
- 2025InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactionscited by 72
- 2024DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptionscited by 62
- 2024GraspXL: Generating Grasping Motions for Diverse Objects at Scalecited by 60
- 2023CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesiscited by 56
- 2023ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulationcited by 55
- 2024AffordanceLLM: Grounding Affordance from Vision Language Modelscited by 55
- 2023ContactGen: Generative Contact Modeling for Grasp Generationcited by 53
- 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenizationcited by 51
- 2023Dexterous Functional Graspingcited by 39
- 2024GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusioncited by 35
50 most cited of 70 All 70 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.