REVIEW 8 cited by
RobustDexGrasp: Robust Dexterous Grasping of General Objects
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The ability to robustly grasp a variety of objects is essential for dexterous robots. In this paper, we present a framework for zero-shot dynamic dexterous grasping using single-view visual inputs, designed to be resilient to various disturbances. Our approach utilizes a hand-centric object shape representation based on dynamic distance vectors between finger joints and object surfaces. This representation captures the local shape around potential contact regions rather than focusing on detailed global object geometry, thereby enhancing generalization to shape variations and uncertainties. To address perception limitations, we integrate a privileged teacher policy with a mixed curriculum learning approach, allowing the student policy to effectively distill grasping capabilities and explore for adaptation to disturbances. Trained in simulation, our method achieves success rates of 97.0% across 247,786 simulated objects and 94.6% across 512 real objects, demonstrating remarkable generalization. Quantitative and qualitative results validate the robustness of our policy against various disturbances.
Forward citations
Cited by 8 Pith papers
-
HUGS: Guiding Unified Dexterous Grasp Synthesis Across Modes and Scales via Learned Human Priors
An object-conditioned human prior over contact modes and wrists guides force-closure optimization to synthesize diverse multi-mode dexterous grasps across object scales more efficiently than heuristics.
-
On Data Thinning for Model Validation in Small Area Estimation
Thinned-data MSE for small-area models is unbiased for a risk that systematically differs from full-data risk; under Fay-Herriot the gap is closed-form in the model's shrinkage, and the thinning fraction faces a sharp...
-
PAKE: Learning Whole-Body Loco-Manipulation with Partial Kinematic Embeddings
A hierarchical controller using a kinematic normalizing flow for partial inverse-kinematics redundancy plus low-level imitation yields 4.5 cm / 0.14 rad end-effector tracking while walking on a real quadruped-arm platform.
-
Closing the Reality Gap: Zero-Shot Sim-to-Real Deployment for Dexterous Force-Based Grasping and Manipulation
Zero-shot sim-to-real RL policies on a five-finger hand achieve commandable grasp-force tracking and in-hand reorientation using dense tactile simulation, current-to-torque calibration, and actuator randomization.
-
Dexplore: Scalable Neural Control for Dexterous Manipulation from Reference-Scoped Exploration
Dexplore learns dexterous robotic hand control from human MoCap demonstrations by treating them as soft, adaptively shrinking spatial references, then distills the policy into a vision-based controller.
-
ClutterDexGrasp: A Sim-to-Real System for General Dexterous Grasping in Cluttered Scenes
A simulation-trained teacher-student policy achieves zero-shot sim-to-real closed-loop target-oriented dexterous grasping in cluttered scenes, with 83.9 percent real-world success.
-
Towards Biosignals-Free Autonomous Prosthetic Hand Control via Imitation Learning
A VAE-based imitation learning model trained on teleoperated demonstrations enables a prosthetic hand to autonomously grasp and release objects using only wrist camera and proprioception.
-
HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation
HERMES converts a single human motion demonstration into a deployable mobile bimanual dexterous manipulation policy, using RL, depth-image distillation, and closed-loop PnP pose refinement.
Discussion (0). Continue with ORCID to comment.