The paper investigates the multiscale connectivity structure of successful robotic grasps in SE(3) and finds that these sets exhibit heterogeneous yet reproducible connectivity across objects. It proposes a connectivity‑aware sampling strategy that prioritizes bridges, frontiers, boundary extensions, and geometric novelty, which recovers grasp connectivity more efficiently than random or farthest‑point sampling. Experiments also show that connectivity information can improve subsequent grasp discovery and transfer to unseen objects, indicating that the spatial organization of viable actions offers valuable guidance for exploration.
arXiv:2608. 19759v1 Announce Type: cross Abstract: Multifingered grasping is a crucial robotic skill, but current deep-learning grasp planners often struggle to generalize to new objects because they are trained on limited, object-specific datasets.
arXiv:2606. 26428v1 Announce Type: cross Abstract: Multi-fingered robots promise the speed and dexterity of human hands, yet challenging problems such as precise assembly have remained out of reach.
arXiv:2608. 19776v1 Announce Type: cross Abstract: Current dexterous grasp planners primarily optimize for physical stability, focusing on whether an object can be grasped rather than how it should be grasped to support downstream functional tasks.
The paper introduces a continual‑learning framework for single‑view 6‑DoF grasp synthesis with a parallel‑jaw gripper in cluttered scenes. Instead of fine‑tuning a large parametric model, the method updates grasp scores via memory in a learned embedding space and optionally incorporates user demonstrations to generate new candidate grasps. Experiments in simulation and real‑world trials (over 1500 grasps) show that the approach matches baseline performance before adaptation, improves online on unseen objects, and achieves over 90% success on challenging categories after just 50 online attempts.
The paper presents a reinforcement learning framework that refines robotic grasp poses using a Deep Q-Network and keypoint-based object representations. Starting from initial grasp candidates generated by a geometric algorithm on 2D overhead images, the method iteratively improves grasps, converting previously failed attempts into successful ones. Experiments on 300 Dex‑Net objects with a UR5 arm achieved a 100% success rate on items that were ungraspable by geometry alone, and the approach transferred to a Delta robot in real‑world tests.
arXiv:2602. 13197v2 Announce Type: replace-cross Abstract: The ability to learn manipulation skills by watching videos of humans has the potential to unlock a new source of highly scalable data for robot learning.
arXiv:2606. 12109v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable zero-shot generalization in robotic manipulation, yet the vast majority of pre-trained pipelines remain strictly confined to low-DoF parallel grippers.
AdaRoboVLG is a Vision‑Language‑Grasp framework that separates a generalizable base grasp policy from task‑specific understanding. The base policy generates and evaluates physically feasible grasp candidates using kinematic mapping and force‑closure stability, while foundation‑model modules supply composable spatial, cognitive, and temporal priors that adapt grasp synthesis to different robotic hands and environments without retraining. Experiments show strong cross‑hand generalization, effective handling of diverse grasping challenges, and functional grasping in cluttered, dynamic settings.
arXiv:2607. 14341v1 Announce Type: cross Abstract: Robust robotic grasping remains a fundamental challenge for complex real-world applications.
arXiv:2605.10201v3 Announce Type: replace-cross Abstract: Generalizable manipulation involving cross-type object interactions is a critical yet challenging capability in robotics. To reliably accompl...
arXiv:2606. 24712v1 Announce Type: cross Abstract: Humans effortlessly locate and identify objects by touch alone, even without vision.
arXiv:2606. 10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots.