Robust In-Hand Manipulation via Priors in Reinforcement Learning and Mechanical Design

• URL: http://arxiv.org/abs/2607.12105v1
• Date: Mon, 13 Jul 2026 19:32:41 GMT
• Title: Robust In-Hand Manipulation via Priors in Reinforcement Learning and Mechanical Design
• Abstract summary: In-hand manipulation without external sensing is challenging due to uncertainties from finger-object contacts and disturbances by gravity.<n>We introduce two complementary physics priors for robust in-hand rolling.<n>Results show significant improvement in rotation efficiency, grasp stability, and disturbance rejection.
• Score: 4.975198309365314
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In-hand manipulation without external sensing is challenging due to uncertainties from finger-object contacts and disturbances by gravity. While reinforcement learning has shown promise in learning complex finger gaiting, existing approaches do not prioritize maintaining well-conditioned grasps for sustained manipulation. We introduce two complementary physics priors for robust in-hand rolling: a global grasp-quality prior derived from classical grasp analysis and a local contact-geometry prior based on fingertip curvature. The grasp-quality prior is used as a dense reward-shaping term that encourages well-distributed contacts with improved worst-case wrench resistance. The contact-geometry prior is expressed in the fingertip geometry that mechanically shapes the contact interface toward task-aligned rolling while reducing off-axis drift. We evaluate the effect of these priors on learning in-hand rolling manipulation for a multifingered robotic hand manipulating three different objects at four palm orientations. Results show significant improvement in rotation efficiency, grasp stability, and disturbance rejection, suggesting that physics priors embedded in both learning and fingertip morphology improve task robustness and sim-to-real transfer. An overview video can be found at https://youtu.be/pdd1wHxQnJM?si=dM-U5kiiPTYsk3Pk.

Related papers

• AdaDexGrasp: Adaptive Dexterous Grasping via 3D Visuo-Tactile Representation Fusion [60.79507611737292]
  Humans achieve stable and adaptive grasps by seamlessly integrating visual perception and tactile feedback.<n>Existing robotic grasping approaches rely on visual inputs and lack mechanisms for tactile-guided adaptation after contact.<n>We propose a unified visuo-tactile-fusion grasping framework that integrates grasp generation, feasibility prediction, and adaptive refinement.
  arXiv  Detail & Related papers  (2026-08-06T16:29:11Z)
• SECOND-Grasp: Semantic Contact-guided Dexterous Grasping [60.1519218638742]
  Second-Grasp (SEmantic CONtact-guided Dexterous Grasping) is a unified framework that enables robotic hands to adjust grasping strategies based on semantic reasoning.<n>We show that our approach consistently outperforms baselines in lifting success rate on both seen and unseen categories.
  arXiv  Detail & Related papers  (2026-05-13T07:37:00Z)
• TEGA: A Tactile-Enhanced Grasping Assistant for Assistive Robotics via Sensor Fusion and Closed-Loop Haptic Feedback [1.3861223044153617]
  We present the tactile enhanced grasping assistant (TEGA)<n>A closed loop assistive teleoperation framework fuses EMG based intent2force inference with visuotactile sensing mapped into real time vibrotactile feedback.<n>A wearable haptic vest delivers real time tactile feedback, allowing users to dynamically refine grasp force during manipulation.
  arXiv  Detail & Related papers  (2026-03-05T04:12:55Z)
• Rigidity-Based Multi-Finger Coordination for Precise In-Hand Manipulation of Force-Sensitive Objects [5.313029497667778]
  Multi-fingered hands rely solely on fingertip point contacts and are not able to apply pull forces.<n>We propose a dual-layer framework for multi-finger coordination, enabling high-precision manipulation of force-sensitive objects.<n>We validate the framework on a custom dexterous hand, demonstrating the capability to manipulate fragile objects.
  arXiv  Detail & Related papers  (2026-02-15T11:40:39Z)
• TaSA: Two-Phased Deep Predictive Learning of Tactile Sensory Attenuation for Improving In-Grasp Manipulation [45.60949380395733]
  Humans can achieve diverse in-hand manipulations, such as object pinching and tool use, which often involve simultaneous contact between the object and multiple fingers.<n>This is still an open issue for robotic hands because such dexterous manipulation requires distinguishing between tactile sensations generated by their self-contact and those arising from external contact.<n>We introduce TaSA, a two-phased deep predictive learning framework. In the first phase, TaSA explicitly learns self-touch dynamics, modeling how a robot's own actions generate tactile feedback.<n>In the second phase, this learned model is incorporated into the motion learning phase, to emphasize object
  arXiv  Detail & Related papers  (2026-02-05T09:16:06Z)
• ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation [0.10995326465245926]
  We present ForceGrip, a deep learning agent that synthesizes realistic hand manipulation motions.<n>We employ a three-phase curriculum learning framework comprising Finger Positioning, Intention Adaptation, and Dynamic Stabilization.<n>Our evaluations reveal ForceGrip's superior force controllability and plausibility compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-11T05:39:07Z)
• DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation [81.11585774044848]
  We present DeepSimHO, a novel deep-learning pipeline that combines forward physics simulation and backward gradient approximation with a neural network. Our method noticeably improves the stability of the estimation and achieves superior efficiency over test-time optimization.
  arXiv  Detail & Related papers  (2023-10-11T05:34:36Z)
• Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation [59.3035531612715]
  Existing methods often struggle to generate plausible hand poses when the hand is heavily occluded or blurred. In videos, the movements of the hand allow us to observe various parts of the hand that may be occluded or blurred in a single frame. We propose the Deformer: a framework that implicitly reasons about the relationship between hand parts within the same image.
  arXiv  Detail & Related papers  (2023-03-09T02:24:30Z)
• On the Feasibility of Learning Finger-gaiting In-hand Manipulation with Intrinsic Sensing [0.7373617024876725]
  We use model-free reinforcement learning to learn finger-gaiting only via precision grasps. To tackle the inherent instability of precision grasping, we propose the use of initial state distributions. Our method can learn finger-gaiting with significantly improved sample complexity than the state-of-the-art.
  arXiv  Detail & Related papers  (2021-09-26T23:22:29Z)
• Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning [52.37106940303246]
  We learn a model that maps noisy input hand poses to target virtual poses. The agent is trained in a residual setting by using a model-free hybrid RL+IL approach. We test our framework in two applications that use hand pose estimates for dexterous manipulations: hand-object interactions in VR and hand-object motion reconstruction in-the-wild.
  arXiv  Detail & Related papers  (2020-08-07T17:34:28Z)
• The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes? [57.366931129764815]
  We collect more than 9,000 grasping trials using a two-finger gripper equipped with GelSight high-resolution tactile sensors on each finger.<n>Our experimental results indicate that incorporating tactile readings substantially improve grasping performance.
  arXiv  Detail & Related papers  (2017-10-16T05:32:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.