grasp planning

Current research on dexterous hands lacks standardized benchmarks across hardware design, perception modalities, task formulations, datasets, and evaluation protocols, hindering systematic comparison and progress. This work presents the first integrative framework that cohesively unifies hardware architecture, control and learning methodologies, datasets, and evaluation criteria into a four-dimensional analytical structure to systematically trace the field’s technical evolution. By encompassing actuation and transmission mechanisms, multimodal sensing, learning-based control, simulation-to-reality data generation, and standardized assessment metrics, the study elucidates the interdependencies among these dimensions, identifies prevailing limitations, and articulates key open challenges. The contributions include a structured taxonomy and an evolutionary roadmap for dexterous hand research, offering a clear technical trajectory and guiding future investigations toward critical unresolved problems.

This work addresses the challenge of open-loop grasping under uncertainty in object shape and pose, where poor contact coordination often leads to slippage or failure. The authors propose a tactile feedback–based model predictive controller that enables coordinated multi-contact interaction and adaptive force modulation during both approach and grasp phases. Key innovations include perception-driven phase segmentation, arm–hand协同 compensation for pose errors, and a balanced adaptive force coordination mechanism. By analytically linking contact forces to joint motions, the method remains compatible with diverse grasp pose generation strategies. Evaluated across 15,000 simulations involving 478 objects and eight physical experiments, the approach significantly improves grasp success rates while effectively suppressing unintended object motion.

This work addresses the limitations of traditional dexterous manipulation controllers, which rely on strongly assumed analytical models, and end-to-end reinforcement learning approaches, which often suffer from objective conflicts and training instability. The authors propose a skill decomposition framework that integrates physical and control-theoretic priors to decouple in-hand manipulation into analytically tractable subcomponents. By embedding theoretical constraints within each subcomponent to guide learning, this method systematically incorporates classical control knowledge into the learning pipeline for dexterous manipulation. Evaluated across diverse objects, sensor noise levels, actuation delays, and friction conditions, the approach significantly enhances policy learning stability, sample efficiency, and generalization, enabling efficient and precise in-hand repositioning and reorientation.

This work addresses the common oversight in existing grasping methods of spatially non-uniform mechanical properties on object surfaces, which often leads to damage when contacts occur at fragile regions. The authors propose a novel grasping framework that integrates language instructions, 3D reconstruction, and physical awareness: leveraging SAM3D for language-guided 3D reconstruction, they perform physics-informed geometric analysis to generate local contact force tolerance maps, which are then used to filter and re-rank candidate grasp poses according to task consistency and force-map awareness. During execution, an adaptive impedance controller dynamically modulates finger stiffness based on contact points. This approach is the first to incorporate local mechanical tolerance maps throughout the entire grasping pipeline, reframing dexterous manipulation from a purely geometric problem into a joint optimization under physical constraints. Experiments demonstrate stable selection of high-strength contact regions and maintenance of grasp forces within safe thresholds on paper, plastic, and glass cups.

This work addresses the challenges of contact stability and sensor noise robustness in dexterous multi-arm manipulation with multiple point contacts, using planar and multi-pin insertion tasks as representative scenarios. We propose a novel framework integrating contact mechanics modeling with trajectory optimization: for the first time, friction cone constraints, normal force equilibrium conditions, and an analytically derived stability cost function are jointly and explicitly incorporated into multi-contact planning. Trajectories are parameterized via dynamic movement primitives (DMPs), and policy generalization is enhanced through black-box optimization (BBO) coupled with parallel physics-based simulation training. Experiments and simulations demonstrate high success rates under varying hole position offsets, chamfer geometries, and friction coefficients. The method significantly improves robustness against modeling inaccuracies and sensory noise, establishing a verifiable, stability-guaranteed paradigm for multi-contact dexterous manipulation.

This work addresses the prevalent instability of linear controllers—particularly LQR—in rich-contact manipulation under smooth contact dynamics. We systematically identify the root cause: strong coupling among contact transients, ill-conditioning of the Jacobian matrix, and state constraints. To overcome this, we propose a differential simulation framework grounded in smoothed contact modeling, thereby relaxing the implicit smoothness assumption inherent in gradient-based controllers. Furthermore, we introduce a co-optimization method that jointly designs robust open-loop trajectories and feedback gains. Empirical evaluation on over 300 high-contact-density trajectories executed on a dual-arm whole-body manipulation platform demonstrates that standard LQR achieves less than 40% closed-loop stability, whereas our approach significantly improves stability. The source code, models, and hardware experiment videos are publicly available.

This work addresses the limitations of existing dexterous grasping methods, which predominantly rely on static geometric stability and struggle to maintain robustness under dynamic external forces—such as impacts or torques—during tool manipulation. To overcome this, the authors propose Grasp-to-Act, a hybrid system that uniquely integrates human demonstration-guided robust grasp configurations with a residual adaptive controller. By combining physics-based simulation optimization, reinforcement learning, and demonstration-driven grasp synthesis, the approach enables real-time joint-level adjustments during functional tasks to suppress both translational and rotational slip while accurately tracking desired trajectories. Notably, the method achieves zero-shot sim-to-real transfer without task-specific fine-tuning, demonstrating superior performance across five dynamic tasks—hammering, sawing, cutting, stirring, and scooping—with significantly reduced slip and higher task success rates, validated on a 16-degree-of-freedom dexterous hand.

This work addresses the disconnect between dexterous hand design and task-driven control, as well as the limited optimization dimensions in existing approaches, by proposing a unified parametric co-design framework that jointly optimizes palm structure, finger kinematics, fingertip geometry, and surface curvature. Innovatively incorporating fine-grained geometric features—such as surface curvature—into the design space, the method employs a parametric surface deformation kernel to directly model contact interactions, enabling end-to-end simulation-to-reality optimization. Integrating multi-degree-of-freedom finger modeling, task-oriented optimization algorithms, and manufacturability constraints, the approach significantly enhances grasp stability in dynamic manipulation tasks and produces dexterous hand models ready for both simulation and physical fabrication. The resulting designs are open-sourced to advance research in co-design and cross-platform policy transfer.

This work addresses the challenges in non-prehensile dexterous manipulation—namely, infeasible actions due to neglecting gripper physical constraints, poor generalization, and heavy reliance on large datasets or manual design—by proposing a gripper-aware hierarchical planning framework. Centered on executability, the approach decouples object motion planning from grasp feasibility: an upper layer plans object pose trajectories using MoveObject primitives, while a lower layer synthesizes feasible grasp sequences via AdjustGrasp primitives, with collision checking and quasi-static force analysis validating contact-sensitive segments. The method requires no task-specific redesign and supports transfer across tasks and geometric variations. Real-robot experiments on zero-displacement lifting and slot-insertion tasks demonstrate strong robustness and consistent execution performance.

This work addresses the challenge of high-dimensional force control in stable grasping with multi-fingered dexterous hands when handling unknown objects. The authors propose a novel approach that achieves stable grasps without requiring explicit torque modeling or slip detection. By integrating tactile feedback with a second-order cone programming (SOCP) controller, the method enforces that the ratio of tangential to normal forces at each contact point remains below the friction coefficient, thereby simultaneously suppressing both translational and rotational slips. A key insight is that rotational slip inevitably induces local translational slip, allowing the tangential-to-normal force ratio to serve as an early indicator of grasp stability. Experimental validation on twelve diverse objects demonstrates the superior robustness and compliance of the proposed method in real-world grasping tasks.

Existing cross-embodiment dexterous manipulation strategies typically transfer only motion trajectories while neglecting contact force feedback, leading to unstable grasps under conditions such as slippage, object deformation, or visual occlusion. This work proposes a force-position hybrid cross-embodiment interface that encodes motor intent through a shared hand-pose latent space and leverages system identification to calibrate heterogeneous hand force signals into physically meaningful joint torques. These torques are further mapped to fingertip forces and compact load descriptors, enabling contact-aware policy transfer. The approach represents the first method to achieve calibrated contact feedback transfer across structurally diverse dexterous hands, significantly enhancing the reusability, compliance, and robustness of grasping policies. Experimental validation across multiple hands with substantial morphological differences demonstrates its effectiveness, substantially improving success rates in long-horizon manipulation tasks.