tactile model predictive control

This work addresses the challenge of simultaneously maintaining contact and accurately tracking object contours in robotic contour-following tasks by proposing a vision-based tactile model predictive control framework (VBT-MPC). For the first time, model predictive control is directly applied in the contour feature space extracted from an eye-in-hand visuotactile sensor, eliminating the need for separate pose estimation or complex force-control modules. By integrating visuotactile perception with feature-based visual servoing, VBT-MPC achieves high-precision and stable contour tracking across objects with diverse geometries and material properties in both simulation and real-world experiments. This approach substantially simplifies the system architecture while significantly enhancing tracking performance.

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.

To address the limited naturalness and responsiveness of tendon-driven prosthetic wrists, this paper proposes a computationally efficient model predictive control (MPC) framework enabling real-time, user-intent-driven adaptive regulation. The method innovatively integrates Euler–Bernoulli beam theory to formulate a kinematic model and employs Lagrangian mechanics to derive a dynamics model—balancing modeling fidelity with computational tractability for embedded implementation. Comprehensive simulation and experimental validation demonstrate substantial improvements in wrist joint trajectory tracking accuracy and dynamic response speed: operational error decreases by 32%, and subjective naturalness ratings increase by 41%. This work establishes an embeddable, lightweight, and highly adaptive control solution for intelligent prosthetic wrists, advancing practical deployment of responsive, user-centered upper-limb prostheses.

To address the inefficiency of online planning and poor robustness to modeling errors arising from frequent dynamic contact transitions during in-hand manipulation with dexterous hands, this paper proposes a hierarchical motion-contact coordination framework. At the high level, contact-implicit model predictive control (CIMPC) enables real-time joint motion and contact planning; at the low level, a hand-specific force-motion coupled dynamic model is integrated with tactile-feedback-driven closed-loop servo tracking, establishing a unified “planning-and-tracking” architecture. This design supports online compensation for modeling errors and rapid recovery from external disturbances. Evaluated on a physical robot platform across five highly contact-intensive manipulation tasks, the framework achieves superior accuracy, robustness, and real-time performance—demonstrating an average planning latency of under 20 ms—outperforming existing model-based approaches.

Modeling robot contact dynamics and achieving real-time control remain critical challenges in manipulation and locomotion tasks. This paper proposes a lightweight inverse-dynamics trajectory optimization framework that integrates contact-implicit modeling, efficient Hessian approximation, and sparse nonlinear programming structure, substantially reducing computational overhead for contact-sensitive model predictive control (MPC). The open-source real-time MPC solver achieves >100 Hz closed-loop control on a 20-degree-of-freedom bimanual robot platform—marking the first hardware demonstration enabling simultaneous high-dynamic legged locomotion and complex dexterous manipulation under robust contact control. Key contributions include: (i) overcoming the real-time feasibility bottleneck of contact-implicit MPC; and (ii) establishing a unified optimization paradigm that jointly ensures modeling fidelity, computational efficiency, and hardware deployability.

This work addresses the challenge of force perception and distribution in multi-fingered humanoid robot hands when grasping objects with uneven mass distribution or unstable contacts. The authors propose a general control framework based on estimated contact forces, which leverages data from Xela magnetic tactile sensors to train a force estimation model. Rather than using raw tactile signals, the framework directly employs the estimated forces as input to coordinately regulate the motion of the torso, arms, wrists, and fingers, driving the center of pressure at the fingertips toward the centroid of the contact polygon to achieve stable grasps. The approach is compatible with any sensor capable of force estimation and enables dynamic force redistribution among fingers. Experimental results demonstrate an 82.7% success rate across five object-balancing tasks and 80% accuracy in multi-object scenarios.

This study addresses the significant challenge in hybrid force/motion control of relying exclusively on soft tactile sensing to online estimate contact forces and time-varying task frames. To overcome this, the work proposes an end-to-end mapping model based on single-frame optical tactile images, coupled with a self-annotated data acquisition pipeline, enabling real-time reconstruction of contact variables without requiring a nominal environment model. Furthermore, state estimation is achieved by integrating an extended Kalman filter (EKF) with robot proprioceptive data. The proposed approach is validated on a UR10 manipulator, demonstrating closed-loop contact force regulation under both linear and angular motions. These results confirm that high-precision hybrid control can be realized solely through tactile feedback, eliminating the need for external sensors.

研究通过结合非线性模型预测控制和增量非线性动态逆方法，解决了欠驱动空中操作器在接触任务中的位置与力跟踪问题。

This work addresses the challenge of jointly reasoning about geometric constraints, kinematic limits, and nonsmooth contact dynamics in dexterous manipulation by proposing a hierarchical RL-MPC framework. The high-level policy employs reinforcement learning to predict object-centric “contact intentions”—specifying desired contact locations and target poses—while the low-level model predictive controller (MPC), grounded in an implicit contact model, optimizes local contact patterns and generates robust actions accordingly. This approach achieves, for the first time, zero-shot sim-to-real transfer in non-grasping tasks such as pushing and 3D reorientation, attaining near-perfect success rates. Moreover, it reduces training data requirements by an order of magnitude compared to end-to-end methods, substantially enhancing both generalization and robustness.

This work addresses the inherent conflict between high-precision trajectory tracking and compliant contact in dexterous hands under fixed-gain control. The authors propose a drive-agnostic impedance model predictive control (MPC) framework that algebraically reduces tendon-driven systems to a constant-coefficient double integrator via feedforward linearization. An encoder-only augmented Kalman disturbance estimator is embedded to eliminate steady-state errors. For the first time, a constant-\(A_d\) unbiased MPC architecture is applied to dexterous manipulation, achieving high-speed real-time optimization under hard constraints while ensuring stability and recursive feasibility with strong disturbance rejection. Experiments demonstrate that a hydraulic finger attains 0.5 mrad RMS tracking error and 0.1 mrad steady-state error, with only 6.6 mrad peak deflection under contact disturbances. On a 16-DOF LEAP hand, a 2.5 N grasping disturbance is rejected within 0.7 seconds, yielding performance improvements of tens to thousands of times over classical methods.