TL;DR
Quantitative experiments showed that the proposed method generally outperformed the baselines in mass and CoM variations, particularly in terms of success rate, while maintaining robust performance across the evaluated conditions.
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.
Robotic hands offer advanced manipulation capabilities, but their complexity and cost often limit their real-world applications. In contrast, simple parallel grippers, although affordable, are restricted to basic tasks like pick-and-place. Recently, a vibration-based mechanism was proposed to augment parallel grippers and enable in-hand manipulation capabilities for thin objects. Utilizing the stick-slip phenomenon, a simple controller successfully drove a grasped object to a desired position. However, the underactuated nature of the mechanism prevented direct control of the object's orientation. In this paper, we address the manipulation challenge of reconfiguring the object's position and orientation. Hence, we present the excitation of a cyclic phenomenon in which the object's center of mass rotates with a constant radius about the grasping point. Using this cyclic motion, we propose a strategy to manipulate the object to a desired configuration. Alongside an analytical study of the cyclic phenomenon, we propose using duty cycle modulation to operate the vibration actuator for more accurate manipulation. The proposed strategy is validated through finite element analysis, physical experiments and task-specific demonstrations.
Soft grippers enable stable grasping through compliant structures and multipoint contact; however, manipulating the pose of a grasped object while maintaining contact remains challenging, particularly when large pose changes are required. Conventional approaches based on locally estimated drive matrices are limited to small motions owing to the actuator stroke and approximation validity. This study proposes a selective actuation strategy for redundant parallel-driven soft grippers to generate large object pose changes through the iterative application of small motions. By exploiting actuation redundancy, predefined actuator groups that satisfy the force-closure conditions are alternately activated. The partial drive matrices corresponding to each actuator group are extracted from a single, globally estimated drive matrix, enabling the discrete switching of control inputs without re-estimation. After reaching the vicinity of the target pose, the control scheme is switched to a full-actuator configuration for high-precision position and orientation regulation. Experiments using a fabricated redundant soft gripper demonstrated that large pose changes, which are difficult to achieve with a single control action, can be realized step-by-step while maintaining stable grasping.
Dual-arm robots often encounter difficulties when handling easily deformable or structurally complex objects using traditional grasping-based manipulation. In addition, grasping and releasing operations introduce significant time overhead. To address these limitations, this paper proposes a vision-based predictive control framework for dual-arm nonprehensile transportation. The proposed method employs a hybrid end effector design that integrates an elastic tether with a tray, enabling flexible and stable transportation without direct grasping. A predictive control strategy is adopted to optimize dual-arm motion trajectories on the move under kinematic and safety constraints. To further enhance coordination accuracy, a direct visual servoing scheme is incorporated to dynamically regulate the arm velocities, minimizing relative motion between the end effectors and the object. This effectively suppresses oscillations induced by the elastic tether. Both simulation and experimental results demonstrate that the proposed approach ensures convergence to desired states and achieves continuous, stable, and safe object transportation, even in the presence of disturbances.
Contact-rich robotic manipulation requires an accurate model of the kinematic relationship between a robot's joints and the task features it senses. This relationship is rarely known exactly: it changes with each tool the robot picks up and shifts, sometimes almost instantaneously, as contact modes change --- especially for multi-fingered hands that make and break contact at points that are not exactly prescribed, as in full-hand grasping. This paper develops an adaptive scheme that estimates that relationship online, using only joint-angle sensing and a wrist-mounted force/torque sensor, with no exteroceptive measurement of the tool tip. We derive a provably stable kinematic update law that identifies the kinematics of an unknown tool from force/torque feedback alone, and prove stability of both the rigid case and the case with a compliance controller as an inner loop. We show that identification is confined to the directions the motion excites --- so that, for example, a tool's length is unobservable under a rigid insertion push, while a compliant loop's passive yielding partially excites it; and that with a second-order admittance the compliant certificate holds unconditionally in continuous time. We also pose the combined control and estimation problem as a Quadratic Program (QP): the formulation yields the prediction term of the update law exactly but, instructively, cannot reproduce the tracking adaptation term. We validate the scheme in simulation on a peg-in-hole insertion. This work is the first step in a research program aimed at factoring manipulation learning into a task policy which can be learned in isolation of the robot, for instance by reinforcement learning, and an adaptive kinematic component that adapts online to the particular robot, hand, or tool in use.
Dynamic loco-manipulation requires legged robots to coordinate whole-body motion while maintaining stable physical interaction with grasped objects under uncertain external forces. While tactile sensing has been widely studied for robotic manipulation, its role in dynamic whole-body control remains largely unexplored. Existing works without tactile feedback commonly grasp firmly rather than regulate the grasp according to the interaction. We propose TAC-LOCO, a tactile-augmented unified reinforcement learning framework that encodes tactile array observations from compliant grippers into a compact latent representation and joins it with proprioception for unified control of the legs, arm, and gripper. With effective grasp stability reward design, the policy learns to simultaneously track body velocity and end-effector trajectories, moderate grasp force, and prevent object slip under both gradual load changes and sudden release events. We deploy the policy zero-shot on a Unitree Go2 with an Interbotix WidowX 250 arm and tactile gripper, demonstrating dynamic tactile-informed loco-manipulation under varying external interactions, achieving a 47% reduction in grasping force and an object drop rate of less than 1%.