Abstract--Humans naturally grasp objects with minimal level required force for stability, whereas robots often rely on rigid, over-squeezing control. T o narrow this gap, we propose a human-inspired physics-conditioned tactile method (Phy-T ac) for force-optimal stable grasping (FOSG) that unifies pose selection, tactile prediction, and force regulation. A physics-based pose selector first identifies feasible contact regions with optimal force distribution based on surface geometry. Then, a physics-conditioned latent diffusion model (Phy-LDM) predicts the tactile imprint under FOSG target. Last, a latent-space LQR controller drives the gripper toward this tactile imprint with minimal actuation, preventing unnecessary compression. Trained on a physics-conditioned tactile dataset covering diverse objects and contact conditions, the proposed Phy-LDM achieves superior tactile prediction accuracy, while the Phy-T ac outperforms fixed-force and GraspNet-based baselines in grasp stability and force efficiency. Experiments on classical robotic platforms demonstrate force-efficient and adaptive manipulation that bridges the gap between robotic and human grasping.

Contact-rich manipulation depends on applying the correct grasp forces throughout the manipulation task, especially when handling fragile or deformable objects. Most existing imitation learning approaches often treat visuotactile feedback only as an additional observation, leaving applied forces as an uncontrolled consequence of gripper commands. In this work, we present Force-Aware Robotic Manipulation (FARM), an imitation learning framework that integrates high-dimensional tactile data to infer tactile-conditioned force signals, which in turn define a matching force-based action space. We collect human demonstrations using a modified version of the handheld Universal Manipulation Interface (UMI) gripper that integrates a GelSight Mini visual tactile sensor. For deploying the learned policies, we developed an actuated variant of the UMI gripper with geometry matching our handheld version. During policy rollouts, the proposed FARM diffusion policy jointly predicts robot pose, grip width, and grip force. FARM outperforms several baselines across three tasks with distinct force requirements -- high-force, low-force, and dynamic force adaptation -- demonstrating the advantages of its two key components: leveraging force-grounded, high-dimensional tactile observations and a force-based control space. The codebase and design files are open-sourced and available at https://tactile-farm.github.io .

-- We present a unifying theoretical result that connects two foundational principles in robotics: the Signorini law for point contacts, which underpins many simulation methods for preventing object interpenetration, and the center of pressure (also known as the zero-moment point), a key concept used in, for instance, optimization-based locomotion control. Our contribution is the planar Signorini condition, a conic complementarity formulation that models general planar contacts between rigid bodies. We prove that this formulation is equivalent to enforcing the punctual Signorini law across an entire contact surface, thereby bridging the gap between discrete and continuous contact models. A geometric interpretation reveals that the framework naturally captures three physical regimes --sticking, separating, and tilting-- within a unified complementarity structure. This leads to a principled extension of the classical center of pressure, which we refer to as the extended center of pressure. By establishing this connection, our work provides a mathematically consistent and computationally tractable foundation for handling planar contacts, with implications for both the accurate simulation of contact dynamics and the design of advanced control and optimization algorithms in locomotion and manipulation. The Signorini law for punctual contact is fundamental to contact modeling in robotics, mechanics, and computer graphics. It formalizes rigid, frictionless, point contact as a nonpenetration condition expressed via complementarity between the gap and the normal contact force [1]. For a given contact point between two objects in contact, this law states that if a force acts on the contact point, it should be repulsive, and the contact velocity can only separate the objects in contact; however, the two cannot occur simultaneously.

S automation advances, robots are increasingly utilized for complex tasks, reducing manual labor in hazardous environments while improving efficiency, precision, and cost-effectiveness [1]. However, real-world robotic applications require seamless interaction with deformable objects, which presents significant challenges due to material flexibility and unpredictable shape changes [2]. Unlike rigid object manipulation, deformable object manipulation (DOM) requires real-time adaptive control to compensate for continuous state variations and external forces. Traditional physics-based control models, such as mass-spring systems and finite element methods [3], [4], [5], attempt to model deformable object behavior but often fall short in real-world applications due to the sensitvity of control parameters and the difficulty of modeling complex contact dynamics. To address these limitations, recent research has shifted toward machine learning and data-driven approaches, where robots learn from sensor feedback or demonstrations rather than relying on hard-coded models [6]. Predictive learning models [7], [8], [9] have proven effective for latent space learning and object behavior forecasting, improving adaptability across applications such as fabric repositioning [10], crop harvesting [11], [12], medical robotics [13], and deformable linear object manipulation [14], [15]. While significant progress has been made in DOM, little research has focused on deformable tool manipulation (DTM), which introduces additional complexities such as bending dynamics, force regulation, and stability issues.

This paper presents the analytic modeling of mobile heavy-duty manipulators with actively articulated suspension and its optimal control to maximize its static and dynamic stabilization. By adopting the screw theory formalism, we consider the suspension mechanism as a rigid multibody composed of two closed kinematic chains. This mechanical modeling allows us to compute the spatial inertial parameters of the whole platform as a function of the suspension's linear actuators through the articulated-body inertia method. Our solution enhances the computation accuracy of the wheels' reaction normal forces by providing an exact solution for the center of mass and inertia tensor of the mobile manipulator. Moreover, these inertial parameters and the normal forces are used to define metrics of both static and dynamic stability of the mobile manipulator and formulate a nonlinear programming problem that optimizes such metrics to generate an optimal stability motion that prevents the platform's overturning, such optimal position of the actuator is tracked with a state-feedback hydraulic valve control. We demonstrate our method's efficiency in terms of C++ computational speed, accuracy and performance improvement by simulating a 7 degrees-of-freedom heavy-duty parallel-serial mobile manipulator with four wheels and actively articulated suspension.

Contact-rich manipulation remains a major challenge in robotics. Optical tactile sensors like GelSight Mini offer a low-cost solution for contact sensing by capturing soft-body deformations of the silicone gel. However, accurately inferring shear and normal force distributions from these gel deformations has yet to be fully addressed. In this work, we propose a machine learning approach using a U-net architecture to predict force distributions directly from the sensor's raw images. Our model, trained on force distributions inferred from Finite Element Analysis (FEA), demonstrates promising accuracy in predicting normal and shear force distributions. It also shows potential for generalization across sensors of the same type and for enabling real-time application. The codebase, dataset and models are open-sourced and available at https://feats-ai.github.io .

Multi-suction-cup grippers are frequently employed to perform pick-and-place robotic tasks, especially in industrial settings where grasping a wide range of light to heavy objects in limited amounts of time is a common requirement. However, most existing works focus on using one or two suction cups to grasp only irregularly shaped but light objects. There is a lack of research on robust manipulation of heavy objects using larger arrays of suction cups, which introduces challenges in modeling and predicting grasp failure. This paper presents a general approach to modeling grasp strength in multi-suction-cup grippers, introducing new constraints usable for trajectory planning and optimization to achieve fast and reliable pick-and-place maneuvers. The primary modeling challenge is the accurate prediction of the distribution of loads at each suction cup while grasping objects. To solve for this load distribution, we find minimum spring potential energy configurations through a simple quadratic program. This results in a computationally efficient analytical solution that can be integrated to formulate grasp failure constraints in time-optimal trajectory planning. Finally, we present experimental results to validate the efficiency and accuracy of the proposed model.

This paper presents a method for dynamic adjustment of cable preloads based on the actuation redundancy of \acp{CDPR}, which allows increasing or decreasing the platform stiffness depending on task requirements. This is achieved by computing preload parameters with an extended nullspace formulation of the kinematics. The method facilitates the operator's ability to specify a defined preload within the operation space. The algorithms are implemented in a real-time environment, allowing for the use of optimization in hybrid position-force control. To validate the effectiveness of this approach, a simulation study is performed, and the obtained results are compared to existing methods. Furthermore, the method is investigated experimentally and compared with the conventional position-controlled operation of a cable robot. The results demonstrate the feasibility of adaptively adjusting cable preloads during platform motion and manipulation of additional objects.

When humans see a scene, they can roughly imagine the forces applied to objects based on their experience and use them to handle the objects properly. This paper considers transferring this "force-visualization" ability to robots. We hypothesize that a rough force distribution (named "force map") can be utilized for object manipulation strategies even if accurate force estimation is impossible. Based on this hypothesis, we propose a training method to predict the force map from vision. To investigate this hypothesis, we generated scenes where objects were stacked in bulk through simulation and trained a model to predict the contact force from a single image. We further applied domain randomization to make the trained model function on real images. The experimental results showed that the model trained using only synthetic images could predict approximate patterns representing the contact areas of the objects even for real images. Then, we designed a simple algorithm to plan a lifting direction using the predicted force distribution. We confirmed that using the predicted force distribution contributes to finding natural lifting directions for typical real-world scenes. Furthermore, the evaluation through simulations showed that the disturbance caused to surrounding objects was reduced by 26 % (translation displacement) and by 39 % (angular displacement) for scenes where objects were overlapping.

Surface matching usually provides significant deformations that can lead to structural failure due to the lack of physical policy. In this context, partial surface matching of non-linear deformable bodies is crucial in engineering to govern structure deformations. In this article, we propose to formulate the registration problem as an optimal control problem using an artificial neural network where the unknown is the surface force distribution that applies to the object and the resulting deformation computed using a hyper-elastic model. The optimization problem is solved using an adjoint method where the hyper-elastic problem is solved using the feed-forward neural network and the adjoint problem is obtained through the backpropagation of the network. Our process improves the computation speed by multiple orders of magnitude while providing acceptable registration errors.