Contact-force perception is a critical component of safe robotic grasping. With the rapid advances in embodied intelligence technology, humanoid robots have enhanced their multimodal perception capabilities. Conventional force sensors face limitations, such as complex spatial arrangements, installation challenges at multiple nodes, and potential interference with robotic flexibility. Consequently, these conventional sensors are unsuitable for biomimetic robot requirements in object perception, natural interaction, and agile movement. Therefore, this study proposes a sensorless external force detection method that integrates SuperPoint-Scale Invariant Feature Transform (SIFT) feature extraction with finite element analysis to address force perception challenges. A visual analysis method based on the SuperPoint-SIFT feature fusion algorithm was implemented to reconstruct a three-dimensional displacement field of the target object. Subsequently, the displacement field was mapped to the contact force distribution using finite element modeling. Experimental results demonstrate a mean force estimation error of 7.60% (isotropic) and 8.15% (anisotropic), with RMSE < 8%, validated by flexible pressure sensors. To enhance the model’s reliability, a dual-channel video comparison framework was developed. By analyzing the consistency of the deformation patterns and mechanical responses between the actual compression and finite element simulation video keyframes, the proposed approach provides a novel solution for real-time force perception in robotic interactions. The proposed solution is suitable for applications such as precision assembly and medical robotics, where sensorless force feedback is crucial.

This study proposed a Kriging surrogate model incorporating active learning to overcome the high computational costs associated with conducting reliability and sensitivity analyses of industrial liquid storage tank structures. In the proposed method, the Kriging surrogate model efficiently captures the functional relationships between basic variables and structural responses. Two learning functions, i.e., the U learning function and the EFF learning function, are adopted to screen the training sample pool to identify and iteratively update the optimal next training sample point in the model. This strategy significantly reduces the number of limit state functions and finite element analysis calculations required, considerably decreasing the computational cost of analysis. Results from the liquid storage tank case study demonstrate that the adaptive learning Kriging method can achieve failure probability estimation at the order of 10⁻⁵ with only approximately 100 limit state function (LSF) evaluations. Additionally, it is found that the pressure exerted by the tank contents has the most significant impact on the tank’s structural reliability, followed by tank thickness and then tank radius.

Metallurgical industrial robots are increasingly relied upon in modern industries, with growing demands for higher performance. Teleoperation systems, which consist of a master robot and a slave robot, are widely used in the metallurgical field. Stability, tracking, and transparency are key performance requirements for these systems. This study proposes an asymmetric teleoperation system with a novel 6-degree-of-freedom (6-DOF) haptic device as the master robot and a Baxter robot as the slave robot. To enhance the system's tracking and transparency, an LQR (Linear Quadratic Regulator) control algorithm combined with Kalman filtering is introduced for force/position control. Simulation and experimental results demonstrate that the LQR + Kalman filter control algorithm significantly improves control performance compared to the previous Adaptive Fuzzy & PID control algorithm. The system exhibits reduced trajectory tracking errors and enhanced force feedback accuracy, meeting the stringent requirements of asymmetric teleoperation systems in the metallurgical industry. The proposed control strategy not only optimizes the performance of the teleoperation system but also provides a robust solution for real-time control applications in complex industrial environments.