The maintenance of deep-sea net cages, specifically net cleaning and chemical coating application, is currently hindered by intensive labor requirements and the inherent risks of high-altitude maritime operations. Consequently, developing automated climbing robots offers significant advantages in both safety and operational efficiency. However, unlike rigid surfaces, the flexible netting of sea cages is characterized by easy deformation, discontinuity, and an unstructured nature. During climbing, robots frequently encounter unstable grasping or unexpected interference between the gripper and the mesh, which serves as a primary bottleneck for engineering applications. To address these challenges, this paper develops a novel robotic gripper structure specifically designed for climbing flexible netting and proposes a gripper state monitoring system based on multi-modal information fusion. Experimental results conducted in both PyBullet physics simulations and on a physical flexible netting testbed demonstrate that this multi-modal fusion system effectively compensates for the inability of single-force sensors to perceive spatial geometric relationships. This integration significantly enhances grasping stability and operational safety on unstructured, flexible net surfaces.
Zitong Liao, S. Qu, Wenbo Zhou et al.· 2026 IEEE International Conf...· 0 citations
Home-based rehabilitation exoskeletons often suffer from control instability due to low-cost force sensors. This paper presents a robust, sensorless Composite Variable Impedance Control architecture that separates trajectory tracking (virtual stiffness K) from active assistance (adaptive feedforward torque τassist). By eliminating high-frequency force feedback, the system ensures intrinsic stability. Experiments on the CURE platform demonstrate independent modulation of compliance (RMSE 2.64° to 15.90°) and effective assistance during simulated weakness, reducing tracking RMSE from 13.77° to 3.12°. Results show τassist contributes 59.6% of total torque, enabling "High-Assistance, High-Compliance" interaction without reactive stiffening. This provides a stable execution layer for advanced, bio-signal-driven "Assist-as-Needed" (AAN) therapies.
Jun Leng, Pengcheng Li, Hanze Wang et al.· 2026 IEEE International Conf...· 0 citations
StableMimic is presented, a unified tracker trained beyond the nominal tracking distribution that achieves the lowest errors on all four tracking metrics among five methods and attains the lowest values on six of seven post-fall motion and load measures, supporting improved interaction safety under this protocol.
Weihao Wu, Mingzhe Huang, Ruofei Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
