Human joints enable precise bending for fine manipulation and complex movements. Similarly, robotic flexibility relies on bending structures, where accurate bending perception is crucial for precise control and enhanced humanrobot interaction. This paper proposes a C-shaped fiber optic array, embedding a fiber Bragg Grating sensor array into a 2 mm thick silicone layer, successfully achieving a highly sensitive (300 pm/N) and electromagnetic interference-resistant bending sensor. The flexible sensor can sensitively detect external stimuli, such as the touch of a 1g weight or a feather, and exhibits a good linear relationship with curvature, facilitating accurate curvature classification. Additionally, leveraging the wearable nature of the sensor, we achieved the detection of finger bending angles. Finally, by attaching the sensor to the wrist and combining it with deep learning algorithms, we achieved 100% gesture recognition accuracy. This sensor holds significant potential for applications in fields such as fruit size classification, rehabilitation healthcare, and human-robot interaction.

Human fingertips are densely distributed with sensory nerve endings, allowing them to perceive various physical characteristics, including pressure, roughness, etc. In this work, we develop a rigid-flexible coupled bionic robotic finger with perception decoupling and slip detection capabilities. Particularly, slip perception is important in grasping operations. Timely prediction of slippage and adjusting gripping force can improve gripping stability. Fiber Bragg gratings (FBGs) are embedded within both the rigid skeleton and flexible shell of the bionic fingertip. The fibers within the flexible shell are capable of sensing slight pressure, while the optical fibers embedded in the rigid skeleton can measure temperature changes. Firstly, this paper introduces the principles of distributed fiber optic sensors and the morphological design of the bionic fingertip. Then, the fabrication process of the bionic fingertip is described. Finally, we verify the multimodal sensory capabilities of the bionic fingertip through a series of experiments. The results demonstrate that the bionic finger can successfully sense whether the slip has occurred during grasping process. In summary, this rigid-flexible bionic finger is expected to play a significant role in dexterous manipulation, fruit picking and so on.

Programmable manipulation of fluid-based soft robots has recently attracted considerable attention. Achieving parallel control of large-scale ferrofluid droplet robots (FDRs) is still one of the major challenges that remain unsolved. In this article, we develop a distributed magnetic field control platform to generate a series of localized magnetic fields that enable the simultaneous control of many FDRs, allowing teams of FDRs to collaborate in parallel for multifunctional manipulation tasks. Based on the mathematical model using the finite element method, we first evaluate the distribution properties of the local magnetic fields as well as the gradients generated by individual electromagnets. Meanwhile, the locomotion and deformation behavior of the FDR is also characterized to verify the actuation performance of the developed system. Subsequently, a vision-based closed-loop feedback control strategy is then presented, which aims to achieve path tracking of multiple robot formations. Thermal analysis shows that the system's low output power enables reliable and sustained long-term operation. Finally, the developed system is tested through extensive physical experiments with different numbers of FDRs. The results demonstrate the potential of the designed setup in manipulating dozens of FDRs for digital display, message encoding, and microfluidic logistics. To the best of our knowledge, this is the first attempt that allows independent control of such scale droplet robots (up to 72) for cooperative applications.

Tactile sensing is pivotal for enabling effective human-robot interaction, especially in unstructured environments. This work introduces an innovative bioinspired soft robotic finger endowed with shape-adaptive and multi-modal tactile perception capabilities, drawing inspiration from diverse biological tactile sensing modalities. Through an advanced Fin Ray structure, the soft finger features tactile whiskers on its fingertips, facilitating perception of obstacle orientation, fingertip pressure, surface roughness, and grasping ball size. Leveraging distributed optical fiber sensing technology, we develop a sophisticated multi-point, multi-modal tactile perception neural network tailored for the soft finger. Meticulous integration via advanced 3D printing and silicone coating techniques seamlessly embeds optical fiber sensors within the soft robotic finger, creating an intelligent perception-capable bioinspired mechanical system. Experimental validation confirms the soft robotic finger’s sensitive and precise force perception and curvature recognition abilities, achieving accuracies of up to 100%. In summary, our bioinspired robotic finger holds significant promise for applications in intelligent sensing, non-destructive grasping, and fruit classification within unstructured environments, thus advancing the field of robotics and human-robot interaction.

Compared with onshore wind turbines, fault detection and isolation (FDI) process is more important for offshore ones due to both additional loadings and maintenance difficulties. FDI will be more demanding when it comes to deep-sea floating wind turbines. In this work, an ensemble learning method, random forests (RF), is proposed to perform fault detection of offshore wind turbines, as RF is robust to overfitting, producing not only accurate and quick classification, but also importance ranking for each individual feature. At the same time, supplementary dominant signals are determined for each fault through principal component analysis. The NREL FASTv8 code and OC3-Hywind 5MW floating wind turbine baseline model are used to verify this proposed data-driven FDI design.