This paper presents a lightly weighted hydraulic actuator that is designed mainly for robotic applications. This hydraulic cylinder will be used as the main actuator for the hydraulic humanoid robot HYDROïD. For implementation, the knee joint is taken as an example in order to execute the necessary steps to build the actuator from carbon fiber composite material. An optimization process is used to minimize the total weight of the actuator and satisfy its constraints. Meanwhile, the mechanical design with the integrated sensors is shown. In addition, results are discussed on the spot of the weight minimization and actuator performance. Finally, experimental testing is carried out to monitor the pressure and the position readings of the hydraulic cylinder.

In an era marked by the rapid advancement of information technology, individuals now have the ability to enhance their organic bodies with mechanical and computational devices, revolutionizing their capabilities in everyday activities. However, the seamless integration of biosignals with mechanical counterparts continues to pose significant challenges. To address this, fuzzy logic emerges as a potential key to these challenges, offering a promising solution for handling the uncertainties and ambiguity inherent in biosignals. It thereby facilitates improved cyborg intelligence in an array of applications, including but not limited to WBANs, brain-computer interfaces (BCIs), prosthetics, and exoskeletons. Although previous works have highlighted the enhancement of cyborg intelligence using fuzzy sets, all of them only dived single aspects of the cyborg intelligence enhancement applications, leading to a lack of comprehensive understanding. Therefore, we provide a holistic overview of the state-of-the-art applications of fuzzy logic in cyborg enhancement technology, encompassing its benefits, challenges, and potential directions for future research.

In the framework of the HYDROïD humanoid robot project, this paper describes the modeling and design of an electrically actuated head mechanism. Perception and emotion capabilities are considered in the design process. Since HYDROïD humanoid robot is hydraulically actuated, the choice of electrical actuation for the head mechanism addressed in this paper is justified. Considering perception and emotion capabilities leads to a total number of 15 degrees of freedom for the head mechanism which are split on four main sub-mechanisms: the neck, the mouth, the eyes and the eyebrows. Biological data and kinematics performances of human head are taken as inputs of the design process. A new solution of uncoupled eyes is developed to possibly address the master-slave process that links the human eyes as well as vergence capabilities. Modeling each sub-system is carried out in order to get equations of motion, their frequency responses and their transfer functions. The neck pitch rotation is given as a study example. Then, the head mechanism performances are presented through a comparison between model and experimental results validating the hardware capabilities. Finally, the head mechanism is integrated on the HYDROïD upper-body. An object tracking experiment coupled with emotional expressions is carried out to validate the synchronization of the eye rotations with the body motions.

The increasingly pervasive usage of robotic surgery not only calls for advances in clinical application but also implies high availability for preliminary medical education using virtual reality. Virtual reality is currently upgrading medical education by presenting complicated medical information in an immersive and interactive way. A system that allows multiple users to observe and operate via simulated surgical platforms using wearable devices has become an efficient solution for teaching where a real surgical platform is not available. This article developed a bioinspired virtual reality toolkit (BioVRbot) for education and training in robot-assisted minimally invasive surgery. It allows multiple users to manipulate the robots working on cooperative virtual surgery using bioinspired control. The virtual reality scenario is implemented using unity and can be observed with independent virtual reality headsets. A MATLAB server is designed to manage robot motion planning of incremental teleoperation compliance with the remote center of motion constraints. Wearable sensorized gloves are adopted for continuous control of the tooltip and the gripper. Finally, the practical use of the developed surgical virtual system is demonstrated with cooperative operation tasks. It could be further spread into the classroom for preliminary education of robot-assisted surgery for early-stage medical students.

Dexterous robotic grasping with multifingered hands remains a critical challenge in non-visual environments, where diverse object geometries and material properties demand adaptive force modulation and tactile-aware manipulation. To address this, we propose the Reinforcement Learning-Based Multimodal Perception (RLMP) framework, which integrates human-like grasping intuition through operator-worn gloves with tactile-guided reinforcement learning. The framework’s key innovation lies in its Tactile-Driven DCNN architecture—a lightweight convolutional network achieving 98.5% object recognition accuracy using spatiotemporal pressure patterns—coupled with an RL policy refinement mechanism that dynamically correlates finger kinematics with real-time tactile feedback. Experimental results demonstrate reliable grasping performance across deformable and rigid objects while maintaining force precision critical for fragile targets. By bridging human teleoperation with autonomous tactile adaptation, RLMP eliminates dependency on visual input and predefined object models, establishing a new paradigm for robotic dexterity in occlusion-rich scenarios.