This research explores how bio-inspired soft robots can achieve higher levels of autonomy by mimicking natural systems.
A new self-powered bionic e-skin, capable of sensing and visualizing liquid droplet dynamics, was developed to enhance intelligent robotics in liquid environments. This e-skin, utilizing triboelectricity, demonstrates potential for applications in robotics, healthcare, and various safety-critical environments.
A new study published in Radiology paints a promising picture of the role of artificial intelligence (AI) in breast cancer screening.
Researchers have introduced perforation-type anchors to securely attach living skin to robotic surfaces, enhancing biohybrid robots with human-like features. This bioinspired technique offers robust, aesthetically pleasing, and biocompatible integration, crucial for advanced robotics.
A recent study published in JCM compared the efficacy of conventional laparoscopy (CL) and robotic-assisted laparoscopy (RAL) for treating deep endometriosis in Mexican patients. The research aimed to assess perioperative and postoperative outcomes of both techniques in a developing country context.
Researchers developed a reinforcement learning-based controller for lower limb rehabilitation exoskeletons (LLREs), offering robust, patient-agnostic walking assistance. This controller, trained with simulated human-exoskeleton interactions, adapts to various neuromuscular disorders without needing specific control parameter tuning.
An international study led by Radboud University Medical Center and published in The Lancet Oncology compares and transparently assesses AI with clinical outcomes and radiologist assessments.
Researchers, in a study published in The Innovation, developed a bionic spine for soft robots inspired by vertebrate animals' spines. By integrating sensing and actuation into a single device using materials like lead zirconate titanate (PZT), the bionic spine enables complex motions and behaviors without external sensors.
The researchers introduce the ROSMA dataset and methodology in Applied Sciences, facilitating instrument detection and gesture segmentation in robotic surgical tasks. Through manual annotations and a neural network model combining YOLOv4 and LSTM, they achieve high accuracy and generalization capabilities, offering potential applications in surgical data science and beyond.
Researchers introduced a novel approach to signer-independent sign language recognition (SLR) using Neutrosophic hidden Markov models (NHMM). By addressing the challenges of variability and uncertainty inherent in sign gestures, the proposed NHMM system achieved a remarkable gesture recognition rate of 98.5%, outperforming traditional methods.
Terms
While we only use edited and approved content for Azthena
answers, it may on occasions provide incorrect responses.
Please confirm any data provided with the related suppliers or
authors. We do not provide medical advice, if you search for
medical information you must always consult a medical
professional before acting on any information provided.
Your questions, but not your email details will be shared with
OpenAI and retained for 30 days in accordance with their
privacy principles.
Please do not ask questions that use sensitive or confidential
information.
Read the full Terms & Conditions.