Results 61 to 70 of about 7,279,238 (253)

Bio‐Inspired Object Retrieval via Proximity‐Guided Adaptive Thigmotactic Exploration and Neuromorphic Recognition

open access: yesAdvanced Robotics Research, EarlyView.
Sparse active‐infrared proximity sensing is coupled to an adaptive thigmotactic controller for camera‐inaccessible object retrieval. After grasping, receptor‐informed encoding transforms force, temperature, and wrist force–torque signals into spike trains for spiking neural network recognition.
Fengyi Wang, Nitish Thakor, Gordon Cheng
wiley   +1 more source

NAS-HPO-Bench-II-Plus: A Surrogate Benchmark Dataset Toward Practical Scenarios in Joint Neural Architecture Search and Hyperparameter Optimization

open access: yesIEEE Access
Automated machine learning reduces the manual effort required to design deep learning models. Its two major subfields, neural architecture search and hyperparameter optimization, optimize model architectures and training hyperparameters, respectively. In
Yoichi Hirose   +2 more
doaj   +1 more source

Advanced Flexible Robotic Systems for the Early Diagnosis and Treatment of Cancer and Cardiovascular Diseases

open access: yesAdvanced Robotics Research, EarlyView.
Flexible surgical robots are advancing minimally invasive interventions for cardiovascular diseases and cancer by enabling precise navigation through complex, submillimeter anatomical pathways. This review highlights recent innovations in actuation, bio‐integrated sensing, AI‐assisted control, and friction‐reduction technologies, discusses current ...
Hermione Truong   +14 more
wiley   +1 more source

Enhancing Amphibious Flipper‐Based Locomotion Through Terrain‐Dependent Bayesian Optimization of Central Pattern Generator Control

open access: yesAdvanced Robotics Research, EarlyView.
A sea turtle‐inspired amphibious robot uses simulation‐guided optimization to adapt its flipper coordination to different environments. Sensitivity analysis and multiobjective Bayesian optimization identify terrain‐dependent controllers that are validated on hardware.
Nnamdi C. Chikere, Yasemin Ozkan‐Aydin
wiley   +1 more source

Robotic Assistants in the Operating Room: A Systematic Review of Vision‐Based Systems for Nonoperative Tasks

open access: yesAdvanced Robotics Research, EarlyView.
This review brings together 20 publications describing 11 robotic system families developed for instrument handling, sterile‐package opening, supply delivery, and operating room logistics. Perception is becoming more capable through deep learning and language‐guided control, but autonomy remains limited, evidence is largely laboratory‐based, and no ...
Eugenia Mawuenya Akpo   +4 more
wiley   +1 more source

Robotics in Ionizing Radiation Environments: Vulnerabilities, Hardening, and Future Directions

open access: yesAdvanced Robotics Research, EarlyView.
Radiation exposure causes cumulative degradation in robotic sensors, actuators, and electronic logic, often leading to undetected failures. This study maps component vulnerabilities, evaluates hardening and shielding strategies, and identifies testing gaps that must be addressed to enable next‐generation radiation‐tolerant robotic systems.
Francis A. K. Djirackor   +4 more
wiley   +1 more source

Combining Neural Architecture Search and Weight Reshaping for Optimized Embedded Classifiers in Multisensory Glove

open access: yesSensors
Intelligent sensing systems are increasingly used in wearable devices, enabling advanced tasks across various application domains including robotics and human–machine interaction.
Hiba Al Youssef   +4 more
doaj   +1 more source

Overcoming Artificial Structures in Resolution‐Enhanced Hi‐C Data by Signal Decomposition and Multi‐Scale Attention

open access: yesAdvanced Science, EarlyView.
Deep‐learning‐based signal enhancement is an effective way to recover high‐resolution details from a low‐resolution chromatin contact map. However, due to computational challenges, existing methods commonly divide up the contact map into small patches and create artificial discontinuities at patch boundaries.
Qinyao Li   +6 more
wiley   +1 more source

CAS-NAS: A carbon-aware neural architecture search framework for sustainable AI development

open access: yesEngineering Science and Technology, an International Journal
The exponential growth of artificial intelligence has precipitated significant environmental concerns, with large-scale models consuming massive computational resources and generating substantial carbon emissions.
Shahriar Ahsan Taisiq
doaj   +1 more source

HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling

open access: yes, 2022
Dynamic neural networks (DyNNs) have become viable techniques to enable intelligence on resource-constrained edge devices while maintaining computational efficiency.
Niar, Smail   +4 more
core  

Home - About - Disclaimer - Privacy