Results 71 to 80 of about 6,292,535 (287)

Dynamic path planning of autonomous mobile robot in off-road environments using experience replay enhanced distributed proximal policy optimization algorithm

Geo-spatial Information Science
In off-road environments, some problems like insufficient consideration of environmental trafficability, difficulty in model convergence, and limited generalization often exist in autonomous mobile robot (AMR) path planning research based on ...
Qingyun Liu, Xiong You, Xin Zhang, Jiwei Zuo, Jia Li   +4 more
doaj   +1 more source

Flexible Sensors for Robotics Tactile Perception: A Review

Advanced Robotics Research, EarlyView.
Flexible tactile sensing for robotics is reviewed through four interconnected dimensions. Physical mechanisms include piezoresistive, capacitive, piezoelectric, triboelectric, iontronic, and optical sensing. Structural design includes bioinspired, defect‐based, and MEMS‐based tactile systems.
Yu Song, Ying Chen, Yihao Chen, Xue Feng
wiley   +1 more source

Proximal Policy Optimization with Mixed Distributed Training [PDF]

2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), 2019
ICTAI ...
Zhenyu Zhang 0013, Xiangfeng Luo, Tong Liu 0001, Shaorong Xie, Jianshu Wang, Wei Wang 0296, Yang Li 0151, Yan Peng 0001   +7 more
openaire   +4 more sources

CAPO: A Coherence-Adaptive Advantage Mechanism Instantiated in Proximal Policy Optimization

Applied Sciences
Performance degradation caused by temporal-difference signal fluctuations and the inflexibility of fixed proximal constraints remains a key challenge in policy optimization algorithms.
Mingjie Li, Jiajie Hu, Weijun Wang, Tao Zhang, Daoshun Xie, Zhihui Hu, Jiangfeng Xian   +6 more
doaj   +1 more source

TacVerse: A Multisensor Dataset and Benchmark for Cross‐Sensor Vision‐Based Tactile Perception

Advanced Robotics Research, EarlyView.
TacVerse provides a controlled benchmark of 106 800 tactile images from seven vision‐based tactile sensors across shape classification, grating classification, and force regression. Direct cross‐sensor transfer reveals substantial sensor‐shift degradation, with grating and force perception more affected than shape recognition.
Lan Wei, Gurmeher Khurana, Sirine Bhouri, Wenhao Hong, Zeyuan Xin, Qingzheng Cong, Wen Fan, Yanzheng Xiang, Dandan Zhang   +8 more
wiley   +1 more source

A Novel Pak1 Activator Ameliorates ER Stress for HFpEF Therapy

Advanced Science, EarlyView.
Chronic metabolic stress is a major contributor to HFpEF progression. Under prolonged metabolic stress, Pak1 activity becomes impaired, contributing to disrupted ER proteostasis, cardiomyocyte apoptosis, fibrosis, and diastolic dysfunction. Mechanistically, Pak1 overexpression activates the ERK1/2–MNK1–eIF4E signaling axis, promotes translational ...
Honglin Xu, Hongyuan Zhang, Tayyiba Azam, Susanne S. Hille, Yingjuan Liu, Min Zi, Jiaqing Lang, He Yu, Yujia Cao, Bernard D. Keavney, Tamer M. A. Mohamed, Jessica M. Miller, Riham R. E. Abouleisa, Ming Xu, Elizabeth J. Cartwright, Oliver J. Müller, Ming Lei, Xin Wang   +17 more
wiley   +1 more source

Task Offloading Scheme Based on Proximal Policy Optimization Algorithm

Applied Sciences
The rapid development of mobile Internet technology has made users’ requirements for quality of service (QoS) continuously improve. The task unloading process of mobile edge computing has the problem that it is impossible to balance delay and energy ...
Yutong Ma, Junfeng Tian
doaj   +1 more source

Reducing the Treatment Gap and Public Health Burden of Osteoporotic Fractures [PDF]

, 2021
K2P Policy Briefs bring together global research evidence, local evidence and context-specific knowledge to inform deliberations about health policies and programmes.
Hilal, Nadeen, El-Jardali, Fadi, Jamal, Diana, Chakhtoura, Marlene, El-Hajj Fuleihan, Ghada   +4 more
core  

Neuromorphic Devices and Computing for Sensing, Memory, and Control

Advanced Science, EarlyView.
This review introduces neuromorphic devices made from diverse materials. These devices mimic neuronal functions and architectures and, when integrated with artificial or biological computing, can form closed loops with neurons for pressure, optical, acoustic, and biochemical sensing and modulation.
Zhengguang Zhu, Nicholas Schaffer, Xiao Yang   +2 more
wiley   +1 more source

Policy Optimization in Reinforcement Learning: Proximal Policy Optimization

, 2023
This presentation was given in the lecture Artificial Intelligence at FH Kufstein Tirol in November 2022.
openaire   +2 more sources