ETRI-Knowledge Sharing Plaform

Robot Manipulation An Experimental Study Reward Function Multi-Agent Reinforcement Learning Deep Reinforcement Learning Fine-Tuning Deep Learning(DL) Simulation Results Robotic Manipulation Control Problems Visual Representation Resource-Constrained Edge Devices Representation Learning Continuous Control Image Stitching Uncertainty Quantification Control Policy Loss Function Action Space Partial Observations State-Of-The-Art Monitoring System Disaster Monitoring Collaborative Task Cost-Effective Real-World Applications Smart-Eye An Unmanned Aerial Vehicle Online Interaction Power Consumption Video Prediction Multi-Robot Object-Centric Sampled Measurements Number Of Layers Training Time Behavioral Model Aerial Images Computing Systems Computational Power Distributed Multi-Agent System Device Control Dictionary Matrix Disaster Management System Empirical Evaluation Engineering Method Fire Detection High Accuracy High Dispersion Iot Devices Long Horizons Latent Variables Low-Power Limited Interaction Multiple Sensors Satellite Images Need For Task Completion Real Environment Reconstruction Ability Convolution Neural Network(CNN) Compressed Sensing Distributed Network Environment High Resolution Image Hardware Resources Learning Model Learning Outcomes Manipulation Performance Reducing Power Spatial Information Sensory Data Pre-Training Sensor Data Optical Sensor Residual Energy Convergence Analysis Cost-Efficient Cloud Policy Flight Time Goal-Based Heuristic Information Internet Of Thing(IoT) Input Data Limited Information Management Techniques Model Compression Success Rate Policy Model Policy Training New Model Task Performance Real-World Problems Angle Of View(AoV) Detection Accuracy Embedded System Information Services Key Components Monitoring Techniques Monitoring And Response Real-Time State Prediction State-Based Multiple Agents Latent Space Virtual World 3d Locomotion Spatial Resolution Temporal Resolution Robot Simulator Real-World Data Autonomous Driving Average Rewards Autoregressive Models Auto-Encoder(AE) Control Strategy Control Sample Cloud Environment Deep Neural Network(DNN) Decision Support System(DSS) Decision Making System Digital Communication System Energy-Efficient Energy Consumption Image Set Multiple Robots Temperature And Humidity Riverside Area Recognition Technique Simulated Environment Smart Manufacturing Performance Degradation Video Games Trial-And-Error Template Matching Robot Manipulator Robot Control Continuous Action Collaborative Manipulation Convergence Time Collaborative Environment Collaborative Robot Computational Cost Disaster Information Intrusion Detection System(IDS) Deep Convolutional Neural Networks Experience Replay Future Prediction Image-Based Learning Approach Learning Environment Data-Driven Learning Social Loafing Scene Representation Proposed Model Q-Function Uncertainty Estimation Symbol Detection State-Space Model Area Of Interest Object-Oriented Training Process Task Design Temporal Dynamics Time Constraint Robotic Arm Break Down Complex Task Data Augmentation Economic Loss Edge Computing Efficient Training Forest Fire Monitoring Hyper-Connected High Dimensionality Human Monitoring Knowledge Transfer Knowledge Distillation Link Capacity Control Area Natural Disaster Policy Network Power Control(PC) Performance Comparison Wild Fire Wide Range Nonstationary Environment Non-Stationary Characteristic Task Allocation Robotics And Control Robot Learning Analysis Of The Impact Aerial Photographs Attention Mechanism Camera Angle Cloud Infrastructure Decision-Making Process Dynamic Nature Distributed Intelligence Efficient Communication Empirical Investigation End To End(E2E) Edge Cloud Human-Like Image Reconstruction Image Pixels Learning Control Multimodal Data Monitoring Service Recovery Method Stationary Problems Policy Optimization Periodic Communication Video Generation