A5103110750- Quantum Chromodynamics and Particle Interactions
- UAV Applications and Optimization
- Distributed Control Multi-Agent Systems
- Particle physics theoretical and experimental studies
- Dark Matter and Cosmic Phenomena
- Mobile Ad Hoc Networks
- Gear and Bearing Dynamics Analysis
- High-Energy Particle Collisions Research
- Reinforcement Learning in Robotics
- Industrial Vision Systems and Defect Detection
- Machine Fault Diagnosis Techniques
- Non-Destructive Testing Techniques
- Computational Physics and Python Applications
- Video Surveillance and Tracking Methods
- Railway Engineering and Dynamics
- Infrastructure Maintenance and Monitoring
- Robotic Path Planning Algorithms
- Energy Harvesting in Wireless Networks
University Town of Shenzhen
2024
Tsinghua University
2023-2024
University of Electronic Science and Technology of China
2021-2023
Tsinghua–Berkeley Shenzhen Institute
2023
Southwest Jiaotong University
2023
Institute of High Energy Physics
2020
In disaster scenarios, unmanned aerial vehicles (UAVs) can serve as mobile base stations because of their maneuverability and synergy. However, due to constrained UAV communication capabilities limited battery life, resource allocation for sensors in a data-heterogeneous environment is significant challenge when optimizing quality. To address this, we propose AGUZero, an attention-based graph reinforcement learning (RL) framework. Inspired by MuZero [27], AGUZero designed handle dynamic...
An automatic detection method for surface defects on railway tracks holds significant importance in ensuring the safety of transportation. However, practice, exhibit characteristics, such as being scarce number, small size, and having shape variations. Therefore, implementing supervised learning techniques under constraint limited labeled data is a major challenge. To address this problem, we propose designed framework based self-supervised representation rail defect (R-SSRL). Inspired by...
Utilizing unmanned aerial vehicles (UAVs) as mobile access points can assist urban communication systems in establishing emergency networks disaster scenarios. However, large-scale dynamic environments, the extensive exploration space makes effective collaboration among a large number of UAVs challenging. In this paper, to schedule deployment for networking purposes, we propose novel approach, MAEN, using multi-agent reinforcement learning. The grouping and information sharing mechanisms...
Deep learning has demonstrated great vitality in various fields recent years. However, most deep models lack kernel size selection capability and feature importance distinction mechanism. Although there have been studies that considered using the channel attention mechanism to help automatic of size, few researchers used spatial recalibrate choice size. Therefore, this paper, a selective network, based on joint (SKNJA), is proposed for first time further improve ability convolutional neural...