A5066913405- Smart Agriculture and AI
- Modular Robots and Swarm Intelligence
- Arsenic contamination and mitigation
- Adsorption and biosorption for pollutant removal
- Adversarial Robustness in Machine Learning
- Manufacturing Process and Optimization
- Electromagnetic Launch and Propulsion Technology
- Heavy Metal Exposure and Toxicity
- Reinforcement Learning in Robotics
- Space Satellite Systems and Control
- Advanced Measurement and Metrology Techniques
- Hydraulic and Pneumatic Systems
- Transportation Safety and Impact Analysis
- Robotics and Automated Systems
- Metal-Organic Frameworks: Synthesis and Applications
- Space Exploration and Technology
- Remote Sensing and Land Use
- Safety Systems Engineering in Autonomy
Tarim University
2025
Tsinghua University
2024
Changchun University
2024
Taiyuan University of Technology
2024
The 3/2 water proportional directional valve (PDV) is an important hydraulic component to ensure a precise, low impact, and safety control of powered roof support, which has been technical challenge facing coal mining industry for many years. To address this issue, new PDV developed. includes novel three-core follow-up servo mechanism consisting three key components: the pilot inlet valve, outlet main spool. This enables precise reliable opening, closing capacity valve. prototype...
As an important and nutrient-rich economic crop, apple is significantly threatened by leaf diseases, which severely impact yield, making the timely accurate diagnosis segmentation of these diseases crucial. Traditional models face challenges such as low accuracy excessive model size, limiting their applicability on resource-constrained devices. To address issues, this study proposes RMP-UNet, efficient lightweight for disease segmentation. Based traditional UNet architecture, RMP-UNet...
Space robots have played a critical role in autonomous maintenance and space junk removal. Multi-arm can efficiently complete the target capture base reorientation tasks due to their flexibility collaborative capabilities between arms. However, complex coupling properties arising from both multiple arms free-floating present challenges motion planning problems of multi-arm robots. We observe that octopus elegantly achieves similar goals when grabbing prey escaping danger. Inspired by...
Multi-Agent Reinforcement Learning (MARL) promises to address the challenges of cooperation and competition among multiple agents, often involving safety-critical scenarios. However, realizing safe MARL remains a domain limited progress. Current works extend single-agent learning approaches, employing shielding or backup policies ensure safety satisfaction. Nevertheless, these approaches require good weakly distributed with centralized become infeasible when agents encounter complex...