A5031970101- scientometrics and bibliometrics research
- Interdisciplinary Research and Collaboration
- Traditional Chinese Medicine Analysis
- Robotic Path Planning Algorithms
- Data Visualization and Analytics
- Traditional Chinese Medicine Studies
- Big Data and Business Intelligence
- Chromatography in Natural Products
- Reinforcement Learning in Robotics
- Robotics and Sensor-Based Localization
- Natural product bioactivities and synthesis
- Phytochemical Studies and Bioactivities
- Plant-based Medicinal Research
- Biological Activity of Diterpenoids and Biflavonoids
- Robot Manipulation and Learning
- Modular Robots and Swarm Intelligence
- Advanced Image Processing Techniques
- Advanced Graph Neural Networks
- Wood and Agarwood Research
- Advanced Numerical Analysis Techniques
- Medicinal Plant Pharmacodynamics Research
- Advanced Image and Video Retrieval Techniques
- Silicon and Solar Cell Technologies
- Diverse Approaches in Healthcare and Education Studies
- Phytochemistry and Biological Activities
University of Chinese Academy of Sciences
2022-2025
Sichuan Academy of Traditional Chinese Medicine
2012-2025
Institute of Computing Technology
2022-2024
China Shipbuilding Industry Corporation (China)
2021
Dalian University of Technology
2019
China Institute of Atomic Energy
2014
Speed planning in rugged terrain poses challenges due to various constraints, such as traverse efficiency, dynamics, safety, and smoothness. This letter introduces a framework based on Constrained Reinforcement Learning (CRL) that considers all these constraints. In addition, extracting the information constraint be added CRL is also barrier. this letter, extraction module designed quantify semantic geometric attributes of by estimating maximum safe speed. All networks are trained simulators...
Abstract Background Ophiopogonis radix and Liriopes are well known for the treatment of dry coughs phthisis. is occasionally used as a substitute in various prescriptions due to extremely similar pharmacological activities clinical efficacies, but they regarded two different remedies Chinese Pharmacopoeia. Accordingly, establishment reliable analytical approach discrimination quality evaluation required. Objective To establish simple, accurate, method that can simultaneously determine...
Researchers use various skills in their works, such as writing, data analysis and experiments design. These research have greatly influenced the quality of outputs, well scientific impact. Although many indicators been proposed to quantify impact researchers, studies evaluating are very rare. In this paper, we analyze factors affecting researchers’ skill ranking propose a new model based on hypergraph theory evaluate skills. To validate our model, perform PLOS ONE dataset compare rank with...
Model predictive control is a promising method in robot tasks. How to design an effective model structure and efficient prediction framework for still open challenge. To reduce the time consumption avoid compounding-error of multi-step process control, we propose single-model simultaneous framework, which uses single dynamics predict entire horizon simultaneously by taking all actions with current state as inputs. Based on this further adversarial that contains two parts. The generator...
Guided by the basic theory of traditional Chinese medicine and using modern scientific methods, Dao-di herbs pharmacology studies nature, performance, interaction with body its clinical application.It is a bridge between research application herbs. It can objectively describe law efficacy herbs, scientifically explain mechanism explore establish standards methods based on biological effect efficacy, provide basis for special properties, value herbs.Furthermore, we put forward new idea...
To establish a fast sensitive, reproducible LC-MS/MS method to study pharmacokinetic properties of THC, and compare relative bioavailability THC its solid dispersion in mice. 200 mice were divided randomly into two groups, administered orally with THC-solid after fasting (calculate on THC:400 mg x kg(-1)), used HPLC-MS/MS determine the concentration each period at following times: baseline ( predose ), 15, 30, 45 min, 1, 1.5, 2, 3, 4, 6, 24 h dosing. Calculating parameters according C-t...
We present AVS-HRL, a modular Active visual SLAM system based on hierarchical reinforcement learning. The reward function explicitly considers the efficiency of exploration and accuracy mapping by utilizing internal variables SLAM, such as feature points distribution loop-closure signal. Compared to end-to-end active methods, we designed map reconstruction module that can correct cumulative error in incremental process. Furthermore, inputs all neural network modules use more abstract general...