A5101989672- Traffic Prediction and Management Techniques
- Traffic control and management
- Transportation Planning and Optimization
- Software System Performance and Reliability
- Advanced Data Processing Techniques
- Data Quality and Management
- Blockchain Technology Applications and Security
- ECG Monitoring and Analysis
- Privacy-Preserving Technologies in Data
- Mobile Agent-Based Network Management
- Simulation Techniques and Applications
- Software Testing and Debugging Techniques
- Business Process Modeling and Analysis
- Model-Driven Software Engineering Techniques
Beijing Academy of Artificial Intelligence
2023-2024
University of Chinese Academy of Sciences
2023-2024
Chinese Academy of Sciences
2023-2024
Institute of Automation
2023-2024
Shandong Institute of Automation
2023-2024
In recent years, large language models (LLM) have received a lot of attention for their ability to understand, generate and process natural language. By fine-tuning the on specific domains or using prompts, LLMs can summaries tailored different contexts requirements. We hope utilize these advantages LLM in urban traffic signal control provide new paradigm control. this paper, we propose model-driven method, which is designed based artificial systems, computational experiments, parallel...
In the field of urban traffic management, optimising signal control on major arterial road is crucial for reducing congestion and improving overall efficiency. this paper, we explore a novel approach to design implement green wave arterials using Large Language Models (LLM), such as GPT-4. Our combines state-of-the-art LLM with policies, aiming potential application in control. We workflow LLM-driven generation an example. The experiments use SUMO simulation software construct problem road....
The centralized traffic control (CTC) system of intelligent railways plays a vital role in implementing railway dispatching, improving transportation efficiency, and ensuring train safety. However, with the development high-speed (HSRs), construction new lines upgrading existing equipment have become increasingly prevalent, posing significant challenges to safety reliability CTC system. To address these challenges, this article proposes scenario-driven parallel testing method for We use...
This paper uses ChatGPT to assist traffic manager in signal control and verifies the possibility of applying scenarios. We believe has four capabilities, including: knowledge acquisition, data analysis, decision support, programming interface support. Proper use these capabilities can their strategy optimization efforts. constructed a simulation environment used human performing The process evaluating application potential consists steps. First, we conducted test on related issues ChatGPT's...
The data-driven adaptive traffic signal control for real-world scenarios faces two significant challenges: adapting to diverse patterns and addressing the generalization issue from optimization environment deployment environment. To tackle these challenges, this paper proposes a novel approach pattern-aware generalized (PATRAS) based on parallel learning. It establishes an process comprising descriptive learning, predictive prescriptive enabling robust adaptable different patterns. First,...
This paper proposes a parallel system-based predictive control (PPC) method to address the problem of active traffic signal in large-scale urban road networks. The leverages simulated artificial transportation systems infer short-term future operating states real system. During inference process, an efficient learning-based multi-agent reinforcement learning (RL) algorithm is employed optimize cooperative policies. optimized policies are then deployed system at fixed intervals adapt...