A5101466854- Autonomous Vehicle Technology and Safety
- Traffic control and management
- Vehicular Ad Hoc Networks (VANETs)
- Software Testing and Debugging Techniques
- Real-time simulation and control systems
- Transportation Planning and Optimization
- AI-based Problem Solving and Planning
- Advanced Aircraft Design and Technologies
- Software Reliability and Analysis Research
- Biosensors and Analytical Detection
- Industrial Technology and Control Systems
- Network Traffic and Congestion Control
- Vehicle emissions and performance
- Advanced Sensor and Control Systems
- Human-Automation Interaction and Safety
- Engine and Fuel Emissions
- Traffic Prediction and Management Techniques
- Technical Engine Diagnostics and Monitoring
- Network Time Synchronization Technologies
- Thin-Film Transistor Technologies
- Distributed Control Multi-Agent Systems
- Advanced Chemical Sensor Technologies
- Advanced Computing and Algorithms
- Neural Networks and Reservoir Computing
- Analytical Chemistry and Sensors
Huaqiao University
2023
Horizon Robotics (China)
2023
University of Michigan
2018-2020
University of Naples Federico II
2020
Hangzhou Dianzi University
2020
University of Aveiro
2020
Beijing University of Technology
2017
In this paper, we propose a new scenario generation algorithm called Combinatorial Testing Based on Complexity (CTBC) based both combinatorial testing (CT) method and Test Matrix (TM) technique for intelligent driving systems. To guide the procedure in evaluate validity of generated scenarios, further concept complexity test scenario. CTBC considers overall cost testing, reasonable balance between them can be found by using Bayesian optimization account black box property CTBC. The...
In this paper, a methodology of automatic generation test scenarios for intelligent driving systems is proposed, which based on the combination matrix (TM) and combinatorial testing (CT) methods together. With hierarchical model influence factors, an evaluation index scenario complexity designed. Then improved CT algorithm proposed to make balance between efficiency, condition coverage, complexity. This method can ensure required combinational coverage at same time increase overall generated...
The testing of the intelligent driving systems is faced with challenges efficiency because real traffic scenarios are infinite, uncontrollable and difficult to be precisely defined. Based on complexity index scenario that designed measure test effect indirectly, a new combinational algorithm cases generation proposed make balance among multiple objects including coverage, number effect. Then joint simulation platform based Matlab, PreScan Carsim built up realize construction 3D environment,...
To simultaneously deal with the uncertain interaction topology, parametric errors and external disturbances, this paper proposes a new coordinated control scheme for platoon composed of nonlinear heterogeneous automated vehicles (AVs). In scheme, different perturbations are dealt separately to reduce contraction among them by using sliding mode theory. Considering individual dynamics, distributed controller including both lateral longitudinal motions is designed each AV online estimation...
The platooning of automated vehicles has potential to significantly benefit road traffic, while its robust performance is less investigated especially considering increasing complexity interaction topologies. This study presents a decoupled H∞ control method for vehicular platoon comprehensively compromise multiple performances. system first decomposed into an uncertain part and diagonal nominal through the linear transformation, which motivated by eigenvalue decomposition information...
The application of wireless communication to platooning brings such challenges as information delay and varieties interaction topologies. To compensate for the delay, a state predictor based control strategy is proposed, which transmits future nodes instead current values. Based on closed loop dynamics platoon with feedback controller, decoupling presented analysis design system lower order by adopting eigenvalue decomposition topological matrix. A numerical method LMI (Linear Matrix...
To overcome the challenges arising from weakness of wireless communication, this paper presents a distributed <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M2"><mml:mrow><mml:msub><mml:mrow><mml:mi mathvariant="bold-italic">H</mml:mi></mml:mrow><mml:mrow><mml:mi mathvariant="normal">∞</mml:mi></mml:mrow></mml:msub></mml:mrow></mml:math> control method for multi-AVs connected by an uncertain and switching topology in platoon. After compensating powertrain nonlinearities, we...
Due to the limitation of current technologies and product costs, humans are still in driving loop, especially for public traffic. One key problem cooperative is determining time when assistance required by a driver. To overcome disadvantage driver state-based detection algorithm, new index called correction ability proposed, which further combined with risk evaluate capability. Based on this measurement, degraded domain (DD) set up detect degradation The log normal distribution used model...
With the acceleration of urbanization and increase in traffic load, traditional management methods struggle to cope with complexity modern conditions. Intelligent Transportation Systems (ITS), utilizing information technology artificial intelligence, have improved efficiency safety transportation systems. Reinforcement Learning (RL), as an adaptive optimization method, can dynamically adjust signals flow control strategies through trial error reward mechanisms, optimizing signal control....
The field of autonomous driving has witnessed a significant shift towards data-driven planning and control algorithms. Due to the limitation real-world data, simulator-based data is an alternative. However, domain adaptation issue arises when evaluating in with simulator-data trained model. This paper presents processing pipeline scenario mining tool, P3C, specifically designed for make based dataset building more efficient.