Article
Engineering, Civil
Marco Mirabilio, Alessio Iovine, Elena De Santis, Maria Domenica Di Benedetto, Giordano Pola
Summary: This paper introduces a human-inspired Adaptive Cruise Control system that utilizes Model Predictive Control and traffic macroscopic information to enhance the passenger experience by reducing traffic congestion and dangerous emissions while improving safety on the roads.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Thermodynamics
Zifei Nie, Hooman Farzaneh
Summary: This study introduces a real-time dynamic predictive cruise control (PCC) system based on the MPC algorithm to minimize energy consumption for electric vehicles under integrated traffic situations. The system utilizes SPaT-oriented MPC and car-following oriented MPC to calculate optimal control signals and maintain safe interdistances, demonstrating successful validation in real-world tests and robust performance in high-speed driving scenarios.
Article
Computer Science, Artificial Intelligence
A. S. M. Bakibillah, M. A. S. Kamal, Chee Pin Tan, Tomohisa Hayakawa, Jun-ichi Imura
Summary: The traditional optimal control systems for vehicles on slopes do not efficiently utilize gravitational potential energy; the proposed dynamic eco-driving system with model predictive control and fuzzy-tuned weights significantly reduces fuel consumption and CO2 emissions.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Arun Muraleedharan, Hiroyuki Okuda, Tatsuya Suzuki
Summary: This paper presents a successful implementation of randomized model predictive control (MPC) in autonomous driving and addresses several challenges in real-world applications, including sample generation technique and GPU acceleration. The experimental results demonstrate that this method outperforms traditional CPU-based implementation in terms of control performance and computational speed.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2022)
Article
Computer Science, Information Systems
Hongli He, Dan Liu, Xiangyang Lu, Juncai Xu
Summary: An energy-aware ecological driving control strategy is proposed to optimize energy consumption and achieve the most ecological driving. Results show that real-time monitoring of battery pack's remaining power in-vehicle driving, and optimization can lead to a 26% reduction in energy consumption compared to non-optimized vehicles. These findings have practical significance for the future autonomous driving control strategies of intelligent vehicles.
Article
Automation & Control Systems
Jun Chen, Aman Behal, Zhaojian Li, Chong Li
Summary: This paper studies active battery cell balancing control for extending the driving range of electric vehicles based on linear parametric varying model predictive control. The proposed control strategies can reduce imbalance by dynamically transporting electricity among cells. Simulation results show that the proposed control methods can achieve a driving range extension of 9% for dynamic driving cycles and 7% for steady-state conditions.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Information Systems
Zhe Zhang, Haitao Ding, Konghui Guo, Niaona Zhang
Summary: In order to improve the distance per charge of four in-wheel independent motor-drive electric vehicles in intelligent transportation systems, a hierarchical energy management strategy that incorporates computational efficiency and optimization performance is proposed. This strategy combines reinforcement learning with receding horizon optimization at the upper level to solve the cruising velocity for eco-driving, and a multi-objective optimal torque allocation method is proposed at the lower level. The proposed energy management strategy effectively reduces the complexity of the vehicle's intelligent energy-saving control system and achieves a fast solution to the vehicle energy optimization problem, considering both power and safety.
Article
Environmental Studies
Fangwu Ma, Yu Yang, Jiawei Wang, Xinchen Li, Guanpu Wu, Yang Zhao, Liang Wu, Bilin Aksun-Guvenc, Levent Guvenc
Summary: The Eco-CACC proposed in this study combines eco-driving and car-following techniques to minimize energy consumption of automated vehicle platoons. Testing results show that Eco-CACC can significantly improve energy performance compared to manual driving.
TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT
(2021)
Article
Automation & Control Systems
Aaron I. Rabinowitz, Chon Chia Ang, Yara Hazem Mahmoud, Farhang Motallebi Araghi, Richard T. Meyer, Ilya Kolmanovsky, Zachary D. Asher, Thomas H. Bradley
Summary: This article reviews the state of autonomous eco-driving control research and evaluates different methods through simulations. The results show that dynamic programming methods are most effective in improving energy economy but are computationally expensive, while genetic algorithm methods have the potential to improve energy economy and run-time.
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY
(2023)
Article
Energy & Fuels
Eros D. Escobar, Daniel Betancur, Tatiana Manrique, Idi A. Isaac
Summary: This paper presents the development and experimental implementation of a time-varying constraint real-time model predictive secondary voltage control (MPVC) strategy for microgrids. The strategy uses a multi-class Python environment with InfluxDB and SQLExpress databases for data storage and Modbus communication for device interaction. The experimental results demonstrate the effectiveness of the proposed control system in achieving voltage regulation under different disturbance scenarios.
Article
Engineering, Electrical & Electronic
James Fleming, Xingda Yan, Craig Allison, Neville Stanton, Roberto Lott
Summary: The eco-driving assistance system incorporating predictive or feedforward information is effective in increasing energy-efficiency and reducing CO2 emissions. Studies have shown a 6.09% reduction in fuel consumption and improvements in travel time, demonstrating the feasibility of real-time implementation of the system.
IET INTELLIGENT TRANSPORT SYSTEMS
(2021)
Article
Computer Science, Information Systems
Taekgyu Lee, Dongyoon Seo, Jinyoung Lee, Yeonsik Kang
Summary: This study develops a drift controller based on deep neural network (DNN) for autonomous vehicles, which can perform drift maneuvers using the nonlinear model predictive control (NMPC) method. The DNN-based controller demonstrates similar tracking performance to the original controller and stable computation time, making it important for safety critical control objectives like drift maneuvers.
Article
Engineering, Mechanical
ZhiHao Xu, JianHua Li, Feng Xiao, Xu Zhang, ShiXin Song, Da Wang, ChunYang Qi, JianFeng Wang, SiLun Peng
Summary: This study improves the adaptability and fuel economy of vehicles in various environments by establishing a neural network to identify the driving cycles of vehicles, dividing weight intervals according to different driving cycles, and dynamically adjusting the weight values through fuzzy control.
INTERNATIONAL JOURNAL OF AUTOMOTIVE TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Basem Almadani, Najood Alshammari, Anas Al-Roubaiey
Summary: This paper discusses the Adaptive Cruise Control (ACC) system, which allows drivers to minimize driving time. It supports four driving modes and regulates acceleration and deceleration to maintain speed or avoid collisions. The paper proposes a real-time system for integrating ACC components, using RTPS middleware for data exchange. The design of the publish/subscribe model and suggested QoS policies are explained in detail.
Article
Engineering, Electrical & Electronic
Tongxin Li, Bo Sun, Yue Chen, Zixin Ye, Steven H. Low, Adam Wierman
Summary: The paper introduces a real-time aggregate flexibility feedback design called Maximum Entropy Feedback (MEF) and a control algorithm, namely Penalized Predictive Control (PPC), which uses reinforcement learning for approximation. The scheme aims to improve communication efficiency, lower computing costs, and demonstrates the optimality of PPC under certain regularity assumptions through examples.
IEEE TRANSACTIONS ON SMART GRID
(2021)