Review
Automation & Control Systems
P. Stano, U. Montanaro, D. Tavernini, M. Tufo, G. Fiengo, L. Novella, A. Sorniotti
Summary: Automated vehicles are rapidly becoming a reality due to their road safety potential. In the last decade, intensive research on automated driving systems, particularly in model predictive control (MPC) for path tracking, has been conducted with support from industry and governmental organizations. This literature review examines the research conducted from 2015 to 2021 and highlights the significance of MPC in path tracking control literature, discussing different typologies, prediction models, optimal control problem formulations, and presenting practical design indications and recent development trends for further investigations.
ANNUAL REVIEWS IN CONTROL
(2023)
Article
Chemistry, Analytical
Adam Domina, Viktor Tihanyi
Summary: This paper presents a model predictive control (MPC) approach for controlling automated vehicle steering during path tracking. The steering dynamics are modeled using first-order lag and second-order lag, with the first-order system resulting in slightly more accurate path-following. A cascade MPC structure is applied to separate the steering dynamics from the path-following controller. Both steering system models and the cascade MPC are evaluated in simulation and on a test vehicle, demonstrating the effectiveness of the proposed reference definition method.
Article
Engineering, Civil
Yixiao Liang, Yinong Li, Amir Khajepour, Yanjun Huang, Yechen Qin, Ling Zheng
Summary: In this research, a novel scheme is proposed to integrate local motion planning and control for autonomous vehicles. The local motion planning is transformed into the longitudinal control problem and a lateral MPC controller is designed to track the global path and execute the local motion commands. Comprehensive case studies demonstrate the effectiveness of the proposed algorithm.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Alexander Katriniok, Benedikt Rosarius, Petri Mahonen
Summary: This paper proposes a fully distributed control system architecture for safely coordinating connected and automated vehicles at road intersections. By using a model predictive control approach and vehicle-to-vehicle communication, the control problem is solved locally and synchronously. Experimental tests demonstrate the effectiveness of the proposed architecture.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Zhaodong Zhou, Christopher Rother, Jun Chen
Summary: This letter presents an event-triggered model predictive control (MPC) framework for autonomous vehicles (AV) path tracking control using the CARLA simulation environment. Compared with traditional time-triggered MPC, event-triggered MPC only solves the optimization problem when an event is triggered, thus reducing computational requirements.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2023)
Article
Engineering, Electrical & Electronic
Yunfeng Xie, Cong Li, Hui Jing, Weibiao An, Junji Qin
Summary: This study proposes a path tracking and stability-integrated controller based on a model predictive control algorithm for four-wheel independently driven electric vehicles, which can effectively limit the risks associated with high-speed driving on high-adhesion roads and low-adhesion roads.
Article
Engineering, Mechanical
Kai Yang, Xiaolin Tang, Yechen Qin, Yanjun Huang, Hong Wang, Huayan Pu
Summary: This paper compares the performance of Model Predictive Control (MPC) and Robust H-infinity State Feedback Control (RSC) in trajectory tracking through three test cases under different scenarios. Both controllers have their own advantages and disadvantages in various conditions and require a trade-off in practical applications.
CHINESE JOURNAL OF MECHANICAL ENGINEERING
(2021)
Article
Automation & Control Systems
Huiran Wang, Qidong Wang, Wuwei Chen, Linfeng Zhao, Dongkui Tan
Summary: This paper proposes a path tracking method based on model predictive control with a variable predictive horizon, and utilizes response analysis of the path tracking control system along with the design of a particle swarm optimization algorithm to achieve adaptive optimization for the predictive horizon. Experimental results demonstrate that the optimized predictive horizon can adapt to different driving environments, and the proposed path tracking method exhibits good comprehensive performance in terms of path tracking accuracy, driving comfort, and real-time operation.
TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL
(2021)
Article
Computer Science, Artificial Intelligence
Haotian Shi, Yang Zhou, Keshu Wu, Sikai Chen, Bin Ran, Qinghui Nie
Summary: This study proposes an innovative integrated two-dimensional control strategy for connected automated vehicles, using deep reinforcement learning. The strategy efficiently controls the vehicles in terms of both stability-wise longitudinal control performance and accurate lateral path-tracking performance. The controller utilizes vehicle-to-everything communication and roadway geometry information, and applies a physics-informed DRL state fusion approach and reward function to better utilize the information and borrow the merits of control theory concepts. Simulated experiments validate the controller's accuracy and stability-wise performance in diverse traffic scenarios.
KNOWLEDGE-BASED SYSTEMS
(2023)
Review
Automation & Control Systems
Antonio Artunedo, Marcos Moreno-Gonzalez, Jorge Villagra
Summary: This paper addresses the lack of comprehensive comparative assessment of control strategies in the literature by systematically evaluating state-of-the-art model-free and model-based control strategies. The research evaluates and contrasts the performance of these controllers across a wide range of driving scenarios using a comprehensive set of performance metrics. The contributions of this research include the design of a systematic tuning methodology and the use of novel metrics for stability and comfort comparisons.
ANNUAL REVIEWS IN CONTROL
(2024)
Article
Engineering, Civil
Weida Wang, Yuhang Zhang, Chao Yang, Tianqi Qie, Mingyue Ma
Summary: This study proposes a specific adaptive model predictive control strategy for path following of four-wheel independent drive automated vehicles. By estimating uncertainties and updating system models in real-time, controlling vehicles using a designed torque distribution algorithm, the strategy achieves more accurate path following than traditional methods.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Mechanical
Ying Tian, Qiangqiang Yao, Peng Hang, Shengyuan Wang
Summary: An adaptive path tracking control strategy is proposed in this study to improve the path tracking accuracy under high-speed and large-curvature conditions by coordinating active front wheel steering and direct yaw moment. The recursive least square method with a forgetting factor is used to identify the rear tire cornering stiffness and update the prediction model. The adaptive strategy based on fuzzy rules is applied to adjust the weight coefficients in the cost function to adaptively adjust the priorities of path tracking accuracy and vehicle stability.
CHINESE JOURNAL OF MECHANICAL ENGINEERING
(2022)
Article
Automation & Control Systems
Fei Dong, Keyou You, Xiang Li
Summary: In this work, the isoline tracking problem is studied in a GPS-denied environment, where a sensing vehicle is controlled to slide on a desired isoline of a scalar field. A Proportional Integral (PI) controller is designed based on strength-based measurements to drive a new error term to zero, which completes the isoline tracking task. The convergence of the closed-loop tracking system is shown, and numerical simulations and real experiments with various types of vehicles are conducted to validate the performance of the proposed controllers.
SYSTEMS & CONTROL LETTERS
(2023)
Article
Engineering, Mechanical
Illes Voros, Gabor Orosz, Denes Takacs
Summary: This paper analyzes the nonlinear dynamics of path-following control in passenger cars, taking into account specific modeling aspects and their effects. Equilibrium points and singularities in the state space are examined for different vehicle models and controller designs. The stability of stable path following is then analyzed in detail, presenting stability charts and approximating the basin of attraction with numerical continuation. Unsafe zones of control gains are identified, and modifications to the control law are proposed to remove unwanted equilibrium points and increase the basin of attraction, resulting in safer and more reliable vehicle control.
NONLINEAR DYNAMICS
(2023)
Article
Automation & Control Systems
Xiubo Wang, Guangren Duan
Summary: The main results of this paper focus on the nonlinear model predictive control (MPC) tracking optimization based on high-order fully actuated (HOFA) system approaches. The proposed HOFA MPC strategy utilizes the full-actuation property to eliminate the nonlinear dynamics of the system, transforming the nonlinear optimization problem into a series of easy-solve linear convex optimization problems. Through moving horizon optimization, an analytical controller with smooth and low energy is obtained, which has been proven to stabilize the corresponding tracking error closed-loop system. Simulation results are provided to verify the effectiveness of the proposed strategy by transforming non-linear under-actuated models into equivalent HOFA systems.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Engineering, Electrical & Electronic
Luqi Tang, Fuwu Yan, Bin Zou, Wenbo Li, Chen Lv, Kewei Wang
Summary: This paper proposes a novel trajectory prediction framework that captures interactions at different time scales by stacking spatial-temporal layers and handles temporal dependencies using dilated temporal convolution. By using an LSTM-based trajectory generation module, the proposed method is able to generate future trajectories for multiple traffic agents simultaneously, achieving state-of-the-art performance on multiple datasets.
IET INTELLIGENT TRANSPORT SYSTEMS
(2023)
Article
Engineering, Mechanical
Hao Chen, Xiaomin Lian, Chen Lyu
Summary: This paper proposes a novel wheel slip controller for in-wheel motor driven vehicles (IMDVs) based on torque vectoring control scheme. The control strategy regulates the upper limit torque using slip control torque, which changes the motor's effective operational range. Torque coordination is achieved through re-distribution without additional rules. A piecewise integral-proportional control strategy is introduced to reduce dependence on model fidelity. The proposed method shows excellent stability control performance comparable to the traditional PI method.
VEHICLE SYSTEM DYNAMICS
(2023)
Article
Computer Science, Artificial Intelligence
Jingda Wu, Zhiyu Huang, Chen Lv
Summary: In this paper, a novel uncertainty-aware model-based RL method is proposed to improve the learning efficiency and performance in autonomous driving scenarios. By establishing an action-conditioned ensemble model with uncertainty assessment capability, and developing an uncertainty-aware model-based RL method based on adaptive truncation approach, virtual interactions between the agent and environment model are provided to enhance RL's learning efficiency and performance. Validation results demonstrate that the proposed method outperforms the model-free RL approach in terms of learning efficiency, and the model-based approach in terms of both efficiency and performance, indicating its feasibility and effectiveness.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2023)
Article
Engineering, Electrical & Electronic
Lin Chen, Yilin Wang, Jing Zhao, Shihong Ding, Jinwu Gao, Hong Chen
Summary: An adaptive control scheme is proposed based on extremum seeking (ES) for rapid and high-precision servo control of an electronic throttle. It consists of an ES-variable-gain adaptive proportional-integral (ES-API) controller and an adaptive compensator (ES-ACP). The ES-API controller uses maps for the gains designed with respect to the tracking error and the ES-ACP compensates for the nonlinearity inherent in the electronic throttle control (ETC) system. Experimental results demonstrate that the control scheme is capable of accurately and quickly tracking multiple reference trajectories.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
(2023)
Article
Computer Science, Artificial Intelligence
Haiping Du, Siyu Teng, Hong Chen, Jiaqi Ma, Xiao Wang, Chao Gou, Bai Li, Siji Ma, Qinghai Miao, Xiaoxiang Na, Peijun Ye, Hui Zhang, Guiyang Luo, Fei-Yue Wang
Summary: This letter presents a decentralized and hybrid workshop on the potential influence of ChatGPT on research and development in intelligent vehicles. The tests conducted showed that while ChatGPT's information can be updated and corrected, it may not always possess the latest knowledge regarding specific topics. The letter also discusses possible applications of ChatGPT in areas like autonomous driving, human-vehicle interaction, and intelligent transportation systems, highlighting challenges and opportunities associated with these applications.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2023)
Article
Computer Science, Artificial Intelligence
Jieyu Zhu, Yanli Ma, Yiran Zhang, Yaping Zhang, Chen Lv
Summary: In conditionally automated driving, the driver's takeover of control authority is crucial for traffic safety. This study proposes an XGBoost learning method that considers risk potential field to predict the takeover quality under different levels of cognitive non-driving related tasks. Physiological features and selected prediction variables are used to model the takeover quality. The XGBoost model outperforms other machine learning models in different time windows.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Ping Wang, Xiyue Zhang, Jianpeng Shi, Bin Gou, Lin Zhang, Hong Chen, Yunfeng Hu
Summary: This paper proposes an MPC-based control strategy to prevent vehicle rollover during high-speed driving. By considering tire force saturation and real-time rollover index, the control region is divided into different stability regions. State constraints are set based on driver behavior and road conditions to improve overall vehicle performance.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2023)
Article
Automation & Control Systems
Xiao Hu, Hong Chen, Qiao Ren, Xun Gong, Ping Wang, Yunfeng Hu
Summary: This article proposes a well-developed method for the estimation and expansion of the vehicle stability region by improving the region of attraction (RoA) based on sums of squares (SOS) programming. The method reduces conservatism by formulating an improved SOS program with an optimization objective and a customized algorithm. The computational burden is reduced by using a feasibility prejudgment strategy and a dynamic search range. Simulations and hardware-in-the-loop experiments verify the effectiveness of the method.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Automation & Control Systems
Long Chen, Yuchen Li, Chao Huang, Yang Xing, Daxin Tian, Li Li, Zhongxu Hu, Siyu Teng, Chen Lv, Jinjun Wang, Dongpu Cao, Nanning Zheng, Fei-Yue Wang
Summary: Interest in autonomous driving and intelligent vehicles is rapidly growing due to their convenience, safety, and economic benefits. Existing surveys in this field are limited to specific tasks and lack systematic summaries and future research directions. This article consists of three parts, with the first part being a survey that covers the history, milestones, and future research directions of AD and IVs. The second part reviews the development of control, computing system design, communication, HD maps, testing, and human behaviors in IVs. The third part focuses on the perception and planning sections. The objective of this article is to provide a comprehensive overview of AD and IVs, summarize the latest milestones, and guide beginners in understanding their development. This work is expected to offer valuable insights to researchers and beginners, bridging the gap between the past and future.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Article
Engineering, Civil
Yanjun Huang, Shuo Yang, Liwen Wang, Kang Yuan, Hongyu Zheng, Hong Chen
Summary: This paper proposes an efficient self-evolution method for reinforcement learning algorithms using a combination of SAC and BC. The method improves convergence efficiency without sacrificing the exploration advantage of reinforcement learning.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Proceedings Paper
Automation & Control Systems
Yiran Zhang, Zhongxu Hu, Chen Lv
Summary: In highly automated driving vehicles, a human-vehicle interface is still necessary for individualization and emergency intervention. A tactical human-vehicle collaboration framework is proposed, utilizing hand-landmark extraction algorithm and augmented reality visual feedback. Through a vision-based interface, the driver's gesture is projected onto the ground and fed back to the driver through an AR-HUD interface, functioning as a strategic decision or planning suggestion to the vehicle.
2023 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS, AIM
(2023)
Proceedings Paper
Automation & Control Systems
Shanhe Lou, Runjia Tan, Yiran Zhang, Chen Lv
Summary: Industry 5.0 revolutionizes the industrial field with a focus on human-centric intelligent manufacturing. The human-cyber-physical system plays a vital role in optimizing the product lifecycle and ensuring the well-being of stakeholders. Disassembly is crucial for achieving sustainability and flexibility in the mass personalization of products. A human-robot interactive disassembly framework is proposed, considering both the complexity of the task and the ergonomics of operators, enabling optimal disassembly sequences.
2023 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS, AIM
(2023)
Article
Engineering, Civil
Tianci Yang, Carlos Murguia, Chen Lv
Summary: Cooperative Adaptive Cruise Control (CACC) is a technology that allows vehicles on the highway to form tightly-coupled platoons by exchanging inter-vehicle data through wireless communication networks. It improves traffic throughput and safety, while reducing energy consumption. However, the increased vehicle connectivity brings new security challenges, as adversaries can exploit the network to disrupt platooning performance or cause collisions. This manuscript proposes a novel anomaly detection scheme using real-time sensor/network data and mathematical models, but it acknowledges the limitations due to modeling uncertainties, network effects, and noise.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Yangyang Feng, Shuyou Yu, Encong Sheng, Yongfu Li, Shuming Shi, Jianhua Yu, Hong Chen
Summary: This paper proposes a hierarchical control strategy that considers the longitudinal and lateral coupling property of vehicle platoons. By using a predictive control scheme, the strategy predicts and maintains the vehicles on the designated lanes, avoiding the need to solve nonlinear optimization problems and reducing the computational burden. The joint simulation results demonstrate the effectiveness of the proposed strategy in terms of maintaining the velocity and safety distance of vehicles in both straight and curved road scenarios.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Automation & Control Systems
Ran Jiao, Wenjie Liu, Ramy Rashad, Jianfeng Li, Mingjie Dong, Stefano Stramigioli
Summary: A novel end-effector bilateral rehabilitation robotic system (EBReRS) is developed for upper limb rehabilitation of patients with hemiplegia, providing simulations of multiple bimanual coordinated training modes, showing potential for application in home rehabilitation.
Article
Automation & Control Systems
Qiaosheng Pan, Yifang Zhang, Xiaozhu Chen, Quan Wang, Qiangxian Huang
Summary: A resonant piezoelectric rotary motor using parallel moving gears mechanism has been proposed and tested, showing high power output and efficiency.