Article
Engineering, Civil
Jieming Chen, Yue Zhou, Edward Chung
Summary: In this paper, a mixed integer nonlinear programming (MINLP) model is proposed and solved to improve the traffic efficiency and safety at freeway on-ramp merging areas. The proposed method optimizes multiple vehicles' trajectories and their merging sequence to cooperatively minimize disruption from ramps. The evaluation results show that the proposed method outperforms benchmark CAV control algorithms and has promising computational efficiency for real-time merging tasks.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Automation & Control Systems
Wei Xiao, Christos G. Cassandras
Summary: This paper explores the optimal control of Connected and Automated Vehicles (CAVs) to minimize travel time and energy consumption. The results show that under certain conditions, safety and speed constraints remain inactive, simplifying the solution; when these conditions do not apply, a complete solution including all possible constraints is obtained.
Article
Automation & Control Systems
Yang Shi, Zhenbo Wang, Chieh (Ross) Wang, Yunli Shao
Summary: Connected vehicle technologies can solve the challenges faced by drivers when merging onto highways and offer numerous benefits. However, real-time optimal control is still a challenge. To address this, a novel approach is proposed that balances computational efficiency and solution optimality.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Engineering, Civil
Zhibo Gao, Zhizhou Wu, Wei Hao, Keke Long, Young-Ji Byon, Kejun Long
Summary: This paper proposes an optimal trajectory optimization strategy for Connected and Automated Vehicles (CAVs) to cooperatively carry out mainline platooning and on-ramp merging, which achieves improvements in traffic safety and operational efficiencies by considering the lane-changing motivation of merging vehicles and impact of merging on platoons.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Haoji Liu, Weichao Zhuang, Guodong Yin, Zhaojian Li, Dongpu Cao
Summary: This paper proposes a hierarchical cooperative on-ramp merging control strategy for connected and automated vehicles (CAVs) to optimize flexible trajectories and provide safety guarantees in mixed traffic. The strategy includes an upper-level planner and a lower-level controller to solve the optimal control problem (OCP) with mixed state-control constraints efficiently. Comprehensive simulation results show that this strategy can enable merging flexibility and improve traffic efficiency and energy economy in real time.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Hanyu Zhu, Zixin Wang, Fuqian Yang, Yong Zhou, Xiliang Luo
Summary: In the era of internet of vehicles, joint control of traffic signal lights and CAVs is proposed under the reinforcement learning framework to improve traffic efficiency during congestion at bottleneck intersections. By dynamically adjusting rerouting ratios and controlling route choices through common scalar parameters, a model-based method is developed to estimate travel times accurately and efficiently. The integration of deep reinforcement learning tools enables the joint optimization of green time allocation for traffic signals and CAV rerouting, leading to significant improvements in traffic efficiency.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Simeon C. Calvert, Bart van Arem, Daniel D. Heikoop, Marjan Hagenzieker, Giulio Mecacci, Filippo Santoni de Sio
Summary: The increased availability of partially automated vehicles for on-road testing provides researchers and developers with an opportunity to evaluate their performance. Recent accidents involving AVs have raised questions about control and responsibility. A potential discrepancy in AV control is identified through the lens of the moral philosophical framework of Meaningful Human Control (MHC). It is recommended that developers and approval authorities consider control from an MHC perspective to prevent future gaps in control.
IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE
(2021)
Article
Engineering, Civil
Jia Shi, Keqiang Li, Chaoyi Chen, Weiwei Kong, Yugong Luo
Summary: This study proposes an optimized cooperative merging strategy to improve traffic efficiency and safety for ramp merging on highways by establishing connections between sequence scheduling and motion planning in mixed traffic. Through optimal control strategies and a passing sequence tree search process, the final states of different vehicle groups in mixed traffic are effectively optimized, and continuous implementation is achieved through an event-triggered optimization algorithm. Numerical simulations show that our proposed algorithm significantly improves overall traffic efficiency and reduces vehicle-passing delays compared to the traditional FIFO-based cooperation method.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Ergonomics
Guiming Xiao, Jaeyoung Lee, Qianshan Jiang, Helai Huang, Mohamed Abdel-Aty, Ling Wang
Summary: The study estimates the safety effects of Intelligent Connected Vehicles (ICVs) by market penetration rate (MPR) using meta-analysis approach, finding that conflicts decrease exponentially as MPR increases. The case study in the United States suggests that MPR is expected to rise in the future, leading to a reduction in fatal crashes.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Article
Engineering, Civil
Yongjie Xue, Chuan Ding, Bin Yu, Wensa Wang
Summary: This paper proposes a hierarchical merging control algorithm for on-ramp vehicles under connected traffic environment. The algorithm optimizes merging maneuvers to reduce fuel consumption, travel time, and improve passenger comfort. Numerical simulations demonstrate the effectiveness of the proposed algorithm in different merging scenarios.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Kangning Hou, Fangfang Zheng, Xiaobo Liu, Ge Guo
Summary: This paper proposes a hierarchical model for cooperative on-ramp merging control (CORMC) in mixed traffic. The upper-layer employs an anticipatory position searching (APS) algorithm and a collaborative utility choice (CUC) model to determine merging positions and assign cooperative vehicles. The lower-layer ensures safe and smooth merging execution with a cooperative merging control (CMC) model. Simulation results demonstrate the performance benefits of the CORMC model, particularly at higher compliance rates and CAV penetration rates.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Xiao Pan, Boli Chen, Stelios Timotheou, Simos A. Evangelou
Summary: This paper addresses the speed planning problem for connected and autonomous vehicles (CAVs) at an unsignalized intersection with consideration of turning maneuvers. It is shown that the underlying optimization problem, subject to safety constraints, can be formulated as two second-order cone programs with convexification and relaxation. The investigation of Pareto optimal solutions highlights the importance of optimizing the trade-off between travel time and energy consumption.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Zhiqiang Zuo, Xu Yang, Zheng Li, Yijing Wang, Qiaoni Han, Li Wang, Xiaoyuan Luo
Summary: In this paper, a progressive model predictive control scheme (PMPCS) is proposed for the cooperative control of local planning and path tracking for intelligent vehicles. An improved particle swarm optimization (IPSO) based model predictive control (MPC) method is developed to solve the planning and tracking problem. Additionally, a novel planning algorithm considering traffic lights and overtaking time constraint is introduced, combining model predictive control with artificial potential field (APF) and pseudo velocity planning methods. Simulation results demonstrate the reliability and advantages of the proposed algorithm compared to general hierarchical algorithms.
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
(2021)
Article
Computer Science, Information Systems
Chao Sun, Jianghao Leng, Fengchun Sun
Summary: A fast optimal speed planning system for complex urban driving situations is proposed in this article. Through an adaptive hierarchical control framework, the global speed trajectory is computed and followed by jointly using dynamic programming and interior-point optimizer, predicting with Informer model, and adopting target-switching model-predictive controller.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Civil
Fuguo Xu, Tielong Shen
Summary: This paper introduces a new approach to solve the optimal merging control problem for hybrid electric vehicles (HEVs) in a connected environment, aiming to reduce energy consumption and save travel time by deriving a decentralized feedback control law and torque distribution strategy. The study proposes a distance domain-based optimal control problem and evaluates energy consumption at the power device level in vehicle dynamics, solving the optimization problem using Pontryagin's maximum principle and validating the decentralized merging control law through simulations.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Automation & Control Systems
Wei Xiao, Calin Belta, Christos G. Cassandras
Summary: This article presents an adaptive CBFs (aCBFs) approach that can handle time-varying control bounds and noise in system dynamics, and compares its advantages with existing CBF techniques.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2022)
Article
Computer Science, Interdisciplinary Applications
Richard J. Chen, Ming Y. Lu, Jingwen Wang, Drew F. K. Williamson, Scott J. Rodig, Neal Lindeman, Faisal Mahmood
Summary: This study proposes an interpretable strategy for multimodal fusion of histology image and genomic features for survival outcome prediction. The results on glioma and clear cell renal cell carcinoma datasets demonstrate that this approach improves the prognostic determinations.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Automation & Control Systems
Wei Xiao, Calin Belta
Summary: This paper addresses the problem of stabilizing a dynamical system while optimizing costs and satisfying safety constraints and control limitations. By introducing high-order control barrier functions (HOCBFs) and control Lyapunov functions (CLFs), a quadratic program-based approach is proposed to solve the optimal control problem, and two methods are proposed to address the feasibility problem. Finally, the extension of this methodology for safe navigation in unknown environments is demonstrated.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2022)
Article
Engineering, Civil
Salomon Wollenstein-Betech, Mauro Salazar, Arian Houshmand, Marco Pavone, Ioannis Ch. Paschalidis, Christos G. Cassandras
Summary: This paper explores congestion-aware route-planning policies for intermodal Autonomous Mobility-on-Demand (AMoD) systems, optimizing AMoD routing and rebalancing strategies to improve overall system performance under mixed traffic conditions.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Huile Xu, Christos G. Cassandras, Li Li, Yi Zhang
Summary: This study compares the performance of four representative cooperative driving strategies, finding that the Monte Carlo Tree Search-based strategy achieves the best traffic efficiency and fuel consumption performance. Dynamic Resequencing and MCTS strategies both perform well in all metrics. The influence of geometric shape on strategies is more significant than that of arrival rates.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Civil
Arian Houshmand, Christos G. Cassandras, Nan Zhou, Nasser Hashemi, Boqi Li, Huei Peng
Summary: The study introduces an algorithm for eco-routing for PHEVs and validates its effectiveness using traffic data from the city of Boston, demonstrating significant energy savings of around 12%. The algorithm also shows near real-time execution time.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Automation & Control Systems
Xiangyu Meng, Christos G. Cassandras, Xinmiao Sun, Kaiyuan Xu
Summary: This article investigates a multiagent coverage problem with energy-constrained agents. It compares the coverage performance between centralized and decentralized approaches. A centralized coverage control method is developed, and a controller is designed to optimize agent trajectories and charging times to maximize coverage metric.
IEEE TRANSACTIONS ON CONTROL OF NETWORK SYSTEMS
(2022)
Article
Engineering, Civil
Huile Xu, Wei Xiao, Christos G. Cassandras, Yi Zhang, Li Li
Summary: This paper addresses the problem of safely controlling Connected and Automated Vehicles (CAVs) crossing a signal-free intersection with multiple lanes. A general framework is proposed to convert the multi-lane intersection problem into decentralized optimal control problems for each CAV. By combining optimal control and control barrier functions, the proposed method efficiently tracks feasible unconstrained CAV trajectories while ensuring the satisfaction of all safety constraints.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Robotics
Wei Xiao, Tsun-Hsuan Wang, Ramin Hasani, Makram Chahine, Alexander Amini, Xiao Li, Daniela Rus
Summary: This article introduces a method called differentiable control barrier functions (dCBFs) for ensuring the safety of learned models for control. dCBFs are end-to-end trainable and guarantee safety, improving upon the conservative classical control barrier functions (CBFs). The proposed solution, called BarrierNet, relaxes CBF definitions by incorporating environmental dependencies and embedding them into differentiable quadratic programs. BarrierNet can be used with any neural network-based controller and is trained using gradient descent. Evaluations on various problems demonstrate the effectiveness of BarrierNet, including robot traffic merging, robot navigation in 2D and 3D spaces, end-to-end vision-based autonomous driving, and comparison with state-of-the-art approaches.
IEEE TRANSACTIONS ON ROBOTICS
(2023)
Article
Robotics
Makram Chahine, Roya Firoozi, Wei Xiao, Mac Schwager, Daniela Rus
Summary: Game-theoretic motion planners are proposed for controlling systems of multiple highly interactive robots. A fault-tolerant receding horizon game-theoretic motion planner is introduced to address the unrealistic assumption of a priori objective function knowledge. This planner leverages inter-agent communication with intention hypothesis likelihood to infer objectives in real-time.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2023)
Article
Automation & Control Systems
Shirantha Welikala, Christos G. Cassandras
Summary: In this paper, we discuss the problem of estimating the states of a distributed network of nodes through a team of cooperating agents. We propose a distributed online agent controller where each agent controls their trajectory by solving a sequence of receding horizon control problems, and we also leverage machine learning to improve the computational efficiency.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2023)
