Traffic sign recognition (TSR) is one of the most important visual perception tasks for autonomous vehicles. Traffic signs situated far away occupy only a few pixels in the images captured by the cameras of the autonomous vehicle, which presents a challenge for TSR methods to give accurate and reliable results. In this paper, we propose a panoramic active visual system (PAVS) for distant traffic signs recognition. It combines the advantages of the active pan-tilt-zoom(PTZ) camera for long-distance viewing and the advantage of the panoramic camera to have a large field of view. The traffic signs will be preliminarily detected and tracked in the panoramic image and the objects with confidence lower than the threshold will be further detected by the active PTZ camera to get more reliable results. The proposed PAVS are tested with different state-of-the-art (SoTA) TSR networks in real traffic scenes and the experimental results show that, compared to the passive visual system, the performances of the proposed PAVS improve 8.5% in F1-score, 5.3% in mAP, and 60.2% in mean first detection distance (mFD) in traffic sign recognition tasks.

Autonomous vehicles (AVs) have garnered significant attention in the field of smart logistics due to their potential to greatly enhance transportation efficiency. While significant focus has been placed on the capabilities of individual AVs, less attention has been given to the complexities of coordinating multiple vehicles within dynamic traffic environments. Key factors such as combined traffic flow, varying traffic signals, and complex cooperative maneuvers play a major role in effective multi-vehicle scheduling. This paper aims to address these overlooked challenges by exploring dynamic traffic conditions and micro-level cooperation within multi-vehicle routing systems. The large-scale multi-vehicle routing problem (MVRP) is reformulated into a series of smaller-scale cooperative vehicle routing problems (VRPs). A distributed model predictive control-based (DMPC-based) planner is constructed and applied in parallel across connected autonomous vehicles (CAVs). Each instance of distributed model predictive scheduling incorporates a closed-loop vehicle dynamics to predict lane-changing and platooning maneuvers, where feedback controllers are introduced. To optimize routes toward destination, a destination-oriented search space is rebuilt with the filtered feasible routes. By accessing real-time traffic lights, a model predictive control (MPC) problem is formulated, where the vehicle-lane distribution is predicted with a sub-optimization of the shortest queue and combined with the predictive scheduling. Comparisons against existing methods reveal that the proposed planner exhibits significant improvements in time efficiency and successes to avoid traffic congestion, which is available athttps://github.com/ZNianHua/DMPC-planner-for-VRP

Autonomous vehicle platoons are particularly suitable for repetitive tasks due to their capability for efficient coordination, enhanced safety, and reduced driver fatigue. The offline-designed control policy faces difficulties in adapting to changing conditions without driver intervention or vehicle self-learning, which can lead to inadequate coordination among vehicles and an increased risk of collisions or disruptions. This paper presents an iterative learning distributed model predictive control (ILDMPC) strategy designed for 2-dimensional (2-D) autonomous vehicle platoons, allowing vehicles to learn from their previous iterations to minimize control errors and improve overall performance. First, the combined lateral and longitudinal dynamics incorporating load transfer of heterogeneous autonomous vehicle platoons are modeled together. Then, traffic regulations and mechanical constraints are defined and integrated into an optimal control problem with multiple objectives using the ILDMPC framework. This approach differentiates the platoon leader (PL) from the platoon followers (PFs) by employing distinct References. Additionally, the iterative learning is integrated into the optimal control problem via a convex terminal cost within a finite time horizon, completing the ILDMPC strategy. This strategy allows autonomous vehicle platoons to iteratively perform repetitive tasks, achieving optimal performance through iterative online learning. Simulations are carried out to demonstrate the effectiveness of the proposed controller, which is validated to evolve existing control laws and result in a 40% improvement as quantified by the error-based indicator. The associated codes are accessible athttps://github.com/ZNianHua/ILDMPC

In this study, we propose an innovative multi-stage control framework for human-lead-platooning of autonomous vehicles in complex, mixed traffic environments. The framework begins with collecting aggressive driving data from expert human drivers under various weather conditions and visibility levels, which inform a Refined Intelligent Driver Model for predicting the driving states of human-driven vehicles. A novel trust mechanism is then introduced to guide the trajectory selection for each autonomous follower, leveraging a reference set provided by the human-driven leader. In parallel, user-centric preferences (e.g., motion sickness, emotional fear, situational urgency) are captured and converted into precise acceleration and control constraints through a Fuzzy Logic System. Finally, a distributed switching model predictive control algorithm coordinates lane changes and vehicle-following tasks in real time for each follower. The proposed approach is validated through hardware-in-the-loop testing, demonstrating both effectiveness and adaptability in diverse traffic scenarios.

The rapid increase in electric vehicle (EV) adoption underscores the urgent need for advanced charging infrastructure and strategies. This survey provides a comprehensive examination of battery charging, with a particular focus on control and optimization dimensions. It meticulously reviews a variety of control methods and optimization techniques, addressing critical factors such as charging efficiency, battery longevity, safety protocols, thermal management, and cell balancing. By enhancing our understanding of these crucial aspects, this paper not only highlights the current state of battery charging control and optimization but also sets the stage for future research and developments in this dynamic field.

This article studies integral-type event-triggered model predictive control (MPC) of continuous-time nonlinear systems. An integral-type event-triggered mechanism is proposed by incorporating the integral of errors between the actual and predicted state sequences, leading to reduced average sampling frequency. Besides, a new and improved robustness constraint is introduced to handle the additive disturbance, rendering the MPC problem with a potentially enlarged initial feasible region. Furthermore, the feasibility of the designed MPC and the stability of the closed-loop system are rigorously investigated. Several sufficient conditions to guarantee these properties are established, which is related to factors, such as the prediction horizon, the disturbance bound, the triggering level, and the contraction rate for the robustness constraint. The effectiveness of the proposed algorithm is illustrated by numerical examples and comparisons.

This paper investigates the flight control of a quadrotor subject to the model uncertainties and external disturbances. We propose a linear quadratic regulation (LQR) tracking algorithm. However, the designed LQR controller is hard to be implemented because of the existing noises in the measured states. A modified extended Kalman filter (EKF) is then designed for the online estimation of the position, velocity and motor dynamics by using the measured outputs. From the experimental testing results, it is shown that the proposed EKF-based LQR control method solves the tracking problem of the quadrotor with less tracking errors than only using the LQR method.