During the ongoing development and proliferation of autonomous driving, human-driven vehicles (HDVs) and connected automated vehicles (CAVs) will coexist in mixed traffic environments for the foreseeable future. However, current autonomous driving systems often face challenges in ensuring optimal safety and efficiency, particularly in complex conflict scenarios. To address these shortcomings and improve cooperation in mixed traffic environments, this paper presents a game theoretic decision-making method. The proposed framework accounts for both CAV-CAV cooperation and CAV-HDV interaction in mixed traffic at un-signalized intersections. It introduces a parameter updating mechanism based on twin games to dynamically adjust HDVs’ parameters to better predict and respond to variable human driving behaviors. To validate the effectiveness of the proposed cooperative driving framework, the comparative analysis of its safety and efficiency with other established methods is conducted. The results demonstrate that our method successfully ensures both safety and efficiency in mixed traffic environments. Compared with reinforcement learning approaches such as IPPO, it achieves a 35–55% improvement in success rate while maintaining decision stability and traffic efficiency. In contrast to methods that enforce strict safety guarantees, our approach improves the average vehicle speed by 0.1–0.6 m/s and the average CAV speed by 0.7–1.7 m/s, without compromising safety. Additionally, several validation experiments are conducted using a hardware-in-the-loop and human-in-the-loop experimental platform, confirming the practical applicability of the method.

Global vehicle positioning through real-time LiDAR perception matched with online digital maps like OpenStreetMap (OSM) offers a promising solution to reduce reliance on high-quality maps in urban scenarios. However, the accuracy of global positioning based on LiDAR–OSM matching suffers from imprecise planar spatial information in OSM and frame-to-frame inconsistencies with the road network, which limits LiDAR–OSM matching to serving only as global position initialization rather than continuous positioning. To extend the application scenarios and performance of global positioning using OSM, a LiDAR–OSM matching framework is proposed to solve the planar association problem between real-time local perception and corresponding global position initialization sequences. Specifically, the motion consistency assumption is used to extract and reconstruct global candidate sequences that satisfy temporal and spatial continuity, which serves as the foundation for sequence-to-sequence matching with the local odometry. Furthermore, an online sequence-to-sequence transformation matrix estimation and verification mechanism is proposed to obtain a local-to-global solution that is subject to the activity range of vehicles and achieves optimal consistency with the road network. The performance of the proposed method is validated under different odometries and global initialization position confidence in the KITTI dataset. The results demonstrate that the proposed method achieves sub-meter level precision, showing a significant improvement over other LiDAR–OSM positioning methods in most urban sequences.

In autonomous vehicle trajectory tracking, the absence of an accurate vehicle dynamics model can significantly degrade tracking performance. While model-free approaches, such as neural network-based supervised learning and deep reinforcement learning, have shown promising results, they typically require large-scale datasets and long-term training to ensure control convergence and generalizability. To overcome these challenges, we propose the direct data-driven trajectory tracking algebraic regulator, a model-free control framework designed to achieve high-precision trajectory tracking under limited data availability. The tracking problem is first reformulated as an output regulation problem involving an unknown plant and a predefined reference system. Then, leveraging a finite set of input–state data with representative reference trajectories, we synthesize a data-driven feedback control law using an algebraic regulator and semidefinite programming, accounting for both noise-free and noisy datasets. In addition, we formally derive the minimal data required to guarantee the solvability of the regulator, providing practical guidance for data collection. More importantly, we present rigorous theoretical analyses establishing exponential stability of the closed-loop system in the noise-free data setting and exponential convergence to a bounded error in the presence of noisy data. The convergence rate is also thoroughly examined and explicitly characterized. Finally, the effectiveness of the proposed approach is validated through a hardware-in-the-loop experimental setup based on a CarSim/dSPACE platform, demonstrating superior tracking performance compared with benchmark methods, including PID, Stanley, model predictive control, and data-enabled predictive control.

Understanding and modeling driver’s lateral control behavior accurately are essential for developing effective human–machine shared takeover (HMST) system during emergency collision avoidance under dynamic traffic environment. However, little attention has been devoted to modeling driver behavior during HMST. Moreover, existing methods mostly focus on the interaction between a single vehicle and the driver, making it difficult to effectively characterize the nonlinear and uncertain behavior of drivers in dynamic traffic environment. Therefore, this study focuses on modeling of driver lateral control behavior during HMST under dynamic traffic environment, and a Transformer-based modeling method with multi-head attention is proposed. To validate the performance of the purposed approach, comparative experiments against traditional modeling approaches are carried out. And twelve drivers are recruited to perform HMST tasks in different emergency collision avoidance scenarios based on a driving simulator. Results of comparative experiments of different driving scenarios demonstrate the superior accuracy of the proposed method. In addition, the shapley (SHAP) additive explanations is employed to enhance the interpretability of the proposed model, thereby providing a reliable foundation for the development of efficient HMST systems.

Edge following-where an autonomous vehicle tracks a road edge-is a critical component of intelligent transportation systems, underpinning applications such as curbside sweeping, line marking, and container docking at port terminals. Traditional edge-following planners are often open-loop and rely on manually crafted High Definition maps, limiting adaptability. However, substituting static map inputs with real-time sensor references exposes the limitations of single-modal sensing, which struggles to capture irregular curb geometries or subtle height variations, degrading detection and trajectory quality. In this paper, we propose a novel map-free, closed-loop framework that integrates real-time LiDAR-vision fusion with an any-time constrained quadratic-program planner. Our perception pipeline extracts coarse curb candidates directly in the 3-D point cloud-preserving centimetre-scale vertical gradients-and then refines them via a lightweight image segmentation head on a cropped region of interest. The planner formulates each along-edge trajectory as a sparse quadratic programming in the Frenet frame, enforcing hard collision and comfort constraints while guaranteeing feasibility at every iteration and supporting safe interruption under real-time deadlines. This continuous feedback loop adapts instantly to road geometry and dynamic obstacles without High Definition map dependence. Extensive simulations and real UGV trials in a campus sweeping scenario demonstrate the framework’s robustness, responsiveness, and deployability in real-world conditions.

This paper proposes a distributed multi-agent formation control framework, ensuring rigorous safety and solely relying on range-only measurements. To address the challenge of rigid formation control without bearing information, we introduce a bearing estimator with respect to a single landmark. This estimator enables integration with conventional distance-based formation controllers while preserving distributed deployments. To ensure collision-free trajectories in cluttered environments, we develop a safety-critical control law that includes the estimated bearings with control barrier functions (CBFs), formally guaranteeing obstacle avoidance. We rigorously prove the convergence of the bearing estimator, the asymptotic stability of the desired formation shape and the continuity of safety control inputs. The effectiveness of the proposed approach is demonstrated through simulations with multiple agents and obstacles, as well as experimental validation using quadcopters in a cluttered lab environment. A video showcasing the study and experimental results is available at https://www.youtube.com/watch?v=iV0pNrtZbxM.

Learning-based strategy can be well integrated with model-based optimal control to facilitate cooperative multiagent control through the Internet of Things (IoT). In this work, we propose a data-efficient learning-based iterative optimization method with time-varying prediction horizon (TV-LIO) for multiagent collaboration. Our method builds a multiagent optimization problem by introducing a time-domain guided terminal set and an approximated general cost. We collect the historical agent states at previous iterations as a dataset to reconstruct the general cost and the terminal set iteratively, forming closed-loop data-efficient learning. We consider the influence of the predictive time domain on the optimality and feasibility of the optimization problem and design a time-domain recursive updating mechanism to determine the optimal predictive horizon for each agent at the epoch. The continuous feasibility, stability, and recursive convergence of the proposed method are analyzed theoretically. Unlike the traditional optimization approaches that rely on a preplaned reference path, the proposed method integrates the trajectory planning and tracking control for multiple agents. After several iterations, the general cost of the optimization problem monotonically decreases and the optimal states are finally obtained. The proposed approach is validated and the results demonstrate that our approach can obtain the optimal-cost strategy and trajectories with optimizing time domains for the multiagent system.

Vehicle-to-everything-aided autonomous driving (V2X-AD) has a huge potential to provide a safer driving solution. Despite extensive research in transportation and communication to support V2X-AD, the actual utilization of these infrastructures and communication resources in enhancing driving performances remains largely unexplored. This highlights the necessity of collaborative autonomous driving; that is, a machine learning approach that optimizes the information sharing strategy to improve the driving performance of each vehicle. This effort necessitates two key foundations: a platform capable of generating data to facilitate the training and testing of V2X-AD, and a comprehensive system that integrates full driving-related functionalities with mechanisms for information sharing. From the platform perspective, we present V2Xverse, a comprehensive simulation platform for collaborative autonomous driving. This platform provides a complete pipeline for collaborative driving: multi-agent driving dataset generation scheme, codebase for deploying full-stack collaborative driving systems, closed-loop driving performance evaluation with scenario customization. From the system perspective, we introduce CoDriving, a novel end-to-end collaborative driving system that properly integrates V2X communication over the entire autonomous pipeline, promoting driving with shared perceptual information. The core idea is a novel driving-oriented communication strategy, that is, selectively complementing the driving-critical regions in single-view using sparse yet informative perceptual cues. Leveraging this strategy, CoDriving improves driving performance while optimizing communication efficiency. We make comprehensive benchmarks with V2Xverse, analyzing both modular performance and closed-loop driving performance. Experimental results show that CoDriving: i) significantly improves the driving score by 62.49% and drastically reduces the pedestrian collision rate by 53.50% compared to the SOTA end-to-end driving method, and ii) achieves sustaining driving performance superiority over dynamic constraint communication conditions.

This article addresses the issue of networked lane keeping security control for autonomous vehicles subject to aperiodic controller-targeted denial-of-service (DoS) attacks, taking into account time-varying driving speed and nonlinear tire cornering stiffness. To accurately estimate the incompletely measured states and capture the dynamic behaviors appearing at the end of aperiodic DoS attacks, full state gain adjustable switching observer is established for the fuzzy vehicle-road integrated dynamic systems obtained via the tensor product model transformation method. In order to ensure the control quality and simultaneously save the communication resource, new resilient adaptive event-triggered scheme is proposed with a reinforcement learning-based intelligent optimal threshold regulation mechanism based on observed states. Then, an augmented observer-based fuzzy switching system is constructed using the time delay method. In addition, sufficient conditions are established to guarantee global exponential stability of the closed-loop nonlinear lane keeping system with prescribed H∞ performance using a piecewise Lyapunov functional analysis approach. Subsequently, the gains for controller, observer, and trigger are co-designed and computed by solving certain matrix inequalities. Finally, the effectiveness of the proposed security control method is demonstrated through typical maneuver scenario in terms of reasonable triggered times, better tracking performances and acceptable lateral dynamics.

Human-involved interactive environments pose significant challenges for autonomous vehicle decision-making processes due to the complexity and uncertainty of human behavior. It is crucial to develop an explainable and trustworthy decision-making system for autonomous vehicles interacting with pedestrians. Previous studies often used traditional game theory to describe interactions for its interpretability. However, it assumes complete human rationality and unlimited reasoning abilities, which is unrealistic. To solve this limitation and improve model accuracy, this paper proposes a novel framework that integrates the partially observable markov decision process with behavioral game theory to dynamically model AV-pedestrian interactions at the unsignalized intersection. Both the AV and the pedestrian are modeled as dynamic-belief-induced quantal cognitive hierarchy (DB-QCH) models, considering human reasoning limitations and bounded rationality in the decision-making process. In addition, a dynamic belief updating mechanism allows the AV to update its understanding of the opponent’s rationality degree in real-time based on observed behaviors and adapt its strategies accordingly. The analysis results indicate that our models effectively simulate vehicle-pedestrian interactions and our proposed AV decision-making approach performs well in safety, efficiency, and smoothness. It captures key patterns of the driving behavior operated by real human drivers in virtual reality(VR) experiments and even achieves more comfortable navigation compared to our previous VR experimental data.

Effective scene representation is critical for trajectory generation tasks in autonomous driving. Existing attention-based methods often rely on fixed-length input elements, limiting their ability to adapt to dynamic traffic environments, and frequently overlook lane connectivity. Methods that consider lane connectivity often segment lanes into smaller pieces, which consequently creates a more complex graph structure with an increased number of nodes and edges. Additionally, many current approaches select agent interactions based on fixed distance thresholds, which may miss important long-range or indirect interactions and ignore the fact that proximity does not indicate interaction. In this paper, we propose SceneGNN, a novel framework for learning traffic scenario representation through interaction graph learning and lane graph exploration. SceneGNN constructs a single heterogeneous graph that integrates both agents and lanes, leveraging high-definition maps without over-segmentation. To model lane connectivity more effectively, we introduce LaneGNN, which combines an Omnidirectional Lane Aggregator (OLA) and Directional Lane Explorer (DLE) to explore lane-to-lane interdependencies. Additionally, instead of relying on proximity-based heuristics, our interaction graph learner dynamically constructs inter-agent edges based on learned features, allowing the model to capture meaningful interactions beyond mere distance. We evaluate SceneGNN on the Waymo Open Motion Dataset, where it achieves competitive performance. Our results demonstrate that by efficiently capturing both agent-lane relationships and inter-agent interactions, SceneGNN improves the accuracy and scalability of multi-agent trajectory prediction for real-world autonomous driving applications.

Roadside perception has a wider sensing range than onboard detection, providing enhanced sensory information for intelligent transportation systems, thus gaining increasing attention in recent years. However, directly applying onboard perception algorithms on roadside detectors (RSD) is infeasible due to the challenging requirements for high maneuvering target tracking and discriminating highly similar targets. Therefore, an Interactive Siamese Network (ISN) is proposed in this paper to overcome the roadside perception difficulties. Specifically, an interactive similarity contrast encoder-decoder has been developed within the ISN tracker. The sensitivity of algorithm to rapid changes in vehicle states is enhanced through the adaptive adjustment of weights assigned to critical tracking parameters within the loss function. This strategy enhances the ISN tracking effect for long-term trajectories for high maneuvering driving. Then, a global trajectory optimization unit is integrated into the ISN tracker. A trajectory similarity threshold is established to conduct cross-association analysis on similar trajectories, followed by iterative operations on adjacent trajectories. This approach further enhances the resolution of similar trajectories while ensuring the optimality of global trajectories. The proposed method is evaluated on the DAIR-V2X dataset and compared against current state-of-the-art methods. The experimental results verify that the proposed method provides efficient and accurate estimations and tracks vehicles in the intersection area, affording better accuracy and recall rate in high maneuvering target tracking than existing methods.

This study develops novel event triggered finite-time adaptive sliding-mode coordinated control method for networked hysteretic leaf spring suspension system subject to limited bandwidth, uncertainty sprung mass, dynamic constraints, and multiple control objectives. For inherent contradiction between body vibration and suspension chatter space, nonlinear filtering coordinated strategy with variable cut-off frequency is tailored to synthesize controlled variable composed of body and filtered tire displacements to realize smooth switch between hard and soft suspension under large/small suspension deformation. For the transmission congestion of control signals, event-triggered scheme relying on active force is designed to flexibly regulate command release interval to save communication resource and guarantee vibration suppression capability under abrupt road disturbance. To further improve convergence abilities of encapsulated variable and mitigate deterioration of performances from sparse control command, finite-time prescribed performance control is proposed to ensure transient and steady-state performance by accelerating convergence of controlled error to small region within preset time. For reconstructed active suspension system with unknown body weight, step control inputs with estimated weight are generated by employing event-based adaptive sliding-mode control to improve ride comfort and enhance handling properties. Additionally, global stability of networked active suspension system is proved by Lyapunov theory. Finally, the effectiveness and benefits of the proposed control method in real leaf spring suspension system are demonstrated by the simulation and hardware-in-the-loop tests.

An accurate longitudinal dynamics model is essential for state estimation and control of autonomous vehicles. However, existing physical models suffer from limited working conditions and large errors, while pure data-driven models require massive amounts of driving data to cover working conditions fully. To address these issues, a hybrid architecture composed of a neural network-based traction model, a recursive least square-based parameter estimator, and a physics-based dynamics model is proposed for longitudinal dynamics modeling, in which the parameter estimator is used for mass and modified rolling friction coefficient estimation. Under this architecture, the longitudinal dynamics model can be established using limited driving data collected on a test field with a given load, and achieve precise vehicle dynamics characterization under various roads and loads. To design the neural network for traction description, the dynamics of vehicle powertrain and braking systems are analyzed, and a physics-guided neural network, which fully considers the traction transmission characteristics, is formulated. For model training, a two-stage hybrid model training method is proposed, which can train the hybrid model with the co-existence of unknown network and physical parameters. Results demonstrate that the proposed hybrid model can realize accurate parameter estimation and vehicle longitudinal dynamics modeling using limited driving data collected at a test field under a given load, especially with excellent generalization performance under different loads and roads.

This article addresses the issue of adaptive memory event-triggered output feedback finite-time lane-keeping control for autonomous heavy trucks with roll prevention subject to nonlinear corning stiffness, time-varying driving speed, and trace curvature. A novel adaptive memory event-triggered scheme is developed to slow down control command update under unexpected system dynamic fluctuation excited by abrupt trace disturbances by releasing less triggered times, as well as speed up update under large amplitude response but gentle variation around critical crest/trough situation by releasing more triggering times. To overcome the shortcomings of slower convergence and longer response time resulting from designed scheme for control command update, finite-time lane-keeping control with prescribed H∞ performance is employed to achieve expected convergence properties. Additionally, better tracking control quality requirements for designed control strategy are specifically achieved with considered roll prevention control for the sprung mass and front/rear solid axle by eliminating negative effects on yaw motion and decreasing dynamic load transfer rate. Furthermore, sufficient conditions are established to guarantee finite-time boundedness with prescribed H∞ performance and gain matrices for controller and trigger are codesigned and obtained by solving certain matrix inequalities. Benefiting from regulated control command update and roll prevention under an adaptive memory event-triggered scheme, the obtained results illustrating reasonable triggered times, less tracking error, smoother centroid trajectory, smaller roll angle, and decreased dynamic load transfer rate demonstrate the effectiveness of the proposed control strategy.

Roadside unit (RSU) can significantly improve the safety and robustness of autonomous vehicles through Vehicle-to-Everything (V2X) communication. Currently, the usage of a single RSU mainly focuses on real-time inference and V2X collaboration, while neglecting the potential value of the high-quality data collected by RSU sensors. Integrating the vast amounts of data from numerous RSUs can provide a rich source of data for model training. However, the absence of ground truth annotations and the difficulty of transmitting enormous volumes of data are two inevitable barriers to fully exploiting this hidden value. In this paper, we introduce FedRSU, an innovative federated learning framework for self-supervised scene flow estimation. In FedRSU, we present a recurrent self-supervision training paradigm, where for each RSU, the scene flow prediction of points at every timestamp can be supervised by its subsequent future multi-modality observation. Another key component of FedRSU is federated learning, where multiple devices collaboratively train an ML model while keeping the training data local and private. With the power of the recurrent self-supervised learning paradigm, FL is able to leverage innumerable underutilized data from RSU. To verify the FedRSU framework, we construct a large-scale multi-modality dataset RSU-SF. The dataset consists of 17 RSU clients and an additional 4 vehicle clients, covering various scenarios, modalities, and sensor settings. Based on RSU-SF, we show that FedRSU can greatly improve model performance in ITS and provide a comprehensive benchmark under diverse FL scenarios. To the best of our knowledge, we provide the first real-world LiDAR-camera multi-modal dataset and benchmark for the FL community. Code and dataset are available athttps://github.com/wwh0411/FedRSU.

Collision risk modeling with multiple surrounding target vehicles (TVs) is essential for host vehicle (HV) trajectory planning, especially considering challenging TV lateral behaviors. Existing motion-compensated spatial methods ignore TV lateral motion states such as lateral velocity and yaw rate, so that TV lateral behavior cannot be described accurately. Aiming at high-accuracy collision risk modeling, a twisted Gaussian risk model using both longitudinal and lateral motion states for TV behavior description is proposed. Firstly, the HV-TVs system is treated as the superposition of multiple HV-TV units, and a Gaussian risk model is adopted for the collision risk description of the HV-TV unit. Then, by expanding the variances, TV longitudinal and lateral velocities are considered. At last, a twisted Gaussian risk model considering TV yaw rate is constructed based on the projection of the Gaussian risk model. With this twisted Gaussian risk model, TV longitudinal-lateral motion states are considered simultaneously, and TV behaviors can be described for HV-TVs collision risk modeling. For HV trajectory planning, trajectory candidates generated by the maneuver-inspired method are evaluated via the proposed risk model, and the safe and efficient trajectory is selected. Simulation and hardware-in-the-loop experimental results show that the proposed method considering TV longitudinal-lateral motion states allows HV to operate more safely and efficiently than the conventional method.

Accurate trajectory prediction of surrounding vehicles is vital for automated vehicles to achieve high-level driving safety in complex situations. However, most state-of-the-art approaches for multi-vehicle trajectory prediction ignore vehicle motion uncertainty caused by different driving styles. Moreover, the interrelationship between the vehicle and the environment is seldom considered. To address the above problems, this paper proposes a driving risk map-integrated deep learning (DRM-DL) method for interactive trajectory prediction of surrounding vehicles, which comprehensively considers the motion uncertainty, trajectory intention uncertainty and interactions among vehicles, lane lines and road boundaries. Specifically, we adopt a conditional variational autoencoder (CVAE) to generate the candidate trajectories, in which the motion uncertainty is considered using a conditional Gaussian distribution. Furthermore, a driving risk map is constructed to realize a unified and interpretable representation of vehicle-vehicle and vehicle-environment interactions. The probability of each candidate trajectory is assigned using a trajectory probability model and a random selection is adopted to select a guided trajectory, which simulates the driver’s trajectory intention uncertainty. Finally, a relearning module is designed to obtain the precise trajectory prediction for surrounding vehicles. The proposed method is evaluated on the HighD dataset, and the results demonstrate a more accurate and reliable trajectory prediction for surrounding vehicles compared with state-of-the-art methods.

The platoon of connected autonomous vehicles plays an essential role in future intelligent transportation. It can improve traffic efficiency and release traffic congestion. However, there are lots of existing challenging problems of the control of connected autonomous vehicles, such as the negative impact caused by wireless communication and disturbance. To solve these challenges, a multi-objective asymmetric sliding mode control strategy is proposed in this paper. Firstly, the asymmetric degree is introduced in the topological matrix. Then, a sliding mode controller is designed targeting platoon’s tracking performance. Moreover, Lyapunov analysis are used via Riccati inequality to find the controller’s gains and guarantee internal stability and Input-to-output string stability. Finally, a non-dominated sorting genetic algorithm is utilized to find the Pareto optimal asymmetric degree regarding the overall performance of the platoon, including tracking index, fuel consumption, and acceleration standard deviation. Four different information flow topologies, including a random topology are studied. The results indicate that the proposed asymmetric sliding mode controller can ensure platoon’s stability while improving its performance. The tracking ability is improved by 54.61% and 75.17%, fuel economy is improved by 0.78% and 6.34% under the Urban Road and Highway Case Study, respectively.

A timely understanding of target vehicles (TVs) lateral behavior is essential for the decision-making and control of host vehicle. Existing physical model-based methods such as motion-based method and multiple centerline-based method are generally constructed based on TV pose and longitudinal velocity, and tend to ignore TV preview driving characteristic and other useful information such as lateral velocity and yaw rate. To address these issues, a driver preview and multiple centerline model-based probabilistic behavior recognition architecture is proposed for timely and accurate TV lateral behavior prediction. Firstly, a driver preview model is used to describe vehicle preview driving characteristic, and TV preview lateral offset and preview lateral velocity are calculated with TV states and road reference information. Then, the preview lateral offset and preview lateral velocity are combined with multiple centerline model for TV lateral behavior reasoning based on the interacting multiple model-based probabilistic behavior recognition algorithm. With this method, TV preview driving characteristic and lateral motion states are combined for precise TV lateral behavior description. Furthermore, to predict short-term lateral behavior, a preview lateral velocity-dependent transition probability matrix model constructed with Gaussian cumulative distribution function is proposed. Simulation and experimental results show that the proposed method considering vehicle preview driving characteristic predicts TV lateral behavior earlier than the conventional method.

Automated vehicle control requires full knowledge of motion behavior of the preceding target vehicles (PTVs), and the states such as longitudinal/lateral velocity and yaw rate are critical for the PTV behavior description. However, the PTV's lateral states estimation have seldom been addressed in the state-of-the-art literatures. Aimed at providing reliable PTV lateral states, this paper presents a novel combined model-based estimation scheme. Different from the conventional PTV models, the proposed model is constructed based on the host-target vehicle dynamics and road constraints. Specifically, steering angle of the PTV is included in the state vector. The measurements, such as heading angle, road curvature, and lateral distance to the lane center, are available from an onboard vision system. As a vision system inevitably has measurement delay, a modified Kalman filter is developed to address the sampling issue. To verify the proposed approach, hardware-in-the-loop experiments are conducted in designed testing scenarios.