Gábor Orosz

Connected and automated vehicles (CAVs) represent a transformative technology that can revolutionize how people and goods move. The private sector is at the forefront of developing this technology, and many municipalities are attempting to prepare for a more connected and automated future. At the same time, as the CAV technology is not mature yet, academics are directing most of their attention to research on CAVs and their impact on the transportation system, overlooking the need for workforce development. The objective of this paper is to assess the needs for workforce development in CAVs, to identify potential obstacles that educators face in fulfilling those needs, and to propose ways to overcome the obstacles. Toward this end, a workshop was designed to bring together experts to identify the best ways to meet the demand for a workforce skilled in CAVs. As the field of CAVs can be diverse, a survey was distributed ahead of the workshop to identify the main themes around which the workshop was designed: (1) next generation infrastructure for CAVs, (2) human factors with CAVs, (3) modeling, simulation, and testing of CAVs, and (4) travel behavior in the context of CAVs.

This paper investigates a specific human-machine interaction in which an automated vehicle (AV) provides guided control to a following human-driven vehicle (HV). We take into account both the state delay induced by human reaction time and the input delay introduced by the AV controller. The resulting dynamic model is a nonlinear delay differential equation (DDE) with two distinct constant time delays. Our objective is to design a controller for this infinite-dimensional system at the nonlinear level. First, a model reduction is performed using the delayed spectral submanifold approach. This allows us to project the dynamics onto a low-dimensional invariant manifold while capturing the essential nonlinear behavior. Based on this reduced-order model, we then design a nonlinear controller that achieves faster convergence compared to a purely linear controller. The benefits of the proposed approach for closed-loop performance are demonstrated through numerical simulations.

The steering control of an autonomous unicycle is considered. The underlying dynamical model of a single rolling wheel is discussed regarding the steady-state motions and their stability. The unicycle model is introduced as the simplest possible extension of the rolling wheel, where the location of the center of gravity is controlled. With the help of the Appellian approach, a state-space representation of the controlled nonholonomic system is built in a way that the most compact nonlinear equations of motion are constructed. Based on controllability analysis, feedback controllers are designed that successfully carry out lane changing and turning maneuvers. The behavior of the closed-loop system is demonstrated by numerical simulations.

This paper proposes a safety-critical connected cruise control strategy using backstepping control barrier functions to enforce safety for connected automated vehicles while satisfying actuator limits. The proposed approach accounts for the vehicle's response time, modeled as a first-order lag. We investigate the impact of braking limits and lag time on the conservativeness of the safe region in the state space. Using simulations, we confirm that the proposed controller ensures safety while maintaining feasibility.

One of the biggest challenges in teleoperation is the latency in communication and actuation, which usually degrades the control performance and sometimes even makes the remote control impossible. In this paper, the effects of latency on the lateral and yaw dynamics of vehicles are investigated during teleoperated driving (ToD). A kinematic bicycle model is equipped with a generic curvature-based controller to represent the teleoperated vehicle. The stability of motion, the convergence rate to a desired trajectory, and the robustness against changes in longitudinal velocity and latency are quantified. It is also shown that the curvature has non-negligible impact on stability, convergence and robustness. Packet losses in the wireless communication and sampled-data control result in a periodic latency. We compare the stability and performance of ToD maneuvers under constant latency and periodic latency. Our results show that the stability of a ToD maneuver under periodic latency is similar to that under constant latency, unless the latency variations in the periodic latency are large. We use numerical simulations of different maneuvers to verify our analytical results for different latency profiles.

Trajectory tracking with an autonomous unicycle is considered in three-dimensional space. It is shown that with the appropriate choice of pseudo-velocities the lateral and longitudinal dynamics and control can be decoupled at the linear level. Linear state feedback controllers are designed separately for lateral and longitudinal subsystems and these controllers are tested simultaneously for the nonlinear model via numerical simulations.

This manuscript presents a control barrier function based approach to shared control for preventing a vehicle from entering the part of the state space where it is unrecoverable. The maximal phase recoverable ellipse is presented as a safe set in the sideslip angle-yaw rate phase plane where the vehicle’s state can be maintained. An exponential control barrier function is then defined on the maximal phase recoverable ellipse to promote safety. Simulations demonstrate that this approach enables safe drifting, that is, driving at the handling limit without spinning out. Results are then validated for shared control drifting with an experimental vehicle in a closed course. The results show the ability of this shared control formulation to maintain the vehicle’s state within a safe domain in a computationally efficient manner, even in extreme drifting maneuvers.

Autonomous vehicles utilize low-level controllers to ensure vehicles stay within road boundaries while accurately tracking planned high-level reference trajectories. In this paper, we propose a control design that addresses both lateral reference tracking and lane-keeping safety objectives. This design exploits a Lyapunov Function-Based Reference Governor that handles control and safety constraints. We show that such a Reference Governor can be implemented without requiring iterative onboard optimization (i.e., it is optimization-free). Simulation results demonstrate that this approach can achieve accurate lateral reference tracking with safety guarantees. In comparison to an alternative solution that uses Control Barrier Functions and quadratic programming, the proposed method is able to generate larger constrained Domains of Attraction while requiring a shorter computation time of 0.12±0.22 ms.

The nonlinear dynamics of automated vehicles are studied. A 5 degree-of-freedom single track model is derived using the Appellian approach to describe the dynamics of rear-wheel drive and front-wheel steer automobiles. This model captures the interactions between the vehicle body and the wheels while eliminating the calculation of the internal reaction forces and torques. An anisotropic combined slip brush tyre model is constructed to describe tyre characteristics. The handling characteristics are analysed by using bifurcation analysis: stable and unstable invariant solutions are studied while varying the steering angle and driving torque. The results provide insights about the existence and stability of steady states (namely, steady-state cornering, donut, drifting) and periodic orbits, and this knowledge is utilised when designing simple, computationally inexpensive controllers that can stabilise unstable states and navigate the system between them. This establishes a flexible control framework that can be used to realise a large variety of extreme manoeuvres.

In this study, we propose a novel negotiation-based cooperative maneuvering strategy to assist connected automated vehicles (CAVs) in resolving conflicts under different traffic scenarios. We introduce conflict charts to determine when negotiation is necessary, along with a request and response protocol to facilitate traffic conflict resolution. Additionally, we propose an easy-to-implement controller that allows CAVs to resolve conflicts based on the agreement reached through negotiation. Simulation results using real vehicle data are used to demonstrate that the proposed negotiation protocol helps to ensure safety while improving time efficiency compared to cooperations that rely on other communication strategies.

The nonlinear dynamics of vehicles on a virtual ring is investigated. A vehicle chain is considered where a connected automated vehicle (CAV) driving at the head of the chain receives the state of a connected human-driven vehicle (CHV) at the tail. The controller of the CAV is constructed in a way that the CHV is projected in front of it; this closes a virtual ring. We construct the corresponding mathematical model and analyze the effect of nonlinearities with numerical continuation. Then, we present real car experiments with two CHVs and one CAV. Both the theoretical results and the experiments show bistable behavior for certain control parameters. The results provide an essential support for parameter tuning during the control design of CAVs.

In this paper, we propose models with explicit trainable delays for learning teleoperated driving (ToD) behavior from limited vehicle trajectory data. The data-driven model is integrated with physics-based nonlinear vehicle dynamics and formulated as a neural delay differential equation (NDDE). The model can be analyzed using the same tools as developed for classical delay differential equations. The physics-based nonlinearity built into the data-driven model reduces the model complexity, enables training with limited data, and provides good generalizations. An overall latency in the loop is learned and a generic steering controller that characterizes the remote operator is identified at the same time through the training process. This information could be used to evaluate the performance of ToD in the presence of communication latency. We provide examples of learning from simulation data generated by a kinematic vehicle model and from experimental data generated by a human operator driving in a high-fidelity simulation environment. The same data-driven model and training algorithm is used in both cases, which demonstrates the generalizability of the proposed approach.

In this paper, a control barrier function (CBF) is constructed for the lane-keeping problem which is applicable to both human-driven and automated vehicles. Based on the resulting CBF, a safety filter is developed that prevents the vehicle from crossing the lane boundaries, while only modifying the nominal steering input when necessary. The effectiveness of the proposed control approach is demonstrated in a series of numerical simulations and real vehicle experiments with a human driver. The experimental results show that the safety filter can successfully keep the vehicle inside the lane boundaries by seamlessly modifying the steering input of the human driver in a minimally invasive manner.

This brief investigates the guidance of a human driver via an automated lead vehicle, when the automated vehicle is not only responding to a reference velocity but it also takes into account the speed of the subsequent human-driven vehicle (HV). To verify the theoretical results, a human-in-the-loop (HITL) simulation environment is developed, in which a graphical interface illustrates the automated vehicle ahead, while the human operator controls the velocity of the following vehicle via the accelerator and brake pedals. Nine human drivers were involved in the experiments, each of them carried out the driving task for 79 control gain combinations of the automated vehicle. Based on the measurement data, the parameters of the human driver model were estimated using the sweeping least squares method; the measurement results confirmed the applicability of the theoretical model in designing advanced traffic control strategies.

This manuscript presents a control barrier function based approach to shared control for preventing a vehicle from entering the part of the state space where it is unrecoverable. The maximal phase recoverable ellipse is presented as a safe set in the sideslip angle--yaw rate phase plane where the vehicle's state can be maintained. An exponential control barrier function is then defined on the maximal phase recoverable ellipse to promote safety. Simulations demonstrate that this approach enables safe drifting, that is, driving at the handling limit without spinning out. Results are then validated for shared control drifting with an experimental vehicle in a closed course. The results show the ability of this shared control formulation to maintain the vehicle's state within a safe domain in a computationally efficient manner, even in extreme drifting maneuvers.

While control barrier functions provide a powerful tool to endow controllers with formal safety guarantees, robust control barrier functions (RCBF) can be used to extend these guarantees for systems with model inaccuracies. This paper presents a generalized RCBF framework that unifies and extends existing notions of RCBFs for a broad class of model uncertainties. Main results are conditions for robust safety through generalized RCBFs. We apply these generalized principles for more specific design examples: a worst-case type design, an estimation-based design, and a tunable version of the latter. These examples are demonstrated to perform increasingly closer to an oracle design with ideal model information. Theoretical contributions are demonstrated on a practical example of a pendulum with unknown periodic excitation. Using numerical simulations, a comparison among design examples are carried out based on a performance metric depicting the increased likeness to the oracle design.

In this study, we analyze the stability of a path-tracking controller designed for a four-wheel steering vehicle, incorporating the effects of the reference path curvature. By employing a simplified kinematic model of the vehicle with steerable front and rear wheels, we derive analytical expressions for the stability regions and optimal control gains specific to different four-wheel steering strategies. To simplify our calculations, we keep the rear steering angle $δ_r$ proportional to the front steering angle $δ_f$ by using the constant parameter $a$, i.e., $δ_r = aδ_f$, where $δ_f$ is calculated from a control law having both feedforward and feedback terms. Our findings, supported by stability charts and numerical simulations, indicate that for high velocities and paths of small curvatures, the appropriately tuned four-wheel steering controller significantly reduces lateral acceleration and enhances path-tracking performance when compared to using only front-wheel steering. Furthermore, for low velocities and large curvatures, the using negative a values (i.e., steering the rear wheels in the opposite direction than the front wheels) allows for a reduced turning radius, increasing the vehicle's capability to perform sharp turns in confined spaces like in parking lots or on narrow roads.

Leveraging connectivity for controlling connected automated vehicles (CAVs) has great potential for improving the safety and efficiency of transportation. In this paper, we study the safety of connected cruise control (CCC), wherein CAVs respond to multiple preceding vehicles via vehicle-to-everything (V2X) connectivity. Using control barrier function theory, we analyze how connectivity to vehicles farther ahead can be leveraged to improve the CAV's safety, and we propose safety-critical CCC by minimally modifying efficient but not always safe CCC designs. We use simulations to evaluate the proposed safety-critical CCC with respect to safety, energy efficiency and string stability. We also study mixed traffic, and show that increasing the penetration of CAVs can significantly improve safety and performance of road transportation systems.

A continuous motion planning method for connected automated vehicles (CAVs) is considered for generating feasible trajectories in real-time using three consecutive clothoids. The proposed method reduces path planning to a small set of nonlinear algebraic equations such that the generated path can be efficiently checked for feasibility and collision. After path planning, velocity planning is executed while maintaining a parallel simple structure. Key strengths of this framework include its interpretability, shareability, and ability to specify boundary conditions. Its interpretability and shareability stem from the succinct representation of the resulting local motion plan using a handful of physically meaningful parameters. Vehicles may share these parameters via vehicle-to-everything (V2X) communication so that the recipients can precisely reconstruct the planned trajectory of the senders and respond accordingly. The proposed local planner guarantees the satisfaction of boundary conditions, thus ensuring seamless integration with a wide array of higher-level global motion planners. The tunable nature of the method enables tailoring the local plans to specific maneuvers like turns at intersections, lane changes, and U-turns.

In this paper, we demonstrate how the network latency, the longitudinal velocity and the path curvature affect performance of the teleoperated driving (ToD). The performance of a ToD system is studied analytically through stability analysis of a dimensionless vehicle dynamics model with a scaled delay, which integrates the end-to-end (E2E) latency and the longitudinal velocity of the vehicle. We also establish a numerical simulation framework for ToD while incorporating a stochastic latency in the control loop arising from vehicle-to-network-to-vehicle (V2N2V) communication through a wireless network. The stochasticity of the latency mostly comes from the network scalability challenges to support high video bitrates, which also leads to packet drops. We provide simulation results of teleoperating a vehicle in a realistic parking lot scenario and demonstrate the effects of speed, curvature and stochastic latency on the maneuver performance.

Negotiation is a class of cooperation enabled by vehicle-to-everything (V2X) communication, which involves the exchange of maneuver requests and responses between road users. In this paper, we develop criteria for request initiation and response generation under a unified conflict analysis framework. This leads to guaranteed maneuver feasibility in request and response that satisfy user-based behavior preferences. We implement negotiation via commercially available V2X devices, and experimentally evaluate the benefits of negotiation in conflict resolution. We demonstrate that negotiation can significantly benefit time efficiency of maneuvers while ensuring safety, compared to lower levels of cooperation such as status-sharing and intent-sharing. These benefits and their degradation under communication delays are quantified.

This paper presents a methodology by which kinematic variables of road vehicles can be extracted from unmanned aerial vehicle (UAV) footage. The oriented bounding boxes of the vehicles are identified based on the aerial view of the intersection, and the kinematic variables, such as position, longitudinal velocity, lateral velocity, yaw angle and yaw rate, are determined. The bounding boxes are converted to the perspective of a roadside camera using homography, to generate labeled data sets for training the machine learning-based perception systems of smart intersections. Compared to ordinary GPS data-based technology, the proposed method provides smoother data and more information about the dynamics of the vehicles. In the meantime, it does not require any additional instrumentation on the vehicles. The extracted kinematic variables can be used for motion prediction of road traffic participants and for control of connected automated vehicles (CAVs) in intelligent transportation systems.

Intent sharing is a class of cooperation enabled by vehicle-to-everything (V2X) communication, which allows for information exchange between road users about their intended future behaviors. In this paper, we propose a generalized representation of vehicles’ motion intent from a dynamical systems viewpoint. Based on this, we extend the framework of conflict analysis such that intent information can be interpreted in real time to assist the decision-making of intent-receiving vehicles and ensure conflict-free maneuvers. We create intent messages using commercially available V2X radios, and demonstrate experimentally the benefits of sharing intent in cooperative maneuvering. Experiments are performed on a test track where intent-based on-board decision assistance is provided to human drivers in merge scenarios. The experimental results reveal significant benefits of intent sharing in enhancing vehicle safety and time efficiency. Furthermore, we test intent messages on public roads and evaluate the performance in terms of packet delivery ratio. The data collected on public highways are fed into numerical simulations to investigate the effects of intent transmission conditions on conflict resolution.

In this article, the connection between time delay systems and time delay neural networks (TDNNs) is presented from a continuous-time perspective. TDNNs are utilized to learn the nonlinear dynamics of time delay systems from trajectory data. The concept of TDNN with trainable delay (TrTDNN) is established, and training algorithms are constructed for learning the time delays and the nonlinearities simultaneously. The proposed techniques are tested on learning the dynamics of autonomous systems from simulation data and on learning the delayed longitudinal dynamics of a connected automated vehicle (CAV) from real experimental data.

Intelligent road infrastructure consisting of sensors and communications is needed to deploy connected and automated vehicles (CAVs) on real highways. Such infrastructure can support the operation of CAVs (e.g., maneuver coordination and onboard energy management), and bridge the connectivity gap resulting from the currently low penetration of connected vehicles and the limited range of vehicle-to-vehicle communication. Moreover, it also allows us to build high-efficiency transportation systems, leading to societal benefits such as emission reduction, energy efficiency improvement, and productivity increase. In this project, we deploy cellular vehicle-to-everything (CV2X) infrastructure along the highway I-275, which consists of roadside units (RSUs), a server managed by the University of Michigan, and communications between them. The RSUs collect traffic information from the downstream vehicles on highway via a custom V2X communication message called traffic history message (THM). The received THMs are transferred via the RSUs’ LTE Internet to the university server for real-time processing. The processed information is then sent to the upstream RSUs and broadcast to vehicles nearby via another custom V2X message called traffic prediction message (TPM). This allows the upstream vehicles to predict the traffic ahead and plan their motions accordingly. This way, traffic prediction and control can be achieved. We conduct experiments on highway I-275 using the installed RSUs and the designed messages with real vehicles. We demonstrate the effectiveness of the infrastructure-supported traffic prediction tailored to the needs of automated vehicles.

In this paper, we demonstrate the detrimental effects of latency in remote driving with an example of straight-path following. To address the instability and performance degradation caused by the latency in the remote driving control loop, we propose to use an act-and-wait strategy on top of the existing controller. This strategy can potentially stabilize the system under large latency using the original control gains, and achieve dead-beat control with modified control gains. Stability and performance analysis is conducted for the act-and-wait strategy to provide insights on modulating the control input under large latency.

The path-following task of an autonomous unicycle is considered in the three-dimensional space. The equation of motion is derived using the Appellian aproach of non-honolomic dynamics. The resulting nonlinear model is transformed into the path-reference frame. Using pole placement, a linear feedback controller is designed that takes into account the velocity of the maneuver. The resulting controller is tested on the nonlinear model via numerical simulations; lane change maneuvers are carried out successfully at different speeds.

Abstract A methodology is developed to extract vehicle kinematic information from roadside cameras at an intersection using deep learning. The ground truth data of top view bounding boxes are collected with the help of unmanned aerial vehicles (UAVs). These top view bounding boxes containing vehicle position, size, and orientation information, are converted to the roadside view bounding boxes using homography transformation. The ground truth data and the roadside view images are used to train a modified YOLOv5 neural network, and thus, to learn the homography transformation matrix. The output of the neural network is the vehicle kinematic information, and it can be visualized in both the top view and the roadside view. In our algorithm, the top view images are only used in training, and once the neural network is trained, only the roadside cameras are needed to extract the kinematic information.

A model for the longitudinal and pitch dynamics of an electric unicycle (EUC) ridden by a human is derived while considering the independent pitch movements of the EUC body and that of the rider. Experimental data is collected for multiple maneuvers through a high-precision motion capture system and the processed data is used for parameter identification. It is demonstrated that the longitudinal and pitch dynamics are well captured by the model even for maneuvers which involve lateral motion.

A continuous motion planning method for connected automated vehicles is considered for generating feasible trajectories in real-time using three consecutive clothoids. The proposed method reduces path planning to a small set of nonlinear algebraic equations such that the generated path can be efficiently checked for feasibility and collision. After path planning, velocity planning is executed while maintaining a parallel simple structure. Key strengths of this framework include its interpretability, shareability, and ability to specify boundary conditions. Its interpretability and shareability stem from the succinct representation of the resulting local motion plan using a handful of physically meaningful parameters. Vehicles may share these parameters via V2X communication so that the recipients can precisely reconstruct the planned trajectory of the senders and respond accordingly. The proposed local planner guarantees the satisfaction of boundary conditions, thus ensuring seamless integration with a wide array of higher-level global motion planners. The tunable nature of the method enables tailoring the local plans to specific maneuvers like turns at intersections, lane changes, and U-turns.

Connected automated vehicles have shown great potential to improve the efficiency of transportation systems in terms of passenger comfort, fuel economy, stability of driving behavior and mitigation of traffic congestions. Yet, to deploy these vehicles and leverage their benefits, the underlying algorithms must ensure their safe operation. In this paper, we address the safety of connected cruise control strategies for longitudinal car following using control barrier function (CBF) theory. In particular, we consider various safety measures such as minimum distance, time headway and time to conflict, and provide a formal analysis of these measures through the lens of CBFs. Additionally, motivated by how stability charts facilitate stable controller design, we derive safety charts for existing connected cruise controllers to identify safe choices of controller parameters. Finally, we combine the analysis of safety measures and the corresponding stability charts to synthesize safetycritical connected cruise controllers using CBFs. We verify our theoretical results by numerical simulations.