Click on the DOI link to access this article at the publishers website (may not be free).

Click on the DOI link to access this article at the publishers website (may not be free).

This paper discusses scalable cooperative maneuvering using conflict analysis, where conflicts are managed between multiple vehicles in mixed-autonomy environments. Two different classes of cooperation, enabled by vehicle-to-everything (V2X) communication, are considered–status sharing and intent sharing. In status sharing, connected vehicles share their current states, such as position and velocity, while in intent sharing the information about vehicles’ future trajectories is exchanged. The scalability of conflict analysis is studied through traffic scenarios where an ego vehicle interacts with multiple remote vehicles in a safety- and time-critical manner. We show thatpairwiseconflict analysis, which decomposes a large-scale conflict management problem to multiple sequentially solvable smaller-scale problems, is a key component of scalability. Conflict analysis, while being scaled up to more complex traffic scenarios, preserves the efficient consideration of different types of V2X information, time delay effects, and flexible control design. These results are demonstrated using simulations with real traffic data.

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.

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.

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, 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.

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.

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.

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 paper, we propose a data-driven predictive controller for connected automated vehicles (CAVs) traveling in mixed traffic consisting of both connected and non-connected vehicles. We assume a low penetration of connectivity, with only one connected vehicle in the downstream traffic. A model predictive controller is designed to integrate multiple specifications, including safety and energy efficiency, while accounting for the time delay in the longitudinal dynamics of the vehicle. A data-driven prediction method based on the behavioral theory of linear systems is proposed to model the relationship between the speeds of the distant connected vehicle and the vehicle immediately in front of the CAV. The proposed method is evaluated using real traffic data and demonstrates improved prediction accuracy and energy efficiency compared to model-based prediction methods.

Intent sharing is an emerging type of vehicle-to-everything (V2X) communication where vehicles share information about their intended future trajectories. In this study, we implement intent sharing via commercially available V2X devices, and experimentally demonstrate its benefits in resolving conflicts arising in cooperative maneuvering. An extended framework of conflict analysis is used to provide decision-making assistance via on-board warnings to a human-driven vehicle in highway merge scenario. We show that intent information can significantly benefit safety and time efficiency. Using the experimental data, we also evaluate the effects of communication conditions (e.g., sending rate and intent horizon) on the gained benefits.

This paper considers mixed traffic consisting of connected automated vehicles equipped with vehicle-to-everything (V2X) connectivity and human-driven vehicles. A control strategy is proposed for communicating pairs of connected automated vehicles, where the two vehicles regulate their longitudinal motion by responding to each other, and, at the same time, stabilize the human-driven traffic between them. Stability analysis is conducted to find stabilizing controllers, and simulations are used to show the efficacy of the proposed approach. The impact of the penetration of connectivity and automation on the string stability of traffic is quantified. It is shown that, even with moderate penetration, connected automated vehicle pairs executing the proposed controllers achieve significant benefits compared to when these vehicles are disconnected and controlled independently.

This paper focuses on energy-efficient longitudinal controller design for a connected automated truck that travels in mixed traffic consisting of connected and non-connected vehicles. The truck has access to information about connected vehicles beyond line of sight using vehicle-to-everything (V2X) communication. A novel connected cruise control design is proposed which incorporates additional delays into the control law when responding to distant connected vehicles to account for the finite propagation speed of traffic waves. The speeds of non-connected vehicles are modeled as stochastic processes. A fundamental theorem is proven which links the spectral properties of the motion signals to the average energy consumption. Controller synthesis for gain parameters is conducted over downstream traffic data and evaluated over a combination of synthetic and real cycles. It is demonstrated that even with lean penetration of connected vehicles, our controller can bring significant energy savings.

In this paper, we extend the conflict analysis framework to resolve conflicts between multiple vehicles with different levels of automation, while utilizing status-sharing and intent-sharing enabled by vehicle-to-everything (V2X) communication. In status-sharing a connected vehicle shares its current state (e.g., position, velocity) with other connected vehicles, whereas in intent-sharing a vehicle shares information about its future trajectory (e.g., velocity bounds). Our conflict analysis framework uses reachability theory to interpret the information contained in status-sharing and intent-sharing messages through conflict charts. These charts enable real-time decision making and control of a connected automated vehicle interacting with multiple remote connected vehicles. Using numerical simulations and real highway traffic data, we demonstrate the effectiveness of the proposed conflict resolution strategies, and reveal the benefits of intent sharing in mixed-autonomy environments.

In this paper we investigate the effects of connected automated vehicles on traffic patterns. We first experimentally study traffic patterns using two connected human-driven vehicles, which are equipped with vehicle-to-vehicle (V2V) communication, and a connected automated vehicle, which is able to respond to V2V information and control its longitudinal motion. Our experimental results indicate the long-range feedback may benefit traffic flow and that car-following models with delay are able to replicate the experimental results. The data fitted models are used in simulations for a 100-car network to study traffic dynamics with partial penetration of connected automated vehicles.

In this paper, we propose an optimization-based strategy that utilizes vehicle-to-everything (V2X) communication in order to resolve conflicts between vehicles of different automation levels. The strategy consists of a decision checking mechanism and a control law to adjust the decision of an ego vehicle in a certain maneuver based on status update messages received from a remote vehicle involved in that maneuver. Using numerical simulations with real highway data, we demonstrate the proposed opportunistic strategy and show how it improves safety and maximizes the time efficiency of the ego vehicle. We also highlight the benefits of the strategy by comparing the results with an existing conservative strategy.

In this paper we investigate the problem of a vehicle merging to a main road while another vehicle is approaching on that road. We utilize conflict analysis to help the decision making and control for vehicles of different automation levels. We demonstrate that using vehicle-to-everything (V2X) communication, e.g., basic safety message (BSM), we are able to prevent conflict between the two vehicles. We design a longitudinal controller for the merging vehicle and show that V2X communication is also beneficial in improving the time efficiency of the merge. The results are demonstrated by performing simulations based on real highway data.

This paper presents the robustness analysis for the head-to-tail string stability of connected cruise controllers that utilize motion information of human-driven vehicles ahead. In particular, we consider uncertainties arising from the feedback gains and reaction time delays of the human drivers. We utilize the linear fractional transformation and the M-Δ uncertain interconnection structure to represent the uncertainties in the block-diagonal matrix Δ. The uncertain gains are directly incorporated in the uncertain interconnection structure, while the uncertain time delays are taken into account using the Rekasius substitution that preserves the tightness of the robustness bounds. This modeling framework scales are well for large-size connected vehicle systems. We demonstrate through two case studies how parameters in the connected cruise controller can be selected to ensure the robust string stability. Theoretical results are supported by the experiments that highlight the advantage of robust control designs.

Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a controller architecture that combines (1) a model-free RL-based controller with (2) model-based controllers utilizing control barrier functions (CBFs) and (3) online learning of the unknown system dynamics, in order to ensure safety during learning. Our general framework leverages the success of RL algorithms to learn high-performance controllers, while the CBF-based controllers both guarantee safety and guide the learning process by constraining the set of explorable polices. We utilize Gaussian Processes (GPs) to model the system dynamics and its uncertainties. Our novel controller synthesis algorithm, RL-CBF, guarantees safety with high probability during the learning process, regardless of the RL algorithm used, and demonstrates greater policy exploration efficiency. We test our algorithm on (1) control of an inverted pendulum and (2) autonomous carfollowing with wireless vehicle-to-vehicle communication, and show that our algorithm attains much greater sample efficiency in learning than other state-of-the-art algorithms and maintains safety during the entire learning process.

Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on problems arising in continuous control, we propose a functional regularization approach to augmenting model-free RL. In particular, we regularize the behavior of the deep policy to be similar to a policy prior, i.e., we regularize in function space. We show that functional regularization yields a bias-variance trade-off, and propose an adaptive tuning strategy to optimize this trade-off. When the policy prior has control-theoretic stability guarantees, we further show that this regularization approximately preserves those stability guarantees throughout learning. We validate our approach empirically on a range of settings, and demonstrate significantly reduced variance, guaranteed dynamic stability, and more efficient learning than deep RL alone.

In this paper, we investigate a vehicular string traveling on a single lane, where vehicles use connected cruise control to regulate their longitudinal motion based on data received from other vehicles via wireless vehicle-to-vehicle communication. Assuming digital controllers, the sample-and-hold units introduce time-periodic time delays in the control loops and the delays increase when data packets are lost. We investigate the effect of packet losses on plant and string stability while varying the control gains and determine the minimum achievable time gap below which stability cannot be achieved. We propose two predictor feedback control strategies that overcome the destabilizing effect of the time delay caused by the sample-and-hold unit and packet losses.

In this paper, we investigate the identification of the configuration and the dynamics of connected vehicle systems, where wireless vehicle-to-vehicle communication is used to access the motion data of vehicles that are beyond the line of sight. In particular, we first construct a causality detector to determine whether the information received from distant vehicles is relevant to the motion of the receiving vehicle. Then, we design a link-length estimator to identify the number of vehicles between the broadcasting vehicle and the receiving vehicle, which is required for appropriately incorporating the received data into the vehicle control system. Finally, a dynamics identifier is proposed to approximate the nonlinear time-delayed dynamics of vehicle chains, which is needed for the controller design to achieve desired system-level performance. The presented analytical results are validated through numerical simulations using synthetic data and on-road experiments.

In this paper, linear quadratic regulation is used to obtain an optimal design of connected cruise control (CCC). We consider vehicle strings where a CCC vehicle receives position and velocity signals through wireless vehicle-to-vehicle communication from multiple vehicles ahead. Communication delay, driver reaction time, and heterogeneity of vehicles are considered. The optimal feedback law is obtained by minimizing a cost function defined by headway and velocity errors and the acceleration of the CCC vehicle on an infinite horizon. We show that, by decomposing the optimization problem, the feedback gains can be obtained recursively as signals from vehicles farther ahead become available, and that the gains decay exponentially with the number of cars between the source of the signal and the CCC vehicle. Such properties allow graceful degradation of CCC performance under imperfect communication. The effects of the cost function on the head-to-tail string stability are also investigated and the robustness against variations in human parameters is tested. The analytical results are verified by numerical simulations at the nonlinear level. The results allow us to significantly reduce the complexity of CCC design.

In this paper we investigate connected cruise control in which vehicles rely on ad hoc wireless vehicle-to-vehicle communication to control their longitudinal motion. Intermittencies and packet drops in communication channels are shown to introduce stochastic delays in the feedback loops. Sufficient conditions for almost sure stability of equilibria are derived by analyzing the mean and covariance dynamics. In addition, the concept of nσ string stability is proposed to characterize the input-output response in steady state. The stability results are summarized using stability charts in the plane of the control gains and we demonstrate that the stable regimes shrink when the sampling time or the packet drop ratio increases. The mathematical tools developed allow us to design controllers that can achieve plant stability and string stability in connected vehicle systems despite the presence of stochastically varying delays in the control loop.

In this paper, we investigate the effects of heterogeneous connectivity structures and information delays on the dynamics of connected vehicle systems (CVSs), which are composed of vehicles equipped with connected cruise control (CCC) as well as conventional vehicles. First, a general framework is presented for CCC design that incorporates information delays and allows a large variety of connectivity structures. Then, we present delay-dependent criteria for plant stability and head-to-tail string stability of CVSs. The stability conditions are visualized by using stability diagrams, which allow one to evaluate the robustness of vehicle networks against information delays. To achieve modular and scalable design of large networks, we also propose a motif-based approach. Our results demonstrate the advantages of CCC vehicles in improving traffic efficiency, but also show that increasing the penetration of CCC vehicles does not necessarily improve the robustness if the connectivity structure or the control gains are not appropriately designed.

In this paper, we consider a learning strategy that allows one to transmit information between two coupled phase oscillator systems (called teaching and learning systems) via frequency adaptation. The dynamics of these systems can be modeled with reference to a number of partially synchronized cluster states and transitions between them. Forcing the teaching system by steady but spatially nonhomogeneous inputs produces cyclic sequences of transitions between the cluster states, that is, information about inputs is encoded via a "winnerless competition" process into spatio-temporal codes. The large variety of codes can be learned by the learning system that adapts its frequencies to those of the teaching system. We visualize the dynamics using "weighted order parameters (WOPs)" that are analogous to "local field potentials" in neural systems. Since spatio-temporal coding is a mechanism that appears in olfactory systems, the developed learning rules may help to extract information from these neural ensembles.