Search for: All records

This paper studies the problem of data-driven combined longitudinal and lateral control of autonomous vehicles (AVs) such that the AV can stay within a safe but minimum distance from its leading vehicle and, at the same time, in the lane. Most of the existing methods for combined longitudinal and lateral control are either model-based or developed by purely data-driven methods such as reinforcement learning. Traditional model-based control approaches are insufficient to address the adaptive optimal control design issue for AVs in dynamically changing environments and subject to model uncertainty. Moreover, the conventional reinforcement learning approaches require a large volume of data, and cannot guarantee the stability of the vehicle. These limitations are addressed by integrating the advanced control theory with reinforcement learning techniques. To be more specific, by utilizing adaptive dynamic programming techniques and using the motion data collected from the vehicles, a policy iteration algorithm is proposed such that the control policy is iteratively optimized in the absence of the precise knowledge of the AV’s dynamical model. Furthermore, the stability of the AV is guaranteed with the control policy generated at each iteration of the algorithm. The efficiency of the proposed approach is validated by SUMO simulation, a microscopic traffic simulation platform, for different traffic scenarios. 

Well-calibrated traffic flow models are fundamental to understanding traffic phenomena and designing control strategies. Traditional calibration has been developed based on optimization methods. In this paper, we propose a novel physics-informed, learning-based calibration approach that achieves performances comparable to and even better than those of optimization-based methods. To this end, we combine the classical deep autoencoder, an unsupervised machine learning model consisting of one encoder and one decoder, with traffic flow models. Our approach informs the decoder of the physical traffic flow models and thus induces the encoder to yield reasonable traffic parameters given flow and speed measurements. We also introduce the denoising autoencoder into our method so that it can handle not only with normal data but also corrupted data with missing values. We verified our approach with a case study of Interstate 210 Eastbound in California. It turns out that our approach can achieve comparable performance to the-state-of-the-art calibration methods given normal data and outperform them given corrupted data with missing values. History: This paper has been accepted for the Transportation Science Special Issue on ISTTT25 Conference. Funding: This study was supported by the National Science Foundation [Grant CMMI-1949710] and the C2SMART Research Center, a Tier 1 University Transportation Center. 

The majority of the past research dealing with lane-changing controller design of autonomous vehicles (𝐴𝑉 s) is based on the assumption of full knowledge of the model dynamics of the 𝐴𝑉 and the surrounding vehicles. However, in the real world, this is not a very realistic assumption as accurate dynamic models are difficult to obtain. Also, the dynamic model parameters might change over time due to various factors. Thus, there is a need for a learning-based lane change controller design methodology that can learn the optimal control policy in real time using sensor data. In this paper, we have addressed this need by introducing an optimal learningbased control methodology that can solve the real-time lane-changing problem of 𝐴𝑉 s, where the input-state data of the 𝐴𝑉 is utilized to generate a near-optimal lane-changing controller by approximate/adaptive dynamic programming (ADP) technique. In the case of this type of complex lane-changing maneuver, the lateral dynamics depend on the longitudinal velocity of the vehicle. If the longitudinal velocity is assumed constant, a linear parameter invariant model can be used. However, assuming constant velocity while performing a lane-changing maneuver is not a realistic assumption. This assumption might increase the risk of accidents, especially in the case of lane abortion when the surrounding vehicles are not cooperative. Thus, in this paper, the dynamics of the 𝐴𝑉 are assumed to be a linear parameter-varying system. Thus we have two challenges for the lane-changing controller design: parameter-varying, and unknown dynamics. With the help of both gain scheduling and ADP techniques combined, a learning-based control algorithm that can generate a near-optimal lane-changing controller without having to know the accurate dynamic model of the 𝐴𝑉 is proposed. The inclusion of a gain scheduling approach with ADP makes the controller applicable to non-linear and/or parameter-varying 𝐴𝑉 dynamics. The stability of the learning-based gain scheduling controller has also been rigorously proved. Moreover, a data-driven lane-changing decision-making algorithm is introduced that can make the 𝐴𝑉 perform a lane abortion if safety conditions are violated during a lane change. Finally, the proposed learning-based gain scheduling controller design algorithm and the lane-changing decision-making methodology are numerically validated using MATLAB, SUMO simulations, and the NGSIM dataset. 

This paper introduces a learning-based optimal control strategy enhanced with nonmodel-based state estimation to manage the complexities of lane-changing maneuvers in autonomous vehicles. Traditional approaches often depend on comprehensive system state information, which may not always be accessible or accurate due to dynamic traffic environments and sensor limitations. Our methodology dynamically adapts to these uncertainties and sensor noise by iteratively refining its control policy based on real-time sensor data and reconstructed states. We implemented an experimental setup featuring a scaled vehicle equipped with GPS, IMUs, and cameras, all processed through an Nvidia Jetson AGX Xavier board. This approach is pivotal as it addresses the limitations of simulations, which often fail to capture the complexity of dynamic real-world conditions. The results from real-world experiments demonstrate that our learning-based control system achieves smoother and more consistent lane-changing behavior compared to traditional direct measurement approaches. This paper underscores the effectiveness of integrating Adaptive Dynamic Programming (ADP) with state estimation techniques, as demonstrated through small-scale experiments. These experiments are crucial as they provide a practical validation platform that simulates real-world complexities, representing a significant advancement in the control systems used for autonomous driving. 

The advancements of connected vehicle (CV) technologies promise significant safety, mobility, and environmental benefits for future transportation systems. These benefits will largely rely on the market penetration rate (MPR) of CVs and connected infrastructure. However, higher MPR is not guaranteed to result in greater benefits in a transportation system in some cases even if we do not consider the deployment cost of CVs. Therefore, understanding the optimal CV MPR to achieve the best system benefits is informative and can provide some guidance for transportation agencies to use appropriate incentives or other policies to potentially affect the speed of CV adoption. Instead of using the traditional incremental method, this paper proposed a simulation-based approach combined with Bayesian optimization to determine the optimal CV MPR that achieves the highest performance benefits for a freeway segment. The proposed methodology is tested in the I-210 E (in California, U.S.) simulation freeway segment built and calibrated in Simulation of Urban Mobility software as a case study. The weighted sum of the average total travel time on the mainline and the average queue length of on-ramps is formulated as the objective function to optimize the CV MPR. Different weight combinations are tested as different scenarios. The optimization results of these scenarios show that, when the weight of total travel time is high, the optimal CV MPR tends to be high. On the contrary, when the weight of queue length increases, higher CV MPRs may not guarantee higher benefits for the traffic system. The globally optimal CV MPR can be as low as 3%. The case study also confirms the effectiveness of optimizing the CV MPR based on microsimulation and Bayesian optimization. 

Access to high-quality data is an important barrier in the digital analysis of urban settings, including applications within computer vision and urban design. Diverse forms of data collected from sensors in areas of high activity in the urban environment, particularly at street intersections, are valuable resources for researchers interpreting the dynamics between vehicles, pedestrians, and the built environment. In this paper, we present a high-resolution audio, video, and LiDAR dataset of three urban intersections in Brooklyn, New York, totaling almost 8 unique hours. The data were collected with custom Reconfigurable Environmental Intelligence Platform (REIP) sensors that were designed with the ability to accurately synchronize multiple video and audio inputs. The resulting data are novel in that they are inclusively multimodal, multi-angular, high-resolution, and synchronized. We demonstrate four ways the data could be utilized — (1) to discover and locate occluded objects using multiple sensors and modalities, (2) to associate audio events with their respective visual representations using both video and audio modes, (3) to track the amount of each type of object in a scene over time, and (4) to measure pedestrian speed using multiple synchronized camera views. In addition to these use cases, our data are available for other researchers to carry out analyses related to applying machine learning to understanding the urban environment (in which existing datasets may be inadequate), such as pedestrian-vehicle interaction modeling and pedestrian attribute recognition. Such analyses can help inform decisions made in the context of urban sensing and smart cities, including accessibility-aware urban design and Vision Zero initiatives.