Autonomous driving in dense, dynamic environments requires decision-making systems that can exploit both spatial structure and long-horizon temporal dependencies while remaining robust to uncertainty. This work presents a novel framework that integrates multi-channel bird's-eye-view occupancy grids with transformer-based sequence modeling for tactical driving in complex roundabout scenarios. To address the imbalance between frequent low-risk states and rare safety-critical decisions, we propose the Uncertainty-Weighted Decision Transformer (UWDT). UWDT employs a frozen teacher transformer to estimate per-token predictive entropy, which is then used as a weight in the student model's loss function. This mechanism amplifies learning from uncertain, high-impact states while maintaining stability across common low-risk transitions. Experiments in a roundabout simulator, across varying traffic densities, show that UWDT consistently outperforms other baselines in terms of reward, collision rate, and behavioral stability. The results demonstrate that uncertainty-aware, spatial-temporal transformers can deliver safer and more efficient decision-making for autonomous driving in complex traffic environments.

Task offloading management in 6G vehicular net-works is crucial for maintaining network efficiency, particularly as vehicles generate substantial data. Integrating secure communication through authentication introduces additional computational and communication overhead, significantly impacting offloading efficiency and latency. This paper presents a unified framework incorporating lightweight Identity-Based Cryptographic (IBC) authentication into task offloading within cloud-based 6G Vehicular Twin Networks (VTNs). Utilizing Proximal Policy Optimization (PPO) in Deep Reinforcement Learning (DRL), our approach optimizes authenticated offloading decisions to minimize latency and enhance resource allocation. Performance evaluation under varying network sizes, task sizes, and data rates reveals that IBC authentication can reduce offloading efficiency by up to 50 % due to the added overhead. Besides, increasing network size and task size can further reduce offloading efficiency by up to 91.7%. As a countermeasure, increasing the transmission data rate can improve the offloading performance by as much as 63%, even in the presence of authentication overhead. The code for the simulations and experiments detailed in this paper is available on GitHub for further reference and reproducibility [1].

Recent research in pedestrian simulation often aims to develop realistic behaviors in various situations, but it is challenging for existing algorithms to generate behaviors that identify weaknesses in automated vehicles’ performance in extreme and unlikely scenarios and edge cases. To address this, specialized pedestrian behavior algorithms are needed. Current research focuses on realistic trajectories using social force models and reinforcement learning based models. However, we propose a reinforcement learning algorithm that specifically targets collisions and better uncovers unique failure modes of automated vehicle controllers. Our algorithm is efficient and generates more severe collisions, allowing for the identification and correction of weaknesses in autonomous driving algorithms in complex and varied scenarios.

A connected and automated vehicle safety metric determines the performance of a subject vehicle (SV) by analyzing the data involving the interactions among the SV and other dynamic road users and environmental features. When the data set contains only a finite set of samples collected from the naturalistic mixed multi-modal traffic driving environment, a metric is expected to generalize the safety assessment outcome from the observed finite samples to the unobserved cases by specifying in what domain the SV is expected to be safe and how safe the SV is, statistically, in that domain. However, to the best of our knowledge, none of the existing safety metrics is able to justify the above properties with an operational domain specific, guaranteed complete, and provably unbiased safety evaluation outcome. In this paper, we propose a novel safety metric that involves the$\alpha $-shape and the$\epsilon $-almost robustly forward invariant set to characterize the SV’s almost safe operable domain and the probability for the SV to remain inside the safe domain indefinitely, respectively. The empirical performance of the proposed method is demonstrated in several different operational design domains through a series of cases covering a variety of fidelity levels (real-world and simulators), driving environments (highway, urban, and intersections), road users (car, truck, and pedestrian), and SV driving behaviors (human driver and self driving algorithms).

Driving simulators play a large role in developing and testing new intelligent vehicle systems. The visual fidelity of the simulation is critical for building vision-based algorithms and conducting human driver experiments. Low visual fidelity breaks immersion for human-in-the-loop driving experiments. Conventional computer graphics pipelines use detailed 3D models, meshes, textures, and rendering engines to generate 2D images from 3D scenes. These processes are labor-intensive, and they do not generate photorealistic imagery. Here we introduce a hybrid generative neural graphics pipeline for improving the visual fidelity of driving simulations. Given a 3D scene, we partially-render only important objects of interest, such as vehicles, and use generative adversarial processes to synthesize the background and the rest of the image. To this end, we propose a novel image formation strategy to form 2D semantic images from 3D scenery consisting of simple object models without textures. These semantic images are then converted into photorealistic RGB images with a state-of-the-art Generative Adversarial Network (GAN) trained on real-world driving scenes. This replaces repetitiveness with randomly generated but photorealistic surfaces. Finally, the partially-rendered and GAN synthesized images are blended with a blending GAN. We show that the photorealism of images generated with the proposed method is more similar to real-world driving datasets such as Cityscapes and KITTI than conventional approaches. This comparison is made using semantic retention analysis and Frechet Inception Distance (FID) measurements.

An online evolving method, named evolving finite state machine (e-FSM), is proposed to develop an optimal Markov driving model. The model has the same properties as a standard Markov model, but its states and transition dynamics evolve without human supervision. In this article, we introduce: 1) the principles of the e-FSM’s novel capabilities:online state determinationandonline transition-dynamics identificationfor elaborating the Markov driving model and 2) an advanced online evolving framework (a-OEF) for supporting the reinforcement-learning-based controller’s decision making by using the evolved model. For the evaluation of the proposed methodology and framework, the ego vehicle is controlled by the double deep${Q}$-network (DDQN) controller with and without the a-OEF in the multilane driving scenario where various naturalistic traffic situations are simulated. Simulation results show that better control performance in terms offastandsafedriving is achieved via the DDQN with the a-OEF, which demonstrates that the Markov driving models evolved by the e-FSMs effectively support detecting and revising the controller’s incorrect decision making.

Monocular vision based navigation for automated driving is a challenging task due to the lack of enough information to compute temporal relationships among objects on the road. Optical flow is an option to obtain temporal information from monocular camera images, and has been used widely with the purpose of identifying objects and their relative motion. This work proposes to generate an artificial potential field, i.e. visual potential field, from a sequence of images using sparse optical flow, which is used together with a gradient tracking sliding mode controller to navigate the vehicle to destination without collision with obstacles. The angular reference for the vehicle is computed online. This work considers that the vehicle does not require to have a priori information from the map or obstacles to navigate successfully. The proposed technique is tested both in synthetic and real images.

Vehicle-pedestrian interaction (VPI) is one of the most challenging tasks for automated driving systems. The design of driving strategies for such systems usually starts with verifying VPI in simulation. This work proposed an improved framework for the study of VPI in uncontrolled pedestrian crossing scenarios. The framework admits the mutual effect between the pedestrian and the vehicle. A multi-state social force based pedestrian motion model was designed to describe the microscopic motion of the pedestrian crossing behavior. The pedestrian model considers major interaction factors such as the accepted gap of the pedestrian's decision on when to start crossing, the desired speed of the pedestrian, and the effect of the vehicle on the pedestrian while the pedestrian is crossing the road. Vehicle driving strategies focus on the longitudinal motion control, for which the feedback obstacle avoidance control and the model predictive control were tested and compared in the framework. The simulation results verified that the proposed framework can generate a variety of VPI scenarios, consisting of either the pedestrian yielding to the vehicle or the vehicle yielding to the pedestrian. The framework can be easily extended to apply different approaches to the VPI problems.

Automated driving in urban settings is challenging. Human participant behavior is difficult to model, and conventional, rule-based Automated Driving Systems (ADSs) tend to fail when they face unmodeled dynamics. On the other hand, the more recent, end-to-end Deep Reinforcement Learning (DRL) based model-free ADSs have shown promising results. However, pure learning-based approaches lack the hard-coded safety measures of model-based controllers. Here we propose a hybrid approach for integrating a path planning pipe into a vision based DRL framework to alleviate the shortcomings of both worlds. In summary, the DRL agent is trained to follow the path planner's waypoints as close as possible. The agent learns this policy by interacting with the environment. The reward function contains two major terms: the penalty of straying away from the path planner and the penalty of having a collision. The latter has precedence in the form of having a significantly greater numerical value. Experimental results show that the proposed method can plan its path and navigate between randomly chosen origin-destination points in CARLA, a dynamic urban simulation environment. Our code is open-source and available online.

This research presents a novel framework for automated fault detection in cyber-physical systems, with specific focus on large-scale vehicle networks. Agents in a network develop system identification models of themselves which are sent to a local or global authority. The authority excites the system models and generates a fixed-size vector for each one using an echo state network coupled with an autoencoder. The resultant vectors are grouped using standard clustering algorithms, with each group representing similar system model responses. A human expert labels each group once, so that any new group members can be can be associated with the group label. The largest group is assumed to be operating nominally, with all other groups representing a fault or off-nominal operation. We apply our framework to a detailed vehicle cooling system model to demonstrate its efficacy.

Predicting the collective motion of a group of pedestrians (a crowd) under the vehicle influence is essential for the development of autonomous vehicles to deal with mixed urban scenarios where interpersonal interaction and vehicle-crowd interaction (VCI) are significant. This usually requires a model that can describe individual pedestrian motion under the influence of nearby pedestrians and the vehicle. This study proposed two pedestrian trajectory datasets, CITR dataset and DUT dataset, so that the pedestrian motion models can be further calibrated and verified, especially when vehicle influence on pedestrians plays an important role. CITR dataset consists of experimentally designed fundamental VCI scenarios (front, back, and lateral VCIs) and provides unique ID for each pedestrian, which is suitable for exploring a specific aspect of VCI. DUT dataset gives two ordinary and natural VCI scenarios in crowded university campus, which can be used for more general purpose VCI exploration. The trajectories of pedestrians, as well as vehicles, were extracted by processing video frames that come from a down-facing camera mounted on a hovering drone as the recording equipment. The final trajectories of pedestrians and vehicles were refined by Kalman filters with linear point-mass model and nonlinear bicycle model, respectively, in which xy-velocity of pedestrians and longitudinal speed and orientation of vehicles were estimated. The statistics of the velocity magnitude distribution demonstrated the validity of the proposed dataset. In total, there are approximate 340 pedestrian trajectories in CITR dataset and 1793 pedestrian trajectories in DUT dataset. The dataset is available at GitHub.

Pedestrian safety is of paramount importance for intelligent transportation systems. This study focuses on the scenarios where pedestrians appear as crowds and interact with moving vehicles in a relatively-free space. Based on social force model (SFM), a vehicle-crowd interaction (VCI) model is pro- posed to describe both the behavior of crowd pedestrians and vehicle. Specifically, a heuristic-based and effective modeling of vehicle influence on pedestrians is designed and incorporated into the crowd-only SFM. Qualitative analysis of systematic simulations of various VCI scenarios demonstrates the effective- ness of the proposed model. This model can effectively describe the VCI scenarios such as vehicle approaching from different directions, vehicle zigzagging, and vehicle sharply turning.

The IEEE 802.11p, 1609.3, and 1609.4 WAVE standards are designed to facilitate intervehicle communication and ultimately improve traffic safety. Multiple safety applications and control algorithms have been proposed to use 802.11p Dedicated Short-Range Communication (DSRC) radios and message structures. An urban environment provides many challenges for vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. These include multiple propagation paths and many occlusions, particularly in areas where V2V messages would be most useful such as blind spots, buildings, and other obstructions. The dense urban environments and high concentration of vehicles make it difficult to predict how reliable this communication will be. The Ohio State University's Vehicle and Traffic Simulator (VaTSim) is designed as a microsimulator of traffic. This paper describes the incorporation of V2V communication into VaTSim using Network Simulator 3 (NS3) and physical layer modeling to determine how different road layouts and building configurations will affect 802.11p communication. This paper explains the theory used to define the simulated line-of-sight (LOS) propagation, non-LOS (NLOS) propagation calculations, channel switching congestion, and the experiments performed to validate the models and the simulation.

This paper presents the cooperative adaptive cruise control implementation of Team Mekar at the Grand Cooperative Driving Challenge (GCDC). The Team Mekar vehicle used a dSpace microautobox for access to the vehicle controller area network bus and for control of the autonomous throttle intervention and the electric-motor-operated brake pedal. The vehicle was equipped with real-time kinematic Global Positioning System (RTK GPS) and an IEEE 802.11p modem installed in an onboard computer for vehicle-to-vehicle (V2V) communication. The Team Mekar vehicle did not have an original-equipment-manufacturer-supplied adaptive cruise control (ACC). ACC/Cooperative adaptive cruise control (CACC) based on V2V-communicated GPS position/velocity and preceding vehicle acceleration feedforward were implemented in the Team Mekar vehicle. This paper presents experimental and simulation results of the Team Mekar CACC implementation, along with a discussion of the problems encountered during the GCDC cooperative mobility runs.

In this paper, we review technologies for autonomous ground vehicles and their present capabilities in research and in the automotive market. We outline technology requirements for enhanced functions and for infrastructure development. Since the recent Grand Challenge competition is a major force to advance technology in this field, we specifically refer to our experiences in developing a participating vehicle. We present a multisensor platform that has been proven in an off-road environment. It combines different sensing modalities that inherently yield uncertain information. Finite-state machines are formulated to generate rule-based autonomous behavior that enables fully autonomous off-road driving. Overall, the intent of the paper is to evaluate approaches and technologies used in the two Grand Challenges as they contribute to the needs of autonomous cars on the road

The primary focus of study in this paper is the background control theory for automated lane change maneuvers. We provide an analytic approach for the systematic development of controllers that will cause an autonomous vehicle to accomplish a smooth lane change suitable for use in an Automated Highway System. The design is motivated by the discontinuous availability of valid preview data from the sensing systems during lane-to-lane transitions. The task is accomplished by the generation of a virtual yaw reference and the utilization of a robust switching controller to generate steering commands that cause the vehicle to track that reference. In this way, the open loop lane change problem is converted into an equivalent virtual reference trajectory tracking problem. The approach considers optimality in elapsed time at an operating longitudinal velocity. Although the analysis is performed assuming that the road is straight, the generalization of the proposed algorithm to arbitrary road segments is rather straightforward. The outlined lane change algorithm has been implemented and tested on The Ohio State University test vehicles. Some of the experimental results are presented at the conclusion of this paper.