Autonomous vehicles (AV) offer a cost-effective solution for scientific missions such as underwater tracking. Recently, reinforcement learning (RL) has emerged as a powerful method for controlling AVs in complex marine environments. However, scaling these techniques to a fleet--essential for multi-target tracking or targets with rapid, unpredictable motion--presents significant computational challenges. Multi-Agent Reinforcement Learning (MARL) is notoriously sample-inefficient, and while high-fidelity simulators like Gazebo's LRAUV provide 100x faster-than-real-time single-robot simulations, they offer no significant speedup for multi-vehicle scenarios, making MARL training impractical. To address these limitations, we propose an iterative distillation method that transfers high-fidelity simulations into a simplified, GPU-accelerated environment while preserving high-level dynamics. This approach achieves up to a 30,000x speedup over Gazebo through parallelization, enabling efficient training via end-to-end GPU acceleration. Additionally, we introduce a novel Transformer-based architecture (TransfMAPPO) that learns multi-agent policies invariant to the number of agents and targets, significantly improving sample efficiency. Following large-scale curriculum learning conducted entirely on GPU, we perform extensive evaluations in Gazebo, demonstrating that our method maintains tracking errors below 5 meters over extended durations, even in the presence of multiple fast-moving targets. This work bridges the gap between large-scale MARL training and high-fidelity deployment, providing a scalable framework for autonomous fleet control in real-world sea missions.
Connected Autonomous Vehicles (CAVs) operate in dynamic, open, and multi-domain networks, rendering them vulnerable to various threats. Trust Management Systems (TMS) systematically organize essential steps in the trust mechanism, identifying malicious nodes against internal threats and external threats, as well as ensuring reliable decision-making for more cooperative tasks. Recent advances in machine learning (ML) offer significant potential to enhance TMS, especially for the strict requirements of CAVs, such as CAV nodes moving at varying speeds, and opportunistic and intermittent network behavior. Those features distinguish ML-based TMS from social networks, static IoT, and Social IoT. This survey proposes a novel three-layer ML-based TMS framework for CAVs in the vehicle-road-cloud integration system, i.e., trust data layer, trust calculation layer and trust incentive layer. A six-dimensional taxonomy of objectives is proposed. Furthermore, the principles of ML methods for each module in each layer are analyzed. Then, recent studies are categorized based on traffic scenarios that are against the proposed objectives. Finally, future directions are suggested, addressing the open issues and meeting the research trend. We maintain an active repository that contains up-to-date literature and open-source projects at https://github.com/octoberzzzzz/ML-based-TMS-CAV-Survey.
The potential to improve road safety, reduce human driving error, and promote environmental sustainability have enabled the field of autonomous driving to progress rapidly over recent decades. The performance of autonomous vehicles has significantly improved thanks to advancements in Artificial Intelligence, particularly Deep Learning. Nevertheless, the opacity of their decision-making, rooted in the use of accurate yet complex AI models, has created barriers to their societal trust and regulatory acceptance, raising the need for explainability. We propose a post-hoc, model-agnostic solution to provide teleological explanations for the behaviour of an autonomous vehicle in urban environments. Building on Intention-aware Policy Graphs, our approach enables the extraction of interpretable and reliable explanations of vehicle behaviour in the nuScenes dataset from global and local perspectives. We demonstrate the potential of these explanations to assess whether the vehicle operates within acceptable legal boundaries and to identify possible vulnerabilities in autonomous driving datasets and models.
This paper quantitatively investigates the crash severity of Autonomous Vehicles (AVs) with spatially localized machine learning and macroscopic measures of the urban built environment. We address spatial heterogeneity and spatial autocorrelation, while focusing on land use patterns and human behavior. Our Geographical Random Forest (GRF) model, accompanied with a crash severity risk map of San Francisco, presents three findings that are useful for commercial operations of AVs and robotaxis. First, spatially localized machine learning performed better than regular machine learning, when predicting AV crash severity. Bias-variance tradeoff was evident as we adjust the localization weight hyperparameter. Second, land use was the most important built environment measure, compared to intersections, building footprints, public transit stops, and Points Of Interests (POIs). Third, it was predicted that city center areas with greater diversity and commercial activities were more likely to result in low-severity AV crashes, than residential neighborhoods. Residential land use may be associated with higher severity due to human behavior and less restrictive environment. This paper recommends to explicitly consider geographic locations, and to design safety measures specific to residential neighborhoods, when robotaxi operators train their AV systems.
As Cellular Vehicle-to-Everything (C-V2X) evolves towards future sixth-generation (6G) networks, Connected Autonomous Vehicles (CAVs) are emerging to become a key application. Leveraging data-driven Machine Learning (ML), especially Deep Reinforcement Learning (DRL), is expected to significantly enhance CAV decision-making in both vehicle control and V2X communication under uncertainty. These two decision-making processes are closely intertwined, with the value of information (VoI) acting as a crucial bridge between them. In this paper, we introduce Sequential Stochastic Decision Process (SSDP) models to define and assess VoI, demonstrating their application in optimizing communication systems for CAVs. Specifically, we formally define the SSDP model and demonstrate that the MDP model is a special case of it. The SSDP model offers a key advantage by explicitly representing the set of information that can enhance decision-making when available. Furthermore, as current research on VoI remains fragmented, we propose a systematic VoI modeling framework grounded in the MDP, Reinforcement Learning (RL) and Optimal Control theories. We define different categories of VoI and discuss their corresponding estimation methods. Finally, we present a structured approach to leverage the various VoI metrics for optimizing the ``When", ``What", and ``How" to communicate problems. For this purpose, SSDP models are formulated with VoI-associated reward functions derived from VoI-based optimization objectives. While we use a simple vehicle-following control problem to illustrate the proposed methodology, it holds significant potential to facilitate the joint optimization of stochastic, sequential control and communication decisions in a wide range of networked control systems.
Improving end-users' understanding of decisions made by autonomous vehicles (AVs) driven by artificial intelligence (AI) can improve utilization and acceptance of AVs. However, current explanation mechanisms primarily help AI researchers and engineers in debugging and monitoring their AI systems, and may not address the specific questions of end-users, such as passengers, about AVs in various scenarios. In this paper, we conducted two user studies to investigate questions that potential AV passengers might pose while riding in an AV and evaluate how well answers to those questions improve their understanding of AI-driven AV decisions. Our initial formative study identified a range of questions about AI in autonomous driving that existing explanation mechanisms do not readily address. Our second study demonstrated that interactive text-based explanations effectively improved participants' comprehension of AV decisions compared to simply observing AV decisions. These findings inform the design of interactions that motivate end-users to engage with and inquire about the reasoning behind AI-driven AV decisions.
With the advancement of large language models and embodied Artificial Intelligence (AI) in the intelligent transportation scenarios, the combination of them in intelligent transportation spawns the Vehicular Embodied AI Network (VEANs). In VEANs, Autonomous Vehicles (AVs) are typical agents whose local advanced AI applications are defined as vehicular embodied AI agents, enabling capabilities such as environment perception and multi-agent collaboration. Due to computation latency and resource constraints, the local AI applications and services running on vehicular embodied AI agents need to be migrated, and subsequently referred to as vehicular embodied AI agent twins, which drive the advancement of vehicular embodied AI networks to offload intensive tasks to Roadside Units (RSUs), mitigating latency problems while maintaining service quality. Recognizing workload imbalance among RSUs in traditional approaches, we model AV-RSU interactions as a Stackelberg game to optimize bandwidth resource allocation for efficient migration. A Tiny Multi-Agent Bidirectional LSTM Proximal Policy Optimization (TMABLPPO) algorithm is designed to approximate the Stackelberg equilibrium through decentralized coordination. Furthermore, a personalized neural network pruning algorithm based on Path eXclusion (PX) dynamically adapts to heterogeneous AV computation capabilities by identifying task-critical parameters in trained models, reducing model complexity with less performance degradation. Experimental validation confirms the algorithm's effectiveness in balancing system load and minimizing delays, demonstrating significant improvements in vehicular embodied AI agent deployment.
Lane-changing (LC) behavior, a critical yet complex driving maneuver, significantly influences driving safety and traffic dynamics. Traditional analytical LC decision (LCD) models, while effective in specific environments, often oversimplify behavioral heterogeneity and complex interactions, limiting their capacity to capture real LCD. Data-driven approaches address these gaps by leveraging rich empirical data and machine learning to decode latent decision-making patterns, enabling adaptive LCD modeling in dynamic environments. In light of the rapid development of artificial intelligence and the demand for data-driven models oriented towards connected vehicles and autonomous vehicles, this paper presents a comprehensive survey of data-driven LCD models, with a particular focus on human drivers LC decision-making. It systematically reviews the modeling framework, covering data sources and preprocessing, model inputs and outputs, objectives, structures, and validation methods. This survey further discusses the opportunities and challenges faced by data-driven LCD models, including driving safety, uncertainty, as well as the integration and improvement of technical frameworks.
Autonomous Vehicles (AV) proliferation brings important and pressing security and reliability issues that must be dealt with to guarantee public safety and help their widespread adoption. The contribution of the proposed research is towards achieving more secure, reliable, and trustworthy autonomous transportation system by providing more capabilities for anomaly detection, data provenance, and real-time response in safety critical AV deployments. In this research, we develop a new framework that combines the power of Artificial Intelligence (AI) for real-time anomaly detection with blockchain technology to detect and prevent any malicious activity including sensor failures in AVs. Through Long Short-Term Memory (LSTM) networks, our approach continually monitors associated multi-sensor data streams to detect anomalous patterns that may represent cyberattacks as well as hardware malfunctions. Further, this framework employs a decentralized platform for securely storing sensor data and anomaly alerts in a blockchain ledger for data incorruptibility and authenticity, while offering transparent forensic features. Moreover, immediate automated response mechanisms are deployed using smart contracts when anomalies are found. This makes the AV system more resilient to attacks from both cyberspace and hardware component failure. Besides, we identify potential challenges of scalability in handling high frequency sensor data, computational constraint in resource constrained environment, and of distributed data storage in terms of privacy.
Trajectory prediction is a key element of autonomous vehicle systems, enabling them to anticipate and react to the movements of other road users. Evaluating the robustness of prediction models against adversarial attacks is essential to ensure their reliability in real-world traffic. However, current approaches tend to focus on perturbing the past positions of surrounding agents, which can generate unrealistic scenarios and overlook critical vulnerabilities. This limitation may result in overly optimistic assessments of model performance in real-world conditions. In this work, we demonstrate that perturbing not just past but also future states of adversarial agents can uncover previously undetected weaknesses and thereby provide a more rigorous evaluation of model robustness. Our novel approach incorporates dynamic constraints and preserves tactical behaviors, enabling more effective and realistic adversarial attacks. We introduce new performance measures to assess the realism and impact of these adversarial trajectories. Testing our method on a state-of-the-art prediction model revealed significant increases in prediction errors and collision rates under adversarial conditions. Qualitative analysis further showed that our attacks can expose critical weaknesses, such as the inability of the model to detect potential collisions in what appear to be safe predictions. These results underscore the need for more comprehensive adversarial testing to better evaluate and improve the reliability of trajectory prediction models for autonomous vehicles.
Autonomous vehicle perception systems have traditionally relied on costly LiDAR sensors to generate precise environmental representations. In this paper, we propose a camera-only perception framework that produces Bird's Eye View (BEV) maps by extending the Lift-Splat-Shoot architecture. Our method combines YOLOv11-based object detection with DepthAnythingV2 monocular depth estimation across multi-camera inputs to achieve comprehensive 360-degree scene understanding. We evaluate our approach on the OpenLane-V2 and NuScenes datasets, achieving up to 85% road segmentation accuracy and 85-90% vehicle detection rates when compared against LiDAR ground truth, with average positional errors limited to 1.2 meters. These results highlight the potential of deep learning to extract rich spatial information using only camera inputs, enabling cost-efficient autonomous navigation without sacrificing accuracy.
Vision-Language-Action (VLA) models mark a transformative advancement in artificial intelligence, aiming to unify perception, natural language understanding, and embodied action within a single computational framework. This foundational review presents a comprehensive synthesis of recent advancements in Vision-Language-Action models, systematically organized across five thematic pillars that structure the landscape of this rapidly evolving field. We begin by establishing the conceptual foundations of VLA systems, tracing their evolution from cross-modal learning architectures to generalist agents that tightly integrate vision-language models (VLMs), action planners, and hierarchical controllers. Our methodology adopts a rigorous literature review framework, covering over 80 VLA models published in the past three years. Key progress areas include architectural innovations, parameter-efficient training strategies, and real-time inference accelerations. We explore diverse application domains such as humanoid robotics, autonomous vehicles, medical and industrial robotics, precision agriculture, and augmented reality navigation. The review further addresses major challenges across real-time control, multimodal action representation, system scalability, generalization to unseen tasks, and ethical deployment risks. Drawing from the state-of-the-art, we propose targeted solutions including agentic AI adaptation, cross-embodiment generalization, and unified neuro-symbolic planning. In our forward-looking discussion, we outline a future roadmap where VLA models, VLMs, and agentic AI converge to power socially aligned, adaptive, and general-purpose embodied agents. This work serves as a foundational reference for advancing intelligent, real-world robotics and artificial general intelligence. >Vision-language-action, Agentic AI, AI Agents, Vision-language Models
Human drivers exhibit individual preferences regarding driving style. Adapting autonomous vehicles to these preferences is essential for user trust and satisfaction. However, existing end-to-end driving approaches often rely on predefined driving styles or require continuous user feedback for adaptation, limiting their ability to support dynamic, context-dependent preferences. We propose a novel approach using multi-objective reinforcement learning (MORL) with preference-driven optimization for end-to-end autonomous driving that enables runtime adaptation to driving style preferences. Preferences are encoded as continuous weight vectors to modulate behavior along interpretable style objectives$\unicode{x2013}$including efficiency, comfort, speed, and aggressiveness$\unicode{x2013}$without requiring policy retraining. Our single-policy agent integrates vision-based perception in complex mixed-traffic scenarios and is evaluated in diverse urban environments using the CARLA simulator. Experimental results demonstrate that the agent dynamically adapts its driving behavior according to changing preferences while maintaining performance in terms of collision avoidance and route completion.
The safety of autonomous cars has come under scrutiny in recent years, especially after 16 documented incidents involving Teslas (with autopilot engaged) crashing into parked emergency vehicles (police cars, ambulances, and firetrucks). While previous studies have revealed that strong light sources often introduce flare artifacts in the captured image, which degrade the image quality, the impact of flare on object detection performance remains unclear. In this research, we unveil PaniCar, a digital phenomenon that causes an object detector's confidence score to fluctuate below detection thresholds when exposed to activated emergency vehicle lighting. This vulnerability poses a significant safety risk, and can cause autonomous vehicles to fail to detect objects near emergency vehicles. In addition, this vulnerability could be exploited by adversaries to compromise the security of advanced driving assistance systems (ADASs). We assess seven commercial ADASs (Tesla Model 3, "manufacturer C", HP, Pelsee, AZDOME, Imagebon, Rexing), four object detectors (YOLO, SSD, RetinaNet, Faster R-CNN), and 14 patterns of emergency vehicle lighting to understand the influence of various technical and environmental factors. We also evaluate four SOTA flare removal methods and show that their performance and latency are insufficient for real-time driving constraints. To mitigate this risk, we propose Caracetamol, a robust framework designed to enhance the resilience of object detectors against the effects of activated emergency vehicle lighting. Our evaluation shows that on YOLOv3 and Faster RCNN, Caracetamol improves the models' average confidence of car detection by 0.20, the lower confidence bound by 0.33, and reduces the fluctuation range by 0.33. In addition, Caracetamol is capable of processing frames at a rate of between 30-50 FPS, enabling real-time ADAS car detection.
Despite the impressive achievements of AI, including advancements in generative models and large language models, there remains a significant gap in the ability of AI to handle uncertainty and generalize beyond the training data. We argue that AI models, especially in autonomous systems, fail to make robust predictions when faced with unfamiliar or adversarial data, as evidenced by incidents with autonomous vehicles. Traditional machine learning approaches struggle to address these issues due to an overemphasis on data fitting and domain adaptation. This position paper posits a paradigm shift towards epistemic artificial intelligence, emphasizing the need for models to learn not only from what they know but also from their ignorance. This approach, which focuses on recognizing and managing uncertainty, offers a potential solution to improve the resilience and robustness of AI systems, ensuring that they can better handle unpredictable real-world environments.
As a safety-critical cyber-physical system, cybersecurity and related safety issues for Autonomous Vehicles (AVs) have been important research topics for a while. Among all the modules on AVs, perception is one of the most accessible attack surfaces, as drivers and AVs have no control over the outside environment. Most current work targeting perception security for AVs focuses on perception correctness. In this work, we propose an impact analysis based on inference time attacks for autonomous vehicles. We demonstrate in a simulation system that such inference time attacks can also threaten the safety of both the ego vehicle and other traffic participants.
Cyber-Physical Systems (CPS) are abundant in safety-critical domains such as healthcare, avionics, and autonomous vehicles. Formal verification of their operational safety is, therefore, of utmost importance. In this paper, we address the falsification problem, where the focus is on searching for an unsafe execution in the system instead of proving their absence. The contribution of this paper is a framework that (a) connects the falsification of CPS with the falsification of deep neural networks (DNNs) and (b) leverages the inherent interpretability of Decision Trees for faster falsification of CPS. This is achieved by: (1) building a surrogate model of the CPS under test, either as a DNN model or a Decision Tree, (2) application of various DNN falsification tools to falsify CPS, and (3) a novel falsification algorithm guided by the explanations of safety violations of the CPS model extracted from its Decision Tree surrogate. The proposed framework has the potential to exploit a repertoire of \emph{adversarial attack} algorithms designed to falsify robustness properties of DNNs, as well as state-of-the-art falsification algorithms for DNNs. Although the presented methodology is applicable to systems that can be executed/simulated in general, we demonstrate its effectiveness, particularly in CPS. We show that our framework, implemented as a tool \textsc{FlexiFal}, can detect hard-to-find counterexamples in CPS that have linear and non-linear dynamics. Decision tree-guided falsification shows promising results in efficiently finding multiple counterexamples in the ARCH-COMP 2024 falsification benchmarks~\cite{khandait2024arch}.
Vehicle platooning has been a promising solution for improving traffic efficiency and throughput. However, a failure in a single vehicle, including communication loss with neighboring vehicles, can significantly disrupt platoon performance and potentially trigger cascading effects. Similar to modern autonomous vehicles, platoon systems require human drivers to take control during failures, leading to scenarios where vehicles are operated by drivers with diverse driving styles. This paper presents a novel multi-model approach for simultaneously identifying signal drop locations and driver attitudes in vehicular platoons using only tail vehicle measurements. The proposed method distinguishes between attentive and distracted driver behaviors by analyzing the propagation patterns of disturbances through the platoon system. Beyond its application in platooning, our methodology for detecting driver behavior using a multi-model approach provides a novel framework for human driver identification. To enhance computational efficiency for real-time applications, we introduce a blending-based identification method utilizing chosen models and weighted interpolation, significantly reducing the number of required models while maintaining detection accuracy. The effectiveness of our approach is validated through high-fidelity CarSim/Simulink environment simulations. Results demonstrate that the proposed method can accurately identify both the location of signal drops and the corresponding driver behavior. This approach minimizes the complexity and cost of fault detection while ensuring accuracy and reliability.
Autonomous Vehicles (AVs) require precise lane and object detection to ensure safe navigation. However, centralized deep learning (DL) approaches for semantic segmentation raise privacy and scalability challenges, particularly when handling sensitive data. This research presents a new federated learning (FL) framework that integrates secure deep Convolutional Neural Networks (CNNs) and Differential Privacy (DP) to address these issues. The core contribution of this work involves: (1) developing a new hybrid UNet-ResNet34 architecture for centralized semantic segmentation to achieve high accuracy and tackle privacy concerns due to centralized training, and (2) implementing the privacy-preserving FL model, distributed across AVs to enhance performance through secure CNNs and DP mechanisms. In the proposed FL framework, the methodology distinguishes itself from the existing approach through the following: (a) ensuring data decentralization through FL to uphold user privacy by eliminating the need for centralized data aggregation, (b) integrating DP mechanisms to secure sensitive model updates against potential adversarial inference attacks, and (c) evaluating the frameworks performance and generalizability using RGB and semantic segmentation datasets derived from the CARLA simulator. Experimental results show significant improvements in accuracy, from 81.5% to 88.7% for the RGB dataset and from 79.3% to 86.9% for the SEG dataset over 20 to 70 Communication Rounds (CRs). Global loss was reduced by over 60%, and minor accuracy trade-offs from DP were observed. This study contributes by offering a scalable, privacy-preserving FL framework tailored for AVs, optimizing communication efficiency while balancing performance and data security.
Since the emergence of autonomous driving technology, it has advanced rapidly over the past decade. It is becoming increasingly likely that autonomous vehicles (AVs) would soon coexist with human-driven vehicles (HVs) on the roads. Currently, safety and reliable decision-making remain significant challenges, particularly when AVs are navigating lane changes and interacting with surrounding HVs. Therefore, precise estimation of the intentions of surrounding HVs can assist AVs in making more reliable and safe lane change decision-making. This involves not only understanding their current behaviors but also predicting their future motions without any direct communication. However, distinguishing between the passing and yielding intentions of surrounding HVs still remains ambiguous. To address the challenge, we propose a social intention estimation algorithm rooted in Directed Acyclic Graph (DAG), coupled with a decision-making framework employing Deep Reinforcement Learning (DRL) algorithms. To evaluate the method's performance, the proposed framework can be tested and applied in a lane-changing scenario within a simulated environment. Furthermore, the experiment results demonstrate how our approach enhances the ability of AVs to navigate lane changes safely and efficiently on roads.