Urban intersections with diverse vehicle types, from small cars to large semi-trailers, pose significant challenges for traffic control. This study explores how robot vehicles (RVs) can enhance heterogeneous traffic flow, particularly at unsignalized intersections where traditional methods fail during power outages. Using reinforcement learning (RL) and real-world data, we simulate mixed traffic at complex intersections with RV penetration rates ranging from 10% to 90%. Results show that average waiting times drop by up to 86% and 91% compared to signalized and unsignalized intersections, respectively. We observe a "rarity advantage," where less frequent vehicles benefit the most (up to 87%). Although CO2emissions and fuel consumption increase with RV penetration, they remain well below those of traditional signalized traffic. Decreased space headways also indicate more efficient road usage. These findings highlight RVs’ potential to improve traffic efficiency and reduce environmental impact in complex, heterogeneous settings.

Traffic congestion remains a significant challenge in modern urban networks. Autonomous driving technologies have emerged as a potential solution. Among traffic control methods, reinforcement learning has shown superior performance over traffic signals in various scenarios. However, prior research has largely focused on small-scale networks or isolated intersections, leaving large-scale mixed traffic control largely unexplored. This study presents the first attempt to use decentralized multi-agent reinforcement learning for large-scale mixed traffic control in which some intersections are managed by traffic signals and others by robot vehicles. Evaluating a real-world network in Colorado Springs, CO, USA with 14 intersections, we measure traffic efficiency via average waiting time of vehicles at intersections and the number of vehicles reaching their destinations within a time window (i.e., throughput). At 80% RV penetration rate, our method reduces waiting time from 6.17 s to 5.09 s and increases throughput from 454 vehicles per 500 seconds to 493 vehicles per 500 seconds, outperforming the baseline of fully signalized intersections. These findings suggest that integrating reinforcement learning-based control large-scale traffic can improve overall efficiency and may inform future urban planning strategies.

This paper proposes a new control algorithm for human-robot co-transportation using a robot manipulator equipped with a mobile base and a robotic arm. We integrate the regular Model Predictive Control (MPC) with a novel pose optimization mechanism to more efficiently mitigate disturbances (such as human behavioral uncertainties or robot actuation noise) during the task. The core of our methodology involves a two-step iterative design: At each planning horizon, we determine the optimal pose of the robotic arm (joint angle configuration) from a candidate set, aiming to achieve the lowest estimated control cost. This selection is based on solving a disturbance-aware Discrete Algebraic Riccati Equation (DARE), which also determines the optimal inputs for the robot’s whole body control (including both the mobile base and the robotic arm). To validate the effectiveness of the proposed approach, we provide theoretical derivation for the disturbance-aware DARE and perform simulated experiments and hardware demos using a Fetch robot under varying conditions, including different trajectories and different levels of disturbances. The results reveal that our proposed approach outperforms baseline algorithms.

Reinforcement learning (RL) holds significant promise for adaptive traffic signal control. While existing RL-based methods demonstrate effectiveness in reducing vehicular congestion, their predominant focus on vehicle-centric optimization leaves pedestrian mobility needs and safety challenges unaddressed. In this paper, we present a deep RL framework for adaptive control of eight traffic signals along a real-world urban corridor, jointly optimizing both pedestrian and vehicular efficiency. Our single-agent policy is trained using real-world pedestrian and vehicle demand data derived from Wi-Fi logs and video analysis. The results demonstrate significant performance improvements over traditional fixed-time signals, reducing average wait times per pedestrian and per vehicle by up to 67% and 52% respectively, while simultaneously decreasing total wait times for both groups by up to 67% and 53%. Additionally, our results demonstrate generalization capabilities across varying traffic demands, including conditions entirely unseen during training, validating RL’s potential for developing transportation systems that serve all road users.

Accurate vehicle trajectory prediction is critical for safe and efficient autonomous driving, especially in mixed traffic environments when both human-driven and autonomous vehicles co-exist. However, uncertainties introduced by inherent driving behaviors—such as acceleration, deceleration, and left and right maneuvers—pose significant challenges for reliable trajectory prediction. We introduce a Maneuver-Intention-Aware Transformer (MIAT) architecture, which integrates a maneuver intention awareness control mechanism with spatiotemporal interaction modeling to enhance long-horizon trajectory predictions. We systematically investigate the impact of varying awareness of maneuver intention on both short-and long-horizon trajectory predictions. Evaluated on the real-world NGSIM dataset and benchmarked against various transformer- and LSTM-based methods, our approach achieves an improvement of up to 4.7% in short-horizon predictions and a 1.6% in long-horizon predictions compared to other intention-aware benchmark methods. Moreover, by leveraging intention awareness control mechanism, MIAT realizes an 11.1% performance boost in long-horizon predictions, with a modest drop in short-horizon performance. The source code and datasets are available at https://github.com/cpraskoti/MIAT.

Extreme weather and infrastructure vulnerabilities pose significant challenges to urban mobility, particularly at intersections where signals become inoperative. To address this growing concern, we introduce Beacon, a naturalistic driving dataset capturing traffic dynamics during blackouts at two major intersections in Memphis, TN, USA. The dataset provides detailed traffic movements, including timesteps, origin, and destination lanes for each vehicle over four hours of peak periods. We analyze traffic demand, vehicle trajectories, and density across different scenarios, demonstrating high-fidelity reconstruction under unsignalized, signalized, and mixed traffic conditions. We find that integrating robot vehicles (RVs) into traffic flow can substantially reduce intersection delays, with wait time improvements of up to 82.6%. However, this enhanced traffic efficiency comes with varying environmental impacts, as decreased vehicle idling may lead to higher overall CO2emissions. To the best of our knowledge, Beacon is the first publicly available traffic dataset for naturalistic driving behaviors during blackouts at intersections.

This paper presents a novel robust online calibration framework for Ultra-Wideband (UWB) anchors in UWB-aided Visual-Inertial Navigation Systems (VINS). Accurate anchor positioning, a process known as calibration, is crucial for integrating UWB ranging measurements into state estimation. While several prior works have demonstrated satisfactory results by using robot-aided systems to autonomously calibrate UWB systems, there are still some limitations: 1) these approaches assume accurate robot localization during the initialization step, ignoring localization errors that can compromise calibration robustness, and 2) the calibration results are highly sensitive to the initial guess of the UWB anchors’ positions, reducing the practical applicability of these methods in real-world scenarios. Our approach addresses these challenges by explicitly incorporating the impact of robot localization uncertainties into the calibration process, ensuring robust initialization. To further enhance the robustness of the calibration results against initialization errors, we propose a tightly-coupled Schmidt Kalman Filter (SKF)-based online refinement method, making the system suitable for practical applications. Simulations and real-world experiments validate the improved accuracy and robustness of our approach.

We address the challenge of achieving flocking behavior in swarm robotic systems without compromising the privacy of individual robots’ aggregation capabilities. Traditional flocking algorithms are susceptible to privacy breaches, as adversaries can deduce the identity and aggregation abilities of robots by observing their movements. We introduce a novel control mechanism for privacy-preserving flocking, leveraging the Laplace mechanism within the framework of differential privacy. Our method mitigates privacy breaches by introducing a controlled level of noise, thus obscuring sensitive information. We explore the trade-off between privacy and utility by varying the differential privacy parameter$\epsilon$. Our quantitative analysis reveals that$\epsilon \leq 0.13$represents a lower threshold where private information is almost completely protected, whereas$\epsilon \geq 0.85$marks an upper threshold where private information cannot be protected at all. Empirical results validate that our approach effectively maintains privacy of the robots’ aggregation abilities throughout the flocking process.Note to Practitioners—This paper was motivated by the problem of preserving privacy of individual robots in a swarm robotic system. Existing approaches to address this issue generally consider that accomplishing complex tasks requiring explicit information sharing between robots, while explicit communication in public channel carries the risk of information leakage. It is not always like this in real adversarial environments, and this assumption restricts the investigation of privacy in autonomous systems. This paper suggests that an individual robot can use its sensors onboard to perceive states of other neighbors in a distributed way without explicit communication. Despite avoiding information leakage during explicit information sharing between robots, the configuration of swarm can still reveal sensitive information about the ability of each robot. In this paper, we propose a privacy-preserving approach for flocking control using the Laplace mechanism based on the concept of differential privacy. The solution prevents an adversary with full knowledge of the swarm’s configuration from learning the sensitive information of individual robots, thus ensuring the security of swarm robots in terms of sensitive information during ongoing missions.

Microscopic traffic simulation plays a crucial role in transportation engineering by providing insights into in-dividual vehicle behavior and overall traffic flow. How-ever, creating a realistic simulator that accurately repli-cates human driving behaviors in various traffic conditions presents significant challenges. Traditional simulators relying on heuristic models often fail to deliver accurate simulations due to the complexity of real-world traffic environments. Due to the covariate shift issue, existing imitation learning-based simulators often fail to generate stable long-term simulations. In this paper, we propose a novel approach called learner-aware supervised imitation learning to address the covariate shift problem in multi-agent imi-tation learning. By leveraging a variational autoencoder simultaneously modeling the expert and learner state distribution, our approach augments expert states such that the augmented state is aware of learner state distribution. Our method, applied to urban traffic simulation, demon-strates significant improvements over existing state-of-the-art baselines in both short-term microscopic and long-term macroscopic realism when evaluated on the real-world dataset pNEUMA.

Traffic congestion is a persistent problem in our society. Previous methods for traffic control have proven futile in alleviating current congestion levels leading researchers to explore ideas with robot vehicles given the increased emergence of vehicles with different levels of autonomy on our roads. This gives rise to mixed traffic control, where robot vehicles regulate human-driven vehicles through reinforcement learning (RL). However, most existing studies use precise observations that require domain expertise and hand engineering for each road network’s observation space. Additionally, precise observations use global information, such as environment outflow, and local information, i.e., vehicle positions and velocities. Obtaining this information requires updating existing road infrastructure with vast sensor environments and communication to potentially unwilling human drivers. We consider image observations, a modality that has not been extensively explored for mixed traffic control via RL, as the alternative: 1) images do not require a complete re-imagination of the observation space from environment to environment; 2) images are ubiquitous through satellite imagery, in-car camera systems, and traffic monitoring systems; and 3) images only require communication to equipment. In this work, we show robot vehicles using image observations can achieve competitive performance to using precise information on environments, including ring, figure eight, intersection, merge, and bottleneck. In certain scenarios, our approach even outperforms using precision observations, e.g., up to 8% increase in average vehicle velocity in the merge environment, despite only using local traffic information as opposed to global traffic information.

Human-driven vehicles (HVs) amplify naturally occurring perturbations in traffic, leading to congestion – a major contributor to increased fuel consumption, higher collision risks, and reduced road capacity utilization. While previous research demonstrates that Robot Vehicles (RVs) can be leveraged to mitigate these issues, most such studies rely on simulations with simplistic models of human car-following behaviors. In this work, we analyze real-world driving trajectories and extract a wide range of acceleration profiles. We then incorporates these profiles into simulations for training RVs to mitigate congestion. We evaluate the safety, efficiency, and stability of mixed traffic via comprehensive experiments conducted in two mixed traffic environments (Ring and Bottleneck) at various traffic densities, configurations, and RV penetration rates. The results show that under real-world perturbations, prior RV controllers experience performance degradation on all three objectives (sometimes even lower than 100% HVs). To address this, we introduce a reinforcement learning based RV that employs a congestion stage classifier to optimize the safety, efficiency, and stability of mixed traffic. Our RVs demonstrate significant improvements: safety by up to 66%, efficiency by up to 54%, and stability by up to 97%.

With the growing use of machine learning algorithms and ubiquitous sensors, many ‘perception-to-control’ systems are being developed and deployed. To ensure their trustworthiness, improving their robustness through adversarial training is one potential approach. We propose a gradient-free adversarial training technique, named AutoJoin, to effectively and efficiently produce robust models for image-based maneuvering. Compared to other state-of-the-art methods with testing on over 5M images, AutoJoin achieves significant performance increases up to the 40% range against perturbations while improving on clean performance up to 300%. AutoJoin is also highly efficient, saving up to 86% time per training epoch and 90% training data over other state-of-the-art techniques. The core idea of AutoJoin is to use a decoder attachment to the original regression model creating a denoising autoencoder within the architecture. This architecture allows the tasks ‘maneuvering’ and ‘denoising sensor input’ to be jointly learnt and reinforce each other’s performance.

Controlling and coordinating urban traffic flow through robot vehicles is emerging as a novel transportation paradigm for the future. While this approach garners growing attention from researchers and practitioners, effectively managing and coordinating large-scale mixed traffic remains a challenge. We introduce an effective framework for large-scale mixed traffic control via privacy-preserving crowdsourcing and dynamic vehicle routing. Our framework consists of three modules: a privacy-protecting crowdsensing method, a graph propagation-based traffic forecasting method, and a privacy-preserving route selection mechanism. We evaluate our framework using a real-world road network. The results show that our framework accurately forecasts traffic flow, efficiently mitigates network-wide RV shortage issue, and coordinates large-scale mixed traffic. Compared to other baseline methods, our framework not only reduces the RV shortage issue up to 69.4% but also reduces the average waiting time of all vehicles in the network up to 27%.

Effective and rapid triaging from primary care into secondary care plays a pivotal role in providing patients with timely treatment and managing increasing demands for healthcare resources. Existing triaging methods from primary care to secondary care are labor-intensive processes that involve manually reviewing referral data from multiple sources and can cause long referral to treatment time. There has been no research using machine learning methods that automatically analyzes heterogeneous data including referral letters to recognize regularities to support the primary to secondary care triage. In this paper, we propose a heterogeneous data-driven hybrid machine learning model including Natural Language Processing (NLP) to improve hospital triage efficiency at the point of triage. The proposed model achieved a precision of 0.83, recall of 0.82, F1-Score of 0.83, accuracy of 0.82, AUC of 0.90 in identifying patients with non-inflammatory conditions (NIC) and inflammatory arthritis (IA) at the point of triage with explainable risk stratifications. Our model is piloted in a real-world trial in a large secondary care hospital in the UK to compare referral accuracy and time saved between our model and clinicians, and evaluate its acceptability by users. Our model achieved precision and recall of 0.83 and 0.81, compared with the precision and recall of 0.80 and 0.78 by clinicians. The research also shows that our model enabled decision support can save clinicians 8 h per week in assessing the referral assessment. This paper is the first study to streamline hospital triage from primary care to secondary care using machine learning.

The interconnectedness and interdependence of modern graphs are growing ever more complex, causing enormous resources for processing, storage, communication, and decision-making of these graphs. In this work, we focus on the task of graph sparsification: an edge-reduced graph of a similar structure to the original graph is produced while various user-defined graph metrics are largely preserved. Existing graph sparsification methods are mostly sampling-based, which introduce high computation complexity in general and lack of flexibility for a different reduction objective. We present SparRL, the first generic and effective graph sparsification framework enabled by deep reinforcement learning. SparRL can easily adapt to different reduction goals and promise graph-size-independent complexity. Extensive experiments show that SparRL outperforms all prevailing sparsification methods in producing high-quality sparsified graphs concerning a variety of objectives.

Despite significant advancements, collision-free navigation in autonomous driving is still challenging, considering the navigation module needs to balance learning and planning to achieve efficient and effective control of the vehicle. We propose a novel framework of inverse reinforcement learning with hybrid-weight trust-region optimization and curriculum learning (IRL-HC) for autonomous maneuvering. Our method can incorporate both expert demonstration (from real driving) and domain knowledge (hard constraints such as collision avoidance, goal reaching, etc. encoded in reward functions) to learn an effective control policy. The hybrid-weight trustregion optimization is used to determine the difficulty of the task curriculum for fast incremental curriculum learning and improve the efficiency of inverse reinforcement learning by hybrid weight tuning of different sets of hyperparameters. IRL-HC is also compatible with domain-dependent techniques such as learn-from-accident, which can further boost performance. Overall, IRL-HC can reduce the number of collisions up to 48%, increase the training efficiency by 2.8x, and enable the vehicle to drive 10x further compared to other methods.

We introduce a simple yet effective framework for improving the robustness of learning algorithms against image corruptions for autonomous driving. These corruptions can occur due to both internal (e.g., sensor noises and hardware abnormalities) and external factors (e.g., lighting, weather, visibility, and other environmental effects). Using sensitivity analysis with FID-based parameterization, we propose a novel algorithm exploiting basis perturbations to improve the overall performance of autonomous steering and other image processing tasks, such as classification and detection, for self-driving cars. Our model not only improves the performance on the original dataset, but also achieves significant performance improvement on datasets with multiple and unseen perturbations, up to 87% and 77%, respectively. A comparison between our approach and other SOTA techniques confirms the effectiveness of our technique in improving the robustness of neural network training for learning-based steering and other image processing tasks.

Abstract Virtualized traffic via various simulation models and real‐world traffic data are promising approaches to reconstruct detailed traffic flows. A variety of applications can benefit from the virtual traffic, including, but not limited to, video games, virtual reality, traffic engineering and autonomous driving. In this survey, we provide a comprehensive review on the state‐of‐the‐art techniques for traffic simulation and animation. We start with a discussion on three classes of traffic simulation models applied at different levels of detail. Then, we introduce various data‐driven animation techniques, including existing data collection methods, and the validation and evaluation of simulated traffic flows. Next, we discuss how traffic simulations can benefit the training and testing of autonomous vehicles. Finally, we discuss the current states of traffic simulation and animation and suggest future research directions.

Autonomous driving has gained significant advancements in recent years. However, obtaining a robust control policy for driving remains challenging as it requires training data from a variety of scenarios, including rare situations (e.g., accidents), an effective policy architecture, and an efficient learning mechanism. We propose ADAPS for producing robust control policies for autonomous vehicles. ADAPS consists of two simulation platforms in generating and analyzing accidents to automatically produce labeled training data, and a memoryenabled hierarchical control policy. Additionally, ADAPS offers a more efficient online learning mechanism that reduces the number of iterations required in learning compared to existing methods such as DAGGER [1]. We present both theoretical and experimental results. The latter are produced in simulated environments, where qualitative and quantitative results are generated to demonstrate the benefits of ADAPS.

Rapid urbanization and increasing traffic have caused severe social, economic, and environmental problems in metropolitan areas worldwide. Traffic reconstruction and visualization using existing traffic data can provide novel tools for vehicle navigation and routing, congestion analysis, and traffic management. While traditional data collection methods are becoming increasingly common (e.g. using in-road sensors), GPS devices are also becoming ubiquitous. In this paper, we address the problem of traffic reconstruction, visualization, and animation using mobile vehicle data (i.e. GPS traces). We first conduct city-scale traffic reconstruction using statistical learning on mobile vehicle data for traffic animation and visualization, and then dynamically complete missing data using metamodel-based simulation optimization in areas of insufficient data coverage. We evaluate our approach quantitatively and qualitatively, and demonstrate our results with 2D visualization of citywide traffic, as well as 2D and 3D animation of reconstructed traffic in virtual environments.

Abstract Representing the majority of living animals, insects are the most ubiquitous biological organisms on Earth. Being able to simulate insect swarms could enhance visual realism of various graphical applications. However, the very complex nature of insect behaviors makes its simulation a challenging computational problem. To address this, we present a general biologically‐inspired framework for visual simulation of insect swarms. Our approach is inspired by the observation that insects exhibit emergent behaviors at various scales in nature. At the low level, our framework automatically selects and configures the most suitable steering algorithm for the local collision avoidance task. At the intermediate level, it processes insect trajectories into piecewise‐linear segments and constructs probability distribution functions for sampling waypoints. These waypoints are then evaluated by the Metropolis‐Hastings algorithm to preserve global structures of insect swarms at the high level. With this biologically inspired, data‐driven approach, we are able to simulate insect behaviors at different scales and we evaluate our simulation using both qualitative and quantitative metrics. Furthermore, as insect data could be difficult to acquire, our framework can be adopted as a computer‐assisted animation tool to interpret sketch‐like input as user control and generate simulations of complex insect swarming phenomena.

Smart healthcare is a complex domain for systems integration due to human and technical factors and heterogeneous data sources involved. As a part of smart city, it is such a complex area where clinical functions require smartness of multi-systems collaborations for effective communications among departments, and radiology is one of the areas highly relies on intelligent information integration and communication. Therefore, it faces many challenges regarding integration and its interoperability such as information collision, heterogeneous data sources, policy obstacles, and procedure mismanagement. The purpose of this study is to conduct an analysis of data, semantic, and pragmatic interoperability of systems integration in radiology department, and to develop a pragmatic interoperability framework for guiding the integration. We select an on-going project at a local hospital for undertaking our case study. The project is to achieve data sharing and interoperability among Radiology Information Systems (RIS), Electronic Patient Record (EPR), and Picture Archiving and Communication Systems (PACS). Qualitative data collection and analysis methods are used. The data sources consisted of documentation including publications and internal working papers, one year of non-participant observations and 37 interviews with radiologists, clinicians, directors of IT services, referring clinicians, radiographers, receptionists and secretary. We identified four primary phases of data analysis process for the case study: requirements and barriers identification, integration approach, interoperability measurements, and knowledge foundations. Each phase is discussed and supported by qualitative data. Through the analysis we also develop a pragmatic interoperability framework that summaries the empirical findings and proposes recommendations for guiding the integration in the radiology context.

Clinical pathway is an approach to standardise care processes to support the implementations of clinical guidelines and protocols. It is designed to support the management of treatment processes including clinical and non-clinical activities, resources and also financial aspects. It provides detailed guidance for each stage in the management of a patient with the aim of improving the continuity and coordination of care across different disciplines and sectors. However, in the practical treatment process, the lack of knowledge sharing and information accuracy of paper-based clinical pathways burden health-care staff with a large amount of paper work. This will often result in medical errors, inefficient treatment process and thus poor quality medical services. This paper first presents a theoretical underpinning and a co-design research methodology for integrated pathway management by drawing input from organisational semiotics. An approach to integrated clinical pathway management is then proposed, which aims to embed pathway knowledge into treatment processes and existing hospital information systems. The capability of this approach has been demonstrated through the case study in one of the largest hospitals in China. The outcome reveals that medical quality can be improved significantly by the classified clinical pathway knowledge and seamless integration with hospital information systems.