Abstract

In this work, we conduct performance analysis of a Fault Tolerant Control (FTC) scheme for hexacopter actuator failure through hardware-based fault detection and dynamic control reallocation. Hall effect sensors are used to monitor motor speeds and compared with the reference signals generated by the flight controller (FC) for anomaly detection. Experimental flight tests demonstrate the efficacy of the proposed FTC in detecting the faults and subsequent flight stabilization. The performance of the proposed FTC (quantified in terms of tracking error in attitude dynamics) is compared with the ideal fault detection (no delay between fault occurrence and control reallocation) case.

Abstract

Lane detection is critical for Advanced Driver Assistance Systems (ADAS) in autonomous vehicles. Deep learning models offer high accuracy but are computationally demanding for resource-constrained edge platforms, while lightweight image processing algorithms are energy-efficient but often falter in complex scenarios. This paper presents RL-ALMS (Reinforcement Learning-based Adaptive and Lightweight Model Selection), a framework that dynamically switches between deep learning and image processing lane detection models in electric vehicles (EVs). RL-ALMS employs a contextual multi-armed bandit with Thompson sampling to intelligently select the optimal model based on road conditions, battery state, and accuracy needs. The novelty lies in its system-level integration of a battery-aware reward function and a sustainability-driven selection mechanism, specifically designed to balance real-time detection accuracy with long-term EV energy constraints. Experimental results on an edge computing platform demonstrate RL-ALMS achieves 90.3% average accuracy over a 50km journey while maintaining 81.2% battery reserve, significantly outperforming fixed high-accuracy (battery depletion) and energy-efficient (64.5% accuracy) strategies. RL-ALMS maintains consistent performance across diverse conditions, representing a practical advancement for energy-constrained, real-time lane detection in EVs.

Abstract

Modern transportation systems face growing challenges in managing traffic flow, ensuring safety, and maintaining operational efficiency amid dynamic traffic patterns. Addressing these challenges requires intelligent solutions capable of real-time monitoring, predictive analytics, and adaptive control. This paper proposes an architecture for DigIT, a Digital Twin (DT) platform for Intelligent Transportation Systems (ITS), designed to overcome the limitations of existing frameworks by offering a modular and scalable solution for traffic management. Built on a Domain Concept Model (DCM), the architecture systematically models key ITS components enabling seamless integration of predictive modeling and simulations. The architecture leverages machine learning models to forecast traffic patterns based on historical and real-time data. To adapt to evolving traffic patterns, the architecture incorporates adaptive Machine Learning Operations (MLOps), automating the deployment and lifecycle management of predictive models. Evaluation results highlight the effectiveness of the architecture in delivering accurate predictions and computational efficiency.

Abstract

Urbanization, driven by technological advancements, has brought about improved connectivity and efficiency, especially with the rise of Internet of Things (IoT) devices. Smart cities use these innovations to manage resources better and enhance resident’s quality of life. However, implementing smart city initiatives comes with challenges like monitoring, maintaining, and testing urban infrastructure. Digital Twin (DT) entails the connection of physical facilities or devices with their digital counterparts, facilitating real-time monitoring, manipulation, and predictive analysis of their behavior. This concept offers a virtual replica of assets, processes, and systems, enabling insights into their real-time performance and predictive behaviors. By simulating real-world scenarios, DT aids in planning maintenance activities and conducting comprehensive testing, thereby enhancing the resilience and efficiency of smart city systems. Particularly in the context of managing water networks, DT technology holds significant promise. Visualization capabilities provide intuitive insights into the system’s behavior, facilitating informed decision-making. This visualization, coupled with actuation capabilities, enables control actions based on predictive analytics and optimization algorithms, allowing for proactive management of water resources and infrastructure. To this end, in this paper, we present the architecture of WaterTwin, a DT developed for water quality networks in smart city systems. We demonstrate our approach through the use of a water quality network at the smart city living lab, IIIT Hyderabad campus.

Abstract

The Robotic Mobile Fulfillment System (RMFS) is an automated technology to fulfill various types of orders (e.g., vehicle assembly) in modern warehouses or factories. In particular, battery-equipped mobile robots move racks that contain various components (Stock Keeping Unit) by visiting replenishment or picking stations to complete orders. We formulate the preliminary system model to optimize the order throughput and energy consumption of mobile robots, which consists of (i) rack allocation, (ii) task allocation, and (iii) route routing.

Abstract

With advances in vehicular communications technology such as Vehicle-to-Infrastructure (V2I) and Vehicle-to-Vehicle (V2V), the computation of vehicular tasks has become distributed facilitated by computation offloading from the vehicular platform to road side units (RSUs) or the cloud infrastructure. In this work, due to communication overheads, we do not consider the cloud and only consider offloading horizontally across RSU nodes. However, the advantage of offloading depends upon how the tasks are scheduled across the RSUs. Unlike existing horizontal offloading works, this work explores the benefits of online task partitioned scheduling for computation offloading from multiple vehicles to RSUs or edge nodes. Specifically, we propose a new efficient timeslot-based online hybrid partitioned scheduling algorithm, which splits some tasks into subtasks and schedules them across RSU nodes while considering vehicle flow constraints. We compared and evaluated the effectiveness of our proposed hybrid partitioned scheduling algorithm with the fully partitioned algorithm. We also compared the performance of the aforementioned algorithms with an optimal scheduling algorithm utilizing several experiments conducted on a real-world vehicular dataset.

Abstract

Urbanization, driven by technological advancements, has brought about improved connectivity and efficiency, especially with the rise of Internet of Things (IoT) devices. Smart cities use these innovations to manage resources better and enhance resident’s quality of life. However, implementing smart city projects comes with challenges like monitoring, maintaining, and testing urban infrastructure. Digital Twin(DT) entails the connection of physical facilities or devices with their digital counterparts, facilitating real-time monitoring, manipulation, and predictive analysis of their behavior. This innovative concept offers a virtual replica of assets, processes and systems, enabling insights into their real-time performance and predictive behaviors. By simulating real-world scenarios, DT aids in planning maintenance activities and conducting comprehensive testing, thereby enhancing the resilience and efficiency of Smart City Systems. Particularly in the context of managing water networks, DT technology holds significant promise. Visualization capabilities provide intuitive insights, while actuation enables control actions based on predictive analytics and optimization algorithms. To this end, in this paper, we present the architecture of WaterTwin, a DT we developed for water quality networks in smart city systems. We demonstrate our approach through the use case of a water quality network in the smart city living lab of the IIIT Hyderabad campus.

Abstract

Edge server-assisted computation offloading enables vehicles to leverage server compute resources to deliver connected services, overcoming the limitations of onboard resources. Understanding the compute workloads of edge servers is crucial for effective resource management and scheduling, yet this task is challenging due to the complex interplay of factors such as vehicle mobility and computation offloading patterns. To address this, we propose an empirical analysis framework that systematically characterizes the compute workloads of edge servers. We begin by formalizing the relationships among three key aspects: local load (generated by vehicles), composite load (imposed on edge servers), and traffic flow (vehicle mobility patterns). Our framework then uses models of the local load and traffic flow as inputs to generate the composite loads on edge servers. Experiments were conducted by injecting between 600 and 5,000 vehicles per hour in two distinct geographical areas, New York City and Tampa. We provide a quantitative analysis demonstrating how the composite loads on edge servers vary with changes in traffic flows, geographical areas, and offloading patterns.

Abstract

Lane marker identification is crucial for developing Intelligent Transportation Systems and Autonomous Vehicles. While deep learning models excel in accuracy, their high com- putational requirements make them unsuitable for low-power edge devices. While various image-processing-based algorithms are used to pre-process images at different stages, there is a lack of an efficient algorithm specifically designed to enhance the lane-modeling stage. This paper proposes a two-stage pre- processing algorithm, consisting of a static phase and a dy- namic phase, to implement a divide-and-conquer approach for enhancing existing lane-modeling algorithms. The static phase generates an initial pixel label map and seed locations, while the dynamic phase uses the pre-processed input image and seed locations to generate a dynamic pixel map for localizing lane marking zones. Focusing on the center two lanes, the proposed method improves overall accuracy and recall, which is critical for capturing smaller lane details. Experimental results demonstrate the superior performance of the proposed two-stage algorithm compared to traditional HT and PHT methods, with the two- stage algorithm outperforming the standard HT(0.88 vs 0.92) and PHT(0.89 vs 0.95) in terms of Average Accuracy and Recall. Additionally, the two-stage PHT method significantly reduces power consumption compared to the Ultra Fast Lane Detection (UFLD) model, making it ideal for low-power edge devices like the Raspberry Pi 4B and Jetson Nano.

Abstract

This paper explores the critical issue of enhancing cybersecurity measures for low-cost, Wi-Fi-based Unmanned Aerial Vehicles (UAVs) against Distributed Denial of Service (DDoS) attacks. In the current work, we have explored three variants of DDoS attacks, namely Transmission Control Proto col (TCP), Internet Control Message Protocol (ICMP), and TCP + ICMPflooding attacks, and developed a detection mechanism that runs on the companion computer of the UAV system. As a part of the detection mechanism, we have evaluated various machine learning, and deep learning algorithms, such as XGBoost, Isolation Forest, Long Short-Term Memory (LSTM), Bidirectional-LSTM (Bi-LSTM), LSTM with attention, Bi LSTM with attention, and Time Series Transformer (TST) in terms of various classification metrics. Our evaluation reveals that algorithms with attention mechanisms outperform their counterparts in general, and TST stands out as the most efficient model with a run time of ∼0.1 seconds. TST has demonstrated an F1 score of 0.999, 0.997, and 0.943 for TCP, ICMP, and TCP + ICMP flooding attacks respectively. In this work, we present the necessary steps required to build an on board DDoS detection mechanism. Further, we also present the ablation study to identify the best TST hyperparameters for DDoS detection, and we have also underscored the advantage of adapting learnable positional embeddings in TST for DDoS detection with an improvement in F1 score from 0.94 to 0.99.