101 papers
This paper proposes a cost-effective, open-source platform utilizing 1:10 scaled mini-cars equipped with ROS2 and an ETSI-compliant OScar stack to bridge the gap between simulation and field testing for cooperative, connected, and automated vehicle research, demonstrated through a validated intersection collision warning application.
This paper proposes a dual-AoI-based Markov decision process framework to optimize transmission scheduling in wireless monitoring systems with random data arrivals and unreliable channels, deriving a low-complexity threshold policy that outperforms existing approaches by addressing the inefficiency of conventional methods that ignore asynchronous AoI evolution.
The paper presents CrossCheck, a shadow validation system for Wide Area Network SDN controllers that effectively detects invalid inputs to prevent network outages while maintaining a zero false positive rate even under conditions of noisy or corrupted telemetry data.
This paper presents "Moveover," a novel V2N-based algorithm and communication protocol that enables autonomous vehicles to cross intersections without stopping by delegating trajectory optimization to individual vehicles while using a local controller for collision prevention, demonstrating significant improvements in travel time and emissions under various network conditions and intersection layouts.
This study evaluates uncoordinated proactive interference mitigation techniques for FMCW automotive radars in dense traffic scenarios, concluding that chirp-by-chirp frequency hopping combined with sufficient bandwidth is the most effective method for ensuring system reliability, whereas compass-based directional approaches offer limited value relative to their complexity.
This paper presents U-Parking, a distributed autonomous parking system that combines Ultra-Wideband-assisted robust localization with Large Language Model-driven intelligent planning to achieve reliable automated parking in challenging indoor environments, as demonstrated on real vehicles.
This paper proposes an adaptive personalized federated reinforcement learning algorithm to optimize UAV trajectories and RIS phase controls for maximizing downlink rates in dynamic, heterogeneous Space-air-ground integrated networks (SAGINs) that integrate LEO satellites, RIS-assisted UAV relays, and fluid antenna systems.
This paper addresses the competitive multi-service UAV deployment in the low-altitude economy by proposing an authenticity-guaranteed auction mechanism and a resilient federated reinforcement learning solution that optimizes resource allocation while ensuring robustness against transmission errors and malicious behavior among self-interested service providers.
This paper presents a human-centric body-scale NFC networking system for ultra-low-power wearables that utilizes Meander NFC to create stable, surface-confined communication on clothing and picoRing NFC to bridge distance gaps between distributed nodes, thereby enabling robust surface-to-multipoint interactions.
This paper proposes and validates a joint Visible Light Communication and Ambient Backscatter architecture for batteryless Ambient IoT networks, detailing its fundamental concepts, diverse applications, and experimental proof-of-concept demonstrations while outlining future research directions and deployment challenges.
This paper proposes TCCO, a Transformer-based framework that decouples congestion control from the kernel to leverage external computational resources and self-attention mechanisms for noise filtering and coordinated multipath transmission, demonstrating superior adaptability and performance on wireless uplinks compared to state-of-the-art baselines.
This paper proposes a distributed auction framework for repeated spectrum allocation in heterogeneous networks where user equipments utilize large language models as reasoning agents to strategically adapt their bidding and association decisions over time, resulting in superior channel access and budget efficiency compared to traditional static policies.
Threadle is a high-performance, memory-efficient C# engine designed to store and query massive, multilayer, mixed-mode networks by utilizing a pseudo-projection approach that avoids the prohibitive memory costs of materializing two-mode data projections.
This survey systematically analyzes state-of-the-art dynamic routing and cascading strategies for efficiently selecting among multiple independent large language models based on query characteristics, proposing a conceptual framework to balance performance and cost while highlighting open challenges in generalization.
The paper introduces vLLM Semantic Router, a signal-driven decision framework that composes heterogeneous request features and neural classifiers into configurable policies to intelligently route queries across diverse Mixture-of-Modality models while enforcing privacy, safety, and cost constraints in production environments.
This paper proposes an AI-driven mesh architecture that integrates proximity-based low-power nodes, spatial frequency reuse, and LSTM-based traffic prediction to achieve up to 84 times better energy efficiency and 74 percent lower deployment costs, effectively replacing inefficient, diesel-dependent macro-cell networks with a sustainable, solar-powered solution for both rural and ultra-dense urban environments.
This white paper presents a comprehensive energy-efficiency characterization and modeling of a commercial O-RAN system based on rigorous measurements from a production-like testbed, aiming to provide operators with the quantitative data needed to optimize energy consumption and support sustainable network operations.
This paper addresses the fundamental challenge of optimally grouping periodic time-triggered signals into size-constrained messages and scheduling them on a single resource to maximize communication efficiency while ensuring deterministic delivery.
This paper proposes an auction-based framework for allocating shared reconfigurable intelligent surfaces (RISs) in multi-cell networks, where deep reinforcement learning agents optimize bidding strategies to dynamically balance spectral efficiency and cost constraints.
This paper proposes a novel framework for predicting arterial traffic states using real-world connected vehicle data, featuring a two-stage traffic state extraction method and an Abnormality-aware Spatiotemporal Graph Convolution Network (AASTGCN) that effectively handles both normal and abnormal traffic conditions by separately modeling them with a dual-expert architecture and a gated-fusion mechanism.