This letter introduces a novel method for predicting blockages in millimeter-wave communication systems towards enabling reliable connectivity. Using a self-supervised learning approach, radio frequency data are labeled with blockage-causing object locations extracted from light detection and range data. These labeled RF data train a deep learning model that predicts object locations. The predicted positions are then used to forecast blockages, ensuring adaptability without retraining when the transmitter-receiver positions change. Experiments achieve up to 74% accuracy in dynamic environments, demonstrating the effectiveness of the proposed solution.

The integration of machine learning tools into telecom networks, has led to two prevailing paradigms, namely, language-based systems, such as Large Language Models (LLMs), and physics-based systems, such as Digital Twins (DTs). While LLM-based approaches enable flexible interaction and automation, they lack explicit representations of network dynamics. DTs, in contrast, offer a high-fidelity network simulation, but remain scenario-specific and are not designed for learning or decision-making under uncertainty. This gap becomes critical for 6G systems, where decisions must take into account the evolving network states, uncertainty, and the cascading effects of control actions across multiple layers. In this article, we introduce the Telecom World Model (TWM) concept, an architecture for learned, action-conditioned, uncertainty-aware modeling of telecom system dynamics. We decompose the problem into two interacting worlds, a controllable system world consisting of operator-configurable settings and an external world that captures propagation, mobility, traffic, and failures. We propose a three-layer architecture, comprising a field world model for spatial environment prediction, a control/dynamics world model for action-conditioned Key Performance Indicator (KPI) trajectory prediction, and a telecom foundation model layer for intent translation and orchestration. We showcase a comparative analysis between existing paradigms, which demonstrates that TWM jointly provides telecom state grounding, fast action-conditioned roll-outs, calibrated uncertainty, multi-timescale dynamics, model-based planning, and LLM-integrated guardrails. Furthermore, we present a proof-of-concept on network slicing to validate the proposed architecture, showing that the full three-layer pipeline outperforms single-world baselines and accurately predicts KPI trajectories.

Remote robotic systems operating over wireless networks must maintain reliable control despite limited communication resources, changing channel conditions, and environmental disturbances.However, continuously transmitting high-dimensional sensory observations, such as camera images, increases communication overhead and energy consumption while reducing robustness under unreliable connectivity.To address these challenges, this paper proposes a resilient communication-aware remote robotic control framework based on coupled control and wireless Joint Embedding Predictive Architecture (JEPA) world models that jointly capture robot dynamics and wireless channel evolution from visual observations and a combination of raw and structured radio frequency (RF) representations based on spectrograms and Persistence Images(PIs).The learned latent representations enable predictive communication scheduling by jointly forecasting future robot states and wireless conditions, thereby reducing unnecessary uplink transmissions while maintaining reliable control performance.Furthermore, an adaptive resilience mechanism detects latent prediction discrepancies and efficiently adapts perception embeddings to accommodate wireless and visual environmental changes without retraining the complete control policy.The proposed framework is evaluated in a synchronized Gazebo-Robot Operating System (ROS)-Sionna robot-wireless simulation environment under diverse wireless propagation and perception perturbations.Experimental results demonstrate significant improvements in communication efficiency, robustness, and resilience while maintaining navigation performance compared with conventional Proportional Integral Derivative (PID), model-free Deep Q-Network (DQN), and predictive approaches based on Vision Transformers(ViTs).

Satellite-airborne-terrestrial edge computing networks (SATECNs) emerge as a global solution for Internet of Things (IoT) since they can provide global coverage even in remote areas and under natural disasters. However, their dynamic and non-stationary nature makes control and resource allocation more challenging. Preserving data freshness is crucial in many IoT applications and requires timely decisions. To address these challenges, we present a knowledge-base software-defined networking architecture for satellite–airborne–terrestrial networks (KB-SAT-SDN) that enables collaboration between SDN controllers to optimize SAT configurations. A shared knowledge base (KB) is built through lifelong learning (LL) to continuously adapt and efficiently manage computing and networking resources to minimize the age of information (AoI) and energy consumption. To further accelerate learning, we exploit the heterogeneity of nodes and offloading decisions by defining different learning domains and designing a cross-domain lifelong learning (CDLL-SATECN) algorithm. With domain-specific projections, knowledge is shared between domains. Numerical results show that CDLL reduces average AoI and energy by up to 70% and converges 8× faster than existing baselines. It achieves the lowest or near-lowest penalty across all RL domains, nearly halving Natural Actor-Critic (NAC)’s penalty in the most complex domains. LEO assistance lowers penalty/AoI from 61.9/49.4 to 48.5/45.1 relative to a domain without LEO, while reducing UAV energy and queues. The sensitivity analysis confirms that CDLL maintains a stable AoI–energy tradeoff over a broad range of weighting parameters.

Multi-camera wireless perception requires a base station (BS) to maintain timely and reliable latent beliefs from distributed cameras under limited uplink resources. Conventional Age-of-Information (AoI) measures the age of the latest received update but not task-relevant latent content. We introduce Age-of-Latent (AoL) to quantify the freshness of each camera's latest decoded latent representation. A finite temporal window of integration (TWI) determines the task-commitment time and available uplink slots, creating a tradeoff among update opportunities, prediction duration, commit-time AoL, prediction reliability, and accumulated resource cost. Within this horizon, redundant or overlapping views enable correlated prediction, reducing reliance on the highest-cost communication and encoding configuration to maintain BS-side latent beliefs. We formulate a joint AoL-resource minimization problem coupling task-level TWI selection with slot-level encoder selection, scheduling, and NOMA power allocation under prediction-reliability constraints. We propose correlation-aware latent prediction for AoL minimization (CoLA), which uses Lyapunov optimization for task-level TWI selection based on AoL-resource cost and prediction uncertainty, and proximal policy optimization for slot-level resource control. Results on a warehouse multi-camera RF dataset show that CoLA adapts the TWI to camera-update availability and achieves the most favorable AoL-resource tradeoff among the benchmarks while maintaining prediction reliability, particularly under prolonged and severe camera outages.

The vast amount of content generated in the Metaverse and unpredictable user demands make real-time optimization of communication, computing, and caching increasingly challenging. These issues highlight the need for intelligent mechanisms that reduce redundant content transmission and improve resource efficiency. To address this, joint semantic-aware caching and rendering schemes that leverage content similarity are proposed to enable reusability across Metaverse environments. The goal is to optimize user-server associations, caching, and rendering decisions to efficiently utilize network resources, thereby maximizing resource savings and service quality. Reusing content across heterogeneous Metaverse environments, however, requires a learning algorithm capable of adapting to diverse task settings. To this end, a lifelong learning-based algorithm, Deep-Centralized ELLA (DC-ELLA), incorporating dictionary learning is developed to accommodate diverse user requests by dynamically extracting knowledge from different semantic environments. Simulation results show that the proposed caching and rendering schemes significantly outperform traditional approaches, while DC-ELLA enhances convergence speed and stability, demonstrating superior performance in dynamic scenarios. By exploiting knowledge and content from prior requests, the approach achieves scalable adaptation to new Metaverse environments.

6G must be designed to withstand, adapt to, and evolve amid prolonged, complex disruptions. Mobile networks' shift from efficiency-first to sustainability-aware has motivated this white paper to assert that resilience is a primary design goal, alongside sustainability and efficiency, encompassing technology, architecture, and economics. We promote resilience by analysing dependencies between mobile networks and other critical systems, such as energy, transport, and emergency services, and illustrate how cascading failures spread through infrastructures. We formalise resilience using the 3R framework: reliability, robustness, resilience. Subsequently, we translate this into measurable capabilities: graceful degradation, situational awareness, rapid reconfiguration, and learning-driven improvement and recovery. Architecturally, we promote edge-native and locality-aware designs, open interfaces, and programmability to enable islanded operations, fallback modes, and multi-layer diversity (radio, compute, energy, timing). Key enablers include AI-native control loops with verifiable behaviour, zero-trust security rooted in hardware and supply-chain integrity, and networking techniques that prioritise critical traffic, time-sensitive flows, and inter-domain coordination. Resilience also has a techno-economic aspect: open platforms and high-quality complementors generate ecosystem externalities that enhance resilience while opening new markets. We identify nine business-model groups and several patterns aligned with the 3R objectives, and we outline governance and standardisation. This white paper serves as an initial step and catalyst for 6G resilience. It aims to inspire researchers, professionals, government officials, and the public, providing them with the essential components to understand and shape the development of 6G resilience.

Just like power, water, and transportation systems, wireless networks are a crucial societal infrastructure. As natural and human-induced disruptions continue to grow, wireless networks must be resilient. This requires them to withstand and recover from unexpected adverse conditions, shocks, unmodeled disturbances and cascading failures. Unlike robustness and reliability, resilience is based on the understanding that disruptions will inevitably happen. Resilience, as elasticity, focuses on the ability to bounce back to favorable states, while resilience as plasticity involves agents and networks that can flexibly expand their states and hypotheses through real-time adaptation and reconfiguration. This situational awareness and active preparedness, adapting world models and counterfactually reasoning about potential system failures and the best responses, is a core aspect of resilience. This article will first disambiguate resilience from reliability and robustness, before delving into key mathematical foundations of resilience grounded in abstraction, compositionality and emergence. Subsequently, we focus our attention on a plethora of techniques and methodologies pertaining to the unique characteristics of resilience, as well as their applications through a comprehensive set of use cases. Ultimately, the goal of this paper is to establish a unified foundation for understanding, modeling, and engineering resilience in wireless communication systems, while laying a roadmap for the next-generation of resilient-native and intelligent wireless systems.

Wireless sensor networks (WSNs) with energy harvesting (EH) are expected to play a vital role in intelligent 6G systems, especially in industrial sensing and control, where continuous operation and sustainable energy use are critical. Given limited energy resources, WSNs must operate efficiently to ensure long-term performance. Their deployment, however, is challenged by dynamic environments where EH conditions, network scale, and traffic rates change over time. In this work, we address system dynamics that yield different learning tasks, where decision variables remain fixed but strategies vary, as well as learning domains, where both decision space and strategies evolve. To handle such scenarios, we propose a cross-domain lifelong reinforcement learning (CD-L2RL) framework for energy-efficient WSN design. Our CD-L2RL algorithm leverages prior experience to accelerate adaptation across tasks and domains. Unlike conventional approaches based on Markov decision processes or Lyapunov optimization, which assume relatively stable environments, our solution achieves rapid policy adaptation by reusing knowledge from past tasks and domains to ensure continuous operations. We validate the approach through extensive simulations under diverse conditions. Results show that our method improves adaptation speed by up to 35

Ensuring the stability of wireless networked control systems (WNCS) with nonlinear and control-non-affine dynamics, where system behavior is nonlinear with respect to both states and control decisions, poses a significant challenge, particularly under limited resources. However, it is essential in the context of 6G, which is expected to support reliable communication to enable real-time autonomous systems. This paper proposes a joint communication and control solution consisting of: i) a deep Koopman model capable of learning and mapping complex nonlinear dynamics into linear representations in an embedding space, predicting missing states, and planning control actions over a future time horizon; and ii) a scheduling algorithm that schedules sensor-controller communication based on Lyapunov optimization, which dynamically allocates communication resources based on system stability and available resources. Control actions are computed within this embedding space using a linear quadratic regulator (LQR) to ensure system stability. The proposed model is evaluated under varying conditions and its performance is compared against two baseline models; one that assumes systems are control-affine, and another that assumes identical control actions in the embedding and original spaces. The evaluation results demonstrate that the proposed model outperforms both baselines, by achieving stability while requiring fewer transmissions.

Our future society will be increasingly digitalized, hyper-connected and globally data driven. The sixth generation (6G) and beyond 6G wireless networks are expected to bridge the digital and physical worlds by providing wireless connectivity as a service to different vertical sectors, making the society increasingly dependent on wireless networks. Thus, any disruption to these networks would have a significant impact with far-reaching consequences. Disruptions can occur for a variety of reasons, including planned outages, natural disasters, and deliberate cybersecurity attacks. Resilience against such disruptions is expected to be one of the most important defining features of future wireless networks. This paper first discusses a generic framework for designing future resilient wireless networks. A novel resilient-by-design framework consisting of four building blocks, namely predict, preempt, protect and progress, is then proposed as a specific example.

In this work, we propose an automated wireless medium access control (MAC) protocol design based on multi-agent reinforcement learning (MARL), in which multiple wireless devices (WDs) and a base station (BS) exchange control messages without prior knowledge of their meanings to coordinate data delivery across the network. In current approaches, the BS acts as a MAC expert, while the WDs are the only learning entities. As a result, the learned MAC protocols are constrained by the BS’s predefined knowledge. In contrast, our approach enables both WDs and the BS to act as learning agents, fostering the collaborative development of new ad hoc communication protocols. However, this approach introduces additional challenges in managing heterogeneous agents that learn simultaneously, alongside conventional issues such as the learned protocols being overfitted to training parameters, including the number of transmitted packets and the number of WDs managed by the BS. To overcome these limitations, we propose a novel learning framework that facilitates the emergence of MAC protocols with robust generalization capabilities. This framework incorporates innovative features such as a novel BS policy model, two distinct reward functions for the WDs and the BS, and different update routines for the agents’ policies. Moreover, we leverage the concepts of parameter sharing and state abstraction to enhance generalization in the WDs’ policies. The MAC protocols generated using the proposed framework are evaluated against state-of-the-art approaches. Simulation results show that the proposed solution significantly outperforms the benchmarks in terms of generalization capabilities.

Enhancing the sustainability and efficiency of wireless sensor networks (WSNs) in dynamic and unpredictable environments requires adaptive communication and energy harvesting (EH) strategies. We propose a novel adaptive control strategy for WSNs that optimizes data transmission and EH to minimize overall energy consumption while ensuring queue stability and energy storing constraints under dynamic environmental conditions. The notion of adaptability therein is achieved by transferring the known environment-specific knowledge to new conditions resorting to the lifelong reinforcement learning (L2RL) concepts. We evaluate our proposed method against two baseline frameworks: Lyapunov-based optimization, and policy-gradient reinforcement learning (RL). Simulation results demonstrate that our approach rapidly adapts to changing environmental conditions by leveraging transferable knowledge, achieving near-optimal performance approximately 30% faster than the RL method and 60% faster than the Lyapunov-based approach.

With a large number of deep space (DS) missions anticipated by the end of this decade, reliable and high-capacity DS communications are needed more than ever. Nevertheless, existing technologies are far from meeting such a goal. Improving current systems does not only require engineering leadership, but also, very crucially, investigating potential technologies that overcome the unique challenges of ultra-long DS links. To the best of our knowledge, there has not been any comprehensive surveys of DS communications technologies over the last decade. Free space optical (FSO) is an emerging DS technology, proven to acquire lower communications systems size weight and power (SWaP) and achieve a very high capacity compared to its counterpart radio frequency (RF), the currently used DS technology. In this survey, we discuss the pros and cons of deep space optical communications (DSOC) and review their physical and networking characteristics. Furthermore, we provide, for the first time, thoughtful discussions about implementing orbital angular momentum (OAM) and quantum communications (QC) for DS. We elaborate on how these technologies among other field advances including interplanetary network (IPN) and RF/FSO systems improve reliability, capacity, and security. This paper provides a holistic survey of DSOC technologies gathering 247 fragmented pieces of literature and including novel perspectives aiming to set the stage for more developments in the field.

This work presents a use case of federated learning (FL) applied to discovering a maze with LiDAR sensors-equipped robots. Goal here is to train classification models to accurately identify the shapes of grid areas within two different square mazes made up with irregular shaped walls. Due to the use of different shapes for the walls, a classification model trained in one maze that captures its structure does not generalize for the other. This issue is resolved by adopting FL framework between the robots that explore only one maze so that the collective knowledge allows them to operate accurately in the unseen maze. This illustrates the effectiveness of FL in real-world applications in terms of enhancing classification accuracy and robustness in maze discovery tasks.

The evolving landscape of the Internet of Things (IoT) has given rise to a pressing need for an efficient communication scheme. As the IoT user ecosystem continues to expand, traditional communication protocols grapple with substantial challenges in meeting its burgeoning demands, including energy consumption, scalability, data management, and interference. In response to this, the integration of wireless power transfer and data transmission has emerged as a promising solution. This paper considers an energy harvesting (EH)-oriented data transmission scheme, where a set of users are charged by their own multi-antenna power beacon (PB) and subsequently transmits data to a base station (BS) using an irregular slotted aloha (IRSA) channel access protocol. We propose a closed-form expression to model energy consumption for the present scheme, employing average channel state information (A-CSI) beamforming in the wireless power channel. Subsequently, we employ the reinforcement learning (RL) methodology, wherein every user functions as an agent tasked with the goal of uncovering their most effective strategy for replicating transmissions. This strategy is devised while factoring in their energy constraints and the maximum number of packets they need to transmit. Our results underscore the viability of this solution, particularly when the PB can be strategically positioned to ensure a strong line-of-sight connection with the user, highlighting the potential benefits of optimal deployment.

Achieving control stability is one of the key design challenges of scalable Wireless Networked Control Systems (WNCS) under limited communication and computing resources. This paper explores the use of an alternative control concept defined as tail-based control, which extends the classical Linear Quadratic Regulator (LQR) cost function for multiple dynamic control systems over a shared wireless network. We cast the control of multiple control systems as a network-wide optimization problem and decouple it in terms of sensor scheduling, plant state prediction, and control policies. Toward this, we propose a solution consisting of a scheduling algorithm based on Lyapunov optimization for sensing, a mechanism based on Gaussian Process Regression (GPR) for state prediction and uncertainty estimation, and a control policy based on Reinforcement Learning (RL) to ensure tail-based control stability. A set of discrete time-invariant mountain car control systems is used to evaluate the proposed solution and is compared against four variants that use state-of-the-art scheduling, prediction, and control methods. The experimental results indicate that the proposed method yields 22% reduction in overall cost in terms of communication and control resource utilization compared to state-of-the-art methods.

Automatically learning medium access control (MAC) communication protocols via multiagent reinforcement learning (MARL) has received huge attention to cater to the extremely diverse realworld scenarios expected in 6G wireless networks.Several state-of-the-art solutions adopt the centralized training with decentralized execution (CTDE) learning method, where agents learn optimal MAC protocols by exploiting the information exchanged with a central unit.Despite the promising results achieved in these works, two notable challenges are neglected.First, these works were designed to be trained in computer simulations assuming an omniscient environment and neglecting communication overhead issues, thus making the implementation impractical in real-world scenarios.Second, the learned protocols fail to generalize outside of the scenario they were trained on.In this paper, we propose a new feasible learning framework that enables practical implementations of training procedures, thus allowing learned MAC protocols to be tailor-made for the scenario where they will be executed.Moreover, to address the second challenge, we leverage the concept of state abstraction and imbue it into the MARL framework for better generalization.As a result, the policies are learned in an abstracted observation space that contains only useful information extracted from the original high-dimensional and redundant observation space.Simulation results show that our feasible learning framework exhibits performance comparable to that of the infeasible solutions.In addition, the learning frameworks adopting observation abstraction offer better generalization capabilities, in terms of the number of UEs, number of data packets to transmit, and channel conditions.

This work explores the advantages of using persistence diagrams (PDs), topological signatures of raw point cloud data, in a point-to-point communication setting. PD is a structural semantics in the sense that it carries information about the shape and structure of the data. Instead of transmitting raw data, the transmitter communicates its PD semantics, and the receiver carries out inference using the received semantics. We propose novel qualitative definitions for distortion and rate of PD semantics while quantitatively characterizing the trade-offs among the distortion, rate, and inference accuracy. Simulations demonstrate that unlike raw data or autoencoder (AE)-based latent representations, PD semantics leads to more effective use of transmission channels, enhanced degrees of freedom for incorporating error detection/correction capabilities, and improved robustness to channel imperfections. For instance, in a binary symmetric channel with nonzero crossover probability settings, the minimum rate required for Bose, Chaudhuri, and Hocquenghem (BCH)-coded PD semantics to achieve an inference accuracy over 80 AE-latent representations. Moreover, results suggest that the gains of PD semantics are even more pronounced when compared with the rate requirements of raw data.