Peizheng Li

Peizheng Li, Shuxiao Ding, Xieyuanli Chen et al.

Accurately perceiving instances and predicting their future motion are key tasks for autonomous vehicles, enabling them to navigate safely in complex urban traffic. While bird's-eye view (BEV) representations are commonplace in perception for autonomous driving, their potential in a motion prediction setting is less explored. Existing approaches for BEV instance prediction from surround cameras rely on a multi-task auto-regressive setup coupled with complex post-processing to predict future instances in a spatio-temporally consistent manner. In this paper, we depart from this paradigm and propose an efficient novel end-to-end framework named POWERBEV, which differs in several design choices aimed at reducing the inherent redundancy in previous methods. First, rather than predicting the future in an auto-regressive fashion, POWERBEV uses a parallel, multi-scale module built from lightweight 2D convolutional networks. Second, we show that segmentation and centripetal backward flow are sufficient for prediction, simplifying previous multi-task objectives by eliminating redundant output modalities. Building on this output representation, we propose a simple, flow warping-based post-processing approach which produces more stable instance associations across time. Through this lightweight yet powerful design, POWERBEV outperforms state-of-the-art baselines on the NuScenes Dataset and poses an alternative paradigm for BEV instance prediction. We made our code publicly available at: https://github.com/EdwardLeeLPZ/PowerBEV.

Qingwen Zhang, Yi Yang, Peizheng Li et al.

Scene flow estimation predicts the 3D motion at each point in successive LiDAR scans. This detailed, point-level, information can help autonomous vehicles to accurately predict and understand dynamic changes in their surroundings. Current state-of-the-art methods require annotated data to train scene flow networks and the expense of labeling inherently limits their scalability. Self-supervised approaches can overcome the above limitations, yet face two principal challenges that hinder optimal performance: point distribution imbalance and disregard for object-level motion constraints. In this paper, we propose SeFlow, a self-supervised method that integrates efficient dynamic classification into a learning-based scene flow pipeline. We demonstrate that classifying static and dynamic points helps design targeted objective functions for different motion patterns. We also emphasize the importance of internal cluster consistency and correct object point association to refine the scene flow estimation, in particular on object details. Our real-time capable method achieves state-of-the-art performance on the self-supervised scene flow task on Argoverse 2 and Waymo datasets. The code is open-sourced at https://github.com/KTH-RPL/SeFlow along with trained model weights.

Yuzhi Lai, Shenghai Yuan, Peizheng Li et al.

ffective Human-Robot Interaction (HRI) is crucial for enhancing accessibility and usability in real-world robotics applications. However, existing solutions often rely on gesture- only or language-only commands, making interaction inefficient and ambiguous, particularly for users with physical impairments. In this paper, we introduce FAM-HRI, an efficient multimodal framework for HRI that integrates language and gaze inputs via foundation models. By leveraging lightweight Meta ARIA glasses, our system captures real-time multimodal signals and utilizes large language models (LLMs) to fuse user intention with scene context, enabling intuitive and precise robot manipulation. Our method accurately determines the gaze fixation time interval, reducing noise caused by the gaze dynamic nature. Experimental evaluations demonstrate that FAM-HRI achieves a high success rate in task execution while maintaining a low interaction time, providing a practical solution for individuals with limited physical mobility or motor impairments. To support the community, we have released our system design, algorithms, and solutions at https://github.com/laiyuzhi/FAM-HRI.

Hakan Erdol, Xiaoyang Wang, Peizheng Li et al.

The vision of 5G lies in providing high data rates, low latency (for the aim of near-real-time applications), significantly increased base station capacity, and near-perfect quality of service (QoS) for users, compared to LTE networks. In order to provide such services, 5G systems will support various combinations of access technologies such as LTE, NR, NR-U and Wi-Fi. Each radio access technology (RAT) provides different types of access, and these should be allocated and managed optimally among the users. Besides resource management, 5G systems will also support a dual connectivity service. The orchestration of the network therefore becomes a more difficult problem for system managers with respect to legacy access technologies. In this paper, we propose an algorithm for RAT allocation based on federated meta-learning (FML), which enables RAN intelligent controllers (RICs) to adapt more quickly to dynamically changing environments. We have designed a simulation environment which contains LTE and 5G NR service technologies. In the simulation, our objective is to fulfil UE demands within the deadline of transmission to provide higher QoS values. We compared our proposed algorithm with a single RL agent, the Reptile algorithm and a rule-based heuristic method. Simulation results show that the proposed FML method achieves higher caching rates at first deployment round 21% and 12% respectively. Moreover, proposed approach adapts to new tasks and environments most quickly amongst the compared methods.

Peizheng Li, Xiaoyang Wang, Robert Piechocki et al.

Measuring customer experience on mobile data is of utmost importance for global mobile operators. The reference signal received power (RSRP) is one of the important indicators for current mobile network management, evaluation and monitoring. Radio data gathered through the minimization of drive test (MDT), a 3GPP standard technique, is commonly used for radio network analysis. Collecting MDT data in different geographical areas is inefficient and constrained by the terrain conditions and user presence, hence is not an adequate technique for dynamic radio environments. In this paper, we study a generative model for RSRP prediction, exploiting MDT data and a digital twin (DT), and propose a data-driven, two-tier neural network (NN) model. In the first tier, environmental information related to user equipment (UE), base stations (BS) and network key performance indicators (KPI) are extracted through a variational autoencoder (VAE). The second tier is designed as a likelihood model. Here, the environmental features and real MDT data features are adopted, formulating an integrated training process. On validation, our proposed model that uses real-world data demonstrates an accuracy improvement of about 20% or more compared with the empirical model and about 10% when compared with a fully connected prediction network.

Peizheng Li, Hakan Erdol, Keith Briggs et al.

Setting the transmit power setting of 5G cells has been a long-term topic of discussion, as optimized power settings can help reduce interference and improve the quality of service to users. Recently, machine learning (ML)-based, especially reinforcement learning (RL)-based control methods have received much attention. However, there is little discussion about the generalisation ability of the trained RL models. This paper points out that an RL agent trained in a specific indoor environment is room-dependent, and cannot directly serve new heterogeneous environments. Therefore, in the context of Open Radio Access Network (O-RAN), this paper proposes a distributed cell power-control scheme based on Federated Reinforcement Learning (FRL). Models in different indoor environments are aggregated to the global model during the training process, and then the central server broadcasts the updated model back to each client. The model will also be used as the base model for adaptive training in the new environment. The simulation results show that the FRL model has similar performance to a single RL agent, and both are better than the random power allocation method and exhaustive search method. The results of the generalisation test show that using the FRL model as the base model improves the convergence speed of the model in the new environment.

Peizheng Li, Jonathan Thomas, Xiaoyang Wang et al.

The next generation of networks will actively embrace artificial intelligence (AI) and machine learning (ML) technologies for automation networks and optimal network operation strategies. The emerging network structure represented by Open RAN (O-RAN) conforms to this trend, and the radio intelligent controller (RIC) at the centre of its specification serves as an ML applications host. Various ML models, especially Reinforcement Learning (RL) models, are regarded as the key to solving RAN-related multi-objective optimization problems. However, it should be recognized that most of the current RL successes are confined to abstract and simplified simulation environments, which may not directly translate to high performance in complex real environments. One of the main reasons is the modelling gap between the simulation and the real environment, which could make the RL agent trained by simulation ill-equipped for the real environment. This issue is termed as the sim2real gap. This article brings to the fore the sim2real challenge within the context of O-RAN. Specifically, it emphasizes the characteristics, and benefits that the digital twins (DT) could have as a place for model development and verification. Several use cases are presented to exemplify and demonstrate failure modes of the simulations trained RL model in real environments. The effectiveness of DT in assisting the development of RL algorithms is discussed. Then the current state of the art learning-based methods commonly used to overcome the sim2real challenge are presented. Finally, the development and deployment concerns for the RL applications realisation in O-RAN are discussed from the view of the potential issues like data interaction, environment bottlenecks, and algorithm design.

Wei Wang, Peizheng Li, Angela Doufexi et al.

In reconfigurable intelligent surface (RIS)-assisted wireless communication systems, the pointing accuracy and intensity of reflections depend crucially on the 'profile,' representing the amplitude/phase state information of all elements in a RIS array. The superposition of multiple single-reflection profiles enables multi-reflection for distributed users. However, the optimization challenges from periodic element arrangements in single-reflection and multi-reflection profiles are understudied. The combination of periodical single-reflection profiles leads to amplitude/phase counteractions, affecting the performance of each reflection beam. This paper focuses on a dual-reflection optimization scenario and investigates the far-field performance deterioration caused by the misalignment of overlapped profiles. To address this issue, we introduce a novel deep reinforcement learning (DRL)-based optimization method. Comparative experiments against random and exhaustive searches demonstrate that our proposed DRL method outperforms both alternatives, achieving the shortest optimization time. Remarkably, our approach achieves a 1.2 dB gain in the reflection peak gain and a broader beam without any hardware modifications.

Peizheng Li, Adnan Aijaz, Tim Farnham et al.

Recently, the concept of digital twins (DTs) has received significant attention within the realm of 5G/6G. This demonstration shows an innovative DT design and implementation framework tailored toward integration within the 5G infrastructure. The proposed DT enables near real-time anomaly detection capability pertaining to user connectivity. It empowers the 5G system to proactively execute decisions for resource control and connection restoration.

Lina Zhang, Tonmoy Monsoor, Mehmet Efe Lorasdagi et al.

Multimodal Large Language Models (MLLMs) have demonstrated robust capabilities in recognizing everyday human activities, yet their potential for analyzing clinically significant involuntary movements in neurological disorders remains largely unexplored. This pilot study evaluates the capability of MLLMs for automated recognition of pathological movements in seizure videos. We assessed the zero-shot performance of state-of-the-art MLLMs on 20 ILAE-defined semiological features across 90 clinical seizure recordings. MLLMs outperformed fine-tuned Convolutional Neural Network (CNN) and Vision Transformer (ViT) baseline models on 13 of 18 features without task-specific training, demonstrating particular strength in recognizing salient postural and contextual features while struggling with subtle, high-frequency movements. Feature-targeted signal enhancement (facial cropping, pose estimation, audio denoising) improved performance on 10 of 20 features. Expert evaluation showed that 94.3 percent of MLLM-generated explanations for correctly predicted cases achieved at least 60 percent faithfulness scores, aligning with epileptologist reasoning. These findings demonstrate the potential of adapting general-purpose MLLMs for specialized clinical video analysis through targeted preprocessing strategies, offering a path toward interpretable, efficient diagnostic assistance. Our code is publicly available at https://github.com/LinaZhangUCLA/PathMotionMLLM.

Lina Zhang, Tonmoy Monsoor, Peizheng Li et al.

While Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficiency in general video understanding, their capacity to interpret involuntary, and spatio-temporally evolving pathologic motor behaviors such as seizure semiology remains largely untested. To address this gap, we introduce Seizure-Semiology-Suite, a clinically grounded dataset and benchmark for fine-grained, structured seizure semiology understanding. The dataset includes 438 seizure videos annotated with over 35,000 dense labels covering 20 ILAE-defined semiological features. Building on this dataset, we propose a seven-task hierarchical benchmark that systematically evaluates MLLMs from low-level visual perception to temporal sequencing, narrative report generation, and seizure diagnosis. To enable clinically meaningful evaluation of generated reports, we further introduce the Report Quality Index for Seizure Semiology (Seizure-RQI). Extensive baselines across 11 open-weight MLLMs reveal systematic weaknesses in laterality reasoning, temporal localization, symptom sequencing, and clinically faithful reporting. We show that seizure-specific fine-tuning substantially improves performance across tasks, and that a two-stage neuro-symbolic framework achieves an F1 score of 0.96 on epileptic versus non-epileptic seizure classification. Seizure-Semiology-Suite establishes a rigorous benchmark for evaluating multimodal models in safety-critical medical video understanding and guides the development of clinically reliable, domain-adaptive multimodal intelligence.

Xingchi Liu, Peizheng Li, Ziming Zhu

Radio signal-based (indoor) localisation technique is important for IoT applications such as smart factory and warehouse. Through machine learning, especially neural networks methods, more accurate mapping from signal features to target positions can be achieved. However, different radio protocols, such as WiFi, Bluetooth, etc., have different features in the transmitted signals that can be exploited for localisation purposes. Also, neural networks methods often rely on carefully configured models and extensive training processes to obtain satisfactory performance in individual localisation scenarios. The above poses a major challenge in the process of determining neural network model structure, or hyperparameters, as well as the selection of training features from the available data. This paper proposes a neural network model hyperparameter tuning and training method based on Bayesian optimisation. Adaptive selection of model hyperparameters and training features can be realised with minimal need for manual model training design. With the proposed technique, the training process is optimised in a more automatic and efficient way, enhancing the applicability of neural networks in localisation.

Peizheng Li, Shuxiao Ding, You Zhou et al.

Open-world 3D semantic occupancy prediction aims to generate a voxelized 3D representation from sensor inputs while recognizing both known and unknown objects. Transferring open-vocabulary knowledge from vision-language models (VLMs) offers a promising direction but remains challenging. However, methods based on VLM-derived 2D pseudo-labels with traditional supervision are limited by a predefined label space and lack general prediction capabilities. Direct alignment with pretrained image embeddings, on the other hand, often fails to achieve reliable performance because of inconsistent image and text representations in VLMs. To address these challenges, we propose AGO, a novel 3D occupancy prediction framework with adaptive grounding to handle diverse open-world scenarios. AGO first encodes surrounding images and class prompts into 3D and text embeddings, respectively, leveraging similarity-based grounding training with 3D pseudo-labels. Additionally, a modality adapter maps 3D embeddings into a space aligned with VLM-derived image embeddings, reducing modality gaps. Experiments on Occ3D-nuScenes show that AGO improves unknown object prediction in zero-shot and few-shot transfer while achieving state-of-the-art closed-world self-supervised performance, surpassing prior methods by 4.09 mIoU. Code is available at: https://github.com/EdwardLeeLPZ/AGO.

Peizheng Li, Xinyi Lin, Adnan Aijaz

Semantic communication promises task-aligned transmission but must reconcile semantic fidelity with stringent latency guarantees in immersive and safety-critical services. This paper introduces a time-constrained human-in-the-loop reinforcement learning (TC-HITL-RL) framework that embeds human feedback, semantic utility, and latency control within a semantic-aware Open radio access network (RAN) architecture. We formulate semantic adaptation driven by human feedback as a constrained Markov decision process (CMDP) whose state captures semantic quality, human preferences, queue slack, and channel dynamics, and solve it via a primal--dual proximal policy optimization algorithm with action shielding and latency-aware reward shaping. The resulting policy preserves PPO-level semantic rewards while tightening the variability of both air-interface and near-real-time RAN intelligent controller processing budgets. Simulations over point-to-multipoint links with heterogeneous deadlines show that TC-HITL-RL consistently meets per-user timing constraints, outperforms baseline schedulers in reward, and stabilizes resource consumption, providing a practical blueprint for latency-aware semantic adaptation.

Yuzhi Lai, Shenghai Yuan, Peizheng Li et al.

We present SEER-VAR, a novel framework for egocentric vehicle-based augmented reality (AR) that unifies semantic decomposition, Context-Aware SLAM Branches (CASB), and LLM-driven recommendation. Unlike existing systems that assume static or single-view settings, SEER-VAR dynamically separates cabin and road scenes via depth-guided vision-language grounding. Two SLAM branches track egocentric motion in each context, while a GPT-based module generates context-aware overlays such as dashboard cues and hazard alerts. To support evaluation, we introduce EgoSLAM-Drive, a real-world dataset featuring synchronized egocentric views, 6DoF ground-truth poses, and AR annotations across diverse driving scenarios. Experiments demonstrate that SEER-VAR achieves robust spatial alignment and perceptually coherent AR rendering across varied environments. As one of the first to explore LLM-based AR recommendation in egocentric driving, we address the lack of comparable systems through structured prompting and detailed user studies. Results show that SEER-VAR enhances perceived scene understanding, overlay relevance, and driver ease, providing an effective foundation for future research in this direction. Code and dataset will be made open source.

Peizheng Li, Zhenghao Zhang, David Holtz et al.

End-to-end autonomous driving methods built on vision language models (VLMs) have undergone rapid development driven by their universal visual understanding and strong reasoning capabilities obtained from the large-scale pretraining. However, we find that current VLMs struggle to understand fine-grained 3D spatial relationships which is a fundamental requirement for systems interacting with the physical world. To address this issue, we propose SpaceDrive, a spatial-aware VLM-based driving framework that treats spatial information as explicit positional encodings (PEs) instead of textual digit tokens, enabling joint reasoning over semantic and spatial representations. SpaceDrive employs a universal positional encoder to all 3D coordinates derived from multi-view depth estimation, historical ego-states, and text prompts. These 3D PEs are first superimposed to augment the corresponding 2D visual tokens. Meanwhile, they serve as a task-agnostic coordinate representation, replacing the digit-wise numerical tokens as both inputs and outputs for the VLM. This mechanism enables the model to better index specific visual semantics in spatial reasoning and directly regress trajectory coordinates rather than generating digit-by-digit, thereby enhancing planning accuracy. Extensive experiments validate that SpaceDrive achieves state-of-the-art open-loop performance on the nuScenes dataset and the second-best Driving Score of 78.02 on the Bench2Drive closed-loop benchmark over existing VLM-based methods.

Yuzhi Lai, Shenghai Yuan, Peizheng Li et al.

Gaze is a valuable means of communication for impaired people with extremely limited motor capabilities. However, robust gaze-based intent recognition in multi-object environments is challenging due to gaze noise, micro-saccades, viewpoint changes, and dynamic objects. To address this, we propose an object-centric gaze grounding framework that stabilizes intent through a sticky-glance algorithm, jointly modeling geometric distance and direction trends. The inferred intent remains anchored to the object even under short glances with minimal 3 gaze samples, achieving a tracking rate of 0.94 for dynamic targets and selection accuracy of 0.98 for static targets. We further introduce a continuous shared control and multi-modal interaction paradigm, enabling high-readiness control and human-in-loop feedback, thereby reducing task duration for nearly 10 \%. Experiments across dynamic tracking, multi-perspective alignment, a baseline comparison, user studies, and ablation studies demonstrate improved robustness, efficiency, and reduced workload compared to representative baselines.

Adrián Sánchez-Mompó, Ioannis Mavromatis, Peizheng Li et al.

This study presents an empirical investigation into the energy consumption of Discriminative and Generative AI models within real-world MLOps pipelines. For Discriminative models, we examine various architectures and hyperparameters during training and inference and identify energy-efficient practices. For Generative AI, Large Language Models (LLMs) are assessed, focusing primarily on energy consumption across different model sizes and varying service requests. Our study employs software-based power measurements, ensuring ease of replication across diverse configurations, models, and datasets. We analyse multiple models and hardware setups to uncover correlations among various metrics, identifying key contributors to energy consumption. The results indicate that for Discriminative models, optimising architectures, hyperparameters, and hardware can significantly reduce energy consumption without sacrificing performance. For LLMs, energy efficiency depends on balancing model size, reasoning complexity, and request-handling capacity, as larger models do not necessarily consume more energy when utilisation remains low. This analysis provides practical guidelines for designing green and sustainable ML operations, emphasising energy consumption and carbon footprint reductions while maintaining performance. This paper can serve as a benchmark for accurately estimating total energy use across different types of AI models.

Shuxiao Ding, Yutong Yang, Julian Wiederer et al.

Query denoising has become a standard training strategy for DETR-based detectors by addressing the slow convergence issue. Besides that, query denoising can be used to increase the diversity of training samples for modeling complex scenarios which is critical for Multi-Object Tracking (MOT), showing its potential in MOT application. Existing approaches integrate query denoising within the tracking-by-attention paradigm. However, as the denoising process only happens within the single frame, it cannot benefit the tracker to learn temporal-related information. In addition, the attention mask in query denoising prevents information exchange between denoising and object queries, limiting its potential in improving association using self-attention. To address these issues, we propose TQD-Track, which introduces Temporal Query Denoising (TQD) tailored for MOT, enabling denoising queries to carry temporal information and instance-specific feature representation. We introduce diverse noise types onto denoising queries that simulate real-world challenges in MOT. We analyze our proposed TQD for different tracking paradigms, and find out the paradigm with explicit learned data association module, e.g. tracking-by-detection or alternating detection and association, benefit from TQD by a larger margin. For these paradigms, we further design an association mask in the association module to ensure the consistent interaction between track and detection queries as during inference. Extensive experiments on the nuScenes dataset demonstrate that our approach consistently enhances different tracking methods by only changing the training process, especially the paradigms with explicit association module.

Peizheng Li, Ioannis Mavromatis, Tim Farnham et al.

Seamless integration of artificial intelligence (AI) and machine learning (ML) techniques with wireless systems is a crucial step for 6G AInization. However, such integration faces challenges in terms of model functionality and lifecycle management. ML operations (MLOps) offer a systematic approach to tackle these challenges. Existing approaches toward implementing MLOps in a centralized platform often overlook the challenges posed by diverse learning paradigms and network heterogeneity. This article provides a new approach to MLOps targeting the intricacies of future wireless networks. Considering unique aspects of the future radio access network (RAN), we formulate three operational pipelines, namely reinforcement learning operations (RLOps), federated learning operations (FedOps), and generative AI operations (GenOps). These pipelines form the foundation for seamlessly integrating various learning/inference capabilities into networks. We outline the specific challenges and proposed solutions for each operation, facilitating large-scale deployment of AI-Native 6G networks.

Peizheng Li, Adnan Aijaz

The convergence of robotics, advanced communication networks, and artificial intelligence (AI) holds the promise of transforming industries through fully automated and intelligent operations. In this work, we introduce a novel co-working framework for robots that unifies goal-oriented semantic communication (SemCom) with a Generative AI (GenAI)-agent under a semantic-aware network. SemCom prioritizes the exchange of meaningful information among robots and the network, thereby reducing overhead and latency. Meanwhile, the GenAI-agent leverages generative AI models to interpret high-level task instructions, allocate resources, and adapt to dynamic changes in both network and robotic environments. This agent-driven paradigm ushers in a new level of autonomy and intelligence, enabling complex tasks of networked robots to be conducted with minimal human intervention. We validate our approach through a multi-robot anomaly detection use-case simulation, where robots detect, compress, and transmit relevant information for classification. Simulation results confirm that SemCom significantly reduces data traffic while preserving critical semantic details, and the GenAI-agent ensures task coordination and network adaptation. This synergy provides a robust, efficient, and scalable solution for modern industrial environments.

Peizheng Li, Xinyi Lin, Adnan Aijaz

Error detection and correction are essential for ensuring robust and reliable operation in modern communication systems, particularly in complex transmission environments. However, discussions on these topics have largely been overlooked in semantic communication (SemCom), which focuses on transmitting meaning rather than symbols, leading to significant improvements in communication efficiency. Despite these advantages, semantic errors -- stemming from discrepancies between transmitted and received meanings -- present a major challenge to system reliability. This paper addresses this gap by proposing a comprehensive framework for detecting and correcting semantic errors in SemCom systems. We formally define semantic error, detection, and correction mechanisms, and identify key sources of semantic errors. To address these challenges, we develop a Gaussian process (GP)-based method for latent space monitoring to detect errors, alongside a human-in-the-loop reinforcement learning (HITL-RL) approach to optimize semantic model configurations using user feedback. Experimental results validate the effectiveness of the proposed methods in mitigating semantic errors under various conditions, including adversarial attacks, input feature changes, physical channel variations, and user preference shifts. This work lays the foundation for more reliable and adaptive SemCom systems with robust semantic error management techniques.

Peizheng Li, Ioannis Mavromatis, Ajith Sahadevan et al.

We present a large-scale, longitudinal visual dataset of urban streetlights captured by 22 fixed-angle cameras deployed across Bristol, U.K., from 2021 to 2025. The dataset contains over 526,000 images, collected hourly under diverse lighting, weather, and seasonal conditions. Each image is accompanied by rich metadata, including timestamps, GPS coordinates, and device identifiers. This unique real-world dataset enables detailed investigation of visual drift, anomaly detection, and MLOps strategies in smart city deployments. To promtoe seconardary analysis, we additionally provide a self-supervised framework based on convolutional variational autoencoders (CNN-VAEs). Models are trained separately for each camera node and for day/night image sets. We define two per-sample drift metrics: relative centroid drift, capturing latent space deviation from a baseline quarter, and relative reconstruction error, measuring normalized image-domain degradation. This dataset provides a realistic, fine-grained benchmark for evaluating long-term model stability, drift-aware learning, and deployment-ready vision systems. The images and structured metadata are publicly released in JPEG and CSV formats, supporting reproducibility and downstream applications such as streetlight monitoring, weather inference, and urban scene understanding. The dataset can be found at https://doi.org/10.5281/zenodo.17781192 and https://doi.org/10.5281/zenodo.17859120.

Wei Wang, Peizheng Li, Angela Doufexi et al.

Optimizing discrete phase shifts in large-scale reconfigurable intelligent surfaces (RISs) is challenging due to their non-convex and non-linear nature. In this letter, we propose a heuristic-integrated deep reinforcement learning (DRL) framework that (1) leverages accumulated actions over multiple steps in the double deep Q-network (DDQN) for RIS column-wise control and (2) integrates a greedy algorithm (GA) into each DRL step to refine the state via fine-grained, element-wise optimization of RIS configurations. By learning from GA-included states, the proposed approach effectively addresses RIS optimization within a small DRL action space, demonstrating its capability to optimize phase-shift configurations of large-scale RISs.

Haiyuan Li, Hari Madhukumar, Peizheng Li et al.

Deep Reinforcement Learning (DRL) has emerged as a powerful solution for meeting the growing demands for connectivity, reliability, low latency and operational efficiency in advanced networks. However, most research has focused on theoretical analysis and simulations, with limited investigation into real-world deployment. To bridge the gap and support practical DRL deployment for network management, we first present an orchestration framework that integrates ETSI Multi-access Edge Computing (MEC) with Open RAN, enabling seamless adoption of DRL-based strategies across different time scales while enhancing agent lifecycle management. We then identify three critical challenges hindering DRL's real-world deployment, including (1) asynchronous requests from unpredictable or bursty traffic, (2) adaptability and generalization across heterogeneous topologies and evolving service demands, and (3) prolonged convergence and service interruptions due to exploration in live operational environments. To address these challenges, we propose a three-fold solution strategy: (a) advanced time-series integration for handling asynchronized traffic, (b) flexible architecture design such as multi-agent DRL and incremental learning to support heterogeneous scenarios, and (c) simulation-driven deployment with transfer learning to reduce convergence time and service disruptions. Lastly, the feasibility of the MEC-O-RAN architecture is validated on an urban-wide testing infrastructure, and two real-world use cases are presented, showcasing the three identified challenges and demonstrating the effectiveness of the proposed solutions.

Jikun Gao, Ioannis Mavromatis, Peizheng Li et al.

Federated learning (FL) systems face performance challenges in dealing with heterogeneous devices and non-identically distributed data across clients. We propose a dynamic global model aggregation method within Asynchronous Federated Learning (AFL) deployments to address these issues. Our aggregation method scores and adjusts the weighting of client model updates based on their upload frequency to accommodate differences in device capabilities. Additionally, we also immediately provide an updated global model to clients after they upload their local models to reduce idle time and improve training efficiency. We evaluate our approach within an AFL deployment consisting of 10 simulated clients with heterogeneous compute constraints and non-IID data. The simulation results, using the FashionMNIST dataset, demonstrate over 10% and 19% improvement in global model accuracy compared to state-of-the-art methods PAPAYA and FedAsync, respectively. Our dynamic aggregation method allows reliable global model training despite limiting client resources and statistical data heterogeneity. This improves robustness and scalability for real-world FL deployments.

Peizheng Li, Ioannis Mavromatis, Aftab Khan

UMBRELLA is a large-scale, open-access Internet of Things (IoT) ecosystem incorporating over 200 multi-sensor multi-wireless nodes, 20 collaborative robots, and edge-intelligence-enabled devices. This paper provides a guide to the implemented and prospective artificial intelligence (AI) capabilities of UMBRELLA in real-world IoT systems. Four existing UMBRELLA applications are presented in detail: 1) An automated streetlight monitoring for detecting issues and triggering maintenance alerts; 2) A Digital twin of building environments providing enhanced air quality sensing with reduced cost; 3) A large-scale Federated Learning framework for reducing communication overhead; and 4) An intrusion detection for containerised applications identifying malicious activities. Additionally, the potential of UMBRELLA is outlined for future smart city and multi-robot crowdsensing applications enhanced by semantic communications and multi-agent planning. Finally, to realise the above use-cases we discuss the need for a tailored MLOps platform to automate UMBRELLA model pipelines and establish trust.

Peizheng Li, Jonathan Thomas, Xiaoyang Wang et al.

Radio access network (RAN) technologies continue to evolve, with Open RAN gaining the most recent momentum. In the O-RAN specifications, the RAN intelligent controllers (RICs) are software-defined orchestration and automation functions for the intelligent management of RAN. This article introduces principles for machine learning (ML), in particular, reinforcement learning (RL) applications in the O-RAN stack. Furthermore, we review the state-of-the-art research in wireless networks and cast it onto the RAN framework and the hierarchy of the O-RAN architecture. We provide a taxonomy for the challenges faced by ML/RL models throughout the development life-cycle: from the system specification to production deployment (data acquisition, model design, testing and management, etc.). To address the challenges, we integrate a set of existing MLOps principles with unique characteristics when RL agents are considered. This paper discusses a systematic model development, testing and validation life-cycle, termed: RLOps. We discuss fundamental parts of RLOps, which include: model specification, development, production environment serving, operations monitoring and safety/security. Based on these principles, we propose the best practices for RLOps to achieve an automated and reproducible model development process. At last, a holistic data analytics platform rooted in the O-RAN deployment is designed and implemented, aiming to embrace and fulfil the aforementioned principles and best practices of RLOps.

Peizheng Li, Han Cui, Aftab Khan et al.

This paper studies a WiFi indoor localisation technique based on using a deep learning model and its transfer strategies. We take CSI packets collected via the WiFi standard channel sounding as the training dataset and verify the CNN model on the subsets collected in three experimental environments. We achieve a localisation accuracy of 46.55 cm in an ideal $(6.5m \times 2.5m)$ office with no obstacles, 58.30 cm in an office with obstacles, and 102.8 cm in a sports hall $(40 \times 35m)$. Then, we evaluate the transfer ability of the proposed model to different environments. The experimental results show that, for a trained localisation model, feature extraction layers can be directly transferred to other models and only the fully connected layers need to be retrained to achieve the same baseline accuracy with non-transferred base models. This can save 60% of the training parameters and reduce the training time by more than half. Finally, an ablation study of the training dataset shows that, in both office and sport hall scenarios, after reusing the feature extraction layers of the base model, only 55% of the training data is required to obtain the models' accuracy similar to the base models.

Peizheng Li, Han Cui, Aftab Khan et al.

This paper studies the indoor localisation of WiFi devices based on a commodity chipset and standard channel sounding. First, we present a novel shallow neural network (SNN) in which features are extracted from the channel state information (CSI) corresponding to WiFi subcarriers received on different antennas and used to train the model. The single-layer architecture of this localisation neural network makes it lightweight and easy-to-deploy on devices with stringent constraints on computational resources. We further investigate for localisation the use of deep learning models and design novel architectures for convolutional neural network (CNN) and long-short term memory (LSTM). We extensively evaluate these localisation algorithms for continuous tracking in indoor environments. Experimental results prove that even an SNN model, after a careful handcrafted feature extraction, can achieve accurate localisation. Meanwhile, using a well-organised architecture, the neural network models can be trained directly with raw data from the CSI and localisation features can be automatically extracted to achieve accurate position estimates. We also found that the performance of neural network-based methods are directly affected by the number of anchor access points (APs) regardless of their structure. With three APs, all neural network models proposed in this paper can obtain localisation accuracy of around 0.5 metres. In addition the proposed deep NN architecture reduces the data pre-processing time by 6.5 hours compared with a shallow NN using the data collected in our testbed. In the deployment phase, the inference time is also significantly reduced to 0.1 ms per sample. We also demonstrate the generalisation capability of the proposed method by evaluating models using different target movement characteristics to the ones in which they were trained.