DBDavid Boyle

David Boyle

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


David Boyle has a total of 68 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Dual Actor DDPG for Airborne STAR-RIS assisted communications

    by Danish Rizvi, David Boyle

  • Open Access

    Explainable Reinforcement and Causal Learning for Improving Trust to 6G Stakeholders

    by Miguel Arana-Catania, Amir Sonee, Abdul-Manan Khan, Kavan Fatehi, Yun Tang, Bailu Jin, Anna Soligo, David Boyle, Radu Calinescu, Poonam Yadav, et al.

    Future telecommunications will increasingly integrate AI capabilities into network infrastructures to deliver seamless and harmonized services closer to end-users. However, this progress also raises significant trust and safety concerns. The machine learning systems orchestrating these advanced services will widely rely on deep reinforcement learning (DRL) to process multi-modal requirements datasets and make semantically modulated decisions, introducing three major challenges: (1) First, we acknowledge that most explainable AI research is stakeholder-agnostic while, in reality, the explanations must cater for diverse telecommunications stakeholders, including network service providers, legal authorities, and end users, each with unique goals and operational practices; (2) Second, DRL lacks prior models or established frameworks to guide the creation of meaningful long-term explanations of the agent’s behaviour in a goal-oriented RL task, and we introduce state-of-the-art approaches such as reward machine and sub-goal automata that can be universally represented and easily manipulated by logic programs and verifiably learned by inductive logic programming of answer set programs; (3) Third, most explainability approaches focus on correlation rather than causation, and we emphasise that understanding causal learning can further enhance 6G network optimisation. Together, in our judgement they form crucial enabling technologies for trustworthy services in 6G. This review offers a timely resource for academic researchers and industry practitioners by highlighting the methodological advancements needed for explainable DRL (X-DRL) in 6G. It identifies key stakeholder groups, maps their needs to X-DRL solutions, and presents case studies showcasing practical applications. By identifying and analysing these challenges in the context of 6G case studies, this work aims to inform future research, transform industry practices, and highlight unresolved gaps in this rapidly evolving field.


  • Is That Rain? Understanding Effects on Visual Odometry Performance for Autonomous AAVs and Efficient DNN-Based Rain Classification at the Edge

    by Andrea Albanese, Yanran Wang, Davide Brunelli, David Boyle

    The development of safe and reliable autonomous unmanned aerial vehicles relies on the ability of the system to recognise and adapt to changes in the local environment based on sensor inputs. State-of-the-art local tracking and trajectory planning are typically performed using camera sensor input to the flight control algorithm, but the extent to which environmental disturbances like rain affect the performance of these systems is largely unknown. In this paper, we first describe the development of an open dataset comprising 335k images to examine these effects for seven different classes of precipitation conditions and show that a worst-case average tracking error of 1.5 m is possible for a state-of-the-art visual odometry system (VINS-Fusion). We then use the dataset to train a set of deep neural network models suited to mobile and constrained deployment scenarios to determine the extent to which it may be possible to efficiently and accurately classify these ‘rainy’ conditions. The most lightweight of these models (MobileNetV3 small) can achieve an accuracy of 90% with a memory footprint of just 1.28 MB and a frame rate of 93 FPS, which is suitable for deployment in resource-constrained and latency-sensitive systems. We demonstrate a classification latency in the order of milliseconds using typical flight computer hardware. Accordingly, such a model can feed into the disturbance estimation component of an autonomous flight controller. In addition, data from unmanned aerial vehicles with the ability to accurately determine environmental conditions in real time may contribute to developing more granular timely localised weather forecasting.


  • Adaptive Probabilistic Planning for the Uncertain and Dynamic Orienteering Problem

    by Qiuchen Qian, Yanran Wang, David Boyle

    The orienteering problem (OP) is a well-studied routing problem that has been extended to incorporate uncertainties, reflecting stochastic or dynamic travel costs, prize-collection costs, and prizes. Existing approaches may, however, be inefficient in real-world applications due to insufficient modeling knowledge and initially unknowable parameters in online scenarios. Thus, we propose the uncertain and dynamic OP (UDOP), modeling travel costs as distributions with unknown and time-variant parameters. UDOP also associates uncertain travel costs with dynamic prizes and prize-collection costs for its objective and budget constraints. To address UDOP, we develop an Adaptive Approach for Probabilistic paths (ADAPT), iteratively performing “execution” and “online planning” based on an initial “offline” solution. The execution phase updates the system status and records online cost observations. The online planner employs a Bayesian approach to adaptively estimate power consumption and optimize path sequence based on safety beliefs. We evaluate ADAPT in a practical autonomous aerial vehicle charging scheduling problem (CSP) for wireless rechargeable sensor networks (WRSNs). The UAV must optimize its path to recharge sensor nodes efficiently while managing its energy under uncertain conditions. ADAPT maintains comparable solution quality and computation time while offering superior robustness. Extensive simulations show that ADAPT achieves a 100% mission success rate (MSR) across all tested scenarios, outperforming comparable heuristic-based and frequentist approaches that fail up to 70% (under challenging conditions) and averaging 67% MSR, respectively. This work advances the field of OP with uncertainties, offering a reliable and efficient approach for real-world applications in uncertain and dynamic environments.


  • Open Access

    Multi-Agent Reinforcement Learning With Action Masking for UAV-Enabled Mobile Communications

    by Danish Rizvi, David Boyle

    Unmanned Aerial Vehicles (UAVs) are increasingly used as aerial base stations to provide ad hoc communications infrastructure. Building upon prior research efforts which consider either static nodes, 2D trajectories or single UAV systems, this paper focuses on the use of multiple UAVs for providing wireless communication to mobile users in the absence of terrestrial communications infrastructure. In particular, we jointly optimize UAV 3D trajectory and NOMA power allocation to maximize system throughput. Firstly, a weighted K-means-based clustering algorithm establishes UAV-user associations at regular intervals. Then the efficacy of training a novel Shared Deep Q-Network (SDQN) with action masking is explored. Unlike training each UAV separately using DQN, the SDQN reduces training time by using the experiences of multiple UAVs instead of a single agent. We also show that SDQN can be used to train a multi-agent system with differing action spaces. Simulation results confirm that: 1) training a shared DQN outperforms a conventional DQN in terms of maximum system throughput (+20%) and training time (-10%); 2) it can converge for agents with different action spaces, yielding a 9% increase in throughput compared to Mutual DQN algorithm; and 3) combining NOMA with an SDQN architecture enables the network to achieve a better sum rate compared with existing baseline schemes.


  • Constrained Reinforcement Learning Using Distributional Representation for Trustworthy Quadrotor UAV Tracking Control

    by Yanran Wang, David Boyle

    Simultaneously accurate and reliable tracking control for quadrotors in complex dynamic environments is challenging. The chaotic nature of aerodynamics, derived from drag forces and moment variations, makes precise identification difficult. Consequently, many existing quadrotor tracking systems treat these aerodynamic effects as simple ‘disturbances’ in conventional control approaches. We propose a novel and interpretable trajectory tracker integrating a distributional Reinforcement Learning (RL) disturbance estimator for unknown aerodynamic effects with a Stochastic Model Predictive Controller (SMPC). Specifically, the proposed estimator ‘Constrained Distributional REinforced-Disturbance-estimator’ (ConsDRED) effectively identifies uncertainties between the true and estimated values of aerodynamic effects. Control parameterization employs simplified affine disturbance feedback to ensure convexity, which is seamlessly integrated with the SMPC. We theoretically guarantee that ConsDRED achieves an optimal global convergence rate, and sublinear rates if constraints are violated with certain error decreases as neural network dimensions increase. To demonstrate practicality, we show convergent training, in simulation and real-world experiments, and empirically verify that ConsDRED is less sensitive to hyperparameter settings compared with canonical constrained RL. Our system substantially improves accumulative tracking errors by at least 70%, compared with the recent art. Importantly, the proposed ConsDRED-SMPC framework balances the trade-off between pursuing high performance and obeying conservative constraints for practical implementations. Note to Practitioners —This work is motivated by challenges in training Reinforcement Learning (RL) for autonomous navigation in unmanned aerial vehicles, but its implications extend to other high-criticality applications in, for example, healthcare and financial services. The implementation of RL algorithm policies may exhibit various deficiencies, including (i) opaque or unstable training due to the blackbox nature of deep neural networks, (ii) difficulty in reproducing RL outcomes, and (iii) heightened costs associated with robustness investigation, e.g., hyperparameter tuning and generalization. We present a novel ‘Constrained Distributional REinforced-Disturbance-estimator’ (ConsDRED) to identify uncertainties arising from aerodynamic disturbances in agile flight. The proposed algorithm demonstrates at least an optimal convergence rate for both global optimization and constraint violations. Theoretical guarantees offered by this approach can make training convergence processes more transparent and provide a degree of confidence in the expected convergence outcomes in real-world applications, thereby addressing, to a considerable extent, the deficiencies related to (i) and (ii). Our robustness investigation, related to (iii), empirically demonstrates that ConsDRED is significantly less sensitive to hyperparameter settings compared to traditional constrained RL approaches. The experiments further showcase the generalization capability of ConsDRED by introducing new and previously unseen external forces in real-world scenarios. While ConsDRED strikes a reasonable balance between performance and interpretability, there remains a trade-off with conservative decision-making. Hence, we must strike a balance between the desired degree of interpretability and the acceptable level of scalability in RL algorithms. Our proposed flight control framework evidences such a balance between high performance and safety constraints. A fundamental limitation is the computational complexity, where we sample at 16 Hz for disturbance estimation owing to limited onboard computational resources. This may be improved in the future by implementing dedicated hardware.


  • Open Access

    High-Frequency Inductive Power Transfer Through Soil for Agricultural Applications

    by Juan M. Arteaga, John Sanchez, Faraj Elsakloul, Maria Marin, Cody Zesiger, Nunzio Pucci, Gareth J. Norton, Darrin J. Young, David. E. Boyle, Eric. M. Yeatman, et al.

    This paper presents 13.56 MHz inductive power transfer (IPT) through soil for sensors in agricultural applications. Two IPT system designs and their prototypes are presented. The first was designed for gathering data and observing the relationship between the performance of the coil driving circuits in response to water content, salinity, organic matter and compaction of the soil. The second prototype was designed as an application demonstrator, featuring IPT to an in-house sensor node enclosure buried 200 mm under the surface of an agricultural field. The results highlight that from the parameters studied, the combination of high salinity and high water content significantly increases the losses of the IPT system. The experiments demonstrate an over 40% rise in the losses from dc source to dc load after a 16% increase in soil water content and high salinity. In the technology demonstrator we mounted an IPT transmitter on a drone to wirelessly power an in-house bank of supercapacitors in the buried sensor-node enclosure. A peak power transfer of 30 W received at over 40% efficiency was achieved from a 22 V power supply on the drone to the energy storage under the ground. The coil separation in these experiments was 250 mm of which 200 mm correspond to the layer of soil. The coupling factor in all the experiments was lower than 5%. This system was trialled in the field for forty days and wireless power was performed five times throughout.


  • Open Access

    Paralinguistic Privacy Protection at the Edge

    by Ranya Aloufi, Hamed Haddadi, David Boyle

    Voice user interfaces and digital assistants are rapidly entering our lives and becoming singular touch points spanning our devices. These always-on services capture and transmit our audio data to powerful cloud services for further processing and subsequent actions. Our voices and raw audio signals collected through these devices contain a host of sensitive paralinguistic information that is transmitted to service providers regardless of deliberate or false triggers. As our emotional patterns and sensitive attributes like our identity, gender, and well-being are easily inferred using deep acoustic models, we encounter a new generation of privacy risks by using these services. One approach to mitigate the risk of paralinguistic-based privacy breaches is to exploit a combination of cloud-based processing with privacy-preserving, on-device paralinguistic information learning and filtering before transmitting voice data. In this article we introduce EDGY , a configurable, lightweight, disentangled representation learning framework that transforms and filters high-dimensional voice data to identify and contain sensitive attributes at the edge prior to offloading to the cloud. We evaluate EDGY’s on-device performance and explore optimization techniques, including model quantization and knowledge distillation, to enable private, accurate, and efficient representation learning on resource-constrained devices. Our results show that EDGY runs in tens of milliseconds with 0.2% relative improvement in “zero-shot” ABX score or minimal performance penalties of approximately 5.95% word error rate (WER) in learning linguistic representations from raw voice signals, using a CPU and a single-core ARM processor without specialized hardware.


  • Open Access

    5-axis multi-material 3D printing of curved electrical traces

    by Freddie Hong, Borut Lampret, Connor Myant, Steve Hodges, David Boyle