Interpretability in reinforcement learning is crucial for ensuring AI systems align with human values and fulfill the diverse related requirements including safety, robustness and fairness. Building on recent approaches to encouraging sparsity and locality in neural networks, we demonstrate how the penalisation of non-local weights leads to the emergence of functionally independent modules in the policy network of a reinforcement learning agent. To illustrate this, we demonstrate the emergence of two parallel modules for assessment of movement along the X and Y axes in a stochastic Minigrid environment. Through the novel application of community detection algorithms, we show how these modules can be automatically identified and their functional roles verified through direct intervention on the network weights prior to inference. This establishes a scalable framework for reinforcement learning interpretability through functional modularity, addressing challenges regarding the trade-off between completeness and cognitive tractability of reinforcement learning explanations.

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.

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. The efficacy of training a novel Shared Deep Q-Network (SDQN) with action masking is then 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 learning algorithms; and 3) combining NOMA with an SDQN architecture enables the network to achieve a better sum rate compared with existing baseline schemes.

The Close Enough Traveling Salesman Problem (CETSP) is a well-known variant of the classic Traveling Salesman Problem whereby the agent may complete its mission at any point within a target neighborhood. Heuristics based on overlapped neighborhoods, known as Steiner Zones (SZ), have gained attention in addressing CETSPs. While SZs offer effective approximations to the original graph, their inherent overlap imposes constraints on the search space, potentially conflicting with global optimization objectives. Here we present the Close Enough Orienteering Problem with Non-uniform Neighborhoods (CEOP-N), which extends CETSP by introducing variable prize attributes and non-uniform cost considerations for prize collection. To tackle CEOP-N, we develop a new approach featuring a Randomized Steiner Zone Discretization (RSZD) scheme coupled with a hybrid algorithm based on Particle Swarm Optimization (PSO) and Ant Colony System (ACS) - CRaSZe-AntS. The RSZD scheme identifies sub-regions for PSO exploration, and ACS determines the discrete visiting sequence. We evaluate the RSZD's discretization performance on CEOP instances derived from established CETSP instances, and compare CRaSZe-AntS against the most relevant state-of-the-art heuristic focused on single-neighborhood optimization for CEOP. We also compare the performance of the interior search within SZs and the boundary search on individual neighborhoods in the context of CEOP-N. Our results show CRaSZe-AntS can yield comparable solution quality with significantly reduced computation time compared to the single-neighborhood strategy, where we observe an averaged 140.44% increase in prize collection and 55.18% reduction of execution time. CRaSZe-AntS is thus highly effective in solving emerging CEOP-N, examples of which include truck-and-drone delivery scenarios.

Simultaneously accurate and reliable tracking control for quadrotors in complex dynamic environments is challenging. As aerodynamics derived from drag forces and moment variations are chaotic and difficult to precisely identify, most current quadrotor tracking systems treat them as simple `disturbances' in conventional control approaches. We propose a novel, interpretable trajectory tracker integrating a Distributional Reinforcement Learning disturbance estimator for unknown aerodynamic effects with a Stochastic Model Predictive Controller (SMPC). The proposed estimator `Constrained Distributional Reinforced disturbance estimator' (ConsDRED) accurately identifies uncertainties between true and estimated values of aerodynamic effects. Simplified Affine Disturbance Feedback is used for control parameterization to guarantee convexity, which we then integrate with a SMPC. We theoretically guarantee that ConsDRED achieves at least an optimal global convergence rate and a certain sublinear rate if constraints are violated with an error decreases as the width and the layer of neural network 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 approaches. We demonstrate our system improves accumulative tracking errors by at least 70% compared with the recent art. Importantly, the proposed framework, ConsDRED-SMPC, balances the tradeoff between pursuing high performance and obeying conservative constraints for practical implementations

Reinforcement Learning or optimal control can provide effective reasoning for sequential decision-making problems with variable dynamics. Such reasoning in practical implementation, however, poses a persistent challenge in interpreting the reward function and corresponding optimal policy. Consequently, formalizing the sequential decision-making problems as inference has a considerable value, as probabilistic inference in principle offers diverse and powerful mathematical tools to infer the stochastic dynamics whilst suggesting a probabilistic interpretation of the reward design and policy convergence. In this study, we propose a novel Adaptive Wasserstein Variational Optimization (AWaVO) to tackle these challenges in sequential decision-making. Our approach utilizes formal methods to provide interpretations of reward design, transparency of training convergence, and probabilistic interpretation of sequential decisions. To demonstrate practicality, we show convergent training with guaranteed global convergence rates not only in simulation but also in real robot tasks, and empirically verify a reasonable tradeoff between high performance and conservative interpretability.

Optimal maintenance of sensor nodes in a Wireless Rechargeable Sensor Network (WRSN) requires effective scheduling of power delivery vehicles by solving the Charging Scheduling Problem (CSP). Deploying Unmanned Aerial Vehicles (UAVs) as mobile chargers has emerged as a promising solution due to their mobility and flexibility. The CSP can be formulated as a Mixed-Integer Non-Linear Programming problem whose optimization objective is maximizing the recharged energy of sensor nodes within the UAV battery constraint. While many studies have demonstrated satisfactory performance of heuristic algorithms in addressing specific routing problems, few studies explore online updating (i.e., mission re-planning `on the fly') in the CSP context. Here we present a new offline and online mission planner leveraging a first-principles power consumption model that uses real-time state information and environmental information. The planner, namely Rapid Online Metaheuristic-based Planner (ROMP), supplements solutions from a Guided Local Search (GLS) with our Context-aware Black Hole Algorithm. Our results demonstrate that ROMP outperforms GLS in most cases tested. We developed and proposed FastROMP to speed up the online mission (re-)planning algorithm by introducing a new online adjustment operator that uses the latest state information as input, eliminating the need for re-initialization. FastROMP not only provides a better quality route, but it also significantly reduces computational time. The reduction ranges from 39.57% in sparse deployment to 93.3% in denser deployments.

Accuracy and stability are common requirements for Quadrotor trajectory tracking systems. Designing an accurate and stable tracking controller remains challenging, particularly in unknown and dynamic environments with complex aerodynamic disturbances. We propose a Quantile-approximation-based Distributional-reinforced Uncertainty Estimator (QuaDUE) to accurately identify the effects of aerodynamic disturbances, i.e., the uncertainties between the true and estimated Control Contraction Metrics (CCMs). Taking inspiration from contraction theory and integrating the QuaDUE for uncertainties, our novel CCM-based trajectory tracking framework tracks any feasible reference trajectory precisely whilst guaranteeing exponential convergence. More importantly, the convergence and training acceleration of the distributional RL are guaranteed and analyzed, respectively, from theoretical perspectives. We also demonstrate our system under unknown and diverse aerodynamic forces. Under large aerodynamic forces (>2m/s^2), compared with the classic data-driven approach, our QuaDUE-CCM achieves at least a 56.6% improvement in tracking error. Compared with QuaDRED-MPC, a distributional RL-based approach, QuaDUE-CCM achieves at least a 3 times improvement in contraction rate.

This paper presents a novel trajectory tracker for autonomous quadrotor navigation in dynamic and complex environments. The proposed framework integrates a distributional Reinforcement Learning (RL) estimator for unknown aerodynamic effects into a Stochastic Model Predictive Controller (SMPC) for trajectory tracking. Aerodynamic effects derived from drag forces and moment variations are difficult to model directly and accurately. Most current quadrotor tracking systems therefore treat them as simple `disturbances' in conventional control approaches. We propose Quantile-approximation-based Distributional Reinforced-disturbance-estimator, an aerodynamic disturbance estimator, to accurately identify disturbances, i.e., uncertainties between the true and estimated values of aerodynamic effects. Simplified Affine Disturbance Feedback is employed for control parameterization to guarantee convexity, which we then integrate with a SMPC to achieve sufficient and non-conservative control signals. We demonstrate our system to improve the cumulative tracking errors by at least 66% with unknown and diverse aerodynamic forces compared with recent state-of-the-art. Concerning traditional Reinforcement Learning's non-interpretability, we provide convergence and stability guarantees of Distributional RL and SMPC, respectively, with non-zero mean disturbances.

Voice-enabled interactions provide more human-like experiences in many popular IoT systems. Cloud-based speech analysis services extract useful information from voice input using speech recognition techniques. The voice signal is a rich resource that discloses several possible states of a speaker, such as emotional state, confidence and stress levels, physical condition, age, gender, and personal traits. Service providers can build a very accurate profile of a user's demographic category, personal preferences, and may compromise privacy. To address this problem, a privacy-preserving intermediate layer between users and cloud services is proposed to sanitize the voice input. It aims to maintain utility while preserving user privacy. It achieves this by collecting real time speech data and analyzes the signal to ensure privacy protection prior to sharing of this data with services providers. Precisely, the sensitive representations are extracted from the raw signal by using transformation functions and then wrapped it via voice conversion technology. Experimental evaluation based on emotion recognition to assess the efficacy of the proposed method shows that identification of sensitive emotional state of the speaker is reduced by ~96 %.