Critically endangered species in Canadian North Atlantic waters are systematically surveyed to estimate species populations which influence governing policies. Due to its impact on policy, population accuracy is important. This paper lays the foundation towards a data-driven glare modelling system, which will allow surveyors to preemptively minimize glare. Surveyors use a detection function to estimate megafauna populations which are not explicitly seen. A goal of the research is to maximize useful imagery collected, to that end we will use our glare model to predict glare and optimize for glare-free data collection. To build this model, we leverage a small labelled dataset to perform semi-supervised learning. The large dataset is labelled with a Cascading Random Forest Model using a na\"ive pseudo-labelling approach. A reflectance model is used, which pinpoints features of interest, to populate our datasets which allows for context-aware machine learning models. The pseudo-labelled dataset is used on two models: a Multilayer Perceptron and a Recurrent Neural Network. With this paper, we lay the foundation for data-driven mission planning; a glare modelling system which allows surveyors to preemptively minimize glare and reduces survey reliance on the detection function as an estimator of whale populations during periods of poor subsurface visibility.

This work has been submitted to the IEEE for possible publication in the IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI) on 7 January 2022. Abstract--The artificial intelligence (AI) system designer for thermal comfort faces insufficient data recorded from the current user or overfitting due to unreliable training data. This work introduces the reliable data set for training the AI subsystem for thermal comfort. This paper presents the control algorithm based on shallow supervised learning, which is simple enough to be implemented in the Internet of Things (IoT) system for residential usage using ASHRAE RP-884 and ASHRAE Global Thermal Comfort Database II. No training data for thermal comfort is available as reliable as this dataset, but the direct use of this data can lead to overfitting. This work offers the algorithm for data filtering and semantic data augmentation for the ASHRAE database for the supervised learning process. Overfitting always becomes a problem due to the psychological aspect involved in the thermal comfort decision. The method to check the AI system based on the psychrometric chart against overfitting is presented. This paper also assesses the most important parameters needed to achieve human thermal comfort. This method can support the development of reinforced learning for thermal comfort. HE decarbonising heat and buildings has become one heat pump is not a drop-in replacement for gas-boilers [5]. The UK is committed to If the heat pump is installed in poorly performed or leaky reaching net-zero emissions by 2050 [1]. The support includes buildings, the efficiency will decrease.

In this paper, we study scheduling of a queueing system with zero knowledge of instantaneous network conditions. We consider a one-hop single-server queueing system consisting of $K$ queues, each with time-varying and non-stationary arrival and service rates. Our scheduling approach builds on an innovative combination of adversarial bandit learning and Lyapunov drift minimization, without knowledge of the instantaneous network state (the arrival and service rates) of each queue. We then present two novel algorithms \texttt{SoftMW} (SoftMaxWeight) and \texttt{SSMW} (Sliding-window SoftMaxWeight), both capable of stabilizing systems that can be stablized by some (possibly unknown) sequence of randomized policies whose time-variation satisfies a mild condition. We further generalize our results to the setting where arrivals and departures only have bounded moments instead of being deterministically bounded and propose \texttt{SoftMW+} and \texttt{SSMW+} that are capable of stabilizing the system. As a building block of our new algorithms, we also extend the classical \texttt{EXP3.S} (Auer et al., 2002) algorithm for multi-armed bandits to handle unboundedly large feedback signals, which can be of independent interest.

Merging satellite products and ground-based measurements is often required for obtaining precipitation datasets that simultaneously cover large regions with high density and are more accurate than pure satellite precipitation products. Machine and statistical learning regression algorithms are regularly utilized in this endeavour. At the same time, tree-based ensemble algorithms are adopted in various fields for solving regression problems with high accuracy and low computational cost. Still, information on which tree-based ensemble algorithm to select for correcting satellite precipitation products for the contiguous United States (US) at the daily time scale is missing from the literature. In this study, we worked towards filling this methodological gap by conducting an extensive comparison between three algorithms of the category of interest, specifically between random forests, gradient boosting machines (gbm) and extreme gradient boosting (XGBoost). We used daily data from the PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks) and the IMERG (Integrated Multi-satellitE Retrievals for GPM) gridded datasets. We also used earth-observed precipitation data from the Global Historical Climatology Network daily (GHCNd) database. The experiments referred to the entire contiguous US and additionally included the application of the linear regression algorithm for benchmarking purposes. The results suggest that XGBoost is the best-performing tree-based ensemble algorithm among those compared...

The off-the-shelf drones are simple to operate and easy to maintain aerial systems. However, due to proprietary flight software, these drones usually do not provide any open-source interface which can enable them for autonomous flight in research or teaching. This work introduces a package for ROS1 and ROS2 for straightforward interfacing with off-the-shelf drones from the Parrot ANAFI family. The developed ROS package is hardware agnostic, allowing connecting seamlessly to all four supported drone models. This framework can connect with the same ease to a single drone or a team of drones from the same ground station. The developed package was intensively tested at the limits of the drones' capabilities and thoughtfully documented to facilitate its use by other research groups worldwide.

Recently, neural control policies have outperformed existing model-based planning-and-control methods for autonomously navigating quadrotors through cluttered environments in minimum time. However, they are not perception aware, a crucial requirement in vision-based navigation due to the camera's limited field of view and the underactuated nature of a quadrotor. We propose a learning-based system that achieves perception-aware, agile flight in cluttered environments. Our method combines imitation learning with reinforcement learning (RL) by leveraging a privileged learning-by-cheating framework. Using RL, we first train a perception-aware teacher policy with full-state information to fly in minimum time through cluttered environments. Then, we use imitation learning to distill its knowledge into a vision-based student policy that only perceives the environment via a camera. Our approach tightly couples perception and control, showing a significant advantage in computation speed (10 times faster) and success rate. We demonstrate the closed-loop control performance using hardware-in-the-loop simulation.

The impressive performance of artificial neural networks has come at the cost of high energy usage and CO$_2$ emissions. Unconventional computing architectures, with magnetic systems as a candidate, have potential as alternative energy-efficient hardware, but, still face challenges, such as stochastic behaviour, in implementation. Here, we present a methodology for exploiting the traditionally detrimental stochastic effects in magnetic domain-wall motion in nanowires. We demonstrate functional binary stochastic synapses alongside a gradient learning rule that allows their training with applicability to a range of stochastic systems. The rule, utilising the mean and variance of the neuronal output distribution, finds a trade-off between synaptic stochasticity and energy efficiency depending on the number of measurements of each synapse. For single measurements, the rule results in binary synapses with minimal stochasticity, sacrificing potential performance for robustness. For multiple measurements, synaptic distributions are broad, approximating better-performing continuous synapses. This observation allows us to choose design principles depending on the desired performance and the device's operational speed and energy cost. We verify performance on physical hardware, showing it is comparable to a standard neural network.

The demand for a huge amount of data for machine learning (ML) applications is currently a bottleneck in an empirically dominated field. We propose a method to combine prior knowledge with data-driven methods to significantly reduce their data dependency. In this study, component-based machine learning (CBML) as the knowledge-encoded data-driven method is examined in the context of energy-efficient building engineering. It encodes the abstraction of building structural knowledge as semantic information in the model organization. We design a case experiment to understand the efficacy of knowledge-encoded ML in sparse data input (1% - 0.0125% sampling rate). The result reveals its three advanced features compared with pure ML methods: 1. Significant improvement in the robustness of ML to extremely small-size and inconsistent datasets; 2. Efficient data utilization from different entities' record collections; 3. Characteristics of accepting incomplete data with high interpretability and reduced training time. All these features provide a promising path to alleviating the deployment bottleneck of data-intensive methods and contribute to efficient real-world data usage. Moreover, four necessary prerequisites are summarized in this study that ensures the target scenario benefits by combining prior knowledge and ML generalization.

Miniaturized autonomous unmanned aerial vehicles (UAVs) are an emerging and trending topic. With their form factor as big as the palm of one hand, they can reach spots otherwise inaccessible to bigger robots and safely operate in human surroundings. The simple electronics aboard such robots (sub-100mW) make them particularly cheap and attractive but pose significant challenges in enabling onboard sophisticated intelligence. In this work, we leverage a novel neural architecture search (NAS) technique to automatically identify several Pareto-optimal convolutional neural networks (CNNs) for a visual pose estimation task. Our work demonstrates how real-life and field-tested robotics applications can concretely leverage NAS technologies to automatically and efficiently optimize CNNs for the specific hardware constraints of small UAVs. We deploy several NAS-optimized CNNs and run them in closed-loop aboard a 27-g Crazyflie nano-UAV equipped with a parallel ultra-low power System-on-Chip. Our results improve the State-of-the-Art by reducing the in-field control error of 32% while achieving a real-time onboard inference-rate of ~10Hz@10mW and ~50Hz@90mW.

Nearly four hours into Tesla's marathon Investor Day, someone in the audience tried again to bring Elon Musk, the Tesla (and Twitter and SpaceX) CEO back to the present day. From a stage at the Gigafactory in Austin, Texas, Musk had announced an ambitious "Master Plan 3" to save the world. For $10 trillion in manufacturing investment, Musk said, the world could move wholesale to a renewable electricity grid, powering electric cars, planes, and ships. "Earth can and will move to a sustainable energy economy, and will do so in your lifetime," Musk proclaimed. More details will be revealed in a forthcoming white paper, he said.