Using a game engine, we have developed a virtual environment which models important aspects of critical incident scenarios. We focused on modelling phenomena relating to the identification and ...gathering of key forensic evidence, in order to develop and test a system which can handle chemical, biological, radiological/nuclear or explosive (CBRNe) events autonomously. This allows us to build and validate AI-based technologies, which can be trained and tested in our custom virtual environment before being deployed in real-world scenarios. We have used our virtual scenario to rapidly prototype a system which can use simulated Remote Aerial Vehicles (RAVs) to gather images from the environment for the purpose of mapping. Our environment provides us with an effective medium through which we can develop and test various AI methodologies for critical incident scene assessment, in a safe and controlled manner
Multi-class classification algorithms are very widely used, but we argue that they are not always ideal from a theoretical perspective, because they assume all classes are characterized by the data, ...whereas in many applications, training data for some classes may be entirely absent, rare, or statistically unrepresentative. We evaluate one-sided classifiers as an alternative, since they assume that only one class (the target) is well characterized. We consider a task of identifying whether a substance contains a chlorinated solvent, based on its chemical spectrum. For this application, it is not really feasible to collect a statistically representative set of outliers, since that group may contain anything apart from the target chlorinated solvents. Using a new one-sided classification toolkit, we compare a One-Sided k-NN algorithm with two well-known binary classification algorithms, and conclude that the one-sided classifier is more robust to unexpected outliers.
Autonomous robotics and artificial intelligence techniques can be used to support human personnel in the event of critical incidents. These incidents can pose great danger to human life. Some ...examples of such assistance include: multi-robot surveying of the scene; collection of sensor data and scene imagery, real-time risk assessment and analysis; object identification and anomaly detection; and retrieval of relevant supporting documentation such as standard operating procedures (SOPs). These incidents, although often rare, can involve chemical, biological, radiological/nuclear or explosive (CBRNE) substances and can be of high consequence. Real-world training and deployment of these systems can be costly and sometimes not feasible. For this reason, we have developed a realistic 3D model of a CBRNE scenario to act as a testbed for an initial set of assisting AI tools that we have developed.
Accidents and attacks that involve chemical, biological, radiological/nuclear or explosive (CBRNE) substances are rare, but can be of high consequence. Since the investigation of such events is not ...anybody's routine work, a range of AI techniques can reduce investigators' cognitive load and support decision-making, including: planning the assessment of the scene; ongoing evaluation and updating of risks; control of autonomous vehicles for collecting images and sensor data; reviewing images/videos for items of interest; identification of anomalies; and retrieval of relevant documentation. Because of the rare and high-risk nature of these events, realistic simulations can support the development and evaluation of AI-based tools. We have developed realistic models of CBRNE scenarios and implemented an initial set of tools.
This paper describes an architecture for controlling non-player characters (NPC) in the First Person Shooter (FPS) game Unreal Tournament 2004. Specifically, the DRE-Bot architecture is made up of ...three reinforcement learners, Danger, Replenish and Explore, which use the tabular Sarsa(λ) algorithm. This algorithm enables the NPC to learn through trial and error building up experience over time in an approach inspired by human learning. Experimentation is carried to measure the performance of DRE-Bot when competing against fixed strategy bots that ship with the game. The discount parameter, γ, and the trace parameter, λ, are also varied to see if their values have an effect on the performance.
X-ray computed tomography (XCT) is a valuable reconnaissance tool for three-dimensional imaging and identification of distinct lithologies in extraterrestrial samples. It will be used as part of the ...preliminary examination of samples returned from asteroid (101955) Bennu by the Origins, Spectral Interpretation, Resource Identification, and Security–Regolith Explorer (OSIRIS-REx) mission. However, it must first be established whether x-rays generated during XCT could degrade or alter the organic composition of the returned samples by radiolysis. To test this, we split a crushed sample of the Murchison CM2 meteorite, kept one portion as a control, and irradiated the other portion up to the maximum x-ray dosage (~180 Gy) that a Bennu sample would experience during an XCT imaging experiment. We then extracted organic compounds from both splits and conducted (i) nontargeted soluble organic analyses to compare the chemical distributions of C-, H-, O-, N-, and S-bearing species and (ii) targeted measurements to quantify the abundances of 96 individual soluble organic molecules that included protein amino acids, amines, carboxylic acids, hydroxy acids, carbonyl compounds, polycyclic aromatic hydrocarbons, alcohols, sugars, and N-heterocycles. We found that XCT imaging of the Murchison meteorite had no measurable impact on the relative abundances or enantiomeric compositions of most of the soluble organic compounds targeted in this study. Elevated total abundances of several soluble organic compound classes were observed in the XCT-scanned Murchison sample relative to the control. This is likely related to particle size heterogeneity and specific surface area differences between the sample aliquots used for the extractions, rather than a result of the x-ray exposure. Assuming the samples returned from asteroid Bennu by OSIRIS-REx have a similar composition to carbonaceous chondrites, these data provide confidence that XCT will not significantly alter their soluble organic compositions.
Bennu (101195), target of the Origins, Spectral Interpretation, Resource Identification, Security, Regolith Explorer (OSIRIS-REx) mission, is a type-B asteroid with abundant spectral evidence for ...hydrated silicates, low thermal inertia "boulders" and frequent bursts of particle emission. We suggest that Bennu's parent body formed in the outer solar system before it was perturbed into the asteroid belt and then evolved into a near-Earth object. We show that this is consistent with models of planetesimal evolution. Bennu has many characteristics expected for a dormant comet, and could potentially contain a minimum of 1 wt.% adsorbed water if its gross mineralogy is consistent with the Orgueil meteorite. This is in addition to any ice or water contained within the hydrous minerals themselves. Based on this hypothesis, we predict the properties of the samples that will be returned to Earth by the OSIRIS-REx mission, including abundant phyllosilicate minerals, amorphous hydrated silicates and low-density, very high-porosity aggregates, already observed by the OSIRIS-REx instrument suite. We predict enrichments in D/H and 15N/14N, high C/Mg ratios (>∼7 wt%), and a greater range of organic compositions than found in meteorites, including an organic component poor in aromatics, and a more labile organic fraction. Ammonium salts, ranging from NH4Cl to ammonium-organic acid salts could carry much of the nitrogen in comets, yet only NH4CH3COO and heavier salts are sufficiently stable to be found in these returned samples. Water adsorbed onto highly porous grains should also be detected provided that the sample return capsule remains below 300 K during Earth return, and this water should be isotopically heavy.
Organics found in comet 81P/Wild 2 samples show a heterogeneous and unequilibrated distribution in abundance and composition. Some organics are similar, but not identical, to those in interplanetary ...dust particles and carbonaceous meteorites. A class of aromatic-poor organic material is also present. The organics are rich in oxygen and nitrogen compared with meteoritic organics. Aromatic compounds are present, but the samples tend to be relatively poorer in aromatics than are meteorites and interplanetary dust particles. The presence of deuterium and nitrogen-15 excesses suggest that some organics have an interstellar/protostellar heritage. Although the variable extent of modification of these materials by impact capture is not yet fully constrained, a diverse suite of organic compounds is present and identifiable within the returned samples.