A common and intuitive way of identifying the proximity relationship between two entities is to use the preposition ‘near’ (e.g. ‘near (inn, village)’). However, the ‘near’ relation is vague, often asymmetric and context-dependent, and hence incorporating factors such as the effect of type, size and scale of reference object and associated features is required for cognitive modeling. In this work, we interpreted spatial proximity as described in the historic Corpus of Lake District Writing comprising travel narratives as early as the 16th century. At a time when modern transportation modes were not available, it is interesting to explore how proximity has been perceived and recounted with various context factors explicit or implied. We utilized pre-trained BERT and its variants to first identify the broader semantics of ‘near’ and generate contextual embeddings. We further identified the contextual factors of spatial nearness. Finally, we used quantitative distances between entities to measure the departure of context-dependent proximities from objective notions of distance.

Some of the most powerful language models currently are proprietary systems, accessible only via (typically restrictive) web or software programming interfaces. This is the LanguageModels-as-a-Service (LMaaS) paradigm. In contrast with scenarios where full model access is available, as in the case of open-source models, such closed-off language models present specific challenges for evaluating, benchmarking, and testing them. This paper has two goals: on the one hand, we delineate how the aforementioned challenges act as impediments to the accessibility, reproducibility, reliability, and trustworthiness of LMaaS. We systematically examine the issues that arise from a lack of information about language models for each of these four aspects. We conduct a detailed analysis of existing solutions, put forth a number of recommendations, and highlight directions for future advancements. On the other hand, it serves as a synthesized overview of the licences and capabilities of the most popular LMaaS.

Artificial intelligence (AI) has made remarkable progress across various domains, with large language models like ChatGPT gaining substantial attention for their human-like text-generation capabilities. Despite these achievements, improving spatial reasoning remains a significant challenge for these models. Benchmarks like StepGame evaluate AI spatial reasoning, where ChatGPT has shown unsatisfactory performance. However, the presence of template errors in the benchmark has an impact on the evaluation results. Thus there is potential for ChatGPT to perform better if these template errors are addressed, leading to more accurate assessments of its spatial reasoning capabilities. In this study, we refine the StepGame benchmark, providing a more accurate dataset for model evaluation. We analyze GPT’s spatial reasoning performance on the rectified benchmark, identifying proficiency in mapping natural language text to spatial relations but limitations in multi-hop reasoning. We provide a flawless solution to the benchmark by combining template-to-relation mapping with logic-based reasoning. This combination demonstrates proficiency in performing qualitative reasoning on StepGame without encountering any errors. We then address the limitations of GPT models in spatial reasoning. To improve spatial reasoning, we deploy Chain-of-Thought and Tree-of-thoughts prompting strategies, offering insights into GPT’s cognitive process. Our investigation not only sheds light on model deficiencies but also proposes enhancements, contributing to the advancement of AI with more robust spatial reasoning capabilities.

Autoregressive Large Language Models have transformed the landscape of Natural Language Processing. Pre-train and prompt paradigm has replaced the conventional approach of pre-training and fine-tuning for many downstream NLP tasks. This shift has been possible largely due to LLMs and innovative prompting techniques. LLMs have shown great promise for a variety of downstream tasks owing to their vast parameters and huge datasets that they are pre-trained on. However, in order to fully realize their potential, their outputs must be guided towards the desired outcomes. Prompting, in which a specific input or instruction is provided to guide the LLMs toward the intended output, has become a tool for achieving this goal. In this paper, we discuss the various prompting techniques that have been applied to fully harness the power of LLMs. We present a taxonomy of existing literature on prompting techniques and provide a concise survey based on this taxonomy. Further, we identify some open problems in the realm of prompting in autoregressive LLMs which could serve as a direction for future research.

Abstract—Large Language Models (LLMs) suffer from inherent stochasticity, limiting their utility in high-stakes enterprise environments where determinism and auditability are required. This paper introduces the MFOUR Vibe Framework (MVF), a platform-agnostic architectural standard that transforms probabilistic natural language intent into deterministic software artifacts. We define a five-layer topology, comprising the Kernel Identity, Synaptic Routing, Interface Contracts, Context Anchoring, and the Mirror Test. Furthermore, we introduce The Vibe Integrity Score (VIS), a quantitative metric for evaluating the structural adherence of generative outputs. This specification provides the foundational schema and logic protocols for building "Glass Box" AI systems that are observable, secure, and commercially viable.

Planning is a fundamental property of human intelligence. Reasoning about asynchronous plans is challenging since it requires sequential and parallel planning to optimize time costs. Can large language models (LLMs) succeed at this task? Here, we present the first large-scale study investigating this question. We find that a representative set of closed and open-source LLMs, including GPT-4 and LLaMA-2, behave poorly when not supplied with illustrations about the task-solving process in our benchmark AsyncHow. We propose a novel technique called *Plan Like a Graph* (PLaG) that combines graphs with natural language prompts and achieves state-of-the-art results. We show that although PLaG can boost model performance, LLMs still suffer from drastic degradation when task complexity increases, highlighting the limits of utilizing LLMs for simulating digital devices. We see our study as an exciting step towards using LLMs as efficient autonomous agents. Our code and data are available at https://github.com/fangru-lin/graph-llm-asynchow-plan.

Location retrieval based on visual information is to retrieve the location of an agent (e.g.human, robot) or the area they see by comparing their observations with a certain representation of the environment.Existing methods generally treat the problem as a content-based image retrieval problem and have demonstrated promising results in terms of localization accuracy.However, these methods are challenging to scale up due to the volume of reference data involved; and the image descriptions might not be easily understandable/communicable for humans to describe surroundings.Considering that humans often use less precise but easily produced qualitative spatial language and high-level semantic landmarks when describing an environment, a coarseto-fine qualitative location retrieval method is proposed in this work to quickly narrow down the initial location of an agent by exploiting the available information in large-scale open data.This approach describes and indexes a location/place using the perceived qualitative spatial relations between ordered pairs of covisible landmarks from the perspective of viewers, termed as 'qualitative place signatures' (QPS).The usability and effectiveness of the proposed method were evaluated using openly available datasets, together with simulated observations by considering different types perception errors.

Some of the most powerful language models currently are proprietary systems, accessible only via (typically restrictive) web or software programming interfaces. This is the LanguageModels-as-a-Service (LMaaS) paradigm. In contrast with scenarios where full model access is available, as in the case of open-source models, such closed-off language models present specific challenges for evaluating, benchmarking, and testing them. This paper has two goals: on the one hand, we delineate how the aforementioned challenges act as impediments to the accessibility, reproducibility, reliability, and trustworthiness of LMaaS. We systematically examine the issues that arise from a lack of information about language models for each of these four aspects. We conduct a detailed analysis of existing solutions, put forth a number of recommendations, and highlight directions for future advancements. On the other hand, it serves as a synthesized overview of the licences and capabilities of the most popular LMaaS.

As data sources become ever more numerous with increased feature dimensionality, feature selection for multiview data has become an important technique in machine learning. Semi-supervised multiview feature selection (SMFS) focuses on the problem of how to obtain a discriminative feature subset from heterogeneous feature spaces in the case of abundant unlabeled data with little labeled data. Most existing methods suffer from unreliable similarity graph structure across different views since they separate the graph construction from feature selection and use the fixed graphs that are susceptible to noisy features. Furthermore, they directly concatenate multiple feature projections for feature selection, neglecting the contribution diversity among projections. To alleviate these problems, we present an SMFS to simultaneously select informative features and learn a unified graph through the data fusion from aspects of feature projection and similarity graph. Specifically, SMFS adaptively weights different feature projections and flexibly fuses them to form a joint weighted projection, preserving the complementarity and consensus of the original views. Moreover, an implicit graph fusion is devised to dynamically learn a compatible graph across views according to the similarity structure in the learned projection subspace, where the undesirable effects of noisy features are largely alleviated. A convergent method is derived to iteratively optimize SMFS. Experiments on various datasets validate the effectiveness and superiority of SMFS over state-of-the-art methods.

Service robots are expected to assist users in a constantly growing range of environments and tasks. People may be unique in many ways, and online adaptation of robots is central to personalized assistance. We focus on collaborative tasks in which the human collaborator may not be fully ablebodied, with the aim for the robot to automatically determine the best level of support. We propose a methodology for online adaptation based on Reinforcement Learning and Bayesian inference. As the Reinforcement Learning process continuously adjusts the robot's behavior, the actions that become part of the improved policy are used by the Bayesian inference module as local evidence of human capability, which can be generalized across the state space. The estimated capabilities are then used as pre-conditions to collaborative actions, so that the robot can quickly disable actions that the person seems unable to perform. We demonstrate and validate our approach on two simulated tasks and one real-world collaborative task across a range of motion and sensing capabilities.

We propose a logic of east and west (LEW ) for points in 1D Euclidean space. It formalises primitive direction relations: east (E), west (W) and indeterminate east/west (Iew). It has a parameter τ ∈ N>1, which is referred to as the level of indeterminacy in directions. For every τ ∈ N>1, we provide a sound and complete axiomatisation of LEW , and prove that its satisfiability problem is NP-complete. In addition, we show that the finite axiomatisability of LEW depends on τ : if τ = 2 or τ = 3, then there exists a finite sound and complete axiomatisation; if τ > 3, then the logic is not finitely axiomatisable. LEW can be easily extended to higher-dimensional Euclidean spaces. Extending LEW to 2D Euclidean space makes it suitable for reasoning about not perfectly aligned representations of the same spatial objects in different datasets, for example, in crowd-sourced digital maps.

Acquiring knowledge about object interactions and affordances can facilitate scene understanding and human-robot collaboration tasks. As humans tend to use objects in many different ways depending on the scene and the objects’ availability, learning object affordances in everyday-life scenarios is a challenging task, particularly in the presence of an open set of interactions and objects. We address the problem of affordance categorization for class-agnostic objects with an open set of interactions; we achieve this by learning similarities between object interactions in an unsupervised way and thus inducing clusters of object affordances. A novel depth-informed qualitative spatial representation is proposed for the construction of Activity Graphs (AGs), which abstract from the continuous representation of spatio-temporal interactions in RGB-D videos. These AGs are clustered to obtain groups of objects with similar affordances. Our experiments in a real-world scenario demonstrate that our method learns to create object affordance clusters with a high V-measure even in cluttered scenes. The proposed approach handles object occlusions by capturing effectively possible interactions and without imposing any object or scene constraints.

In order to be trusted by humans, Artificial Intelligence agents should be able to describe rationales behind their decisions. One such application is human action recognition in critical or sensitive scenarios, where trustworthy and explainable action recognizers are expected. For example, reliable pedestrian action recognition is essential for self-driving cars and explanations for real-time decision making are critical for investigations if an accident happens. In this regard, learning-based approaches, despite their popularity and accuracy, are disadvantageous due to their limited interpretability. This paper presents a novel neuro-symbolic approach that recognizes actions from videos with human-understandable explanations. Specifically, we first propose to represent videos symbolically by qualitative spatial relations between objects called qualitative spatial object relation chains. We further develop a neural saliency estimator to capture the correlation between such object relation chains and the occurrence of actions. Given an unseen video, this neural saliency estimator is able to tell which object relation chains are more important for the action recognized. We evaluate our approach on two real-life video datasets, with respect to recognition accuracy and the quality of generated action explanations. Experiments show that our approach achieves superior performance on both aspects to previous symbolic approaches, thus facilitating trustworthy intelligent decision making. Our approach can be used to augment state-of-the-art learning approaches with explainabilities.

In this work, the problem of bootstrapping knowledge in language and vision for autonomous robots is addressed through novel techniques in grammar induction and word grounding to the perceptual world. In particular, we demonstrate a system, called OLAV, which is able, for the first time, to (1) learn to form discrete concepts from sensory data; (2) ground language (n-grams) to these concepts; (3) induce a grammar for the language being used to describe the perceptual world; and moreover to do all this incrementally, without storing all previous data. The learning is achieved in a loosely-supervised manner from raw linguistic and visual data. Moreover, the learnt model is transparent, rather than a black-box model and is thus open to human inspection. The visual data is collected using three different robotic platforms deployed in real-world and simulated environments and equipped with different sensing modalities, while the linguistic data is collected using online crowdsourcing tools and volunteers. The analysis performed on these robots demonstrates the effectiveness of the framework in learning visual concepts, language groundings and grammatical structure in these three online settings.

Scribble-supervised semantic segmentation has gained much attention recently for its promising performance without high-quality annotations. Due to the lack of supervision, confident and consistent predictions are usually hard to obtain. Typically, people handle these problems by either adopting an auxiliary task with the well-labeled dataset or incorporating a graphical model with additional requirements on scribble annotations. Instead, this work aims to achieve semantic segmentation by scribble annotations directly without extra information and other limitations. Specifically, we propose holistic operations, including minimizing entropy and a network embedded random walk on the neural representation to reduce uncertainty. Given the probabilistic transition matrix of a random walk, we further train the network with self-supervision on its neural eigenspace to impose consistency on predictions between related images. Comprehensive experiments and ablation studies verify the proposed approach, which demonstrates superiority over others; it is even comparable to some full-label supervised ones and works well when scribbles are randomly shrunk or dropped.

Chinese traditional music has been proved to be effective in emotion regulation for thousands of years. Five different groups of Chinese traditional music which have been proved can regulate different emotions (Angry, Depressed, Feverish, Desperate, Sorrowful) in the literature. 54 audios features are extracted by using the Librosa library for each music group. Five features are manually selected using histogram analysis which show significant difference between the five groups of music. Combined with KNN, SVM and Deep forest classification algorithms, the five manually selected audio features are shown to have better classification performance than traditional feature selection algorithms, like PCA and LDA. We hypothesize that these five significant audio features may be the underlying basis why so such music can effectively perform emotion regulation. Based on this classification models, prototype emotion regulation music recommendation interface (TJ-ERMR) was built that can be used for music therapy. In the future, we will use this classification model to find more music to expand the initial repertoire of our music recommendation system.

A DNN architecture referred to as GPRInvNet was proposed to tackle the challenges of mapping the ground-penetrating radar (GPR) B-Scan data to complex permittivity maps of subsurface structures. The GPRInvNet consisted of a trace-to-trace encoder and a decoder. It was specially designed to take into account the characteristics of GPR inversion when faced with complex GPR B-Scan data, as well as addressing the spatial alignment issues between time-series B-Scan data and spatial permittivity maps. It displayed the ability to fuse features from several adjacent traces on the B-Scan data to enhance each trace, and then further condense the features of each trace separately. As a result, the sensitive zones on the permittivity maps spatially aligned to the enhanced trace could be reconstructed accurately. The GPRInvNet has been utilized to reconstruct the permittivity map of tunnel linings. A diverse range of dielectric models of tunnel linings containing complex defects has been reconstructed using GPRInvNet. The results have demonstrated that the GPRInvNet is capable of effectively reconstructing complex tunnel lining defects with clear boundaries. Comparative results with existing baseline methods also demonstrated the superiority of the GPRInvNet. For the purpose of generalizing the GPRInvNet to real GPR data, some background noise patches recorded from practical model testing were integrated into the synthetic GPR data to retrain the GPRInvNet. The model testing has been conducted for validation, and experimental results revealed that the GPRInvNet had also achieved satisfactory results with regard to the real data.

Abstract Whitby is the server-side of an Intelligent Tutoring System application for learning System-Theoretic Process Analysis (STPA), a methodology used to ensure the safety of anything that can be represented with a systems model. The underlying logic driving the reasoning behind Whitby is Situation Calculus, which is a many-sorted logic with situation, action, and object sorts. The Situation Calculus is applied to Ontology Authoring and Contingent Scaffolding: the primary activities within Whitby. Thus many fluents and actions are aggregated in Whitby from these two sub-applications and from Whitby itself, but all are available through a common situation query interface that does not depend upon any of the fluents or actions. Each STPA project in Whitby is a single situation term, which is queried for fluents that include the ontology, and to determine what pedagogical interventions to offer. Initially Whitby was written in Prolog using a module system. In the interest of a cleaner architecture and implementation with improved code reuse and extensibility, the initial application was refactored into Logtalk. This refactoring includes decoupling the Situation Calculus reasoner, Ontology Authoring framework, and Contingent Scaffolding framework into third-party libraries that can be reused in other applications. This extraction was achieved by inverting dependencies via Logtalk protocols and categories, which are reusable interfaces and components that provide functionally cohesive sets of predicate declarations and predicate definitions. In this paper the architectures of two iterations of Whitby are evaluated with respect to the motivations behind the refactor: clean architecture enabling code reuse and extensibility.

In cognitive accounts of concept learning and representation three modelling approaches provide methods for assessing typicality: rulebased, prototype and exemplar models.The prototype and exemplar models both rely on calculating a weighted semantic distance to some central instance or instances.However, it is not often discussed how the central instance(s) or weights should be determined in practice.In this paper we explore how to automatically generate prototypes and typicality measures of concepts from data, introducing a prototype model and discussing and testing against various cognitive models.Following a previous pilot study, we build on the data collection methodology and have conducted a new experiment which provides a case study of spatial language for the current proposal.After providing a brief overview of cognitive accounts and computational models of spatial language, we introduce our data collection environment and study.Following this, we then introduce various models of typicality as well as our prototype model, before comparing them using the collected data and discussing the results.We conclude that our model provides significant improvement over the other given models and also discuss the improvements given by a novel inclusion of functional features in our model.

Humans, in comparison to robots, are remarkably adept at reaching for objects in cluttered environments. The best existing robot planners are based on random sampling of configuration space- which becomes excessively high-dimensional with large number of objects. Consequently, most planners often fail to efficiently find object manipulation plans in such environments. We addressed this problem by identifying high-level manipulation plans in humans, and transferring these skills to robot planners. We used virtual reality to capture human participants reaching for a target object on a tabletop cluttered with obstacles. From this, we devised a qualitative representation of the task space to abstract the decision making, irrespective of the number of obstacles. Based on this representation, human demonstrations were segmented and used to train decision classifiers. Using these classifiers, our planner produced a list of waypoints in task space. These waypoints provided a high-level plan, which could be transferred to an arbitrary robot model and used to initialise a local trajectory optimiser. We evaluated this approach through testing on unseen human VR data, a physics-based robot simulation, and a real robot (dataset and code are publicly available1). We found that the human-like planner outperformed a state-of-the-art standard trajectory optimisation algorithm, and was able to generate effective strategies for rapid planning- irrespective of the number of obstacles in the environment.

We propose a logic of directions for points (LD) over 2D Euclidean space, which formalises primary direction relations east (E), west (W), and indeterminate east/west (Iew), north (N), south (S) and indeterminate north/south (Ins). We provide a sound and complete axiomatisation of it, and prove that its satisfiability problem is NP-complete.

In previous work exploring how to automatically generate typicality measures for spatial prepositions in grounded settings, we considered a semantic model based on Prototype Theory and introduced a method for learning its parameters from data. However, though there is much to suggest that spatial prepositions exhibit polysemy, each term was treated as exhibiting a single sense. The ability for terms to represent distinct but related meanings is unexplored in the work on grounded semantics and referring expressions, where even homonymy is rarely considered. In this paper we address this problem by analysing the issue of reference using spatial language and examining how the polysemy exhibited by spatial prepositions can be incorporated into semantic models for situated dialogue. We support our approach on theoretical developments of Prototype Theory, which suggest that polysemy may be analysed in terms of radial categories, characterised by having several prototypicality centres. After providing a brief overview of polysemy in spatial language and a review of the related work, we define the Baseline Model and discuss how polysemy may be incorporated to improve it. We introduce a method of identifying polysemes based on `ideal meanings' and a modification of the `principled polysemy' framework. In order to compare polysemes and aid typicality judgements we then introduce a notion of `polyseme hierarchy'. Subsequently, we test the performance of the extended Polysemy Model by comparing it to the Baseline Model as well as a data-driven model of polysemy which we derive with a clustering algorithm. We conclude that our method for incorporating polysemy into the Baseline Model provides significant improvement. Finally, we analyse the properties and behaviour of the generated Polysemy Model, providing some insight into the improvement in performance, as well as justification for the given methods.

Urban infrastructure assets (e.g. roads, water pipes) perform critical functions to the health and well-being of society. Although it has been widely recognised that different infrastructure assets are highly interconnected, infrastructure management in practice such as planning, installation and maintenance are often undertaken by different stakeholders without considering these dependencies due to the lack of relevant data and cross-domain knowledge, which may cause unexpected cascading social, economic and environmental effects. In this paper, we present a knowledge based decision support system for urban infrastructure inter-asset management. By considering various infrastructure assets (e.g. road, ground, cable), triggers (e.g. pipe leaking) and potential consequences (e.g. traffic disruption) as a holistic system, we model each sub-domain using a modular ontology and encapsulate the interdependence between them using a set of rules. Moreover, qualitative likelihood is assigned to each rule by domain experts (e.g. civil engineers) to encode the uncertainty of knowledge, and an inference engine is applied to predict the potential consequences of a given trigger with location specific data and the encoded rules. A web-based prototype system has been developed based on the above concept and demonstrated to a wide range of stakeholders. The system can assist in the process of decision making by aiding data collation and integration, as well as presenting potential consequences of possible triggers, advising on whether additional information is needed or suggesting ways of obtaining such information. The work shows an intelligent approach to integrate and process multi-source data to pioneer a novel way to aid a complex decision process with a high social impact.

The success of intelligent mobile robots operating and collaborating with humans in daily living environments depends on their ability to generalise and learn human movements, and obtain a shared understanding of an observed scene. In this paper we aim to understand human activities being performed in real-world environments from long-term observation from an autonomous mobile robot. For our purposes, a human activity is defined to be a changing spatial configuration of a person's body interacting with key objects that provide some functionality within an environment. To alleviate the perceptual limitations of a mobile robot, restricted by its obscured and incomplete sensory modalities, potentially noisy visual observations are mapped into an abstract qualitative space in order to generalise patterns invariant to exact quantitative positions within the real world. A number of qualitative spatial-temporal representations are used to capture different aspects of the relations between the human subject and their environment. Analogously to information retrieval on text corpora, a generative probabilistic technique is used to recover latent, semantically-meaningful concepts in the encoded observations in an unsupervised manner. The small number of concepts discovered are considered as human activity classes, granting the robot a low-dimensional understanding of visually observed complex scenes. Finally, variational inference is used to facilitate incremental and continuous updating of such concepts that allows the mobile robot to efficiently learn and update its models of human activity over time resulting in efficient life-long learning.

Vision and touch are two of the important sensing modalities for humans and they offer complementary information for sensing the environment. Robots could also benefit from such multi-modal sensing ability. In this paper, addressing for the first time (to the best of our knowledge) texture recognition from tactile images and vision, we propose a new fusion method named Deep Maximum Covariance Analysis (DMCA) to learn a joint latent space for sharing features through vision and tactile sensing. The features of camera images and tactile data acquired from a GelSight sensor are learned by deep neural networks. But the learned features are of a high dimensionality and are redundant due to the differences between the two sensing modalities, which deteriorates the perception performance. To address this, the learned features are paired using maximum covariance analysis. Results of the algorithm on a newly collected dataset of paired visual and tactile data relating to cloth textures show that a good recognition performance of greater than 90% can be achieved by using the proposed DMCA framework. In addition, we find that the perception performance of either vision or tactile sensing can be improved by employing the shared representation space, compared to learning from unimodal data.

We present an interactive decision support system for assisting city infrastructure inter-asset management. It combines real-time site specific data retrieval, a knowledge base co-created with domain experts and an inference engine capable of predicting potential consequences and risks resulting from the available data and knowledge. The system can give explanations of each consequence, cope with incomplete and uncertain data by making assumptions about what might be the worst case scenario, and making suggestions for further investigation. This demo presents multiple real-world scenarios, and demonstrates how modifying assumptions (parameter values) can lead to different consequences.

Effective recognition of complex long-term activities is becoming an increasingly important task in artificial intelligence. In this paper, we propose a novel approach for building models of complex long-term activities. First, we automatically learn the hierarchical structure of activities by learning about the 'parent-child' relation of activity components from a video using the variability in annotations acquired using multiple annotators. This variability allows for extracting the inherent hierarchical structure of the activity in a video. We consolidate hierarchical structures of the same activity from different videos into a unified stochastic grammar describing the overall activity. We then describe an inference mechanism to interpret new instances of activities. We use three datasets, which have been annotated by multiple annotators, of daily activity videos to demonstrate the effectiveness of our system.

The explosive growth of text data requires effective methods to represent and classify these texts. Many text learning methods have been proposed, like statistics-based methods, semantic similarity methods, and deep learning methods. The statistics-based methods focus on comparing the substructure of text, which ignores the semantic similarity between different words. Semantic similarity methods learn a text representation by training word embedding and representing text as the average vector of all words. However, these methods cannot capture the topic diversity of words and texts clearly. Recently, deep learning methods such as CNNs and RNNs have been studied. However, the vanishing gradient problem and time complexity for parameter selection limit their applications. In this paper, we propose a novel and efficient text learning framework, named Latent Topic Text Representation Learning. Our method aims to provide an effective text representation and text measurement with latent topics. With the assumption that words on the same topic follow a Gaussian distribution, texts are represented as a mixture of topics, i.e., a Gaussian mixture model. Our framework is able to effectively measure text distance to perform text categorization tasks by leveraging statistical manifolds. Experimental results on text representation and classification, and topic coherence demonstrate the effectiveness of the proposed method.

We present a cognitively plausible novel framework capable of learning the grounding in visual semantics and the grammar of natural language commands given to a robot in a table top environment. The input to the system consists of video clips of a manually controlled robot arm, paired with natural language commands describing the action. No prior knowledge is assumed about the meaning of words, or the structure of the language, except that there are different classes of words (corresponding to observable actions, spatial relations, and objects and their observable properties). The learning process automatically clusters the continuous perceptual spaces into concepts corresponding to linguistic input. A novel relational graph representation is used to build connections between language and vision. As well as the grounding of language to perception, the system also induces a set of probabilistic grammar rules. The knowledge learned is used to parse new commands involving previously unseen objects.

For autonomous robots to collaborate on joint tasks with humans they require a shared understanding of an observed scene. We present a method for unsupervised learning of common human movements and activities on an autonomous mobile robot, which generalises and improves on recent results. Our framework encodes multiple qualitative abstractions of RGBD video from human observations and does not require external temporal segmentation. Analogously to information retrieval in text corpora, each human detection is modelled as a random mixture of latent topics. A generative probabilistic technique is used to recover topic distributions over an auto-generated vocabulary of discrete, qualitative spatio-temporal code words. We show that the emergent categories align well with human activities as interpreted by a human. This is a particularly challenging task on a mobile robot due to the varying camera viewpoints which lead to incomplete, partial and occluded human detections.

We present an uncertainty management scheme in rule-based systems for decision making in the domain of urban infrastructure. Our aim is to help end users make informed decisions. Human reasoning is prone to a certain degree of uncertainty but domain experts frequently find it difficult to quantify this precisely, and thus prefer to use qualitative (rather than quantitative) confidence levels to support their reasoning. Secondly, there is uncertainty in data when it is not currently available (missing). In order to incorporate human-like reasoning within rule-based systems we use qualitative confidence levels chosen by domain experts in urban infrastructure. We introduce a mechanism for the representation of confidence of input facts and inference rules, and for the computation of confidence in the inferred facts. We also present a mechanism for computing inferences in the presence of missing facts, and their effect on the confidence of inferred facts.

With the recent proliferation of human-oriented robotic applications in domestic and industrial scenarios, it is vital for robots to continually learn about their environments and about the humans they share their environments with. In this paper, we present a novel, online, incremental framework for unsupervised symbol grounding in real-world, human environments for autonomous robots. We demonstrate the flexibility of the framework by learning about colours, people names, usable objects and simple human activities, integrating state-of-the-art object segmentation, pose estimation, activity analysis along with a number of sensory input encodings into a continual learning framework. Natural language is grounded to the learned concepts, enabling the robot to communicate in a human-understandable way. We show, using a challenging real-world dataset of human activities as perceived by a mobile robot, that our framework is able to extract useful concepts, ground natural language descriptions to them, and, as a proof-of-concept, generate simple sentences from templates to describe people and the activities they are engaged in.

The problem of automatically recognizing and fitting hyperbolae from ground-penetrating radar (GPR) images is addressed, and a novel technique computationally suitable for real-time on-site application is proposed. After preprocessing of the input GPR images, a novel thresholding method is applied to separate the regions of interest from background. A novel column-connection clustering (C3) algorithm is then applied to separate the regions of interest from each other. Subsequently, a machine learnt model is applied to identify hyperbolic signatures from outputs of the C3 algorithm, and a hyperbola is fitted to each such signature with an orthogonal-distance hyperbola fitting algorithm. The novel clustering algorithm C3 is a central component of the proposed system, which enables the identification of hyperbolic signatures and hyperbola fitting. Only two features are used in the machine learning algorithm, which is easy to train using a small set of training data. An orthogonal-distance hyperbola fitting algorithm for “south-opening” hyperbolae is introduced in this work, which is more robust and accurate than algebraic hyperbola fitting algorithms. The proposed method can successfully recognize and fit hyperbolic signatures with intersections with others, hyperbolic signatures with distortions, and incomplete hyperbolic signatures with one leg fully or largely missed. As an additional novel contribution, formulas to compute an initial “south-opening” hyperbola directly from a set of given points are derived, which make the system more efficient. The parameters obtained by fitting hyperbolae to hyperbolic signatures are very important features; they can be used to estimate the location and size of the related target objects and the average propagation velocity of the electromagnetic wave in the medium. The effectiveness of the proposed system is tested on both synthetic and real GPR data.

We show that by using qualitative spatio-temporal abstraction methods, we can learn common human movements and activities from long term observation by a mobile robot. Our novel framework encodes multiple qualitative abstractions of RGBD video from detected activities performed by a human as encoded by a skeleton pose estimator. Analogously to informational retrieval in text corpora, we use Latent Semantic Analysis (LSA) to uncover latent, semantically meaningful, concepts in an unsupervised manner, where the vocabulary is occurrences of qualitative spatio-temporal features extracted from video clips, and the discovered concepts are regarded as activity classes. The limited field of view of a mobile robot represents a particular challenge, owing to the obscured, partial and noisy human detections and skeleton pose-estimates from its environment. We show that the abstraction into a qualitative space helps the robot to generalise and compare multiple noisy and partial observations in a real world dataset and that a vocabulary of latent activity classes (expressed using qualitative features) can be recovered.

The transport network in many countries relies on extended portions which run underground in tunnels. As tunnels age, repairs are required to prevent dangerous collapses. However repairs are expensive and will affect the operational efficiency of the tunnel. We present a decision support system (DSS) based on supervised machine learning methods that learns to predict the risk factor and the resulting repair urgency in the tunnel maintenance planning of a European national rail operator. The data on which the prototype has been built consists of 47 tunnels of varying lengths. For each tunnel, periodic survey inspection data is available for multiple years, as well as other data such as the method of construction of the tunnel. Expert annotations are also available for each 10m tunnel segment for each survey as to the degree of repair urgency which are used for both training and model evaluation. We show that good predictive power can be obtained and discuss the relative merits of a number of learning methods.

This paper aims to lay a foundation for a systematic study of mechanisms for construction of definitions within a formal theory, by investigating operators for incremental construction of definitions of new relations from an existing set of primitives and previously defined relations. To illustrate our method, we apply it to two of the best known relation sets studied in KRR: Allen's Interval Algebra and Region Connection Calculus. We also show that systematic exploration of definitional possibilities can yield interesting insights into relation sets that were originally defined in a more ad hoc way, and opens the possibility for discovering new vocabulary for extending or refining existing calculi or for developing completely new calculi.

Activity classification from smart environment data is typically done employing ad hoc solutions customised to the particular dataset at hand. In this work we introduce a general purpose collection of features for recognising human activities across datasets of different type, size and nature. The first experimental test of our feature collection achieves state of the art results on well known datasets, and we provide a feature importance analysis in order to compare the potential relevance of features for activity classification in different datasets.

Assessing the Underworld (ATU) is a large interdisciplinary UK research project, which addresses challenges in integrated inter-asset maintenance. As assets on the surface of the ground (e.g. roads or pavements) and those buried under it (e.g. pipes and cables) are supported by the ground, the properties and processes of soil affect the performance of these assets to a significant degree. In order to make integrated decisions, it is necessary to combine the knowledge and expertise in multiple areas, such as roads, soil, buried assets, sensing, etc. This requires an underpinning knowledge model, in the form of an ontology. Within this context, we present a new ontology for describing soil properties (e.g. soil strength) and processes (e.g. soil compaction), as well as how they affect each other. This ontology can be used to express how the ground affects and is affected by assets buried under the ground or on the ground surface. The ontology is written in OWL 2 and openly available from the University of Leeds data repository: http://doi.org/10.5518/54 .

This paper proposes a novel method for jointly estimating the track of a moving object and the events in which it participates. The method is intended for dealing with generic objects that are hard to localise and track with the performance of current detection algorithms - our focus is on events involving carried objects. The tracks for other objects with which the target object interacts (e.g. the carrying person) are assumed to be given. The method is posed as maximisation of a posterior probability defined over event sequences and temporally-disjoint subsets of the tracklets from an earlier tracking process. The probability function is a Hidden Markov Model coupled with a term that penalises non-smooth tracks and large gaps in the observed data. We evaluate the method using tracklets output by three state of the art trackers on the new created MINDSEYE2015 dataset and demonstrate improved performance.

Event models obtained automatically from video can be used in applications ranging from abnormal event detection to content based video retrieval. When multiple agents are involved in the events, characterizing events naturally suggests encoding interactions as relations. Learning event models from this kind of relational spatio-temporal data using relational learning techniques such as Inductive Logic Programming (ILP) hold promise, but have not been successfully applied to very large datasets which result from video data. In this paper, we present a novel framework REMIND (Relational Event Model INDuction) for supervised relational learning of event models from large video datasets using ILP. Efficiency is achieved through the learning from interpretations setting and using a typing system that exploits the type hierarchy of objects in a domain. The use of types also helps prevent over generalization. Furthermore, we also present a type-refining operator and prove that it is optimal. The learned models can be used for recognizing events from previously unseen videos. We also present an extension to the framework by integrating an abduction step that improves the learning performance when there is noise in the input data. The experimental results on several hours of video data from two challenging real world domains (an airport domain and a physical action verbs domain) suggest that the techniques are suitable to real world scenarios.

This paper presents a novel approach to incorporate multiple contextual factors into a tracking process, for the purpose of reducing false positive detections. While much previous work has focused on improving object detection on static images using context, these have not been integrated into the tracking process. Our hypothesis is that a significant improvement can result from the use of context in dynamically influencing the linking of object detections, during the tracking process. To verify this hypothesis, we augment a state of the art dynamic programming based tracker with contextual information by reformulating the maximum a posteriori (MAP) estimation formulation. This formulation introduces contextual factors that first of all augment detection strengths and secondly provides temporal context. We allow both these types of factors to contribute organically to the linking process by learning the relative contribution of each of these factors jointly during a gradient decent based optimisation process. Our experiments demonstrate that the proposed approach contributes to a significantly superior performance on a recent challenging video dataset, which captures complex scenes with a wide range of object types and diverse backgrounds.

Increasing the expressiveness of qualitative spatial calculi is an essential step towards meeting the requirements of applications. This can be achieved by combining existing calculi in a way that we can express spatial information using relations from multiple calculi. The great challenge is to develop reasoning algorithms that are correct and complete when reasoning over the combined information. Previous work has mainly studied cases where the interaction between the combined calculi was small, or where one of the two calculi was very simple. In this paper we tackle the important combination of topological and directional information for extended spatial objects. We combine some of the best known calculi in qualitative spatial reasoning, the RCC8 algebra for representing topological information, and the Rectangle Algebra (RA) and the Cardinal Direction Calculus (CDC) for directional information. We consider two different interpretations of the RCC8 algebra, one uses a weak connectedness relation, the other uses a strong connectedness relation. In both interpretations, we show that reasoning with topological and directional information is decidable and remains in NP. Our computational complexity results unveil the significant differences between RA and CDC, and that between weak and strong RCC8 models. Take the combination of basic RCC8 and basic CDC constraints as an example: we show that the consistency problem is in P only when we use the strong RCC8 algebra and explicitly know the corresponding basic RA constraints.

Learning from imbalanced data is an important problem in data mining research. Much research has addressed the problem of imbalanced data by using sampling methods to generate an equally balanced training set to improve the performance of the prediction models, but it is unclear what ratio of class distribution is best for training a prediction model. Bagging is one of the most popular and effective ensemble learning methods for improving the performance of prediction models; however, there is a major drawback on extremely imbalanced data-sets. It is unclear under which conditions bagging is outperformed by other sampling schemes in terms of imbalanced classification. These issues motivate us to propose a novel approach, unevenly balanced bagging (UBagging) to boost the performance of the prediction model for imbalanced binary classification. Our experimental results demonstrate that UBagging is effective and statistically significantly superior to single learner decision trees J48 (SingleJ48), bagging, and equally balanced bagging (BBagging) on 32 imbalanced data-sets.

Archaeological features are the result of anthropogenic interference with the natural soil matrix. This causes differences in the composition and structure of the soil. These influence the development and health of the vegetation on the surface which may be detectable remotely. Indeed much work has been conducted using aerial photography indicating that the use of current remote sensing technologies could lead to improved detection. This paper explores the potential of hyperspectral and full waveform LiDAR data for the mapping of archaeology at an arable site in the UK. It is demonstrated that the archaeological features are detectable by both sensor types most successfully when looking at products that pertain to biomass. This means there is great potential for data fusion approaches using these products. These could be used to improve the spatial resolution of the hyperspectral data and potentially to improve the analysis of biomass in spectra analysis of vegetation parameters.

The complexity of ontology authoring and the difficulty to master the use of existing ontology authoring tools, put significant constraints on the involvement of both domain experts and knowledge engineers in ontology authoring. This often requires substantial effort for fixing ontologies defects (e.g. inconsistency, unsatisfiability, missing or unintended implications, redundancy, isolated entities). The paper argues that ontology authoring tools should provide immediate semantic feedback upon entering ontological constructs. We present a framework to analyse input axioms and provide meaningful feedback at a semantic level. The framework has been used to augment an existing Controlled Natural Language-based ontology authoring tool – ROO. An experimental study with ROO has been conducted to examine users' reactions to the semantic feedback and the effect on their ontology authoring behaviour. The study strongly supported responsive intuitive ontology authoring tools, and identified future directions to extend and integrate semantic feedback.

Current research on qualitative spatial representation and reasoning mainly focuses on one single aspect of space. In real‐world applications, however, multiple spatial aspects are often involved simultaneously. This paper investigates problems arising in reasoning with combined topological and directional information. We use the RCC8 algebra and the rectangle algebra (RA) for expressing topological and directional information, respectively. We give examples to show that the bipath‐consistency algorithm Bipath‐Consistency is incomplete for solving even basic RCC8 and RA constraints. If topological constraints are taken from some maximal tractable subclasses of RCC8, and directional constraints are taken from a subalgebra, termed DIR49, of RA, then we show that Bipath‐Consistency is able to separate topological constraints from directional ones. This means, given a set of hybrid topological and directional constraints from the above subclasses of RCC8 and RA, we can transfer the joint satisfaction problem in polynomial time to two independent satisfaction problems in RCC8 and RA. For general RA constraints, we give a method to compute solutions that satisfy all topological constraints and approximately satisfy each RA constraint to any prescribed precision.

In many areas of visual surveillance, the observed activity follows re-occurring patterns.This paper demonstrates how such patterns can be exploited to improve the detection rate of independent event detectors.We present a temporal model based on pairwise correlations between event timings, which efficiently exploits limited training data.This is combined with the response from potentially heterogeneous independent event detectors to improve the robustness of detections over extended sequences.We demonstrate the efficacy of our system with rigorous testing on a large real-world dataset of aircraft servicing operations.We describe the implementation of a binary classifier based on local histograms of optical flow which is used as the independent event detector in our experiments.

Live workflow monitoring and the resulting user interaction in industrial settings faces a number of challenges. A formal workflow may be unknown or implicit, data may be sparse and certain isolated actions may be undetectable given current visual feature extraction technology. This paper attempts to address these problems by inducing a structural workflow model from multiple expert demonstrations. When interacting with a naive user, this workflow is combined with spatial and temporal information, under a Bayesian framework, to give appropriate feedback and instruction. Structural information is captured by translating a Markov chain of actions into a simple place/transition petri-net. This novel petri-net structure maintains a continuous record of the current workbench configuration and allows multiple sub-sequences to be monitored without resorting to second order processes. This allows the user to switch between multiple sub-tasks, while still receiving informative feedback from the system. As this model captures the complete workflow, human inspection of safety critical processes and expert annotation of user instructions can be made. Activity classification and user instruction results show a significant on-line performance improvement when compared to the existing Hidden Markov Model or pLSA based state of the art. Further analysis reveals that the majority of our model's classification errors are caused by small de-synchronisation events rather than significant workflow deviations. We conclude with a discussion of the generalisability of the induced place/transition petri-net to other activity recognition tasks and summarise the developments of this model.

Statutory records of underground utility apparatus (such as pipes and cables) are notoriously inaccu-rate, so street surveys are usually undertaken before road excavation takes place to minimize the extent and duration of excavation and for health and safety reasons. This involves the use of sensors such as Ground Penetrating Radar (GPR). The GPR scans are then manually interpreted and combined with the expectations from the utility records and other data such as surveyed manholes. The task is com-plex owing to the difficulty in interpreting the sen-sor data, and the spatial complexity and extent of under street assets. We explore the application of AI techniques, in particular Bayesian data fusion (BDF), to automatically generate maps of buried apparatus. Hypotheses about the spatial location and direction of buried assets are extracted by iden-tifying hyperbolae in the GPR scans. The spatial location of surveyed manholes provides further in-put to the algorithm, as well as the prior expecta-tions from the statutory records. These three data sources are used to produce the most probable map of the buried assets. Experimental results on real and simulated data sets are presented. 1

We present a method for unsupervised learning of event classes from videos in which multiple actions might occur simultaneously. It is assumed that all such activities are produced from an underlying set of event class generators. The learning task is then to recover this generative process from visual data. A set of event classes is derived from the most likely decomposition of the tracks into a set of labelled events involving subsets of interacting tracks. Interactions between subsets of tracks are modelled as a relational graph structure that captures qualitative spatio-temporal relationships between these tracks. The posterior probability of candidate solutions favours decompositions in which events of the same class have a similar relational structure, together with other measures of well-formedness. A Markov Chain Monte Carlo (MCMC) procedure is used to efficiently search for the MAP solution. This search moves between possible decompositions of the tracks into sets of unlabelled events and at each move adds a close to optimal labelling (for this decomposition) using spectral clustering. Experiments on real data show that the discovered event classes are often semantically meaningful and correspond well with groundtruth event classes assigned by hand.

In the UK and many other countries, underground networks are used to deliver a range of services to households and industries. Maintaining and upgrading these networks are major undertakings. In order to avoid unnecessary holes dug in wrong places, prior to invasive works it is normally required that excavators should request and obtain record information from all relevant utilities to identify what is buried where. However, the mapping information supplied by utility companies is often of limited use as asset records are usually inaccurate and incomplete. Thus a street survey is often conducted using sensor devices, such as ground penetrating radar (GPR). However, these are costly, and forming a complete picture combining the expectation of the map and the sensor data is an expert task. This paper will investigate an algorithm for utility pipeline mapping based on street survey and GPR data.

This work proposes a graph mining based approach to mine a taxonomy of events from activities for complex videos which are represented in terms of qualitative spatio-temporal relationships. A Hidden Markov Model to obtain stable qualitative spatial relations from noisy measurements is introduced. The effectiveness of the approach is demonstrated through experimental results for a complex aircraft turnaround apron scenario.

This paper proposes a probabilistic robust hyperbola mixture model based on a classification expectation maximization algorithm and applies this algorithm to Ground Penetrating Radar (GPR) spatial data interpretation. Previous work tackling this problem using the Hough transform or neural networks for identifying GPR hyperbolae are unsuitable for on-site applications owing to their computational demands and the difficulties of getting sufficient appropriate training data for neural network based approaches. By incorporating a robust hyperbola fitting algorithm based on orthogonal distance into the probabilistic mixture model, the proposed algorithm can identify the hyperbolae in GPR data in real time and also calculate the depth and the size of the buried utility pipes. The number of the hyperbolae can be determined by conducting model selection using a Bayesian information criterion. The experimental results on both the synthetic/simulated and real GPR data show the effectiveness of this algorithm.

Accurate object tracking is a challenging problem in visual surveillance due to noise segmentation, partial and full object occlusions. In this paper, we present a method for object tracking and primitive event detection by associating tracklet caused by these problems. The aim is to keep track identity across tracking gaps and detect object's motion changes (identify primitive event) that cause tracklet gaps. We first detect moving objects and generate tracklet, then grow these tracklets by finding the best spatial and temporal association of observations to track object across tracklet gaps and indentify the video event they involved. We successfully track multiple moving vehicles and persons under occlusion, noisy detections and split-merge situations and can identify the event that cause tracking gaps.

We propose a framework that learns functional object-categories from spatio-temporal data sets such as those abstracted from video. The data is represented as one activity graph that encodes qualitative spatio-temporal patterns of interaction between objects. Event classes are induced by statistical generalization, the instances of which encode similar patterns of spatio-temporal relationships between objects. Equivalence classes of objects are discovered on the basis of their similar role in multiple event instantiations. Objects are represented in a multidimensional space that captures their role in all the events. Unsupervised learning in this space results in functional object-categories. Experiments in the domain of food preparation suggest that our techniques represent a significant step in unsupervised learning of functional object categories from spatio-temporal patterns of object interaction.

Although it is well recognised that ontologies have an important role to play in data integration, the lack of established ontologies in domains of interest often makes ontology-based integration a difficult task. Previous research on ontology design methodologies shows that manual construction of ontologies is a complex process and it is very hard for a designer to develop a consistent ontology. This paper contributes a formal and semi-automated approach for the development of ontologies in the utility infrastructure domain. It arises from a practical industrial problem of integrating the vast network of underground asset records. These asset records are typically autonomous, i.e. owned and maintained by individual organisations, and are encoded in an uncoordinated way, i.e. without consideration of interoperability with other utility information systems. The proposed approach is based on formal concept analysis (FCA) which is a mathematical approach for abstracting from attribute-based object descriptions. This paper describes techniques developed to support utility ontology development, with a focus on resolving implicit and mismatch data. Some experiments have been carried out to construct a utility ontology with data from utility companies. Though issues addressed in the paper arise in utility ontology development, we anticipate that they should be interesting and relevant to other application domains.

The problem of object recognition may be cast into a spatial grammar framework. The system comprises three novel elements: a spatial organisation of line features, an efficient two dimensional parsing engine, and a genetic algorithm learning routine that induces spatial grammars. Labelling the spatial organisation of feature pairs allows the terminal symbols of the spatial grammar to be defined, and constrains the search space of the feature parser. A genetic algorithm approach is then used to induce appropriate grammars using a supervised learning routine. Early results show that similar foreground and background features can be discriminated using this approach.

We present a method for merging multiple partitions into a single partition, by minimising the ratio of pairwise agreements and contradictions between the equivalence relations corresponding to the partitions. The number of equivalence classes is determined automatically. This method is advantageous when merging segmentations obtained independently. We propose using this consensus approach to merge segmentations of features tracked on video. Each segmentation is obtained by clustering on the basis of mean velocity during a particular time interval.

We discuss the task of reconstructing the topological map of an environment based on the sequences of locations visited by a mobile agent -- this occurs in systems neuroscience, where one runs into the task of reconstructing the global topological map of the environment based on activation patterns of the place coding cells in hippocampus area of the brain. A similar task appears in the context of establishing wifi connectivity maps.

An integrated map of all utility services in a locale would facilitate better management of the road infrastructure and the utilities themselves. To meet this goal, there exists a need to integrate raster scans of paper maps into GIS by capturing the semantic relationships between the objects in the drawings. In this context, commercially available vectorisation algorithms do not produce a sufficiently rich object representation. We present a structural object recognition system that successfully isolates sectional sub- diagrams in maps of underground utilities. This is built upon a vectorisation system based on a constrained Delau-nay triangulation of pen strokes.

There is now a growing literature on qualitative spatial representations covering many aspects of spatial representation including mereology, topology, orientation and distance. In this paper I will briefly outline some of these approaches to qualitative spatial representation and then apply these theories to the task of formalising a non-trivial domain: that of representing cell structure. The paper is thus a contribution to the evaluation of qualitative spatial representations and spatial ontologies and may form the basis of a bio-informatic information system.

We describe an implemented technique for generating event models automatically based on qualitative reasoning and a statistical analysis of video input. Using an existing tracking program which generates labelled contours for objects in every frame, the view from a fixed camera is partitioned into semantically relevant regions based on the paths followed by moving objects. The paths are indexed with temporal information so objects moving along the same path at different speeds can be distinguished. Using a notion of proximity based on the speed of the moving objects and qualitative spatial reasoning techniques, event models describing the behaviour of pairs of objects can be built, again using statistical methods. The system has been tested on a traffic domain and learns various event models expressed in the qualitative calculus which represent human observable events. The system can then be used to recognise subsequent selected event occurrences or unusual behaviours.

We examine a variety of representations for storing and reasoning about spatial information and distinguish between quantitative representations grounded in numerical coordinate systems and qualitative representations, based on a high-level conceptual vocabulary for the description of spatial situations. We suggest that qualitative languages, can add powerful functionality to spatial information systems, which have traditionally processed only quantitative data. Trade-offs between expressive power, computational tractability and 'naturalness' are considered for several qualitative formalisms. We explain how a significant class of topological relations can be described by a 1st-order language and how these can be encoded into 0-order intuitionistic logic to yield an effective reasoning algorithm. We discuss ways of combining qualitative and quantitative information within a coherent architecture and describe an implementation of a hybrid spatial information system, incorporating three types of spatial information: quantitative data-structures are employed in a database of polygonal regions; a qualitative relational language is used to express high-level queries; and intuitionistic propositional logic is used to compute the inferences needed to answer these queries.

Integration of disparate heterogeneous databases requires translation of types. Because a type in one system often has no exact counterpart in the others, fully reliable integration requires deep understanding of the subject domain, with conceptual analysis of type meanings. So far, reliable translation has had to be done by hand. In practice, few types are so crucial as to require full reliability. The EGG/YOLK hierarchy ranks types by the tolerable rashness in translation, based on prototypes in each type. Each defined class (EGG) has a subclass of typical members (YOLK) defined. We exploit Cui, Cohn and Randell's Qualitative Spatial Simulation program to create the hierarchy of all possible relations between source and target EGG/YOLK types, ranked by reliability. Our eventual ranking is based on a poset combining four different preference criteria.