This paper presents a conceptual model of pedestrian mobility spaces in 3D city models. While conceptual models can be specified in various ways, we use standard elements of CityGML and an Application Domain Extension (ADE): The Pedestrian ADE extends CityGML 3.0 to incorporate key parameters related to the physical, legal, and regulatory aspects of pedestrian mobility environments. For this, the extension introduces new feature classes for vertical passages such as stairs and elevators, and adds attributes to existing CityGML classes to represent pedestrian-specific characteristics. The conceptual model is also implemented for demonstration and validation: A real-world case study in Melbourne, Australia, demonstrates the practical application of the Pedestrian ADE to model complex urban environments. Through visualizations, we show how the model can be applied to represent spaces where different types of pedestrians can, cannot, may, or must not walk. This work provides a standardized approach for detailed 3D modeling of pedestrian mobility spaces, supporting various applications in urban planning, transportation, and accessibility analysis.

Pedestrian navigation in crowded environments involves a continuous, subtle negotiation of interpersonal space. This research investigates these pedestrian spacing behaviors through the lens of comfortable distance—an invisible yet perceptible psychological boundary that regulates social interactions and collective movement. We examine how pedestrians perceive and manage this spacing as a dynamic response to social and environmental constraints. Using manually labeled pedestrian interactions from 650 pedestrian tracks recorded in two real-world datasets, we provide empirical evidence of how directional context and social configuration systematically structure spatial behavior. We find significant differences in comfortable distances across directional interactions, conditionally influenced by crowd density, pedestrian speed, spatial freedom, and relative positions. Group membership systematically modifies these associations, although its effect on encountered non-group pedestrians remains limited. By quantifying these spacing patterns, we establish a reproducible baseline for spatial organization, informing socially-aware navigation.

Leisure walking is a physical activity where locomotion through a natural or even urban environment is the goal in itself, e.g., in pursuit of health and wellbeing. In contrast to destination-oriented walks that are focused on navigation efficiency (i.e., shortest or simplest walk from source to destination), leisure walks emphasize experiencing the environment, engaging in activities, and discovering places that may be off route, or intermediate destinations en-route, summarily called points of interest (POIs). POIs are key for recommending leisure walks, yet a detailed analysis of POIs in the context of leisure walking is missing in the literature. This study extracts and annotates POIs of leisure walking recommendations available in WalkingMaps.com.au, creating an annotated dataset to address this research gap and provide a first analysis of leisure walking descriptions. We classify POIs using the verbal description provided in the dataset, match them with data available in OpenStreetMap (OSM), and compare the POIs with nearby alternatives in OSM. Our analysis reveals thematic and spatial patterns in POI selection, offering a machine learning approach to model POI choices for leisure walks. We further evaluate the availability of rich data in OSM for future automated leisure walking recommendation. This study contributes to automated systems for recommending leisure walks, tailoring suggestions based on available information in the spatial open data, and presents an annotated dataset to facilitate future research in this field.

This paper presents a graph model that simultaneously stores route and configurational information about indoor spaces. Existing indoor information models either capture route information to compute shortest paths and to generate route descriptions (i.e., answering how-to-get-to questions), or they store configurational information about objects and places and their spatial relationships to enable spatial querying and inference (i.e., answering where-questions). Consequently, multiple representations of an indoor environment must be stored in information systems to address the various information needs of their users. In this paper, we propose a graph that can capture both configurational and route information in a unified manner. The graph is the dual representation of connected lines of sight, or views. Views can represent continuous movement in an indoor environment, and at the same time, the visible configurational information of each view can be explicitly captured. In this paper, we discuss the conceptual design of the model and an automatic approach to derive the view graph from floorplans. Finally, we demonstrate the capabilities of our model in performing different tasks such as calculating shortest paths, generating route descriptions, and deriving place graphs.

Abstract. Text-based games are environments in which defining the world, the representation of the world to the player (hereafter, agent) and agent interactions with the environment are all through text. Text-based games expose abstract, executable representations of indoor spaces through verbally referenced concepts. Yet, the ability of text-based games to represent indoor environments of real-world complexity is currently limited due to insufficient support for complex space decomposition and space interaction concepts. This paper suggests a procedure to automate the mapping of real-world geometric floorplan information into text-based game environment concepts, using the Microsoft TextWorld game platform as a case. To capture the complexities of indoor spaces, we enrich existing TextWorld concepts supported by theoretical navigation concepts.We first decompose indoor spaces using skeletonization, and then identify formal space concepts and their relationships. We further enhance the spectrum of supported agent interactions with an extended grammar, including egocentric navigation instructions. We demonstrate and discuss these new capabilities in an evacuation scenario. Our implementation extends the capabilities of TextWorld to provide a research testbed for spatial research, including symbolic spatial modelling, interaction with indoor spaces, and agent-based machine learning and language processing tasks.

People can be localized at a particular location in an indoor environment using verbal descriptions referring to distinct visible objects (e.g., landmarks). When a user provides an incomplete initial location description their location may remain ambiguous. Here, we consider a dialogue initiated to update the initial description, which continues until the updated description can be related to a location in the environment. In each interaction, the wayfinder is incrementally asked about the visibility of a particular object to update the initial description. This paper presents an entropy-based model to minimize the number of interactions. We show how this entropy-based model leads to a significant reduction of interactions (i.e., reduction of conversation length, measured by the number of additional referents) compared to baseline models. Moreover, the effect of the initial description, i.e., the first set of visible objects with different combinations, is investigated.

In everyday communication, where-questions are answered by place descriptions. To answer where-questions automatically, computers should be able to generate relevant place descriptions that satisfy inquirers' information needs. Human-generated answers to where-questions constructed based on a few anchor places that characterize the location of inquired places. The challenge for automatically generating such relevant responses stems from selecting relevant anchor places. In this paper, we present templates that allow to characterize the human-generated answers and to imitate their structure. These templates are patterns of generic geographic information derived and encoded from the largest available machine comprehension dataset, MS MARCO v2.1. In our approach, the toponyms in the questions and answers of the dataset are encoded into sequences of generic information. Next, sequence prediction methods are used to model the relation between the generic information in the questions and their answers. Finally, we evaluate the performance of predicting templates for answers to where-questions.

Many place-related questions can only be answered by complex spatial reasoning, a task poorly supported by factoid question retrieval. Such reasoning using combinations of spatial and non-spatial criteria pertinent to place-related questions is increasingly possible on linked data knowledge bases. Yet, to enable question answering based on linked knowledge bases, natural language questions must first be re-formulated as formal queries. Here, we first present an enhanced version of YAGO2geo, the geospatially-enabled variant of the YAGO2 knowledge base, by linking and adding more than one million places from OpenStreetMap data to YAGO2. We then propose a novel approach to translate the place-related questions into logical representations, theoretically grounded in the core concepts of spatial information. Next, we use a dynamic template-based approach to generate fully executable GeoSPARQL queries from the logical representations. We test our approach using the Geospatial Gold Standard dataset and report substantial improvements over existing methods.

The trend to equip information systems with question-answering capabilities raises the design problem of deciding which questions a system should be able to answer. Typical solutions build on mining human conversations or logs from similar systems for question patterns. For the case of questions about geographic places, we present a complementary approach, showing how to derive possible questions from an ontology of spatial information and a classification of place facets. We argue that such an approach reduces the inherent and substantial data bias of current solutions. At a more general level, we provide a novel understanding of spatial questions and their role in designing and using spatial information systems.

Existing question answering systems struggle to answer factoid questions when geospatial information is involved. This is because most systems cannot accurately detect the geospatial semantic elements from the natural language questions, or capture the semantic relationships between those elements. In this paper, we propose a geospatial semantic encoding schema and a semantic graph representation which captures the semantic relations and dependencies in geospatial questions. We demonstrate that our proposed graph representation approach aids in the translation from natural language to a formal, executable expression in a query language. To decrease the need for people to provide explanatory information as part of their question and make the translation fully automatic, we treat the semantic encoding of the question as a sequential tagging task, and the graph generation of the query as a semantic dependency parsing task. We apply neural network approaches to automatically encode the geospatial questions into spatial semantic graph representations. Compared with current template-based approaches, our method generalises to a broader range of questions, including those with complex syntax and semantics. Our proposed approach achieves better results on GeoData201 than existing methods.

Abstract. Understanding syntactic and semantic structure of geographic questions is a necessary step towards true geographic question-answering (GeoQA) machines. The empirical basis for the understanding of the capabilities expected from GeoQA systems are geographic question corpora. Available corpora in English have been mostly drawn from generic Web search logs or limited user studies, supporting the focus of GeoQA systems on retrieving factoids: factual knowledge about particular places and everyday processes. Yet, the majority of questions enquired about in the spatial sciences go beyond simple place facts, with more complex analytical intents informing the questions. In this paper, we introduce a new corpus of geo-analytic questions drawn from English textbooks and scientific articles. We analyse and compare this corpus with two general-purpose GeoQA corpora in terms of grammatical complexity and semantic concepts, using a new parsing method that allows us to differentiate and quantify patterns of a question’s intent.

Geographic questions are among the most frequently asked questions in Web search and question answering systems. While currently responses to the questions are machine-generated by document/snippet retrieval, in the future these responses will need to become more similar to answers provided by humans. Here, we have analyzed human answering behavior as response to simple where questions (i.e., where questions formulated only with one toponym) in terms of type, scale, and prominence of the places referred to. We have used the largest available machine comprehension dataset, MS-MARCO v2.1. This study uses an automatic approach for extraction, encoding and analysis of the questions and answers. Here, the distribution analysis are used to describe the relation between questions and their answers. The results of this study can inform the design of automatic question answering systems for generating useful responses to where questions.

This paper investigates place-related questions submitted to search systems and their human-generated answers. Place-based search is motivated by the need to identify places matching some criteria, to identify them in space or relative to other places, or to characterize the qualities of such places. Human place-related questions have thus far been insufficiently studied and differ strongly from typical keyword queries. They thus challenge today’s search engines providing only rudimentary geographic information retrieval support. We undertake an analysis of the patterns in place-based questions using a large-scale dataset of questions/answers, MS MARCO V2.1. The results of this study reveal patterns that can inform the design of conversational search systems and in-situ assistance systems, such as autonomous vehicles.

Geographic questions are among the most frequently asked questions in Web search and question answering systems. While currently responses to the questions are machine-generated by document/snippet retrieval, in the future these responses will need to become more similar to answers provided by humans. Here, we have analyzed human answering behavior as response to simple where questions (i.e., where questions formulated only with one toponym) in terms of type, scale, and prominence of the places referred to. We have used the largest available machine comprehension dataset, MS-MARCO v2.1. This study uses an automatic approach for extraction, encoding and analysis of the questions and answers. Here, the distribution analysis are used to describe the relation between questions and their answers. The results of this study can inform the design of automatic question answering systems for generating useful responses to where questions.

Place is a central concept in geography and a topic of interest in the social sciences, urban planning, architecture, and most recently in information science. The notion of place has therefore been studied with different foci of interest. Consequently, heterogeneous terminologies, conceptualizations, models, and ontologies have been proposed to capture this elusive concept. Yet these studies complement each other. Utilizing the concept of place facet as a particular type of information about place, in this review paper we bridge these multidisciplinary studies about place. We collect the different facets of place introduced in the literature and synthesize place characteristics by categorizing the identified facets. Finally, we discuss future directions for place-related research.

A place graph is an abstract representation of human place knowledge, which models spatial references. A place graph can be used for various tasks that rely on reasoning and querying of the stored knowledge. In related work, place graphs were constructed from parsing natural language place descriptions using language processing techniques. In this research, we present an innovative approach to derive place graphs from information stored in spatial databases, with a demonstration using OpenStreetMap data. The approach provides a complementary way to generating place graphs from natural language descriptions.

Verbal indoor route descriptions contain human spatial knowledge that this paper aims to represent formally for further analysis and question-answering. Available tools – route graphs for route descriptions, and place graphs for place descriptions – both turn out to fall short on our corpus of verbal indoor route descriptions. Hence, the paper will identify the characteristics of indoor route descriptions, identify strategies for knowledge extraction, and seek a unified graph representation.

In our modern world, search engines have been proposed as one of the challenging research areas. One of the main issues in search engines studies is human computer interaction, which its aim is to understand user's needs. If there is no right query processing approach, the results will be invalid in most cases. Therefore, in this paper we present a new approach to process and analyze the queries for spatial search engines. Our algorithm is implemented in the three steps, including: iterative segmentation of the query, sub-queries processing by finding appropriate candidates for the location-names, the location-types and spatial relationships and finally checking the relationships among these candidates in validation phase. Generally using our method has two major advantages as the search engines can provide the capability of spatial analysis based on the specific process which leads to a better interaction between the users and the search application in geospatial realm and secondly because of the disambiguation technique, user reaches the more desirable result.

Nowadays the selective access to information on the Web is provided by search engines, but in the cases which the data includes spatial information the search task becomes more complex and search engines require special capabilities. The purpose of this study is to extract the information which lies in spatial documents. To that end, we implement and evaluate information extraction from GML documents and a retrieval method in an integrated approach. Our proposed system consists of three components: crawler, database and user interface. In crawler component, GML documents are discovered and their text is parsed for information extraction; storage. The database component is responsible for indexing of information which is collected by crawlers. Finally the user interface component provides the interaction between system and user. We have implemented this system as a pilot system on an Application Server as a simulation of Web. Our system as a spatial search engine provided searching capability throughout the GML documents and thus an important step to improve the efficiency of search engines has been taken.