Umeå University's logo

Grounding spatial deixis is essential for establishing shared spatial understanding in HRI. This paper presents the Spatial Deixis Model (SDM), a perceptual framework allowing a robot to infer the English spatial deixis here and there from pointing gestures and using a dynamic, embodied peri-personal space. We performed an empirical evaluation of the SDM with 12 participants in 5 scenarios with different contexts (e.g., varying distances and/or heights with respect to human and robot). Results show that the localization accuracy for the pointed-at objects across 174 trials is 92% and the overall agreement across all trials is 63.7%, demonstrating that SDM generally captures the dynamic notion of spatial deixis.

How an origin and a destination align with the street network may, anecdotally, be used as a heuristic to infer the length and complexity of routes from the origin to the destination. However, no method of measuring alignment with a street network exists, and furthermore, it is unclear whether and under what circumstances it is useful as a heuristic. In this paper, we propose a novel method for measuring alignment using the Earth Mover's Distance (EMD) between orientation distributions. We evaluated this metric using a dataset of 77,293 origin and destination pairs from 100 cities with different street networks, in order to test the hypothesis that an increasing degree of misalignment is predictive of a longer and more complex route from origin to destination. Our evaluation shows that our method for measuring alignment becomes more useful as a heuristic the more grid-like the street network surrounding the origin and destination is. To conclude, the results obtained indicate that alignment is an important factor for route properties, especially in grid-like street networks, a subclass of routes within an environment where the configuration of the street network makes predicting the length and complexity easier.

The routes displayed on maps by navigation support systems are intended to help users to orient themselves towards reaching the destination and to infer information related to their navigation. Inferring how complex a route is, including how well you think you can remember it and the likelihood of getting lost, may influence expectations on how it is navigated. However, it is not well understood when and where a route displayed on a map is perceived as complex and why someone perceives it this way. Current methods for assessing complexity tend to focus either on (i) the complexity of the route or on (ii) the complexity of the environment as a static and global property. By taking inspiration from navigational map reading and how routes and street networks are perceived on a map, this paper investigates how environmental complexity influences route complexity and length.We developed a new approach to gauge the alignment between the orientation of a route’s origin and destination with respect to the orientation of the streets within the network, and we investigated how this measure relates to route complexity and length.

Navigation services play a crucial role in everyday wayfinding. One of their key features is the turn-by-turn guidance, enabling wayfinders to navigate efficiently between locations. However, over-reliance on turn-by-turn guidance can hinder wayfinders' ability to perceive their surroundings and develop spatial awareness, negatively impacting user experience. Previous research has addressed these issues by modifying instructions, user interaction, or both. However, the applicability of these methods beyond specific studies remains unclear. This paper presents a human-centred study by evaluating an algorithm that automatically generates navigation instructions. The instructions are generated by adding route-defining locations to ‘standard’ turn-by-turn instructions to enhance wayfinder's spatial knowledge acquisition, and improve user experience. Route-defining locations, identified using a previously proposed algorithm, serve as anchors for the wayfinder to form a spatial understanding of the environment. The study involved 36 participants divided into two groups: one received ‘standard’ turn-by-turn (TBT) instructions, while the other received instructions that included route-defining locations (RDL). Participants navigated in an unfamiliar virtual environment, and their wayfinding and route learning were compared between the two groups. Results show that RDL instructions led to better wayfinding and route learning performance compared to TBT instructions, suggesting the potential to improve navigation systems and user experiences.

Today, anyone feeling lost in a city or unsure about how to navigate can use navigation services to look up routes to where they want to go. Current research investigating these services has primarily focused on how to find an appropriate route and how to best support navigation along it, and not how routes and the maps they are presented on are perceived. What makes one route look more difficult to navigate than another? And how does experience with using navigation services and maps in daily life influence how difficult a route is perceived to be? We explored these questions in a survey study where participants rated the perceived difficulty of pedestrian routes in ten different cities. The results show that routes in more complex urban environments were perceived as more complex than routes in easier environments. At least partly, perceived difficulty seems to follow earlier conceptualizations of route complexity, but open questions remain regarding the interplay of environmental structure, route properties, and the map representation.

Machine learning is increasingly used as a computing paradigm in cartographic research. In this extended editorial, we provide some background of the papers in the CaGIS special issue Machine Learning in Cartography with a special focus on pattern recognition in maps, cartographic generalization, style transfer, and map labeling. In addition, the paper includes a discussion about map encodings for machine learning applications and the possible need for explicit cartographic knowledge and procedural modeling in cartographic machine learning models.

Navigation services are essential for daily navigation, providing turn-by-turn instructions to help wayfinders reach their destinations. These services often differ from the heuristics wayfinders use, resulting in a poor user experience. Researchers have attempted to address this issue by developing algorithms that find less complex routes, by integrating prominent locations along the route to make wayfinding easier and to improve a wayfinder’s knowledge about the environment. These approaches, however, have taken a bottom-up approach, involving a limited number of participants navigating in real or virtual environments which may limit generalisability of results. In this study, we took a top-down approach by analysing a large dataset of GPS-based trips in the real world. Using the Geolife dataset, we analysed individual heuristics for route selection in terms of complexity and prominent locations, and found that wayfinders prefer less complex routes, such as routes that require fewer turns or involve simpler intersections. Additionally, we found that wayfinders choose routes with fewer prominent locations, such as routes that bypass well-known landmarks or busy commercial areas. These findings suggest that simplicity and ease of use are prioritized when selecting a route, while overly complex routes or areas with many points of interest are avoided.

Taken literally, geoAI is the use of Artificial Intelligence methods and techniques in solving geo-spatial problems. Similar to AI more generally, geoAI has seen an influx of new (big) data sources and advanced machine learning techniques, but also a shift in the kind of problems under investigation. In this article, we highlight some of these changes and identify current topics and challenges in geoAI.