Identifying Indoor Navigation Landmarks Using a Hierarchical Multi-Criteria Decision Framework

Dubey, Rohit K.; Sohn, Samuel S.; Thrash, Tyler; Höelscher, Christoph; Kapadia, Mubbasir

doi:10.1145/3359566.3360066

Cited by 10 publications

(13 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To simulate realistic perception process, some studies developed agents that can visually perceive signs like human and act according to the instructions on the signs [Dubey et al 2021][Becker-Asano et al 2014]. Besides signs, computational cognitive models for landmark recognition was proposed [Dubey et al 2019b]. Another study modeled utility of wayfinding uncertainty based on traveled distance, direction toward the destination and landmarks [Najian and Dean 2017].…”

Section: Related Workmentioning

confidence: 99%

An Evidence-based Cognitive Model of Uncertainty during Indoor Multi-level Human Wayfinding

Yang

Dubey

Kalantari

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Wayfinding - the process of goal-directed planned movement in an unfamiliar, large, and complex environment is challenging and often executed under uncertainty. Wayfinding uncertainty is a mental state experienced, especially in an unknown environment, when deciding between two or more competing route choices at a decision point. Even though uncertainty is intrinsic and plays a crucial role during wayfinding, the existing computational model of human wayfinding provides no or minimal support for modeling uncertainty during wayfinding. Therefore, it is paramount to incorporate uncertainty into a wayfinding model to produce realistic human wayfinding. In this paper, we ground the wayfinding process on the concept of oriented search (as proposed by Allen (1999)), employing directional information from signage and spatial layout. We model the two most common and prevalent uncertainty during wayfinding: (1) Route-choice uncertainty: Originates when an occupant is at a decision point and has to select a route out of the multiple route choices. (2) Affirm on-route uncertainty: Originates when an occupant is in-between decision points (e.g., a long corridor, large open space) and tries to ascertain if its current location is on the correct route towards the destination. We model route-choice uncertainty as a function of two attributes: the number of possible outcomes and the probability distribution of belief in electing each outcome at a decision point. We conducted a real-world experiment with XX participants to parameterize and validate the wayfinding uncertainty model. After preliminary analysis of the collected and simulated data, we observe similar wayfinding behavior between simulated agents and participants regarding perceived continuous uncertainty during wayfinding and route-choice behavior at decision points.

show abstract

Section: Related Workmentioning

confidence: 99%

An Evidence-based Cognitive Model of Uncertainty during Indoor Multi-level Human Wayfinding

Yang

Dubey

Kalantari

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, few studies have started to develop computational models to identify landmarks from indoor environments (Lyu et al 2015, Fellner et al 2017, Dubey et al 2019, Wang et al 2020, Hu et al 2020. These indoor models often adapted computational frameworks that were originally developed for outdoor landmark selection, and employed similar landmark salience measures and weighting/combination algorithms.…”

Section: Computational Indoor Landmark Selectionmentioning

confidence: 99%

“…For example, Lyu et al (2015), Fellner et al (2017), and Wang et al (2020) used a simple weighted linear approach to combine landmark salience measures for identifying suitable landmarks for indoor environments. Dubey et al (2019) developed a hierarchial landmark salience model and used a linear model to optimize the general weights of visual, structural, and semantic salience and the weights for the fine-grained measures within these three dimensions. Different from the above approaches, Hu et al (2020) developed a machine learning-based approach that employed a genetic programming technique to learn the indoor landmark salience model from their collected empirical landmark selection data.…”

Section: Computational Indoor Landmark Selectionmentioning

confidence: 99%

“…According to the scale of spaces (Montello 1993, Löwen et al 2017, indoor landmarks can be classified into two categories: room-level (Fellner et al 2017), and object-level (or furniture-level) (Ohm et al 2014, Viaene et al 2018. Despite some novel techniques such as virtual reality (Dubey et al 2019) and eye-tracking (Wang et al 2020) for collecting indoor landmark data, the computational approaches for indoor landmark selection (Lyu et al 2015, Fellner et al 2017 still simply adapted the weighted linear models originally proposed for outdoor environments. Hu et al (2020) recently proposed a machine learning method based on genetic programming.…”

Section: Introductionmentioning

confidence: 99%

“…Hu et al (2020) recently proposed a machine learning method based on genetic programming. However, their model only considered the visual and semantic salience of landmarks, and failed to include the structural salience, which has been found essential for landmark selection in many empirical studies (Klippel 2003, Kattenbeck 2015, Dubey et al 2019. More importantly, similar to outdoor landmark selection, none of the exiting indoor models has attempted to consider users' familiarity with the environment in the computational modelling of indoor landmark selection.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Familiarity-dependent computational modelling of indoor landmark selection for route communication: a ranking approach

Zhou

Weibel

Huang

2021

International Journal of Geographical Information Science

View full text Add to dashboard Cite

Landmarks play key roles in human wayfinding and mobile navigation systems. Existing computational landmark selection models mainly focus on outdoor environments, and aim to identify suitable landmarks for guiding users who are unfamiliar with a particular environment, and fail to consider familiar users. This study proposes a familiarity-dependent computational method for selecting suitable landmarks for communicating with familiar and unfamiliar users in indoor environments. A series of salience measures are proposed to quantify the characteristics of each indoor landmark candidate, which are then combined in two LambdaMART-based learning-to-rank models for selecting landmarks for familiar and unfamiliar users, respectively. The evaluation with labelled landmark preference data by human participants shows that people's familiarity with environments matters in the computational modelling of indoor landmark selection for guiding them. The proposed models outperform state-of-the-art models, and achieve hit rates of 0.737 and 0.786 for familiar and unfamiliar users, respectively. Furthermore, semantic relevance of a landmark candidate is the most important measure for the familiar model, while visual intensity is most informative for the unfamiliar model. This study enables the development of human-centered indoor navigation systems that provide familiarity-adaptive landmark-based navigation guidance.

show abstract

Chapter 9 Towards Democratizing Human–Building Simulation and Analytics

Usman

Haworth

Berseth

et al. 2021

Resilience in the Digital Age

View full text Add to dashboard Cite

Identifying Indoor Navigation Landmarks Using a Hierarchical Multi-Criteria Decision Framework

Cited by 10 publications

References 28 publications

An Evidence-based Cognitive Model of Uncertainty during Indoor Multi-level Human Wayfinding

An Evidence-based Cognitive Model of Uncertainty during Indoor Multi-level Human Wayfinding

Familiarity-dependent computational modelling of indoor landmark selection for route communication: a ranking approach

Chapter 9 Towards Democratizing Human–Building Simulation and Analytics

Contact Info

Product

Resources

About