Room Type Research Articles

Penentuan tarif sewa kamar kost melalui perhitungan harga pokok kamar menggunakan metode activity based costing (Studi kasus Eben Kost Manado)

Achieving maximum profit is closely tied to specific calculations regarding the costs incurred to produce a service product, such as the cost of a room. Activity-Based Costing (ABC) is one method used to calculate the cost of a room by evaluating expenses based on the resources consumed by various activities. The objective of this research is to determine room rental rates by calculating the cost of a room using the Activity-Based Costing method at Eben Kost Manado. The research employed a qualitative descriptive approach. Data collection techniques included interviews and documentation. The findings indicate that the room rental rates determined using the Activity-Based Costing method are lower compared to those set by Eben Kost because the ABC method allocates all activity costs to each room type precisely based on each activity's consumption.

Performance Comparison of Random Forest (RF) and Classification and Regression Trees (CART) for Hotel Star Rating Prediction

Purpose: This study proposes to evaluate the effectiveness of Random Forest (RF) compared to Classification and Regression Trees (CART) in prediction of hotel star ratings. The objective is to identify the algorithm that provides the most reliable and accurate classification outcomes based on diverse hotel attributes in accordance with the standard categorization of star hotel categories. This is necessary due to the important role of accurate star ratings in guiding consumer choices and enhancing competitive positioning in the hospitality industry. Method: This study conducted a comprehensive dataset about Hotel in Banyumas Regency, including location, facilities, the size of rooms, type of rooms, price of rooms, and customer reviews, subjected to training through both RF and CART algorithms. Both algorithms are evaluated using accuracy, precision, recall, and F1 score. Additionally, both algorithms due to in the same preprocessing while performing hyperparameter tuning improve the efficacy of each model. Result: The results showed that RF achieved the best overall accuracy and robustness than CART across all tests conducted. Furthermore, RF also outperformed CART in classification effectiveness among classes, including enhanced precision and recall scores across multiple stars rating categories, signifying increased generalization and consistency in classification tasks. RF classifier consistently surpassed the CART classifier in terms of both accuracy and F1-score throughout all random states and test sizes, with a highest score of 0.9932 at a random state of 100 and a test size of 0.4. The most reliable results were obtained using RF with 42 random states and a test size of 0.2, resulting in an accuracy of 0.9909, precision of 1.0, recall of 1.0, and F1 score of 1.0. Simultaneously, CART shows values of 0.9818, 1.0, 1.0, and 1.0, respectively, while maintaining the same variation. This consistent performance, regardless of fluctuations, illustrates the robustness and suitability of RF for classification tasks compared to CART. Novelty: This study offered new insights about the implementation of machine learning about hotel star rating predictions using RF and CART algorithms. Also, the novelty of the collected hotel dataset used in this study. A detailed comparative analysis was also provided, contributing to the existing literature by showing the effectiveness of RF over CART for this specific application. Future studies could explore the integration of additional machine learning methods to further enhance prediction accuracy and operational efficiency in the hospitality industry.

Escaping the Bondage of Bullying: A Game-based Learning Approach

School bullying is a phenomenon of great concern worldwide, with profound implications for the emotional development of those involved. Leveraging the interactive nature of game-based learning provides a unique opportunity for active student engagement that goes beyond traditional pedagogical methods. This article aims to explore students' perceptions of bullying and present a digital game as an alternative educational approach to raising students' awareness, empathy, and empowerment. Furthermore, it will be demonstrated how an art-based virtual museum game engages students in exploring and understanding the phenomenon. A needs assessment on bullying was conducted on a student population sample during the school year 2023 - 2024. Subsequently, a digital 3D escape room type game (named "e-BOB") was used, which was redesigned and reconstructed by the students from an initial project within the Panhellenic Students Competition of Onassis Foundation "Hack the Art: Yiannoulis Halepas". The game was developed using Unity, Blender, and Krita platforms and is set in an art museum. Players interact with the sculptor's exhibits through micro-scenarios and quizzes drawn from the sculptor's life and artwork that tackle the issue of bullying. Key game features include goal achievement within a time limit and discovery of hidden elements. The analysis of the needs assessment data found that all students had been involved in bullying behaviors either as victims, perpetrators or observers. The majority of students focused mainly on direct forms of bullying and less on indirect forms, and most were unable to distinguish bullying from 'simple teasing', demeaning bullying behavior. Those at greater risk are the ones who show some element of differentiation in relation to the stereotypes of the social context in which they live. Several students indicated that the school environment needs to address the issue sufficiently. Finally, the game contributed to students' empathy about bullying, enhancing their self-reflection and managing strategies. Raising awareness, mental empowerment, and empathy for bullying requires dynamic and innovative approaches. With its potential for self-awareness and student activation, game-based learning should be incorporated into educational programs for bullying prevention and management within schools.

Evaluating lead-free alternatives for radiation shielding in diagnostic radiology: a case study from a tertiary general hospital in Korea.

With the continued increase in the number of pieces of diagnostic medical radiography equipment being used, radiation shielding in radiology departments is becoming increasingly important. Lead is the most commonly used material for radiation protection; however, there are numerous disadvantages associated with the use of lead, including environmental hazards and harm to the human body. Alternative shielding materials that can be used as replacements include barium sulfate, tungsten, or bismuth. Among alternative materials, barium sulfate appears to be the most cost-effective and easiest to process. In the present study, before constructing shielding barriers, a barrier thickness program for lead-free barrier materials based on National Council on Radiation Protection and Measurements (NCRP) Report No. 147 was used to determine the appropriate barrier thickness. The required thickness for lead-free boards for each type of diagnostic radiography room was calculated based on a tertiary general hospital in the Republic of Korea.

First impressions on sharing accommodation market platforms: The association between cover image type and property listing price

Shared accommodation platforms, including Airbnb, encourage hosts to post images of rentals. In this study, a hedonic pricing model was developed to test the effects of different cover image scenes (indoor or outdoor) on Airbnb listing prices and to test how strongly the effects were moderated by images’ visual aesthetics or room type. The model was estimated using a dataset of 24,162 Airbnb listings in Beijing, China, from October 2020. Empirical results revealed that 1) compared with Airbnb properties whose cover images showed indoor scenes, properties whose cover images showed outdoor scenes tended to have higher prices; and 2) cover images’ visual aesthetics and room type each significantly moderated the association between cover images and property listing prices. This study is one of the earliest to assess the roles of properties’ cover images in the shared accommodation market. The interaction effects of image scenes and other factors related to cover images were also explored for the first time.

Risk of nosocomial coronavirus disease 2019: comparison between single- and multiple-occupancy rooms

BackgroundThere is an ongoing controversy regarding whether single-occupancy rooms are superior to multiple-occupancy rooms in terms of infection prevention. We investigated whether treatment in a multiple-occupancy room is associated with an increased incidence of nosocomial coronavirus disease 2019 (COVID-19) compared with treatment in a single-occupancy room.MethodsIn this retrospective cohort study, every hospitalization period of adult patients aged ≥ 18 years at a tertiary hospital in Korea from January 1, 2022, to December 31, 2022, was analyzed. If COVID-19 was diagnosed more than 5 days after hospitalization, the case was classified as nosocomial. We estimated the association between the number of patients per room and the risk of nosocomial COVID-19 using a Cox proportional hazards regression model.ResultsIn total, 25,143 hospitalizations per room type were analyzed. The incidence rate of nosocomial COVID-19 increased according to the number of patients per room; it ranged from 3.05 to 38.64 cases per 10,000 patient-days between single- and 6-bed rooms, respectively. Additionally, the hazard ratios of nosocomial COVID-19 showed an increasing trend according to the number of patients per room, ranging from 0.14 (95% confidence interval 0.001–1.03) to 2.66 (95% confidence interval 1.60–4.85) between single- and 6-bed rooms, respectively.ConclusionsWe demonstrated that the incidence of nosocomial COVID-19 increased according to the number of patients per room. To reduce nosocomial infections by respiratory viruses, the use of multiple-occupancy rooms should be minimized.

Simulated fire video collection for advancing understanding of human behavior in building fires.

The goal of the present research was to develop a video collection of simulated fires to investigate how people perceive growing building fires. In fire safety science, a critical factor to occupant responses to building fires is the pre-movement period, determined by how long it takes an individual to initiate taking protective action with an incipient fire. Key to studying the psychological processes that contribute to the duration of the pre-movement period is presenting human subjects with building fires. One approach used in previous research is to present videos of building fires to individuals via scenarios. The numerical simulations used to model fire dynamics can be used to render videos for these scenarios. However, such simulations have predominantly been used in fire protection engineering to design buildings and are relatively inaccessible to social scientists. The present study documents a collection of videos, based on numerical simulations, which can be used by researchers to study human behavior in fire. These videos display developing fires in different types of rooms, growing at different rates, different smoke thickness, among other characteristics. As part of a validation study, participants were presented with subsets of the video clips and were asked to rate the perceived risk posed by the simulated fire. We observed that ratings varied by the intensity and growth rate of the fires, smoke opacity, type of room, and where the viewpoint was located from the fire. These effects aligned with those observed in previous fire science research, providing evidence that the videos could elicit perceived risk using fire simulations. The present research indicates that future studies can utilize the video library of fire simulations to study human perceptions of developing building fires as situational factors are systematically manipulated.

Computational design of residential units’ floor layout: A heuristic algorithm

Computer-aided intelligent design can improve the quality and efficiency of residential building design. However, the design conditions are diverse, and numerous combinations of spatial elements exist. We propose a heuristic algorithm—the combined Monte Carlo tree search (MCTS) and particle swarm optimization (PSO) algorithm (PSO-MCTS)—for the automated design of residential floor layouts. The MCTS algorithm deals with discrete variables (room locations). It considers architectural design experience and design standards during node pruning to compress the search space and simplify the computation. The PSO algorithm deals with continuous variables (room sizes) and accelerates the computing speed due to parallel processing. The PSO-MCTS algorithm achieves a good balance between computational efficiency and accuracy. It is suitable for various design conditions and requirements. The input parameters include the daylight façade, boundary scope, entrance location, room type and size, and relationships with adjacent rooms. The PSO-MCTS provides 100 %, 80 %, and 75 % better results than heuristic algorithms, designs by architects, and a state-of-the-art deep learning model, respectively.

The Impact of Design Factors on User Behavior in a Virtual Hospital Room to Explore Fall Prevention Strategies.

Falls in hospitals pose a significant safety risk, leading to injuries, prolonged hospitalization, and lasting complications. This study explores the potential of augmented reality (AR) technology in healthcare facility design to mitigate fall risk. Few studies have investigated the impact of hospital room layouts on falls due to the high cost of building physical prototypes. This study introduces an innovative approach using AR technology to advance methods for healthcare facility design efficiently. Ten healthy participants enrolled in this study to examine different hospital room designs in AR. Factors of interest included room configuration, door type, exit side of the bed, toilet placement, and the presence of IV equipment. AR trackers captured trajectories of the body as participants navigated through these AR hospital layouts, providing insights into user behavior and preferences. Door type influenced the degree of backward and sideways movement, with the presence of an IV pole intensifying the interaction between door and room type, leading to increased sideways and backward motion. Participants displayed varying patterns of backward and sideways travel depending on the specific room configurations they encountered. AR can be an efficient and cost-effective method to modify room configurations to identify important design factors before conducting physical testing. The results of this study provide valuable insights into the effect of environmental factors on movement patterns in simulated hospital rooms. These results highlight the importance of considering environmental factors, such as the type of door and bathroom location, when designing healthcare facilities.

Hybrid operating rooms and the risk of postoperative hypothermia in pregnant women with placenta previa: A retrospective cohort study.

Births at advanced maternal ages (≥ 35 years) are increasing. This has been associated with a higher incidence of placenta previa, which increases bleeding risk. Hybrid operating rooms, designed to accommodate interventions and cesarean sections, are becoming more prominent because of their dual capabilities and benefits. However, they have been associated with increased postoperative hypothermia in pediatric settings; moreover, this has not been studied in pregnant women with placenta previa. This retrospective cohort study included pregnant women diagnosed with placenta previa who underwent elective cesarean section under general anesthesia between May 2019 and 2023. The patients were categorized according to the operating room type. The primary outcome was to determine whether the hybrid operating room is a risk factor for immediate postoperative hypothermia, defined as a tympanic membrane temperature below 36.0°C. The secondary outcomes were the effects of immediate postoperative hypothermia on the durations of postanesthetic care unit and postoperative hospital stays and incidence of complications. Immediate postoperative hypothermia (tympanic membrane temperature < 36.0°C) was more prevalent in the hybrid than in the standard operating room group (20% vs. 36.6%, p = 0.033), with a relative risk of 2.86 (95% confidence interval 1.24-6.64, p < 0.001). Patients undergoing surgery in the hybrid operating room who experienced immediate postoperative hypothermia stayed longer in the postanesthetic care unit (26 min vs. 40 min, p < 0.001) and in the hospital after surgery (4 days; range 3-5 vs. 4 days; range 4-11, p = 0.021). However, the complication rates of both groups were not significantly different (11.3% vs 7.3%, p = 0.743). Hybrid operating rooms may increase the risk of postoperative hypothermia. Postoperative hypothermia is associated with prolonged postanesthetic care unit and hospital stays. Preventing hypothermia in patients in hybrid operating rooms is of utmost importance.

Comparative performance of contact plate metod and swab method for surface microbial contamination on medical fabrics

BackgroundThe contact plate method is widely accepted and used in various fields where hygiene and contamination levels are crucial. Evidence regarding the applicability of the contact plate method for sampling fabric microbial contamination levels in real medical environments was limited. This study aimed to assess the applicability of the contact plate method for detecting microbial contamination on medical fabrics in a real healthcare environment, thereby providing a benchmark for fabric microbial sampling methods.MethodsIn a level three obstetrics ward of a hospital, twenty-four privacy curtains adjacent to patient beds were selected for this study. The contact plate and swab method were used to collect microbial samples from the privacy curtains on the 1st, 7th, 14th, and 28th days after they were hung. The total colony count on each privacy curtain surface was calculated, and microbial identification was performed.ResultsAfter excluding the effects of time, room type, and curtain location on the detected microbial load, the linear mixed-effects model analysis showed that contact plate method yielded lower colony counts compared to swab method (P < 0.001). However, the contact plate method isolated more microbial species than swab method (P < 0.001). 291 pathogenic strains were isolated using the contact plate method and 133 pathogenic strains were isolated via the swab method. There was no difference between the two sampling methods in the detection of gram-negative bacteria (P = 0.089). Furthermore, the microbial load on curtains in double-occupancy rooms was lower than those in triple-occupancy rooms (P = 0.021), and the microbial load on curtains near windows was lower than that near doors (P = 0.004).ConclusionContact plate method is superior to swab method in strain isolation. Swab method is more suitable for evaluating the bacterial contamination of fabrics.

Image sequence sorting algorithm for commercial tasks.

The sorting of sequences of images is crucial for augmenting user engagement in various virtual commercial platforms, particularly within the real estate sector. A coherent sequence of images respecting room type categorization significantly enhances the intuitiveness and seamless navigation of potential customers through listings. This study methodically formalizes the challenge of image sequence sorting and expands its applicability by framing it as an ordering problem. The complexity lies in devising a universally applicable solution due to computational demands and impracticality of exhaustive searches for optimal sequencing. To tackle this, our proposed algorithm employs a shortest path methodology grounded in semantic similarity between images. Tailored specifically for the real estate sector, it evaluates diverse similarity metrics to efficiently arrange images. Additionally, we introduce a genetic algorithm to optimize the selection of semantic features considered by the algorithm, further enhancing its effectiveness. Empirical evidence from our dataset demonstrates the efficacy of the proposed methodology. It successfully organizes images in an optimal sequence across 85% of the listings, showcasing its effectiveness in enhancing user experience in virtual commercial platforms, particularly in real estate. This study presents a novel approach to sorting sequences of images in virtual commercial platforms, particularly beneficial for the real estate sector. The proposed algorithm effectively enhances user engagement by providing more intuitive and visually coherent image arrangements.

Perancangan Homestay Moni Kecamatan Kelimutu Kabupaten Ende (Tema Arsitektur Neo Vernakuler)

ABSTRACT DOMINGGUS PITERSON BABO 2018320320. Moni Homestay Design, Kelimutu District, Ende Regency (Neo Vernacular Architecture Theme). Faculty of Engineering, University of Flores, Ende, 2023.. Mobile Number : 081339344579, E-mail : babosoni@gmail.com supervisor I : Ir. Dian Fitriawati Mochdar, ST., MT. supervisor II : Fabiola T.A, Kerong. ST., MT. Moni Kelimutu tourist destinations include culinary tourism, shopping tourism, and recreational tourism. This has a positive impact because the number of tourists coming is increasing. Therefore Homestay lodging is a very important element to support the existing potential. Homestay has an important role to introduce the character of each region. Ende Regency is one of the districts with many tribes and precisely in the Kelimutu sub-district, the local community highly respects customs and habits, so Moni's homestay is designed with the Neo Vernacular theme which aims to strengthen the identity and character of the local indigenous tribes. The application of this theme is dominated by wood elements as an aesthetic element of the building both in the facade of the building and in the atmosphere of the building space. Wood is the main material for building traditional Lio houses. So that the Homestay is designed to have the feel of the local environment so that people who stay at this Homestay feel the character of the local area. The methods used in this planning and design are 1). data collection methods include primary data (observation, documentation and interviews) and secondary data (literature studies and comparative studies); 2). The analysis method explains each analysis which contains field data, design criteria (theory), alternative analysis (alternative 1 and alternative 2), and responses (alternative selection). Analysis methods include analysis of design objects; site analysis; functional analysis (space organization, namely the organizational structure of actors, analysis of activities and space requirements (analysis of actors and actors' activities), room analysis (conditions, circulation, organization, relationships, size and zoning of space), shape analysis and analysis of building mass placement patterns; analysis building systems (structure and utilities); as well as analysis of regional regulations. 3). The design method includes design ideas and design concepts, namely the concept of neo vernacular architecture. The results obtained from designing Moni's homestay are based on a neo vernacular architectural approach which emphasizes more on building materials and site processing. The facilities built include the main facilities in the form of accommodation (suite room and standard type homestay), management building, as well as supporting facilities in the form of a cafeteria, photo spot, outdoor room and service area, parking. Keywords: Tourism, Homestay, Neo Vernacular Architecture

Impact of Multidrug-Resistant Organisms on Severe Acquired Brain Injury Rehabilitation: An Observational Study.

Healthcare-associated infections (HAIa) and antimicrobial resistance are expected to be the next threat to human health and are most frequent in people with severe acquired brain injury (SABI), who can be more easily colonized by multidrug-resistant organisms (MDROs). The study's aim is to investigate the impact of MDRO colonizations and infections on SABI rehabilitation outcomes. This retrospective observational study was performed in a tertiary referral specialized rehabilitation hospital. The main outcomes were the presence of carbapenemase-producing Enterobacteriaceae (CPE) colonization, type and timing of HAI and MDRO HAI, and the number of CPE transmissions. We included 48 patients, 31% carrying CPE on admission and 33% colonized during the hospitalization. A total of 101 HAI were identified in 40 patients, with an overall incidence of 10.5/1000 patient days. Some 37% of patients had at least one MDRO infection, with a MDRO infection incidence of 2.8/1000 patient days. The number of HAIs was significantly correlated with the length of stay (LOS) (r = 0.453, p = 0.001). A significant correlation was found between colonization and type of hospital room (p = 0.013). Complications and HAI significantly affected LOS. We suggest that CPE carriers might be at risk of HAI and worse outcomes compared with non-CPE carriers.

An Exploration of Demographic Characteristics Concerning Accommodation Choice Behavior of Tourists in Luong Prabang, Lao PDR

Introduction: The lodging industry plays a crucial role in the tourism sector, with tourists' choices influenced by various factors, including demographic characteristics. Understanding how demographic factors impact tourists' lodging preferences is essential for effective marketing strategies. This study investigates the relationship between tourists' demographic characteristics and their lodging choice behaviors in Luang Prabang, Lao PDR. Methodology: Data were collected from 390 tourists using surveys conducted in Luang Prabang. Demographic characteristics examined include gender, age, education, occupation, country of origin, and income. Lodging choice behaviors analyzed encompass lodging, staying duration, room type, transportation, room cost, and spending cost. The Chi-square statistical method was employed to analyze the data. Results: The analysis revealed significant associations between tourists' demographic characteristics and their lodging choice behaviors. Gender was found to influence lodging preferences, with differences observed in the choice of hotel size, staying duration, and booking methods among different age groups. These findings underscore the importance of considering demographic factors in marketing strategies within the hotel industry. Discussion: The study highlights the relevance of demographic segmentation in understanding and catering to tourists' diverse lodging preferences. By tailoring marketing strategies to specific demographic profiles, businesses can better meet the needs and preferences of different tourist segments. Additionally, the findings contribute to existing literature on the role of demographic factors in shaping tourists' lodging choices.

Handbook, Standard, Room: The Prescription of Residential Room Types in Sweden Between 1942 and 2023

Norms and handbooks have played a key role in the design of residential rooms in Sweden since the 1940s. Ever since, changes in housing policies have led to varying definitions and regulations of residential rooms, allowing their existence, defining their configuration, and framing their performance. And yet, none of these rooms has been built; they are prescribed room types that belong in the pages of handbooks that validate the framework in which housing design can operate. What are these prescribed room types? What do they look like? Who and what do they include? Have they changed over time? In response to these questions, this article follows the evolution of a set of residential room types in the design handbooks that have accompanied housing policy bills in Sweden from 1942 to 2023. These manuals are not the law itself but operate as an interface for professionals and designers by reflecting the practical consequences of the norm. Diagrams, dimensions, texts, and references to housing literature vary from handbook to handbook to define the specific traits of each type of room. By studying these traits in relation to key moments of Swedish housing politics, the article reveals the role that norms and standards have played in the establishment of the regulatory regime in which housing design in Sweden operates today.

Identifying children’s perception of interior space to the earthquake disaster: A case study of elementary school students in Jakarta

Earthquake disasters affected several physical damages and left traumatic experiences to sensitive groups, especially children. This kind of damage results in after-effect risks from the earthquake. Associated with this condition, the United Nation has published that the number of countries with disaster risk reduction strategies starting in 2015 should be increased. This research is aimed to identify children’s perceptions after the earthquake disaster through virtual settings. The framework used a literature review and a simulation of 3D virtual model testing on a group of elementary school students in Jakarta using a certain model type of room and aperture (window). Colour and window size are the main parameters for data showing the children’s preferences. Potential parameters are expected to be produced as guidance and recommendations on the post-disaster (earthquake-specific) in the future design decision. The parameters are aimed to help decision makers and designers to reach disaster risk reduction, in relation with SDGs on social aspect for the future sustainable development of resilient infrastructure, communities, and cities.

The characteristic design of ceiling

The ceiling as part of the building functions to protect the utility and structure of the room from user visual. Moreover, it protects the user from getting affected by the problems of utility that may occur during the use of the building. The ceiling creates a complete room interior design. In considering those aspects, the ceiling needs to be designed and constructed properly according to the need and type of room. This research aims to identify the characteristics of the design and construction of ceilings. The method is a literature review and study field on various buildings. Data of design is drawn with the computer design program AutoCAD for the main concept. The result shows that the characteristics of the ceiling can be classified based on Support utility such as sprinkler, Cooling system, the material used, Type of ceiling, and ceiling height. Further research needs to consider the local influence on the design and construction system of ceilings.

Workflows and locations matter – insights from electronic hand hygiene monitoring into the use of hand rub dispensers across diverse hospital wards

While healthcare-associated infections (HAIs) affect approximately 3.2-6.5% of hospitalised patients in the US and Europe, improving hand hygiene (HH) could reduce HAI rates. Investigating HH is time-consuming and not always objective, and comprehensive, unbiased data is needed to develop effective strategies. Using electronic tools can provide new and detailed insights on the determinants of HH. To evaluate location-dependent usage of wall-mounted dispensers (WMDs) and point-of-care dispensers (POCs) using an electronic HH recording system. In this retrospective study, hand rub volumes were anonymously recorded for 931,446 disinfections from 17 wards in nine German hospitals using the electronic monitoring system NosoEx®. Number of disinfections and rub volumes of WMDs/POCs by ward and room type were analysed. Generally, WMDs were most prevalent. With >3 dispensers per bed and >20 disinfections per patient day, availability and use were highest in intensive care (ICU) and intermediate care (IMC), but here rub volumes from WMDs were lowest (∼2.0 mL). Although most dispensers are located in patient rooms (∼42%), they are more frequently used in hallways. In surgical ICUs, dispensers are often used in patient rooms, where contact with open wounds is common. About 3.6 mL of hand rub is used per disinfection in treatment rooms, the highest volume of all room types. Dispenser use was dependent on location, room type, ward specialisation and workflow. Optimising the location of hand rub dispensers (HRDs)s is not the only solution to improve HH, but can help reduce inconvenience, achieve more ergonomic workflows and better meet user needs.

Foundations of spatial perception for robotics: Hierarchical representations and real-time systems

3D spatial perception is the problem of building and maintaining an actionable and persistent representation of the environment in real-time using sensor data and prior knowledge. Despite the fast-paced progress in robot perception, most existing methods either build purely geometric maps (as in traditional SLAM) or “flat” metric-semantic maps that do not scale to large environments or large dictionaries of semantic labels. The first part of this paper is concerned with representations: we show that scalable representations for spatial perception need to be hierarchical in nature. Hierarchical representations are efficient to store, and lead to layered graphs with small treewidth, which enable provably efficient inference. We then introduce an example of hierarchical representation for indoor environments, namely a 3D scene graph, and discuss its structure and properties. The second part of the paper focuses on algorithms to incrementally construct a 3D scene graph as the robot explores the environment. Our algorithms combine 3D geometry (e.g., to cluster the free space into a graph of places), topology (to cluster the places into rooms), and geometric deep learning (e.g., to classify the type of rooms the robot is moving across). The third part of the paper focuses on algorithms to maintain and correct 3D scene graphs during long-term operation. We propose hierarchical descriptors for loop closure detection and describe how to correct a scene graph in response to loop closures, by solving a 3D scene graph optimization problem. We conclude the paper by combining the proposed perception algorithms into Hydra, a real-time spatial perception system that builds a 3D scene graph from visual-inertial data in real-time. We showcase Hydra’s performance in photo-realistic simulations and real data collected by a Clearpath Jackal robots and a Unitree A1 robot. We release an open-source implementation of Hydra at https://github.com/MIT-SPARK/Hydra.