Dataset Information

High-Level Teleoperation System for Aerial Exploration of Indoor Environments.

ABSTRACT: Exploration of challenging indoor environments is a demanding task. While automation with aerial robots seems a promising solution, fully autonomous systems still struggle with high-level cognitive tasks and intuitive decision making. To facilitate automation, we introduce a novel teleoperation system with an aerial telerobot that is capable of handling all demanding low-level tasks. Motivated by the typical structure of indoor environments, the system creates an interactive scene topology in real-time that reduces scene details and supports affordances. Thus, difficult high-level tasks can be effectively supervised by a human operator. To elaborate on the effectiveness of our system during a real-world exploration mission, we conducted a user study. Despite being limited by real-world constraints, results indicate that our system better supports operators with indoor exploration, compared to a baseline system with traditional joystick control.

SUBMITTER: Isop WA

PROVIDER: S-EPMC7805862 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

High-Level Teleoperation System for Aerial Exploration of Indoor Environments.

Isop Werner Alexander WA Gebhardt Christoph C Nägeli Tobias T Fraundorfer Friedrich F Hilliges Otmar O Schmalstieg Dieter D

Frontiers in robotics and AI 20191023

Exploration of challenging indoor environments is a demanding task. While automation with aerial robots seems a promising solution, fully autonomous systems still struggle with high-level cognitive tasks and intuitive decision making. To facilitate automation, we introduce a novel teleoperation system with an aerial telerobot that is capable of handling all demanding low-level tasks. Motivated by the typical structure of indoor environments, the system creates an interactive scene topology in re ...[more]

PMID: 33501110

Similar Datasets

Project description:Scopulariopsis-like species are often reported from the indoor environment, as well as from clinical samples. The lack of type isolates and thorough phylogenetic studies in the Microascaceae hampered the correct identification of these isolates. Based on recent phylogenetic studies, which resulted in multiple name changes, the aim is to molecularly identify the Scopulariopsis and scopulariopsis-like species which occur in the indoor environment and give an overview of the current species in these genera and their habitats. Strains from the CBS culture collection were supplemented with almost 80 indoor strains of which the internal transcribed spacer 1 and 2 and intervening 5.8S nrDNA (ITS), beta-tubulin (tub2) and translation elongation factor 1-alpha (tef1) gene regions were sequenced for phylogenetic inference. The multi-gene phylogenies recognise 33 Microascus species and 12 Scopulariopsis species and showed that the recently established genus Fuscoannellis, typified by Scopulariopsis carbonaria, should be synonymized with the genus Yunnania. Seven new Microascus species, four new Scopulariopsis species, and one new Yunnania species, are described, and a new name in Microascus and two new name combinations (one in Microascus, and one in Yunnania) are proposed. In the indoor environment 14 Microascus species and three Scopulariopsis species were found. Scopulariopsis brevicaulis (22 indoor isolates) and Microascus melanosporus (19 indoor isolates) are the most common indoor species, in number of isolates, followed by M. paisii (8 indoor isolates) and S. candida (7 indoor isolates). A genus phylogeny based on the ITS, tef1 and the large subunit 28S nrDNA (LSU) of the type or representative isolates of all here recognised species is provided depicting all species habitats. No correlation between phylogenetic relationship and habitat preference could be observed. Ten species which are found indoor are also found in relation with human-derived samples. A table showing recent name changes and a key to common species of Scopulariopsis and scopulariopsis-like genera found indoors is included.

Project description:Over the last 20 years, a significant part of the research in exploratory robotics partially switches from looking for the most efficient way of exploring an unknown environment to finding what could motivate a robot to autonomously explore it. Moreover, a growing literature focuses not only on the topological description of a space (dimensions, obstacles, usable paths, etc.) but rather on more semantic components, such as multimodal objects present in it. In the search of designing robots that behave autonomously by embedding life-long learning abilities, the inclusion of mechanisms of attention is of importance. Indeed, be it endogenous or exogenous, attention constitutes a form of intrinsic motivation for it can trigger motor command toward specific stimuli, thus leading to an exploration of the space. The Head Turning Modulation model presented in this paper is composed of two modules providing a robot with two different forms of intrinsic motivations leading to triggering head movements toward audiovisual sources appearing in unknown environments. First, the Dynamic Weighting module implements a motivation by the concept of Congruence, a concept defined as an adaptive form of semantic saliency specific for each explored environment. Then, the Multimodal Fusion and Inference module implements a motivation by the reduction of Uncertainty through a self-supervised online learning algorithm that can autonomously determine local consistencies. One of the novelty of the proposed model is to solely rely on semantic inputs (namely audio and visual labels the sources belong to), in opposition to the traditional analysis of the low-level characteristics of the perceived data. Another contribution is found in the way the exploration is exploited to actively learn the relationship between the visual and auditory modalities. Importantly, the robot-endowed with binocular vision, binaural audition and a rotating head-does not have access to prior information about the different environments it will explore. Consequently, it will have to learn in real-time what audiovisual objects are of "importance" in order to rotate its head toward them. Results presented in this paper have been obtained in simulated environments as well as with a real robot in realistic experimental conditions.

Project description:Black carbon (BC) is a descriptive term that refers to light-absorbing particulate matter (PM) produced by incomplete combustion and is often used as a surrogate for traffic-related air pollution. Exposure to BC has been linked to adverse health effects. Penetration of ambient BC is typically the primary source of indoor BC in the developed world. Other sources of indoor BC include biomass and kerosene stoves, lit candles, and charring food during cooking. Home characteristics can influence the levels of indoor BC. As people spend most of their time indoors, human exposure to BC can be associated to a large extent with indoor environments. At the same time, due to the cost of environmental monitoring, it is often not feasible to directly measure BC inside multiple individual homes in large-scale population-based studies. Thus, a predictive model for indoor BC is needed to support risk assessment in public health. In this study, home characteristics and occupant activities that potentially modify indoor levels of BC were documented in 23 homes, and indoor and outdoor BC concentrations were measured twice. The homes were located in the Cincinnati-Kentucky-Indiana tristate region and measurements occurred from September 2015 through August 2017. A linear mixed-effect model was developed to predict BC concentration in residential environments. The measured outdoor BC concentrations and the documented home characteristics were utilized as predictors of indoor BC concentrations. After the model was developed, a leave-one-out cross-validation algorithm was deployed to assess the predictive accuracy of the output. The following home characteristics and occupant activities significantly modified the concentration of indoor BC: outdoor BC, lit candles and electrostatic or high efficiency particulate air (HEPA) filters in heating, ventilation and air conditioning (HVAC) systems. Predicted indoor BC concentrations explained 78% of the variability in the measured indoor BC concentrations. The data show that outdoor BC combined with home characteristics can be used to predict indoor BC levels with reasonable accuracy.

Dataset Information

High-Level Teleoperation System for Aerial Exploration of Indoor Environments.

Publications

High-Level Teleoperation System for Aerial Exploration of Indoor Environments.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets