What can we learn from 38,000 rooms? Reasoning about unexplored space in indoor environments

Aydemir, Alper; Jensfelt, Patric; Folkesson, John

doi:10.1109/iros.2012.6386110

Cited by 37 publications

(34 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We think that this has the potential to further increase search efficiency at the viewpoint level. Another interesting future research direction is more sophisticated reasoning about the unexplored part of indoor environment, as in our previous work [57]. For this, we plan to use the learned indoor models from a large annotated floor plan database to help guide the robot in goal-directed exploration.…”

Section: Discussionmentioning

confidence: 99%

Active Visual Object Search in Unknown Environments Using Uncertain Semantics

et al. 2013

Self Cite

View full text Add to dashboard Cite

In this paper, we study the problem of active visual search (AVS) in large, unknown, or partially known environments. We argue that by making use of uncertain semantics of the environment, a robot tasked with finding an object can devise efficient search strategies that can locate everyday objects at the scale of an entire building floor, which is previously unknown to the robot. To realize this, we present a probabilistic model of the search environment, which allows for prioritizing the search effort to those parts of the environment that are most promising for a specific object type. Further, we describe a method for reasoning about the unexplored part of the environment for goal-directed exploration with the purpose of object search. We demonstrate the validity of our approach by comparing it with two other search systems in terms of search trajectory length and time. First, we implement a greedy coverage-based search strategy that is found in previous work. Second, we let human participants search for objects as an alternative comparison for our method. Our results show that AVS strategies that exploit uncertain semantics of the environment are a very promising idea, and our method pushes the state-of-the-art forward in AVS.Index Terms-Active vision, semantic mapping, visual object search.

show abstract

Section: Discussionmentioning

confidence: 99%

Active Visual Object Search in Unknown Environments Using Uncertain Semantics

et al. 2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…The evaluation of their approach was performed considering a large RGB-D dataset, showing the effect of using 3D context in an object detection task. Besides making an RGB-D dataset publicly available in [3], in [4] Aydemir et al also published a dataset called KTH. In this case, the dataset is composed of a set of floor plans that encompasses, in total, 37 buildings, 165 floors and 6248 rooms.…”

Section: Related Workmentioning

confidence: 99%

“…Second, our semantic AVS system relies on textual information as a visual cue, and more specific numbers, extracted from the door signs. Large buildings, for instance, are divided into many small rooms, and usually comply with a pattern of signing each room [1,4,18,34]. Using numbers is different from considering the size of an ROI, or the features and colours of an object, for instance.…”

mentioning

confidence: 99%

Semantic Active Visual Search System Based on Text Information for Large and Unknown Environments

Mantelli

Pittol

Maffei

et al. 2021

J Intell Robot Syst

View full text Add to dashboard Cite

Different high-level robotics tasks require the robot to manipulate or interact with objects that are in an unexplored part of the environment or not already in its field of view. Although much works rely on searching for objects based on their colour or 3D context, we argue that text information is a useful and functional visual cue to guide the search. In this paper, we study the problem of active visual search (AVS) in large unknown environments. In this paper, we present an AVS system that relies on semantic information inferred from texts found in the environment, which allows the robot to reduce the search costs by avoiding not promising regions for the target object. Our semantic planner reasons over the numbers detected from door signs to decide either perform a goal-directed exploration towards unknown parts of the environment or carefully search in the already known parts. We compared the performance of our semantic AVS system with two other search systems in four simulated environments. First, we developed a greedy search system that does not consider any semantic information, and second, we invited human participants to teleoperate the robot while performing the search. Our results from simulation and real-world experiments show that text is a promising source of information that provides different semantic cues for AVS systems.

show abstract

“…The above mentioned approaches normally ignore the reconstruction of room usage. To mitigate this, Aydemir, Jensfelt, and Folkesson (2012) fused heterogeneous and uncertain information such as object observations, shape, size, appearance of rooms, and human input for semantic mapping. Specifically, a probabilistic graphical model was used to represent the conceptual information and perform spatial reasoning, such as room categories and the structure of unexplored space.…”

Section: Related Workmentioning

confidence: 99%

Room semantics inference using random forest and relational graph convolutional networks: A case study of research building

Fan²,

Noskov

et al. 2020

Transactions in GIS

View full text Add to dashboard Cite

Semantically rich maps are the foundation of indoor location‐based services. Many map providers such as OpenStreetMap and automatic mapping solutions focus on the representation and detection of geometric information (e.g., shape of room) and a few semantics (e.g., stairs and furniture) but neglect room usage. To mitigate the issue, this work proposes a general room tagging method for public buildings, which can benefit both existing map providers and automatic mapping solutions by inferring the missing room usage based on indoor geometric maps. Two kinds of statistical learning‐based room tagging methods are adopted: traditional machine learning (e.g., random forests) and deep learning, specifically relational graph convolutional networks (R‐GCNs), based on the geometric properties (e.g., area), topological relationships (e.g., adjacency and inclusion), and spatial distribution characteristics of rooms. In the machine learning‐based approach, a bidirectional beam search strategy is proposed to deal with the issue that the tag of a room depends on the tag of its neighbors in an undirected room sequence. In the R‐GCN‐based approach, useful properties of neighboring nodes (rooms) in the graph are automatically gathered to classify the nodes. Research buildings are taken as examples to evaluate the proposed approaches based on 130 floor plans with 3,330 rooms by using fivefold cross‐validation. The experiments conducted show that the random forest‐based approach achieves a higher tagging accuracy (0.85) than R‐GCN (0.79).

show abstract

What can we learn from 38,000 rooms? Reasoning about unexplored space in indoor environments

Cited by 37 publications

References 10 publications

Active Visual Object Search in Unknown Environments Using Uncertain Semantics

Active Visual Object Search in Unknown Environments Using Uncertain Semantics

Semantic Active Visual Search System Based on Text Information for Large and Unknown Environments

Room semantics inference using random forest and relational graph convolutional networks: A case study of research building

Contact Info

Product

Resources

About