Deep learning of structured environments for robot search

Caley, Jeffrey A.; Lawrance, Nicholas; Hollinger, Geoffrey A.

doi:10.1007/s10514-018-09821-4

Cited by 25 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, we will further investigate the ways of discovering spatial knowledge based on the correlation among geometry, topology, semantics, and spatial distribution of spaces. For instance, to infer the complete geometry and topology of spaces given the semantics and coarse location of points of interest in shopping malls (Caley, Lawrance, & Hollinger, 2019). This will be especially useful in improving indoor volunteered geographic information, whose quality (e.g., accuracy and completeness) cannot be guaranteed.…”

Section: Discussionmentioning

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

Section: Discussionmentioning

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

show abstract

“…In [219], an approach is used based on Petri Net [220] for area exploration, [221] uses partitioning of topological weighted connected graph for terrain coverage such as floor cleaning, [216] based on honey bee swarm-inspired for forging task, [222] based on finite state automata for two heterogeneous robots looking for an object in a possibly cluttered area. Recently some [223][224][225] Machine Learning (ML) based exploration techniques have also been proposed. These approaches are fundamentally different from other disused approaches in terms of control, perception, and theory.…”

Section: Exploration and Mappingmentioning

confidence: 99%

Multi-Robot Coordination Analysis, Taxonomy, Challenges and Future Scope

Verma

Ranga

2021

J Intell Robot Syst

View full text Add to dashboard Cite

Recently, Multi-Robot Systems (MRS) have attained considerable recognition because of their efficiency and applicability in different types of real-life applications. This paper provides a comprehensive research study on MRS coordination, starting with the basic terminology, categorization, application domains, and finally, give a summary and insights on the proposed coordination approaches for each application domain. We have done an extensive study on recent contributions in this research area in order to identify the strengths, limitations, and open research issues, and also highlighted the scope for future research. Further, we have examined a series of MRS state-of-the-art parameters that affect MRS coordination and, thus, the efficiency of MRS, like communication mechanism, planning strategy, control architecture, scalability, and decision-making. We have proposed a new taxonomy to classify various coordination approaches of MRS based on the six broad dimensions. We have also analyzed that how coordination can be achieved and improved in two fundamental problems, i.e., multi-robot motion planning, and task planning, and in various application domains of MRS such as exploration, object transport, target tracking, etc.

show abstract

“…[6] proposes a method of navigating partially-revealed environments in arXiv:1910.08184v1 [cs.RO] 17 Oct 2019 minimum distance by modeling the problem as a Partially Observable Markov Decision Process (POMDP), where optimal actions correspond to frontiers that lead directly to the goal rather than lengthy detours or dead ends. Towards a similar objective, [7] passes an occupancy grid encoding a robot's current knowledge of the environment through a Convolutional Neural Network (CNN) and uses the output to weigh frontiers based on their likelihood of leading to a point of interest. While these works enable shorter-distance navigation through unknown environments to a desired goal, they crucially do not consider robot dynamics.…”

Section: Related Workmentioning

confidence: 99%

Map-Predictive Motion Planning in Unknown Environments

Elhafsi

Ivanovic

Janson

et al. 2020

2020 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Algorithms for motion planning in unknown environments are generally limited in their ability to reason about the structure of the unobserved environment. As such, current methods generally navigate unknown environments by relying on heuristic methods to choose intermediate objectives along frontiers. We present a unified method that combines map prediction and motion planning for safe, time-efficient autonomous navigation of unknown environments by dynamicallyconstrained robots. We propose a data-driven method for predicting the map of the unobserved environment, using the robot's observations of its surroundings as context. These map predictions are then used to plan trajectories from the robot's position to the goal without requiring frontier selection. We demonstrate that our map-predictive motion planning strategy yields a substantial improvement in trajectory time over a naïve frontier pursuit method and demonstrates similar performance to methods using more sophisticated frontier selection heuristics with significantly shorter computation time.

show abstract

Deep learning of structured environments for robot search

Cited by 25 publications

References 21 publications

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

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

Multi-Robot Coordination Analysis, Taxonomy, Challenges and Future Scope

Map-Predictive Motion Planning in Unknown Environments

Contact Info

Product

Resources

About