Heavy Changes in the Input Flow for Learning Geography of a Robot Environment

Khachaturov, Georgii; Figueroa-González, Josué; González-Brambila, Silvia B.; Martínez-Hernández, Juan Manuel

doi:10.1007/978-3-319-59063-9_46

Cited by 1 publication

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But for the lowest geographic level, each item should be represented by a data structure that does not have neither a distinctive shape, nor a name. In this respect, this work together with [14] represents a novel step to overcome obstacles for future practical implementation of the non-coordinate approach to navigation of [13].…”

Section: Non-coordinate Navigationmentioning

confidence: 99%

“…If, for example, EP is empty then the strings are equivalent and there is no HC between corresponding views; otherwise a decision on occurrence of HC is taken by a deeper analysis of EP. We refer the readers to [14] for further details.…”

Section: Detection Of Heavy Changesmentioning

confidence: 99%

“…A newer version of the pilot software described in [14] was used for the experiments. The functions implemented in the package include:…”

Section: Inner Model Of Environmentmentioning

confidence: 99%

“…A corresponding technique for the views like in Fig. 1c was presented in [14]. The relation of heavy change helps to associate the robot views with some neighborhoods of the atlas: two close views generated on a continuous robot trajectory belong to the same neighborhood if there is no heavy change between them, and vice versa.…”

Section: Introductionmentioning

confidence: 99%

“…This work focuses on the logic of creating the network of reference views, this approach was tested using a new version of the software presented in [14].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Generation of Non-Coordinate Navigation Knowledge from a Flow of Input Views

Figueroa-González¹,

Khachaturov²,

Martínez-Hernández³

2019

RCS

Self Cite

View full text Add to dashboard Cite

An approach to automatic generation of a network of reference 'views' specifically structured for non-coordinate robot navigation is presented. The reference views are selected from the input flow while the robot moves along a random continuous trajectory in its environment. The network is organized as an atlas that represents inner model of the robot environment. It accumulates a 'rich' navigation knowledge extracted from the flow of 'poor' views. No coordinate transformation is involved, but fundamental topological concepts: the continuity of a robot trajectory and discontinuities ('heavy changes') detected in the input flow. Avoiding any explicit coordinate transformation becomes possible using a local inversion of the knowledge hidden in the relation 'robot control -change of view'. Both techniques -the inversion and detection of heavy changes -are specific for a particular robot architecture. The approach was verified on a virtual static 2D-workspace.

show abstract

Section: Non-coordinate Navigationmentioning

confidence: 99%

Section: Detection Of Heavy Changesmentioning

confidence: 99%

“…A newer version of the pilot software described in [14] was used for the experiments. The functions implemented in the package include:…”

Section: Inner Model Of Environmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…This work focuses on the logic of creating the network of reference views, this approach was tested using a new version of the software presented in [14].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations