Learning View Graphs for Robot Navigation

Franz, Matthias; Schölkopf, Bernhard; Mallot, Hanspeter A.; Bülthoff, HH

doi:10.1007/978-1-4615-5735-7_9

Cited by 72 publications

(111 citation statements)

References 16 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…laser light or radio waves) and measuring the return. There is a significant literature on vision-based navigation [14,84,58,60,73,66,28,25,64,43], and our experimental section could be characterized simply as occlusion-driven navigation [47,48,9]. In most of the literature, stereo or motion are exploited to provide a three-dimensional map of the environment, which is then handed off to a path planner, separating the photometric from the geometric and topological aspect of the problem.…”

Section: Summary and Discussionsupporting

confidence: 40%

Actionable Information in Vision

Soatto

2013

Machine Learning for Computer Vision

View full text Add to dashboard Cite

Summary. A notion of visual information is introduced as the complexity not of the raw images, but of the images after the effects of nuisance factors such as viewpoint and illumination are discounted. It is rooted in ideas of J. J. Gibson, and stands in contrast to traditional information as entropy or coding length of the data regardless of its use, and regardless of the nuisance factors affecting it. The non-invertibility of nuisances such as occlusion and quantization induces an "information gap" that can only be bridged by controlling the data acquisition process. Measuring visual information entails early vision operations, tailored to the structure of the nuisances so as to be "lossless" with respect to visual decision and control tasks (as opposed to data transmission and storage tasks implicit in communications theory). The definition of visual information suggests desirable properties that a visual representation should possess to best accomplish vision-based decision and control tasks.

show abstract

Section: Summary and Discussionsupporting

confidence: 40%

Actionable Information in Vision

Soatto

2013

Machine Learning for Computer Vision

View full text Add to dashboard Cite

show abstract

“…Templates are created by selecting a number of high-contrast features in the image and storing them together with their relative spatial locations in the image. Franz et al 11 have developed a vision-based system for topological navigation in open environments. This system represents selected places by local 360 • views of the surrounding scenes.…”

Section: Introductionmentioning

confidence: 44%

Object learning and detection using evolutionary deformable models for mobile robot navigation

Mata

Armingol²,

Andrés

et al. 2008

Robotica

View full text Add to dashboard Cite

SUMMARYDeformable models have been studied in image analysis over the last decade and used for recognition of flexible or rigid templates under diverse viewing conditions. This article addresses the question of how to define a deformable model for a real-time color vision system for mobile robot navigation. Instead of receiving the detailed model definition from the user, the algorithm extracts and learns the information from each object automatically. How well a model represents the template that exists in the image is measured by an energy function. Its minimum corresponds to the model that best fits with the image and it is found by a genetic algorithm that handles the model deformation. At a later stage, if there is symbolic information inside the object, it is extracted and interpreted using a neural network. The resulting perception module has been integrated successfully in a complex navigation system. Various experimental results in real environments are presented in this article, showing the effectiveness and capacity of the system.

show abstract

“…Here, we focus on local visual homing methods which are typically used within graph-like topological maps [7,8,9] where connected nodes represent nearby locations in the environment. A local homing algorithm is then used to drive the agent from one node to the next.…”

Section: Introductionmentioning

confidence: 49%

Robust visual homing with landmark angles

Lim¹,

Barnes²

2009

Robotics: Science and Systems V

View full text Add to dashboard Cite

Abstract-This paper presents a novel approach to visual homing for robot navigation on the ground plane, using only the angles of landmark points. We focus on a robust approach, leading to successful homing even in real, dynamic environments where significant numbers of landmark points are wrong or missing. Three homing algorithms are presented, two are shown to be provably convergent, and the other shown to converge empirically. Results from simulations under noise and robot homing in real environments are provided.

show abstract

Learning View Graphs for Robot Navigation

Cited by 72 publications

References 16 publications

Actionable Information in Vision

Actionable Information in Vision

Object learning and detection using evolutionary deformable models for mobile robot navigation

Robust visual homing with landmark angles

Contact Info

Product

Resources

About