Information based adaptive robotic exploration

Bourgault, F.; Makarenko, Alexei; Williams, Stefan B.; Grocholsky, Ben; Durrant‐Whyte, Hugh

doi:10.1109/irds.2002.1041446

Cited by 342 publications

(283 citation statements)

References 4 publications

Supporting

Mentioning

281

Contrasting

Unclassified

Order By: Relevance

“…In particular, [81,13,71] propose "information-based" strategies, although by "information" they mean localization and mapping uncertainty based on range data. Range data are not subject to illumination and viewpoint nuisances, which are suppressed by the active sensing, i.e.…”

Section: Summary and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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 Discussionmentioning

confidence: 99%

“…Similarly to previously cited work [81,13], [26] propose using the decrease of uncertainty as a criterion to select camera parameters, and [3] uses information-theoretic notions to evaluate the "informative content" of laser range measurements depending on their viewpoint.…”

Section: Summary and Discussionmentioning

confidence: 99%

Actionable Information in Vision

Soatto

2013

Machine Learning for Computer Vision

View full text Add to dashboard Cite

show abstract

“…Feder et al [10] proposed the first work on active SLAM that seeks to minimizes both vehicle and landmark uncertainties. Bourgault et al [5] proposed to complement the sparse feature-based SLAM approach with an occupancy grid to provide means of integrating dense range measurements. The proposed exploration policy uses the entropy in the occupancy grid map to stimulate exploration while the uncertainty in the SLAM assures localization accuracy.…”

Section: A Related Workmentioning

confidence: 99%

“…State-of-the-art approaches to active mapping [15,5,8,25,27,22] retain only geometric information while discarding the scene appearance. As a result, a robot trying to perceive the depth of a white wall, would generate different camera trajectories in vain, eventually failing to reduce the uncertainty in the depth measurement [23].…”

Section: B Contributions and Outlinementioning

confidence: 99%

Appearance-based Active, Monocular, Dense Reconstruction for Micro Aerial Vehicles

Förster

Pizzoli

Scaramuzza

2014

Robotics: Science and Systems X

View full text Add to dashboard Cite

Abstract-In this paper, we investigate the following problem: given the image of a scene, what is the trajectory that a robotmounted camera should follow to allow optimal dense depth estimation? The solution we propose is based on maximizing the information gain over a set of candidate trajectories. In order to estimate the information that we expect from a camera pose, we introduce a novel formulation of the measurement uncertainty that accounts for the scene appearance (i.e., texture in the reference view), the scene depth and the vehicle pose. We successfully demonstrate our approach in the case of realtime, monocular reconstruction from a micro aerial vehicle and validate the effectiveness of our solution in both synthetic and real experiments. To the best of our knowledge, this is the first work on active, monocular dense reconstruction, which chooses motion trajectories that minimize perceptual ambiguities inferred by the texture in the scene.

show abstract

“…[7] and [8] optimize the position of the cameras to explore new áreas while avoiding the occlusions. [9] and [10] uses a cell división of the space to characterize the unexplored áreas; the problem of this approach is the application to large environments. [11] uses heuristic methods to get a direction of the movement for exploration.…”

Section: State Of the Artmentioning

confidence: 99%

Optimization in 3D Scene Acquisition with Two Mobile Robots

González

Sebastián

Artieda

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This article presents a method for cooperative reconstruction of three-dimensional scenes using múltiple views. Although the use of múltiple views is one of the most applied in the 3D scenes interpretation, its use with a single mobile robot does not guarantee the perfect localization of the environment, due to odometry errors. Also, the reconstruction of dynamic environments is not allowed for a single robot, which takes views in different instants. This work proposes a system formed by múltiple robots to get a cooperative reconstruction of the scene. The robots decide the best strategy to acquire the image to get the best reconstruction using an objective function defined. In this function, mainly are considered uncertainty of the reconstruction and view points. The result of this optimization is the next position of the robots.

show abstract

Information based adaptive robotic exploration

Cited by 342 publications

References 4 publications

Actionable Information in Vision

Actionable Information in Vision

Appearance-based Active, Monocular, Dense Reconstruction for Micro Aerial Vehicles

Optimization in 3D Scene Acquisition with Two Mobile Robots

Contact Info

Product

Resources

About