Efficient algorithms for Next Best View evaluation

Bissmarck, Fredrik; Svensson, Martin; Tolt, Gustav

doi:10.1109/iros.2015.7354212

Cited by 20 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing NBV planning work covers a variety of scene sizes, from small objects (e.g., the Stanford Bunny [6]) [3,[10][11][12][13][14][15][16][17] to buildings [1,2,4,[18][19][20][21][22][23].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Surface Edge Explorer (see): Planning Next Best Views Directly from 3D Observations

Border

Gammell

Newman

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Surveying 3D scenes is a common task in robotics. Systems can do so autonomously by iteratively obtaining measurements. This process of planning observations to improve the model of a scene is called Next Best View (NBV) planning.NBV planning approaches often use either volumetric (e.g., voxel grids) or surface (e.g., triangulated meshes) representations. Volumetric approaches generalise well between scenes as they do not depend on surface geometry but do not scale to high-resolution models of large scenes. Surface representations can obtain high-resolution models at any scale but often require tuning of unintuitive parameters or multiple survey stages.This paper presents a scene-model-free NBV planning approach with a density representation. The Surface Edge Explorer (SEE) uses the density of current measurements to detect and explore observed surface boundaries. This approach is shown experimentally to provide better surface coverage in lower computation time than the evaluated state-of-the-art volumetric approaches while moving equivalent distances.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Volumetric representations [3,10,12,[18][19][20][21][22]] discretise a bounded scene volume into a voxel grid from which view selection metrics can be computed. Seminal work by Connolly [3] uses a metric that counts the number of unseen voxels visible from potential views on a tessellated sphere encompassing the scene.…”

Section: Related Workmentioning

confidence: 99%

Surface Edge Explorer (see): Planning Next Best Views Directly from 3D Observations

Border

Gammell

Newman

2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

show abstract

“…Subsequently, we provide a detailed description of the single parts in different subsections. As mentioned in previous work from (Bissmarck et al, 2015), we assume an obstacle-free work space where the sensor can move Figure 1. Flowchart of the complete NBV pipeline with the related sections.…”

Section: Methodsmentioning

confidence: 99%

“…This is more flexible than e.g. Occupancy Grid Maps which divide the model and object space in discrete voxels (Bissmarck et al, 2015).…”

Section: The Nbv Findermentioning

confidence: 99%

“…However, such approaches are tailored to controlled environments where strong assumptions about either the change in viewpoint or the possibly occurring objects are made. Respective assumptions cannot be made that easily for an autonomous exploration of unknown space (Dornhege and Kleiner, 2013) or for the 3D reconstruction of unknown objects in both indoor and outdoor scenes (Kawashima et al, 2014;Vásquez and Sucar, 2011;Bissmarck et al, 2015). Accordingly, a new generation of model-free approaches for NBV estimation is required, where approaches relying on acquired object surfaces seem to be more promising (Scott et al, 2003), since they are also applicable for unknown environments as well as for objects which exhibit a concave surface geometry.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Next-Best-View Method Based on Consecutive Evaluation of Topological Relations

Dierenbach¹,

Weinmann²,

Jutzi³

2016

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:This work describes an iterative algorithm for estimating optimal viewpoints, so called next-best-views (NBVs). The goal is to incrementally construct a topological network from the scene during the consecutive acquisition of several views. Our approach is a hybrid method between a surface-based and a volumetric approach with a continuous model space. Hence, a new scan taken from an optimal position should either cover as much as possible from the unknown object surface in one single scan, or densify the existing data and close possible gaps. Based on the point density, we recover the essential and structural information of a scene based on the Growing Neural Gas (GNG) algorithm. From the created graph representation of topological relations, the density of the point cloud at each network node is estimated by approximating the volume of Voronoi cells. The NBV Finder selects a network node as NBV, which has the lowest point density. Our NBV method is self-terminating when all regions reach a predefined minimum point density or the change of the GNG error is zero. For evaluation, we use a Buddha statue with a rather simple surface geometry but still some concave parts and the Stanford Dragon with a more complex object surface containing occluded and concave parts. We demonstrate that our NBV method outperforms a "naive random" approach relying on uniformly distributed sensor positions in terms of efficiency, i.e. our proposed method reaches a desired minimum point density up to 20% faster with less scans.

show abstract

Integrating planning perception and action for informed object search

et al. 2017

View full text Add to dashboard Cite

This paper presents a method to reduce the time spent by a robot with cognitive abilities when looking for objects in unknown locations. It describes how machine learning techniques can be used to decide which places should be inspected first, based on images that the robot acquires passively. The proposal is composed of two concurrent processes. The first one uses the aforementioned images to generate a description of the types of objects found in each object container seen by the robot. This is done passively, regardless of the task being performed. The containers can be tables, boxes, shelves or any other kind of container of known shape whose contents can be seen from a distance. The second process uses the previously computed estimation of the contents of the containers to decide which is the most likely container having the object to be found. This second process is deliberative and takes place only when the robot needs to find an object, whether because it is explicitly asked to locate one or because it is needed as a step to fulfil the mission of the robot. Upon failure to guess the right container, the robot can continue making guesses until the object is found. Guesses are made based on the semantic distance between the object to find and the description of the types of the objects found in each object container. The paper provides quantitative results comparing the efficiency of the proposed method and two base approaches.

show abstract

Efficient algorithms for Next Best View evaluation

Cited by 20 publications

References 13 publications

Surface Edge Explorer (see): Planning Next Best Views Directly from 3D Observations

Surface Edge Explorer (see): Planning Next Best Views Directly from 3D Observations

Next-Best-View Method Based on Consecutive Evaluation of Topological Relations

Integrating planning perception and action for informed object search

Contact Info

Product

Resources

About