Efficient Non-Parametric Surface Representations Using Active Sampling for Push Broom Laser Data

Smith, Mike; Posner, Ingmar; Newman, Paul

doi:10.15607/rss.2010.vi.027

Cited by 12 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In robotics, GPs have been used in terrain and surface modeling (O'Callaghan & Ramos, ; Smith, Posner, & Newman, ; Vasudevan, Ramos, Nettleton, Durrant‐Whyte, & Blair, ). In all these works, the utilization varies with the properties of the applications, the structure of the model, and the usage of the correlation information.…”

Section: Gaussian Processes For Spatial Regression Mapping From Samplmentioning

confidence: 99%

Robotic pipeline wall thickness evaluation for dense nondestructive testing inspection

Miró

Ulapane

Shi

et al. 2018

Journal of Field Robotics

View full text Add to dashboard Cite

This paper addresses automated mapping of the remaining wall thickness of metallic pipelines in the field by means of an inspection robot equipped with nondestructive testing (NDT) sensing. Set in the context of condition assessment of critical infrastructure, the integrity of arbitrary sections in the conduit is derived with a bespoke robot kinematic configuration that allows dense pipe wall thickness discrimination in circumferential and longitudinal direction via NDT sensing with guaranteed sensing lift-off (offset of the sensor from pipe wall) to the pipe wall, an essential barrier to overcome in cement-lined water pipelines. A tailored covariance function for pipeline cylindrical structures within the context of a Gaussian Processes has also been developed to regress missing sensor data incurred by a sampling strategy folllowed in the field to speed up the inspection times, given the slow response of the pulsed eddy current electromagnetic sensor proposed. The data gathered represent not only a visual understanding of the condition of the pipe for asset managers, but also constitute a quantative input to a remaining-life calculation that defines the likelihood of the pipeline for future renewal or repair. Results are presented from deployment of the robotic device on a series of pipeline inspections which demonstrate the feasibility of the device and sensing configuration to provide meaningful 2.5D geometric maps. K E Y W O R D S gaussian process, inspection harsh environments, mapping, NDT, pipeline robot 1 | MOTIVATION-A TAXONOMY OF NDT INSPECTION TECHNIQUES Nondestructive testing (NDT) or evaluation (NDE) is extensively used by the energy and water industry to assess the integrity of their network assets, particularly their larger and most critical conduits (generally refered to as those larger than 350 mm in diameter), in their decision-making process leading their renewal/repair/rehabilitation programs. The key advantage of NDT/NDE is that the structure of the asset is not compromised in estimating its condition. The sensing modality to use is strongly influenced by the material of the asset. Grey Cast Iron (CI) pipelines remain the bulk of the buried critical water infrastructure in the developed world as that was the material of choice for mass production with the advent of the Industrial Revolution in the middle of the 18th century (alongside its less brittle relative of Ductile Iron since 1950s), until carbon steel, asbestos cement, or plastic pipelines (PVC) among other materials made them redundant over the years. The nonhomogeneity of the CI produce means that sensing techniques widely used in the (mild) carbon steel networks in the energy pipeline sector, such as ultrasonics or electromagnetic acoustic transducers, are inadequate for CI, and the underlying techniques of most commercial propositions for CI are instead based on either magnetics (e.g., magnetic flux leakage, pulsed eddy current [PEC], and remote field eddy currents), or the study of the propagation of pressure waves in the pipeline...

show abstract

Section: Gaussian Processes For Spatial Regression Mapping From Samplmentioning

confidence: 99%

Robotic pipeline wall thickness evaluation for dense nondestructive testing inspection

Miró

Ulapane

Shi

et al. 2018

Journal of Field Robotics

View full text Add to dashboard Cite

show abstract

“…However, both of these techniques are limited by their formulation to representing environments in 2.5 dimensions. Smith et al (2010) present a possible method of addressing this by modelling the terrain in the sensor space before being mapped back to the physical space. While this approach is capable of representing overhangs in the environments, querying the model with physical locations as inputs is no longer possible.…”

Section: Applications Of Gaussian Processes To Roboticsmentioning

confidence: 99%

“…Several papers have addressed the issue of preventing the size of the training data growing to unmanageable levels. Notably, Smith et al (2010) suggests using KLdivergence as a metric to gauge the information gained from incorporating new points into the training set and reject those which fail to meet a certain threshold.…”

Section: Nearest Neighbours and Computational Complexitymentioning

confidence: 99%

Gaussian process occupancy maps

O’Callaghan

Ramos

2012

The International Journal of Robotics Research

191

124

View full text Add to dashboard Cite

We introduce a new statistical modelling technique for building occupancy maps. The problem of mapping is addressed as a classification task where the robot's environment is classified into regions of occupancy and free space. This is obtained by employing a modified Gaussian process as a non-parametric Bayesian learning technique to exploit the fact that realworld environments inherently possess structure. This structure introduces dependencies between points on the map which are not accounted for by many common mapping techniques such as occupancy grids. Our approach is an 'anytime' algorithm that is capable of generating accurate representations of large environments at arbitrary resolutions to suit many applications. It also provides inferences with associated variances into occluded regions and between sensor beams, even with relatively few observations. Crucially, the technique can handle noisy data, potentially from multiple sources, and fuse it into a robust common probabilistic representation of the robot's surroundings. We demonstrate the benefits of our approach on simulated datasets with known ground truth and in outdoor urban environments.

show abstract

“…GPs thus handle both uncertainty and incompleteness effectively. In terrain modelling GPs have been used before to model and use the spatial correlation of the given data to estimate the elevation values for other unknown points of interest [8], [9] and more recently [10]. A recent approach for occupancy mapping with GPs has also been presented in [11].…”

Section: Literature Reviewmentioning

confidence: 99%

Learning spatial correlations for Bayesian fusion in pipe thickness mapping

Vidal-Calleja

Bruijn

et al. 2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Abstract-Pipe thickness maps are used to assess the condition in pipelines. Thickness maps are a 2.5D representation similar to elevation maps in robotics. Probabilistic frameworks, however, have barely been used in this context. This paper presents a general approach for generating probabilistic maps from heterogeneous sensor data. The key idea is to learn the spatial correlation of a sensor through Gaussian Process models and use it as priors for Bayesian fusion. This approach is applied to the novel application of pipe thickness mapping. Data from a 3D laser scanner on the outer surface of the pipe and thickness measurements from a contact ultrasonic sensor are fused into a single thickness map with associated uncertainty. Moreover, a dedicated algorithm to model the ultrasonic sensor using kernel density estimation is also proposed. The overall approach is evaluated using the full 3D profile (outer and inner surfaces) of the pipe section as ground truth.

show abstract

Efficient Non-Parametric Surface Representations Using Active Sampling for Push Broom Laser Data

Cited by 12 publications

References 21 publications

Robotic pipeline wall thickness evaluation for dense nondestructive testing inspection

Robotic pipeline wall thickness evaluation for dense nondestructive testing inspection

Gaussian process occupancy maps

Learning spatial correlations for Bayesian fusion in pipe thickness mapping

Contact Info

Product

Resources

About