A Review of Point Cloud Registration Algorithms for Mobile Robotics

Pomerleau, François; Colas, Francis; Siegwart, Roland

doi:10.1561/2300000035

Cited by 516 publications

(248 citation statements)

References 96 publications

Supporting

Mentioning

241

Contrasting

Unclassified

Order By: Relevance

“…If the task is defied by using a 3D object imported into the application, the object is aligned with the initial object and placed on its surface, this is done by executing the algorithm described in Figure 8 which is using the Iterative Closest Point (ICP) algorithm [19]. The source object represents the object which is used to define the trajectory and the destination object is the object which will be processed by the robot.…”

Section: Service Robotsmentioning

confidence: 99%

Robot Engraving Services in Industry

Anton¹,

Anton²,

Constantinescu³

2018

Service Robots

View full text Add to dashboard Cite

This chapter presents a software system created to allow to design complex robot trajectories in the cartesian space, used for tasks like milling or engraving with the aid of a robot. The experimental setup was created using an ABB (ASEA Brown Boveri) IRB 140 robot on which was mounted an engraving tool (which was equipped with a high frequency vibrating pin) or a drilling tool (an electric milling machine controlled with I/O signals) and a computer which is executing a CAD application allowing the design of the path that the robot must follow in order to execute the engraving/milling task. The robot job or task is defined by the set of surfaces of the raw object and of the object after being processed, by subtracting these two surfaces the robot task is given by the set of points resulted after the subtraction. The subtraction operation offers a set of points which must be connected in order to obtain the final trajectory, if the task is to engrave a shape then the tool will be normal to the object surface. The algorithm which is generating the surface is presented along with some experimental results.

show abstract

Section: Service Robotsmentioning

confidence: 99%

Robot Engraving Services in Industry

Anton¹,

Anton²,

Constantinescu³

2018

Service Robots

View full text Add to dashboard Cite

show abstract

“…Many works have tried to improve this algorithm's robustness [10,11]. Some methods focus on the cost function metric.…”

Section: Related Workmentioning

confidence: 99%

Global Registration of 3D LiDAR Point Clouds Based on Scene Features: Application to Structured Environments

et al. 2017

View full text Add to dashboard Cite

Acquiring 3D data with LiDAR systems involves scanning multiple scenes from different points of view. In actual systems, the ICP algorithm (Iterative Closest Point) is commonly used to register the acquired point clouds together to form a unique one. However, this method faces local minima issues and often needs a coarse initial alignment to converge to the optimum. This paper develops a new method for registration adapted to indoor environments and based on structure priors of such scenes. Our method works without odometric data or physical targets. The rotation and translation of the rigid transformation are computed separately, using, respectively, the Gaussian image of the point clouds and a correlation of histograms. To evaluate our algorithm on challenging registration cases, two datasets were acquired and are available for comparison with other methods online. The evaluation of our algorithm on four datasets against six existing methods shows that the proposed method is more robust against sampling and scene complexity. Moreover, the time performances enable a real-time implementation.Data Set: https://liris.cnrs.fr/3d-registration/ Data Set License: ODC Attribute License

show abstract

“…W przypadku wykorzystania czujników RGB-D [16,31] problem rejestracji może być sformułowany jako znalezienie względ-nych transformacji między kolejnymi chmurami punktów oraz przekształce-nie współrzędnych wszystkich punktów do wspólnego układu odniesienia. Istnieje szereg potencjalnych aplikacji rejestracji w robotyce [24], wśród których najważniejszymi są: budowanie trójwymiarowej mapy otoczenia (np. [2]) oraz generowanie trójwymiarowych modeli obiektów (np.…”

Section: Wprowadzenieunclassified

Registration of RGB-D Images: Components of the System

Kornuta

Łępicka

2017

PAR

View full text Add to dashboard Cite

A Review of Point Cloud Registration Algorithms for Mobile Robotics

Cited by 516 publications

References 96 publications

Robot Engraving Services in Industry

Robot Engraving Services in Industry

Global Registration of 3D LiDAR Point Clouds Based on Scene Features: Application to Structured Environments

Registration of RGB-D Images: Components of the System

Contact Info

Product

Resources

About