3D graph based stairway detection and localization for mobile robots

Westfechtel, Thomas; Ohno, Kazunori; Mertsching, Bärbel; Nickchen, Daniel; Kojima, Seiji; Tadokoro, Satoshı

doi:10.1109/iros.2016.7759096

Cited by 24 publications

(20 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the control of the wheel movement on stairs, the problem of continuous scanning of the stairs profile should be addressed to achieve an optimal opening of the segments while moving on the stairs and to perform any corrections of their opening as needed to prevent slippage of the segment to the lower stair while travelling. There exist many methods for detecting the stairs and scanning their dimensions using LIDAR 28 ; solution with laser scanners was introduced in previously mentioned article of Chocoteco et al 20 and in Zheng et al 29 in connection with a hexapod robot. The solution based on cameras with threedimensional measurement possibilities (RGB-D cameras) was introduced in Pérez-Yus et al 30 Among the equipment that is successfully used for scanning the stairs is also known Xbox 360 Kinect (Microsoft) as is shown in Li et al 31 The problem of rising up the first stair is also relatively complex with respect to the proper distance from the first stair at the moment of opening the wheel.…”

Section: Experimental Verificationmentioning

confidence: 99%

The synthesis of a segmented stair-climbing wheel

Mostýn

Krys

Kot

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

The article describes the process of development of an essentially new wheel suitable both for moving on flat ground and for travelling on stairs. The stair-climbing wheel is composed of rotary circular segments arranged around a shared carrier with arms to form a complete circular profile of the wheel adapted for moving on flat ground; for travelling on stairs, individual segments are rotated by an appropriate angle to touch down tangentially on the stepping surface of the stairs. The dimensions of individual segments, the centre of rotation of individual segments and the angle of their partial turn have been chosen so that the length of the arc along which the circular segment rolls is equal to the length of the stepping surface of an average stair, and, at the same time, the circular segment touches down tangentially on the stepping surface while the wheel turns around the edge of the previous segment. Using the rotation angle of the turnable segments, the wheel can be adapted to the height of non-standard stairs. The segments can be inclined in both directions for bidirectional movement of the wheel up and down the stairs. An undercarriage equipped with these wheels can be used in the field of exploratory robots and for the transportation of persons and materials on stairs.

show abstract

Section: Experimental Verificationmentioning

confidence: 99%

The synthesis of a segmented stair-climbing wheel

Mostýn

Krys

Kot

et al. 2018

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…Stairs detection is important in several different fields, such as multi-storey path finding for explorer robots venturing into buildings [13][14][15], as an aid for the visually impaired [16][17][18], and last but not least in the semantic segmentation of 3D models of Architectural Heritage buildings [19,20]. Algorithms developed for the first two cases are usually not directly applicable to semantic segmentation for CH, [15] because they generally work on organized point clouds derived from RGB-D data, while CH applications use unorganized clouds coming from photogrammetry or laser scanners. They may anyway suggest methods valid for unorganized point clouds too.…”

Section: Detection and Segmentation Of Straight Stairsmentioning

confidence: 99%

“…In paper [14], a staircase extraction algorithm based on super-voxels is proposed. In [15] the Authors develop a graph-based detection method for point clouds, which first segments planar regions and extracts the stair tread and riser segments. With these segments, a dynamic graph model is initialized that is used to detect stairs.…”

Section: Detection and Segmentation Of Straight Stairsmentioning

confidence: 99%

“…With these segments, a dynamic graph model is initialized that is used to detect stairs. See [15] also for a good review of some previous approaches useful for unorganized point clouds, and for a discussion on plane-based and edge-based methods. In [16] walls, doors, stairs, and a residual generic class of obstacles on the floor are detected in RGB-D data; stairs are found by searching for points on planes at increasing height from the ground, with a given step height and a tolerance.…”

Section: Detection and Segmentation Of Straight Stairsmentioning

confidence: 99%

See 1 more Smart Citation

A software tool for the semi-automatic segmentation of architectural 3D models with semantic annotation and Web fruition

Nunzio

2018

ACTA IMEKO

View full text Add to dashboard Cite

Semantic segmentation of 3D models of ancient and historic buildings and artifacts is an important modern Cultural Heritage topic. This work describes a software tool currently under development, for interactive and semi-automatic segmentation of 3D models produced by photogrammetric surveys. The system includes some generic and well-known segmentation approaches such as region growing and Locally Convex Connected Patches segmentation, but it also contains original code for specific semantic segmentation of parts of buildings, in particular circular-section columns and straight stairs. The software is modular, so allowing easy expandability. It also has tools for data encoding into formats ready for model fruition by Web technologies. These results were obtained in collaboration with Corvallis SPA (Padua – Italy, http://www.corvallis.it).

show abstract

“…This paper builds on our previous work (Westfechtel et al, 2016). Among other things, we extended our graphbased model to include circular stairways, introduced the concept of competing initializations, and extended the experimental evaluation (i.e.…”

Section: Introductionmentioning

confidence: 99%

Robust stairway-detection and localization method for mobile robots using a graph-based model and competing initializations

Westfechtel

Ohno

Mertsching

et al. 2018

The International Journal of Robotics Research

Self Cite

View full text Add to dashboard Cite

One of the major challenges for mobile robots in human-shaped environments is navigating stairways. This study presents a method for accurately detecting, localizing, and estimating the characteristics of stairways using point cloud data. The main challenge is the wide variety of different structures and shapes of stairways. This challenge is often aggravated by an unfavorable position of the sensor, which leaves large parts of the stairway occluded. This can be further aggravated by sparse point data. We overcome these difficulties by introducing a three-dimensional graph-based stairway-detection method combined with competing initializations. The stairway graph characterizes the general structural design of stairways in a generic way that can be used to describe a large variety of different stairways. By using multiple ways to initialize the graph, we can robustly detect stairways even if parts of the stairway are occluded. Furthermore, by letting the initializations compete against each other, we find the best initialization that accurately describes the measured stairway. The detection algorithm utilizes a plane-based approach. We also investigate different planar segmentation algorithms and experimentally compare them in an application-orientated manner. Our system accurately detects and estimates the stairway parameters with an average error of only 2:5 mm for a variety of stairways including ascending, descending, and spiral stairways. Our method works robustly with different depth sensors for either small-or large-scale environments and for dense and sparse point cloud data. Despite this generality, our system's accuracy is higher than most state-of-the-art stairway-detection methods.

show abstract

3D graph based stairway detection and localization for mobile robots

Cited by 24 publications

References 11 publications

The synthesis of a segmented stair-climbing wheel

The synthesis of a segmented stair-climbing wheel

A software tool for the semi-automatic segmentation of architectural 3D models with semantic annotation and Web fruition

Robust stairway-detection and localization method for mobile robots using a graph-based model and competing initializations

Contact Info

Product

Resources

About