Proceedings Article•
Using EM to Learn 3D Models of Indoor Environments with Mobile Robots
28 Jun 2001-pp 329-336
TL;DR: An algorithm for generating compact 3D models of indoor environments with mobile robots using the expectation maximization algorithm to fit a lowcomplexity planar model to 3D data collected by range finders and a panoramic camera is described.
Abstract: This paper describes an algorithm for generating compact 3D models of indoor environments with mobile robots. Our algorithm employs the expectation maximization algorithm to fit a lowcomplexity planar model to 3D data collected by range finders and a panoramic camera. The complexity of the model is determined during model fitting, by incrementally adding and removing surfaces. In a final post-processing step, measurements are converted into polygons and projected onto the surface model where possible. Empirical results obtained with a mobile robot illustrate that high-resolution models can be acquired in reasonable time.
Citations
More filters
Book•
01 Jan 2005TL;DR: This research presents a novel approach to planning and navigation algorithms that exploit statistics gleaned from uncertain, imperfect real-world environments to guide robots toward their goals and around obstacles.
Abstract: Planning and navigation algorithms exploit statistics gleaned from uncertain, imperfect real-world environments to guide robots toward their goals and around obstacles.
6,425 citations
Book•
01 Jan 2003TL;DR: This article provides a comprehensive introduction into the field of robotic mapping, with a focus on indoor mapping, and describes and compares various probabilistic techniques, as they are presently being applied to a vast array of mobile robot mapping problems.
Abstract: This article provides a comprehensive introduction into the field of robotic mapping, with a focus on indoor mapping. It describes and compares various probabilistic techniques, as they are presently being applied to a vast array of mobile robot mapping problems. The history of robotic mapping is also detailed, along with an extensive list of open research problems.
1,584 citations
TL;DR: The novel techniques include statistical analysis, persistent histogram features estimation that allows for a consistent registration, resampling with additional robust fitting techniques, and segmentation of the environment into meaningful regions.
950 citations
Cites methods from "Using EM to Learn 3D Models of Indo..."
...An EM-based algorithm for learning 3D models of indoor environments is presented in [18]....
[...]
TL;DR: A new algorithm for acquiring occupancy grid maps with mobile robots that employs the expectation maximization algorithm for searching maps that maximize the likelihood of the sensor measurements, and is often more accurate than those generated using traditional techniques.
Abstract: This article describes a new algorithm for acquiring occupancy grid maps with mobile robots. Existing occupancy grid mapping algorithms decompose the high-dimensional mapping problem into a collection of one-dimensional problems, where the occupancy of each grid cell is estimated independently. This induces conflicts that may lead to inconsistent maps, even for noise-free sensors. This article shows how to solve the mapping problem in the original, high-dimensional space, thereby maintaining all dependencies between neighboring cells. As a result, maps generated by our approach are often more accurate than those generated using traditional techniques. Our approach relies on a statistical formulation of the mapping problem using forward models. It employs the expectation maximization algorithm for searching maps that maximize the likelihood of the sensor measurements.
550 citations
01 Oct 2006
TL;DR: This paper proposes a new representation denoted as multi-level surface maps (MLS maps) which allows to store multiple surfaces in each cell of the grid and is well-suited for representing large-scale outdoor environments.
Abstract: To operate outdoors or on non-flat surfaces, mobile robots need appropriate data structures that provide a compact representation of the environment and at the same time support important tasks such as path planning and localization. One such representation that has been frequently used in the past are elevation maps which store in each cell of a discrete grid the height of the surface in the corresponding area. Whereas elevation maps provide a compact representation, they lack the ability to represent vertical structures or even multiple levels. In this paper, we propose a new representation denoted as multi-level surface maps (MLS maps). Our approach allows to store multiple surfaces in each cell of the grid. This enables a mobile robot to model environments with structures like bridges, underpasses, buildings or mines. Additionally, they allow to represent vertical structures. Throughout this paper we present algorithms for updating these maps based on sensory input, to match maps calculated from two different scans, and to solve the loop-closing problem given such maps. Experiments carried out with a real robot in an outdoor environment demonstrate that our approach is well-suited for representing large-scale outdoor environments.
381 citations
Cites methods from "Using EM to Learn 3D Models of Indo..."
...[13] as well as Martin and Thrun [14] apply the EM algorithm to cluster range scans into planes....
[...]
References
More filters
49,597 citations
TL;DR: In this article, a software framework running on processors onboard the new Uranus mobile robot is proposed to maintain a probabilistic, geometric map of the robot's surroundings as it moves.
Abstract: A numeric representation of uncertain and incomplete sensor knowledge called certainty grids was used successfully in several recent mobile robot control programs developed at the Carnegie-Mellon University Mobile Robot Laboratory (MRL). Certainty grids have proven to be a powerful and efficient unifying solution for sensor fusion, motion planning, landmark identification, and many other central problems. MRL had good early success with ad hoc formulas for updating grid cells with new information. A new Bayesian statistical foundation for the operations promises further improvement. MRL proposes to build a software framework running on processors onboard the new Uranus mobile robot that will maintain a probabilistic, geometric map of the robot's surroundings as it moves. The certainty grid representation will allow this map to be incrementally updated in a uniform way based on information coming from various sources, including sonar, stereo vision, proximity, and contact sensors. The approach can correctly model the fuzziness of each reading and, at the same time, combine multiple measurements to produce sharper map features; it can also deal correctly with uncertainties in the robot's motion. The map will be used by planning programs to choose clear paths, identify locations (by correlating maps), identify well-known and insufficiently sensed terrain, and perhaps identify objects by shape. The certainty grid representation can be extended in the time dimension and used to detect and track moving objects. Even the simplest versions of the idea allow us to fairly straightforwardly program the robot for tasks that have hitherto been out of reach. MRL looks forward to a program that can explore a region and return to its starting place, using map "snapshots" from its outbound journey to find its way back, even in the presence of disturbances of its motion and occasional changes in the terrain.
1,105 citations
TL;DR: This paper addresses the problem of building large-scale geometric maps of indoor environments with mobile robots as a constrained, probabilistic maximum-likelihood estimation problem, and devises a practical algorithm for generating the most likely map from data, along with the best path taken by the robot.
Abstract: This paper addresses the problem of building large-scale geometric maps of indoor environments with mobile robots It poses the map building problem as a constrained, probabilistic maximum-likelihood estimation problem It then devises a practical algorithm for generating the most likely map from data, along with the most likely path taken by the robot Experimental results in cyclic environments of size up to 80 by 25 meter illustrate the appropriateness of the approach
826 citations
21 Jun 1994
TL;DR: In this article, two algorithms were developed to register a range scan to a previous scan so as to compute relative robot positions in an unknown environment, using matching tangent lines defined on two scans and minimizing a distance function.
Abstract: We develop two algorithms to register a range scan to a previous scan so as to compute relative robot positions in an unknown environment The first algorithm is used on matching tangent lines defined on two scans and minimizing a distance function The second algorithm iteratively establishes correspondences between points in the two scans and then solves the point-to-point least-squares problem to compute the relative pose Our methods avoid the use of localized features They work in curved environments and can handle partial occlusions >
809 citations
24 Apr 2000
TL;DR: This work presents an incremental method for concurrent mapping and localization for mobile robots equipped with 2D laser range finders, which uses a fast implementation of scan-matching for mapping, paired with a sample-based probabilistic method for localization.
Abstract: We present an incremental method for concurrent mapping and localization for mobile robots equipped with 2D laser range finders. The approach uses a fast implementation of scan-matching for mapping, paired with a sample-based probabilistic method for localization. Compact 3D maps are generated using a multi-resolution approach adopted from the computer graphics literature, fed by data from a dual laser system. Our approach builds 3D maps of large, cyclic environments in real-time, and it is robust. Experimental results illustrate that accurate maps of large, cyclic environments can be generated even in the absence of any odometric data.
794 citations
"Using EM to Learn 3D Models of Indo..." refers background or methods in this paper
...See (Thrun et al., 2000) for more detail....
[...]
...However, unlike the approaches in (Hakim & Boulanger, 1997; Thrun et al., 2000) which generate highly complex models, our focus is on generating low-complexity models that can be rendered in real-time....
[...]
...Building 3D models from robot data has previously been proposed in (Thrun et al., 2000), who describes an online algorithm for pose estimation during mapping using a forward-pointed laser range finder....
[...]
...Building 3D models from robot data has previously been proposed in (Thrun et al., 2000), who describes an online algorithm for pose estimation during mapping using a forward-pointed laser range finder....
[...]
...In all our experiments, we use a real-time algorithm de- scribed in (Thrun et al., 2000) to estimate pose; thus, our assumption is not unrealistic at all—but it lets us focus on the 3D modeling aspects of our work....
[...]