Interacting Markov Random Fields for Simultaneous Terrain Modeling and Obstacle Detection

Wellington, Carl; Courville, Aaron; Stentz, Anthony

doi:10.15607/rss.2005.i.001

Cited by 49 publications

(66 citation statements)

References 13 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adding such a neighborhood consistency assumption to our similarity classifier allows us to remove some of the noise inherent to the classifier. This closely parallels the smoothing assumption used to continually adjust the ground height estimate within the perception system to take into account both evidence from laser data as well as maintaining a degree of smoothness due to the continuity of the ground surface [28].…”

Section: Global Segment Smoothnessmentioning

confidence: 79%

Segmentation-based online change detection for mobile robots

Neuman

Sofman

Stentz

et al. 2011

2011 IEEE International Conference on Robotics and Automation

Self Cite

View full text Add to dashboard Cite

As mobile robotics continues to advance, we are beginning to see intelligent robots with complex perception and planning systems onboard. These systems are often engineered for a specific task, or trained using machine learning to be adaptable and robust. Unfortunately, when faced with the complexities of the real world, almost every current robotic system will eventually encounter a situation which it has not been not trained or designed to handle. Unless a system operates in a highly structured or controlled environment, it will be impossible to determine all of the types of obstacles a robot may encounter. Instead of trying to make robots perfect perception and planning machines, we seek to enable robotic systems to detect situations in which the robot is unfamiliar. When a robot regularly visits an area more than once, we propose the use of a change detection algorithm to identify significant changes in that area over time and inform the robot about possible hazards. If a robot has traversed an area before, we can generally assume it to be safe, but if an unexpected change happens in the robots environment, this may represent a danger to the robot or the safety of humans nearby. We propose an algorithm to segment a 3D scene and use the segmentation as contextual information for an improved change detection algorithm. We will explain our proposed solution in detail and then provide data which show that the performance of change detection is increased by using segmentation. Finally, we will argue that these techniques can enhance the safety and reliability of mobile robots.

show abstract

Section: Global Segment Smoothnessmentioning

confidence: 79%

Segmentation-based online change detection for mobile robots

Neuman

Sofman

Stentz

et al. 2011

2011 IEEE International Conference on Robotics and Automation

Self Cite

View full text Add to dashboard Cite

show abstract

“…One method that does relax this strong independence assumption is described by Wellington et al in [6]. Their system also performs terrain classification as well as some other estimation tasks about the terrain.…”

Section: Previous Workmentioning

confidence: 99%

Online, self-supervised terrain classification via discriminatively trained submodular Markov random fields

Vernaza

Taskar

Lee

2008

2008 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

, "Online, self-supervised terrain classification via discriminatively trained submodular Markov random fields", . May 2008.Online, self-supervised terrain classification via discriminatively trained submodular Markov random fields AbstractThe authors present a novel approach to the task of autonomous terrain classification based on structured prediction. We consider the problem of learning a classifier that will accurately segment an image into "obstacle" and "ground" patches based on supervised input. Previous approaches to this problem have focused mostly on local appearance; typically, a classifier is trained and evaluated on a pixel-by-pixel basis, making an implicit assumption of independence in local pixel neighborhoods. We relax this assumption by modeling correlations between pixels in the submodular MRF framework. We show how both the learning and inference tasks can be simply and efficiently implemented-exact inference via an efficient max flow computation; and learning, via an averaged-subgradient method. Unlike most comparable MRF-based approaches, our method is suitable for implementation on a robot in real-time. Experimental results are shown that demonstrate a marked increase in classification accuracy over standard methods in addition to real-time performance. KeywordsMarkov processes, gradient methods, image classification, image segmentation, mobile robots, random processes, robot vision, terrain mapping, Markov random fields, autonomous terrain classification, averagedsubgradient method, classifier learning, image segmentation, inference task, max flow computation, online self-supervised terrain classification, robot, structured prediction, submodular MRF framework This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it. Abstract-The authors present a novel approach to the task of autonomous terrain classification based on structured prediction. We consider the problem of learning a classifier that will accurately segment an image into "obstacle" and "ground" patches based on supervised input. Previous approaches to this problem have focused mostly on local appearance; typically, a classifier is trained and evaluated on a pixel-bypixel basis, making an implicit assumption of independence in local pixel neighborhoods. We relax this assumption by modeling correlations between pixels in the submodular MRF framework. We show how both the learning and inference tasks can be simply and efficiently implemented-exact inference via an efficient max flow computation; and learning, via a...

show abstract

“…18 Neural networks would seem worthy of investigation for the three-dimensional (3D) LiDAR classification problem. Work has been done by other researchers on classifying aerial LiDAR data that generate elevation maps of limited resolution, 19,20 and some significant work has been done in the case of 3D LiDAR from a rover perspective 4,9,10,[21][22][23] and more specifically other types of classifiers such as Markov random fields, 24 Bayesian classifiers, 25 support vector machines (SVMs) 26 and fuzzy modelling. 11 Hata et al successfully use a neural network to do such classification.…”

Section: Introductionmentioning

confidence: 99%

Training a terrain traversability classifier for a planetary rover through simulation

Hewitt

Ellery

Ruiter

2017

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

A classifier training methodology is presented for Kapvik, a micro-rover prototype. A simulated light detection and ranging scan is divided into a grid, with each cell having a variety of characteristics (such as number of points, point variance and mean height) which act as inputs to classification algorithms. The training step avoids the need for time-consuming and error-prone manual classification through the use of a simulation that provides training inputs and target outputs. This simulation generates various terrains that could be encountered by a planetary rover, including untraversable ones, in a random fashion. A sensor model for a three-dimensional light detection and ranging is used with ray tracing to generate realistic noisy three-dimensional point clouds where all points that belong to untraversable terrain are labelled explicitly. A neural network classifier and its training algorithm are presented, and the results of its output as well as other popular classifiers show high accuracy on test data sets after training. The network is then tested on outdoor data to confirm it can accurately classify real-world light detection and ranging data. The results show the network is able to identify terrain correctly, falsely classifying just 4.74% of untraversable terrain.

show abstract

Interacting Markov Random Fields for Simultaneous Terrain Modeling and Obstacle Detection

Cited by 49 publications

References 13 publications

Segmentation-based online change detection for mobile robots

Segmentation-based online change detection for mobile robots

Online, self-supervised terrain classification via discriminatively trained submodular Markov random fields

Training a terrain traversability classifier for a planetary rover through simulation

Contact Info

Product

Resources

About