Onboard Autonomous Rover Science

Castaño, Rebecca; Estlin, Tara; Gaines, Daniel M.; Chouinard, Caroline; Bomstein, B.; Anderson, Robert C.; Burl, Michael C.; Thompson, David R.; Castano, A.; Judd, M.

doi:10.1109/aero.2007.352700

Cited by 22 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We first implemented this technique in 2010 ), but we did not test this software at a geological field site until now. Such a capability could be useful in giving more scientific autonomy to robotic planetary rovers (Volpe 2003, Fink et al 2005, Castano et al 2007, Halatci, Brooks and Iagnemma 2007, and perhaps in assisting human astronauts in their geological exploration. For example, suppose a semi-autonomous planetary rover equipped with texture-based novelty detection is observing a long series of textures corresponding to hematite concretions embedded in mineral deposits.…”

Section: Introductionmentioning

confidence: 99%

The Cyborg Astrobiologist: matching of prior textures by image compression for geological mapping and novelty detection

McGuire

Bonnici

Bruner

et al. 2014

International Journal of Astrobiology

View full text Add to dashboard Cite

We describe an image-comparison technique of Heidemann and Ritter (2008a,b) that uses image compression, and is capable of: (i) detecting novel textures in a series of images, as well as of: (ii) alerting the user to the similarity of a new image to a previously-observed texture. This image-comparison technique has been implemented and tested using our Astrobiology Phone-cam system, which employs Bluetooth communication to send images to a local laptop server in the field for the image-compression analysis. We tested the system in a field site displaying a heterogeneous suite of sandstones, limestones, mudstones and coalbeds. Some of the rocks are partly covered with lichen. The image-matching procedure of this system performed very well with data obtained through our field test, grouping all images of yellow lichens together and grouping all images of a coal bed together, and giving a 91% accuracy for similarity detection. Such similarity detection could be employed to make maps of different geological units. The novelty-detection performance of our system was also rather good (a 64% accuracy). Such novelty detection may become valuable in searching for new geological units, which could be of astrobiological interest. The current system is not directly intended for mapping and novelty detection of a second field site based upon image-compression analysis of an image database from a first field site, though our current system could be further developed towards this end. Furthermore, the image-comparison technique is an unsupervised technique that is not capable of directly classifying an image as containing a particular geological feature; labeling of such geological features is done post facto by human geologists associated with this study, for the purpose of analyzing the system's performance. By providing more advanced capabilities for similarity detection and novelty detection, this image-compression technique could be useful in giving more scientific autonomy to robotic planetary rovers, and in assisting human astronauts in their geological exploration and assessment.

show abstract

Section: Introductionmentioning

confidence: 99%

The Cyborg Astrobiologist: matching of prior textures by image compression for geological mapping and novelty detection

McGuire

Bonnici

Bruner

et al. 2014

International Journal of Astrobiology

View full text Add to dashboard Cite

show abstract

“…At present, a number of domestic universities and research institutes have carried out some preliminary research in lunar rover and have achieved some results. They are 502 Aerospace Science and Technology Corporation, Beijing University of Aeronautics and Astronautics, Tsinghua University and Harbin Institute of Technology, etc [1]. To achieve lunar rover's roaming is the basis of other follow-up work, and the topographic information provided by the stereo vision system is the key step of lunar rover to achieving secure roaming.…”

Section: Introductionmentioning

confidence: 99%

“…The human-computer interaction mode is more secure, accurate, and reliable and thus becomes the basis of finally achieving automatic working way. Recently, the rock detection algorithm based on the passive image mainly includes: the method based on the edge information [1], the method based on texture analysis [2], the method based on shadow detection [3] and the method based on solid geometry, etc [4]. This paper mainly investigates the segmentation algorithm of a single rock in the image, matching algorithm and three-dimensional reconstruction algorithm, 3D surface evaluation algorithm, and the simulation of mechanism arm located on the relative plane on the rock gotten by surface evaluation algorithm.…”

Section: Introductionmentioning

confidence: 99%

Investigation on Rock Segmentation and 3D Surface Evaluation Based on Binocular Vision

Gao¹,

Niu²,

Li³

et al. 2010

IJIES

View full text Add to dashboard Cite

Planetary exploration is the embodiment of a nation's synthesis science and technology power. The first step is to land a rover to explore the unknown world. The science task always begins from rock and soil. Rock sample and return is one of the important tasks of planetary exploration, which should be accomplished by the rover's hardware and software. A series of algorithms related to main science exploring object-rock are investigated in this paper, such as a single rock's segmentation, shadow elimination, stereo matching and 3D reconstruction. C-means clustering and 3D surface evaluation realized by surrounding binocular vision are described. On the basis of the above algorithms, a virtual mechanism is developed by VC++ and OpenGL. The evaluated information for localization is transformed to the arm and leads the arm to locate the relative plane on the rock and shows the grinding process. The experiments and simulation results based on real image show the validity of these algorithms.

show abstract

“…In particular, we are interested in developing robust onboard detection and localization algorithms for some common types of geologic landforms such as craters, volcanoes, blocks, dunes, dark slope streaks, and plumes. Onboard detection of landforms could be used for a variety of applications, including generation of summary products or statistics (a similar capability has been used in OASIS to produce summary rock catalogs Castano et al 2007), feature-based motion estimation Leroy et al 1999;Cheng et al 2002Cheng et al , 2005, identification of targets for further analysis based on scientist-specified criteria or notions of interestingness, and geolocation using geologic landmarks (similar to Roweis 2007).…”

Section: Introductionmentioning

confidence: 99%

“…The Zoe rover has used onboard autonomy and data analysis to look for chlorophyll in the Atacama Desert of Chile (Wettergreen et al 2005). The OASIS software (Onboard Autonomous Science Investigation System) is a research prototype that has been used successfully in a real-time rover testbed environment to autonomously detect and catalog rocks during traverses and select end-of-day targets for a narrow field-of-view instrument based on image analysis (Castano et al 2006;Castano et al 2007).…”

Section: Introductionmentioning

confidence: 99%

Onboard object recognition for planetary exploration

Burl

Wetzler

2011

Mach Learn

View full text Add to dashboard Cite

Machine learning techniques have shown considerable promise for automating common visual inspection tasks such as the detection of human faces in cluttered scenes. Here, we examine whether similar techniques can be used (or adapted) for the problem of automatically locating geologic landforms in planetary images gathered by spacecraft. Beyond enabling more efficient and comprehensive ground analysis of down-linked data, we are aiming toward perceptive spacecraft that use onboard processing to autonomously analyze their collected imagery and take appropriate actions. In our current study, we have employed various supervised learning algorithms, including neural networks, ensemble methods, support vector machines (SVM), and continuously-scalable template models (CSTM) to derive detectors for craters from ground-truthed images. The resulting detectors are evaluated on a challenging set of Viking Orbiter images of Mars containing roughly one thousand craters. The SVM approach with normalized image patches provides detection and localization performance closest to that of human labelers and is shown to be substantially superior to boundary-based approaches such as the Hough transform. However, the run-time cost in applying the SVM solution in the standard way (spatial scanning in which the SVM is applied to each patch of the image on a window-by-window basis) is too high due both to the number of support vectors required and the number of test vectors generated by sliding a window across the data. We have developed an implementation using FFTs and the overlapand-add technique, which can be used to efficiently apply SVMs to sensor data in resourceconstrained environments such as on a spacecraft. The technique allows exact computation of the SVM decision function over an image using minimal RAM (typically less than 5% of the size of the image) and only O(n s (log 2 d + 11)) real multiplications per pixel, where n s Mach Learn (2011) 84:341-367 is the number of support vectors and d is the dimensionality of the vectors compared with O(n s d) real multiplications per pixel for spatial scanning. Our approach is complementary to reduced set methods providing (in theory) a multiplicative gain in performance.

show abstract

Onboard Autonomous Rover Science

Cited by 22 publications

References 23 publications

The Cyborg Astrobiologist: matching of prior textures by image compression for geological mapping and novelty detection

The Cyborg Astrobiologist: matching of prior textures by image compression for geological mapping and novelty detection

Investigation on Rock Segmentation and 3D Surface Evaluation Based on Binocular Vision

Onboard object recognition for planetary exploration

Contact Info

Product

Resources

About