Stereo vision and rover navigation software for planetary exploration

Abstract

NASA's Mars Exploration Rover (MER) missions will land twin rovers on the surface of Mars in 2004. These rovers will have the ability to navigate safely through unknown and potentially hazardous terrain, using autonomous passive stereo vision to detect potential terrain hazards before driving into them. Unfortunately, the computational power of currently available radiation hardened processors limits the amount of distance (and therefore science) that can be safely achieved by any rover in a given time frame.

A study of visual and tactile terrain classification and classifier fusion for planetary exploration rovers

“…For our present work, the texture length scale of interest is on the order of tens of centimeters. This scale allows us to observe textural appearances of surfaces in the range of four to thirty meters, which corresponds to the range of interest for local planetary rover navigation (Goldberg et al, 2002). In this work we employ a wavelet-based fractal dimension signature method, which yields robust results in natural texture segmentation, as demonstrated by (Espinal et al, 1998).…”

“…Avedisyan (2004) was interested in far field navigation and employed toposemantic techniques, and Mandelbaum (1998) detected obstacles directly from disparity maps. The result of such obstacle detection is often a traversability map that defines regions of the terrain as traversable or untraversable (Goldberg et al, 2002). Note that such methods allow for detection of "geometric" hazards or terrain features such as rocks, however they cannot easily detect "non-geometric" hazards or terrain classes that are not characterized by geometric variation such as sand dunes on Mars.…”

An innovative high accuracy autonomous navigation method for the Mars rovers

“…The main techniques for the rover's autonomous navigation include inertial navigation [7][8][9], vision navigation [10,11] and celestial navigation [12][13][14][15][16][17]. The inertial navigation has the advantages of immune from environment effects, high precision in short time and real-time autonomy.…”

Multifunctional Whisker Arrays for Distance Detection, Terrain Mapping, and Object Feature Extraction

“…As described in [22], range images generated by stereo vision cameras on remote rovers are generally not sufficient to determine a safe driving path. Field of view restrictions and error recovery behaviors can potentially force a rover to run into an unseen area [22,23].…”

“…Field of view restrictions and error recovery behaviors can potentially force a rover to run into an unseen area [22,23]. To solve these problems, a "local map" is constructed of the terrain around the rover [22].…”