Issa Nesnas

Learn More
The inability of current robotic perception techniques to adequately detect non-geometric terrain hazards is a primary cause of failure for robots operating in natural terrain on Mars, the Moon, and Earth. Classical approaches detect surface appearance but do not measure the underlying mechanical properties that determine wheel-terrain interaction. Diurnal(More)
Motivation: Some of the most intriguing science discoveries on Mars came from sites that are currently inaccessible for in-situ analysis and sample return. The recent discovery of recurring slope lineae (RSL), such as those observed in Newton crater, are on steep slopes (25° – 40°) that are hundreds of meters down from the crater rim. In-situ analysis and(More)
Flexible part feeding is a concept used in conjunction with a robotic manipulator, whereby the robot uses its vision system to locate parts that are randomly scattered on the feeder's presentation surface. This setup presents some new challenges for the vision system due to the stochastic nature of flexible feeding. Randomly-oriented parts have to be(More)
This paper presents a method for predicting slip using Gaussian process regression. Slip models are learned for visually classified terrain types as a function of terrain geometry. Spatial correlations between terrain properties are leveraged for on-line slip model adaptation. Results show that regression-based modeling using in-situ rover data outperforms(More)
  • 1