Ara Nefian

Abstract This article describes the robot Stanley, which won the 2005 DARPA Grand Challenge. Stanley was developed for high‐speed desert driving without manual intervention. The robot's software system relied predominately on state‐of‐the‐art artificial intelligence technologies, such as machine learning and probabilistic reasoning. This paper describes the major components of this architecture, and discusses the results of the Grand Challenge race. © 2006 Wiley Periodicals, Inc.

The Radiation Assessment Detector (RAD) on the Mars Science Laboratory's Curiosity rover began making detailed measurements of the cosmic ray and energetic particle radiation environment on the surface of Mars on 7 August 2012. We report and discuss measurements of the absorbed dose and dose equivalent from galactic cosmic rays and solar energetic particles on the martian surface for ~300 days of observations during the current solar maximum. These measurements provide insight into the radiation hazards associated with a human mission to the surface of Mars and provide an anchor point with which to model the subsurface radiation environment, with implications for microbial survival times of any possible extant or past life, as well as for the preservation of potential organic biosignatures of the ancient martian environment.

Volume mixing and isotope ratios secured with repeated atmospheric measurements taken with the Sample Analysis at Mars instrument suite on the Curiosity rover are: carbon dioxide (CO2), 0.960(±0.007); argon-40 ((40)Ar), 0.0193(±0.0001); nitrogen (N2), 0.0189(±0.0003); oxygen, 1.45(±0.09) × 10(-3); carbon monoxide, < 1.0 × 10(-3); and (40)Ar/(36)Ar, 1.9(±0.3) × 10(3). The (40)Ar/N2 ratio is 1.7 times greater and the (40)Ar/(36)Ar ratio 1.6 times lower than values reported by the Viking Lander mass spectrometer in 1976, whereas other values are generally consistent with Viking and remote sensing observations. The (40)Ar/(36)Ar ratio is consistent with martian meteoritic values, which provides additional strong support for a martian origin of these rocks. The isotopic signature δ(13)C from CO2 of ~45 per mil is independently measured with two instruments. This heavy isotope enrichment in carbon supports the hypothesis of substantial atmospheric loss.

Observations by the Mars Science Laboratory Mast Camera (Mastcam) in Gale crater reveal isolated outcrops of cemented pebbles (2 to 40 millimeters in diameter) and sand grains with textures typical of fluvial sedimentary conglomerates. Rounded pebbles in the conglomerates indicate substantial fluvial abrasion. ChemCam emission spectra at one outcrop show a predominantly feldspathic composition, consistent with minimal aqueous alteration of sediments. Sediment was mobilized in ancient water flows that likely exceeded the threshold conditions (depth 0.03 to 0.9 meter, average velocity 0.20 to 0.75 meter per second) required to transport the pebbles. Climate conditions at the time sediment was transported must have differed substantially from the cold, hyper-arid modern environment to permit aqueous flows across several kilometers.

The use of visual features in audio-visual speech recognition (AVSR) is justified by both the speech generation mechanism, which is essentially bimodal in audio and visual representation, and by the need for features that are invariant to acoustic noise perturbation. As a result, current AVSR systems demonstrate significant accuracy improvements in environments affected by acoustic noise. In this paper, we describe the use of two statistical models for audio-visual integration, the coupled HMM (CHMM) and the factorial HMM (FHMM), and compare the performance of these models with the existing models used in speaker dependent audio-visual isolated word recognition. The statistical properties of both the CHMM and FHMM allow to model the state asynchrony of the audio and visual observation sequences while preserving their natural correlation over time. In our experiments, the CHMM performs best overall, outperforming all the existing models and the FHMM.