Autonomous mobile robot navigation, either off-road or on ill-structured roads, presents unique challenges for machine perception. A successful terrain or roadway classifier must be able to learn in a self-supervised manner and adapt to inter-and intra-run changes in the local environment.This paper demonstrates the improvements achieved by augmenting an existing self-supervised image segmentation procedure with an additional supervisory input. Obstacles and roads may differ in appearance at distance because of illumination and texture frequency properties. Reverse optical flow is added as an input to the image segmentation technique to find examples of a region of interest at previous times in the past. This provides representations of this region at multiple scales and allows the robot to better determine where more examples of this class appear in the image.
The Space and Naval Warfare Systems Center, San Diego has been involved in the continuing development of obstacle avoidance for unmanned surface vehicles (USVs) towards the aim of a high level of autonomous navigation. An autonomous USV can fulfill a variety of missions and applications that are of increasing interest for the US Navy and other Department of Defense and Department of Homeland Security organizations. The USV obstacle avoidance package is being developed first by accurately creating a world model based on various sensors such as vision, radar, and nautical charts. Then, with this world model the USV can avoid obstacles with the use of a far-field deliberative obstacle avoidance component and a near-field reactive obstacle avoidance component. This paper addresses the advances made in USV obstacle avoidance during the last two years.
The optical properties of holographic kinoforms are described. It is shown that paraxial designs are not adequate for f/Nos. less than F/10. A nonparaxial design is introduced that retains the high diffraction efficiency of the paraxial designs, yet also produces an unaberrated diffracted wavefront for the design wavelength. Aberration calculations and computer calculations, based on the Huygens-Fresnel principle, of the point spread functions for these elements show the necessity of using the nonparaxial design. Specifications for a surface profile that takes account of the finite thickness of the diffracting surface are given. A model for kinoforms which can be used in optical design programs is proposed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.