No abstract

Abstract. Autonomous navigation in cross-country environments presents many new challenges with respect to more traditional, urban environments. The lack of highly structured components in the scene complicates the design of even basic functionalities such as obstacle detection. In addition to the geometric description of the scene, terrain typing is also an important component of the perceptual system. Recognizing the different classes of terrain and obstacles enables the path planner to choose the most efficient route toward the desired goal.This paper presents new sensor processing algorithms that are suitable for cross-country autonomous navigation. We consider two sensor systems that complement each other in an ideal sensor suite: a color stereo camera, and a single axis ladar. We propose an obstacle detection technique, based on stereo range measurements, that does not rely on typical structural assumption on the scene (such as the presence of a visible ground plane); a color-based classification system to label the detected obstacles according to a set of terrain classes; and an algorithm for the analysis of ladar data that allows one to discriminate between grass and obstacles (such as tree trunks or rocks), even when such obstacles are partially hidden in the grass. These algorithms have been developed and implemented by the Jet Propulsion Laboratory (JPL) as part of its involvement in a number of projects sponsored by the US Department of Defense, and have enabled safe autonomous navigation in high-vegetated, off-road terrain.

In this work, we classify 3D aerial LiDAR height data into roads, grass, buildings, and trees using a supervised parametric classification algorithm. Since the terrain is highly undulating, we subtract the terrain elevations using digital elevation models (DEMs, easily

The Demo III program has as its primary focus the development

In this work we characterize the energy consumption of a visual sensor network testbed. Each node in the testbed consists of a "single-board computer", namely Crossbow's Stargate, equipped with a wireless network card and a webcam. We assess energy consumption of activities representative of the target application (e.g., perimeter surveillance) using a benchmark that runs (individual and combinations of) "basic" tasks such as processing, flash memory access, image acquisition, and communication over the network. In our characterization, we consider the various hardware states the system switches through as it executes these benchmarks, e.g., different radio modes (sleep, idle, transmission, reception), and webcam modes (off, on, and acquiring image). We report both steady-state and transient energy consumption behavior obtained by direct measurements of current with a digital multimeter. We validate our measurements against results obtained using the Stargate's on-board energy consumption measuring capabilities.