Scene perception and traversability analysis are real challenges for autonomous driving systems. In the context of off-road autonomy, there are additional challenges due to the unstructured environments and the existence of various vegetation types. It is necessary for the Autonomous Ground Vehicles (AGVs) to be able to identify obstacles and load-bearing surfaces in the terrain to ensure a safe navigation (McDaniel et al. 2012). The presence of vegetation in off-road autonomy applications presents unique challenges for scene understanding: 1) understory vegetation makes it difficult to detect obstacles or to identify load-bearing surfaces; and 2) trees are usually regarded as obstacles even though only trunks of the trees pose collision risk in navigation. The overarching goal of this dissertation was to study traversability analysis in unstructured forested terrains for off-road autonomy using LIDAR data. More specifically, to address the aforementioned challenges, this dissertation studied the impacts of the understory vegetation density on the solid obstacle detection performance of the off-road autonomous systems. By leveraging a physics-based autonomous driving simulator, a classification-based machine learning framework was proposed for obstacle detection based on point cloud data captured by LIDAR. Features were extracted based on a cumulative approach meaning that information related to each feature was updated at each timeframe when new data was collected by LIDAR. It was concluded that the increase in the density of understory vegetation adversely affected the classification performance in correctly detecting solid obstacles. Additionally, a regression-based framework was proposed for estimating the understory vegetation density for safe path planning purposes according to which the traversabilty risk level was regarded as a function of estimated density. Thus, the denser the predicted density of an area, the higher the risk of collision if the AGV traversed through that area. Finally, for the trees in the terrain, the dissertation investigated statistical features that can be used in machine learning algorithms to differentiate trees from solid obstacles in the context of forested off-road scenes. Using the proposed extracted features, the classification algorithm was able to generate high precision results for differentiating trees from solid obstacles. Such differentiation can result in more optimized path planning in off-road applications.

No description available.

Military reconnaissance and surveillance (R&S) missions are a crucial ingredient in overall mission safety and success. Proper intelligence will provide the ability to counter and neutralize enemy positions and attacks. Accurate detection and identification of threatening targets is one the driving forces behind good R&S intelligence. Understanding this ability and how it is affected by possible field conditions (i.e., motion) was the primary focus of this study. Motion is defined in the current study as the perceived forward self-motion of unmanned ground vehicle (UGV) also called optical flow. For the purpose of this examination, both optical flow and the presence of a foil were manipulated. I examined how optical flow, perceived from an on-board frontal camera on a UGV, affected target detection and identification. The interaction of optical flow and foil distraction, as well as the level of influence each independently had on target detection and identification, were the principle examinations. The effects that were originally predicted for the influence of optical flow on the visual search and identification task were not supported. Across manipulations of optical flow (i.e., present, not present), detection and identification were not significantly different, suggesting that the interruption rates of optical flow were ineffective at 29 frames per second (fps). The most interesting finding in the data set was, in fact, related to the recognition measure. Participants were asked to classify the tank in which they had detected in the environment as either a target or non-target. When under conditions of non-optical flow, participants correctly rejected a foil tank as not being their target more often than they accepted the target as their actual target. These results, however, only appeared to have had an effect in the non-optical flow condition. Further research should be conducted to properly evaluate the effects of varying frame rate interruption on the perception of optical flow. This will subsequently lead to an understanding of the phenomenon that is optical flow, and how it ultimately affects detection and identification tasks.

No description available.

No description available.

Autonomous navigation of mobile robots through unstructured terrain presents many challenges. The task becomes even more difficult with increasing obstacle density, at higher speeds, and when a priori knowledge of the terrain is not available. Reactive navigation schemas are often dismissed as overly simplistic or considered to be inferior to deliberative approaches for off-road navigation. The Potential Field algorithm has been a popular reactive approach for low speed, highly maneuverable mobile robots. However, as vehicle speeds increase, Potential Fields becomes less effective at avoiding obstacles. The traditional shortcomings of the Potential Field approach can be largely overcome by using dynamically expanding perception zones to help track objects of immediate interest. This newly developed technique is hereafter referred to as the Dynamic Expanding Zones (DEZ) algorithm. In this approach, the Potential Field algorithm is used for waypoint navigation and the DEZ algorithm is used for obstacle avoidance. This combination of methods facilitates high-speed navigation in obstacle-rich environments at a fraction of the computational cost and complexity of deliberative methods. The DEZ reactive navigation algorithm is believed to represent a fundamental contribution to the body of knowledge in the area of high-speed reactive navigation. This method was implemented on the Virginia Tech DARPA Grand Challenge vehicles. The results of this implementation are presented as a case study to demonstrate the efficacy of the newly developed DEZ approach. / Master of Science

Energy efficiency is a driving factor in modern electronic design particularly in power conversion where conversion losses directly set the upper limit of system efficiency. A wide variety of commercially available DC-DC conversion elements have inefficiencies in the 90-97% range. The efficiency range of most common commercial-off-the-shelf (COTS) power supplies is 75-85%, highlighting the fact that COTS power supplies have not kept pace with efficiency improvements of modern conversion elements. Unmanned ground vehicles (UGVs) is an application where efficiency can be crucial in extending tight power budgets. In autonomous ground vehicles, geographic diversity with regard to sensor location is inherent because sensor orientation and placement are crucial to performance. Sensor power, therefore, is also distributed by nature of the devices being supplied. This thesis presents the design and evaluation of a smart power module used to implement a distributed power network in an autonomous ground vehicle. The module conversion element demonstrated an average efficiency of 96.7% for loads from 1-4A. Current monitoring and an adjustable output current limit were provided through a second circuit board within the same module enclosure. The module processing element sends periodic updates and receives commands over a CAN bus. The smart power modules successfully supply critical sensing and communication components in an operational autonomous ground vehicle. / Master of Science

Described is the development of a multispectral image labeling system with emphasis on Unmanned Ground Vehicles(UGVs). UGVs operating in unstructured environments face significant problems detecting viable paths when LIDAR is the sole source for perception. Promising advances in computer vision and machine learning has shown that multispectral imagery can be effective at detecting materials in unstructured environments [1][2][3][4][5][6]. This thesis seeks to extend previous work[6][7] by performing pixel level classification with multispectral features and texture. First the images are spatially registered to create a multispectral image cube. Visual, near infrared, shortwave infrared, and visible/near infrared polarimetric data are considered. The aligned images are then used to extract features which are fed to machine learning algorithms. The class list includes common materials present in rural and urban scenes such as vehicles, standing water, various forms of vegetation, and concrete. Experiments are conducted to explore the data requirement for a desired performance and the selection of a hyper-parameter for the textural features. A complete system is demonstrated, progressing from the data collection and labeling to the analysis of the classifier performance. / Master of Science

Recent advances in technology have enabled the development of truly autonomous ground vehicles capable of performing complex navigation tasks. As a result, the demand for practical unmanned ground vehicle (UGV) systems has increased dramatically in recent years. Central to these developments is maturation of emerging mobile robotic intelligent and autonomous capability. While the progress UGV technology has been substantial, there are many challenges that still face unmanned vehicle system developers. Foremost is the improvement of perception hardware and intelligent software that supports the evolution of UGV capability. The development of a Next-generation Experimentation Robotic Vehicle (NERV) serves to provide a small UGV baseline platform supporting experimentation focused on progression of the state-of-the-art in unmanned systems. Supporting research and user feedback highlight the needs that provide justification for an advanced small UGV research platform. Primarily, such a vehicle must be based upon open and technology independent system architecture while exhibiting improved mobility over relatively structured terrain. To this end, a theoretical kinematic model is presented for a novel two-body multi degree-of-freedom, four-wheel drive, small UGV platform. The efficacy of the theoretical kinematic model was validated through computer simulation and experimentation on a full-scale proof-of-concept mobile robotic platform. The kinematic model provides the foundation for autonomous multi-body control. Further, a modular system level design based upon the concepts of the Joint Architecture for Unmanned Systems (JAUS) is offered as an open architecture model providing a scalable system integration solution. Together these elements provide a blueprint for the development of a small UGV capable of supporting the needs of a wide range of leading-edge intelligent system research initiatives. / Master of Science

Teleoperation of an unmanned vehicle is a challenging task for human operators especially when the vehicle is out of line of sight. Improperly designed and applied display interfaces directly affect the operation performance negatively and even can result in catastrophic failures. If these teleoperation missions are human-critical then it becomes more important to improve the operator performance by decreasing workload, managing stress and improving situational awareness. This research aims to develop electrical and control system of an unmanned ground vehicle (UGV) using an All-Terrain Vehicle (ATV) and validate the development with investigation of the effects of force feedback devices on the teleoperation performance. After development, teleoperation tests are performed to verify that force feedback generated from the dynamic obstacle information of the environment improves teleoperation performance. Results confirm this statement and the developed UGV is verified for future research studies. Development of UGV, algorithms and real system tests are included in this thesis.