Traditional autonomy among robotic and other artificial agents was accomplished via automated planning methods that found a viable sequence of actions, which, if executed by an agent, would result in the successful completion of the given task(s). However, many tasks that we would like robotic agents to perform involve goals that are complex, poorly-defined, or hard to specify. Furthermore, significant amounts of data or computation are required for agents to reach reasonable performance. As a result, autonomous systems still rely on human operators to play a supervisory role to ensure that robotic operations are completed quickly and successfully. The presented work aims to improve the traditional methods of robot autonomy by developing an intuitive means for(human operators to adapt/mold the behaviors and decision making of autonomous agents) autonomous agents to leverage the flexibility and expertise of human end users. Specifically, this work shows the results of three machine learning-based approaches for modifying and extending established robot navigation behaviors and skills through human demonstration. Our first project combines Imitation learning with classical navigation software to achieve long-horizon planning and navigation that follows navigation rules specified by a human user. We show that this method can adapt a robot's navigation behavior to become more like that of a human demonstrator. Moreover, for a minimal amount of demonstration data, we find that this approach outperforms recent baselines in both navigation success rate and trajectory similarity to the demonstrator. In the second project, we introduce a method of communicating complex skills over a short-horizon task. Specifically, we explore using imitation learning to teach a robot the complex skill needed to safely navigate through negative obstacles in simulation. We find that this proposed method could imitate complex navigation behaviors and generalize to novel environments in simulation with minimal demonstration. Furthermore, we find that this method compares favorably to a classical motion planning algorithm which was modified to assign traversal cost based on the terrain slope local to the robot's current pose. Finally, we demonstrate a practical implementation of the second approach in a real-world environment. We show that the proposed method results in a policy that can generalize across differently shaped obstacles and across simulation and reality. Moreover, we show that the proposed method still outperforms the classical motion planning algorithm when tasked to navigate negative obstacles in the real world. / Doctor of Philosophy / With the rapid advancement of computing power and growing technical literacy of the general public, the tasks that robots should be able to accomplish have multiplied. Robots can, however, be limited by the human ability to effectively convey how tasks should be performed. For example, autonomous robot navigation to a specified path planning software suite that generates feasible and obstacle-free trajectories through a cluttered environment. While these modules can be modified to meet task-specific constraints and user preferences, current modification procedures require substantial effort on the part of an expert roboticist with a great deal of technical training. The desired tasks and skills are difficult to effectively convey in a machine legible format. These tasks often require technical expertise in multiple mechatronic disciplines and hours of hand tuning that the typical end user does not have. In this dissertation, we examine methods that directly leverage human users to teach robots how to perform tasks that are generally difficult to specify pragmatically. We focus on methods that allow human users to extend established robot navigation behaviors and skills by demonstrating their own preferred approaches. We evaluate the performances of our proposed approaches in terms of navigation success rate, adherence to the demonstrated behavior, and their ability to apply what they have learned to novel environments. Moreover, we showed that our approaches compare favorably to recent machine learning-based approaches to autonomous navigation, and classical navigation techniques with respect to these metrics.

Automation of hydraulic earth moving and construction equipment is of prime economic and social importance in today's marketplace. A human operator can be replaced or augmented with a robotic system when the job is too dull, dirty or dangerous. There are a myriad of applications in both Government and Industry that could benefit from augmenting or replacing an operator of hydraulic equipment with an intelligent robotic system. A specific important situation is the removal of unexploded ordnance (UXO). The removal of UXO is a troubling environmental problem that plagues people around the world. This document addresses the danger that UXO pose to military groups in applications such as active range clearance and disposal of unexploded or dud munitions. Disposing of these munitions is a difficult problem, which first begins by determining their location. The process can be aided through the use of teleoperated hydraulic equipment, which allows the operator to be located at a safe distance from these munitions. In the past, converting a large piece of hydraulic construction equipment for teleoperated use has been an expensive task. An important result of this research is demonstrating that through readily available commercial products and existing design methodologies, such robotic tasks can be accomplished at relatively low cost and in a timely, reliable fashion. / Master of Science

In this paper I describe a motion planning technique for intelligent ground vehicles. The technique is an implementation of a path selection algorithm based on fuzzy inference. The approach extends on the motion planning algorithm known as driving with tentacles. The selection of the tentacle (a drivable path) to follow relies on the calculation of a weighted cost function for each tentacle in the current speed set, and depends on variables such as the distance to the desired position, speed, and the closeness of a tentacle to any obstacles. A Matlab simulation and the practical implementation of the fuzzy inference rule on a Clearpath Husky robot within the Robot Operating System (ROS) framework are provided.

To teleoperate an unmanned vehicle a rich set of information should be gathered from surroundings.These systems use sensors which sends high amounts of data and processing the data in CPUs can be time consuming. Similarly, the algorithms that use the data may work slow because of the amount of the data. The solution is, preprocessing the data taken from the sensors on the vehicle and transmitting only the necessary parts or the results of the preprocessing. In this thesis a 180 degree laser scanner at the front end of an unmanned ground vehicle (UGV) tilted up and down on a horizontal axis and point clouds constructed from the surroundings. Instead of transmitting this data directly to the path planning or obstacle avoidance algorithms, a preprocessing stage has been run. In this preprocess rst, the points belonging to the ground plane have been detected and a simplied version of ground has been constructed then the obstacles have been detected. At last, a simplied ground plane as ground and simple primitive geometric shapes as obstacles have been sent to the path planning algorithms instead of sending the whole point cloud.

<p>The goal of this thesis is to make an unmanned ground vehicle (UGV) follow a given reference trajectory, without colliding with obstacles in its way. This thesis will especially focus on modeling and controlling the UGV, which is based on the power wheelchair Trax from Permobil.</p><p>In order to make the UGV follow a given reference trajectory without colliding, it is crucial to know the position of the UGV at all times. Odometry is used to estimate the position of the UGV relative a starting point. For the odometry to work in a satisfying way, parameters such as wheel radii and wheel base have to be calibrated. Two control signals are used to control the motion of the UGV, one to control the speed and one to control the steering angles of the two front wheels. By modeling the motion of the UGV as a function of the control signals, the motion can be predicted. A path following algorithm is developed in order to make the UGV navigate by maps. The maps are given in advance and do not contain any obstacles. A method to handle obstacles that comes in the way is presented.</p>

The goal of this thesis is to make an unmanned ground vehicle (UGV) follow a given reference trajectory, without colliding with obstacles in its way. This thesis will especially focus on modeling and controlling the UGV, which is based on the power wheelchair Trax from Permobil. In order to make the UGV follow a given reference trajectory without colliding, it is crucial to know the position of the UGV at all times. Odometry is used to estimate the position of the UGV relative a starting point. For the odometry to work in a satisfying way, parameters such as wheel radii and wheel base have to be calibrated. Two control signals are used to control the motion of the UGV, one to control the speed and one to control the steering angles of the two front wheels. By modeling the motion of the UGV as a function of the control signals, the motion can be predicted. A path following algorithm is developed in order to make the UGV navigate by maps. The maps are given in advance and do not contain any obstacles. A method to handle obstacles that comes in the way is presented.

The transient thermal response of a 15-cell, 48 volt, lithium-ion battery pack for an unmanned ground vehicle was simulated with ANSYS Fluent. Heat generation rates and specific heat capacity of a single cell were experimentally measured and used as input to the thermal model. A heat generation load was applied to each battery and natural convection film boundary conditions were applied to the exterior of the enclosure. The buoyancy-driven natural convection inside the enclosure was modeled along with the radiation heat transfer between internal components. The maximum temperature of the batteries reached 65.6 °C after 630 seconds of usage at a simulated peak power draw of 3,600 watts or roughly 85 amps. This exceeds the manufacturer's maximum recommended operating temperature of 60 °C. The pack was redesigned to incorporate a passive thermal management system consisting of a composite expanded graphite matrix infiltrated with a phase-changing paraffin wax. The redesigned battery pack was similarly modeled, showing a decrease in the maximum temperature to 50.3 °C after 630 seconds at the same power draw. The proposed passive thermal management system kept the batteries within their recommended operating temperature range.

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.

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

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