Matching Items (5)
Filtering by
- All Subjects: Machine Learning
Description
There has been a vast increase in applications of Unmanned Aerial Vehicles (UAVs) in civilian domains. To operate in the civilian airspace, a UAV must be able to sense and avoid both static and moving obstacles for flight safety. While indoor and low-altitude environments are mainly occupied by static obstacles, risks in space of higher altitude primarily come from moving obstacles such as other aircraft or flying vehicles in the airspace. Therefore, the ability to avoid moving obstacles becomes a necessity
for Unmanned Aerial Vehicles.
Towards enabling a UAV to autonomously sense and avoid moving obstacles, this thesis makes the following contributions. Initially, an image-based reactive motion planner is developed for a quadrotor to avoid a fast approaching obstacle. Furthermore, A Dubin’s curve based geometry method is developed as a global path planner for a fixed-wing UAV to avoid collisions with aircraft. The image-based method is unable to produce an optimal path and the geometry method uses a simplified UAV model. To compensate
these two disadvantages, a series of algorithms built upon the Closed-Loop Rapid Exploratory Random Tree are developed as global path planners to generate collision avoidance paths in real time. The algorithms are validated in Software-In-the-Loop (SITL) and Hardware-In-the-Loop (HIL) simulations using a fixed-wing UAV model and in real flight experiments using quadrotors. It is observed that the algorithm enables a UAV to avoid moving obstacles approaching to it with different directions and speeds.
for Unmanned Aerial Vehicles.
Towards enabling a UAV to autonomously sense and avoid moving obstacles, this thesis makes the following contributions. Initially, an image-based reactive motion planner is developed for a quadrotor to avoid a fast approaching obstacle. Furthermore, A Dubin’s curve based geometry method is developed as a global path planner for a fixed-wing UAV to avoid collisions with aircraft. The image-based method is unable to produce an optimal path and the geometry method uses a simplified UAV model. To compensate
these two disadvantages, a series of algorithms built upon the Closed-Loop Rapid Exploratory Random Tree are developed as global path planners to generate collision avoidance paths in real time. The algorithms are validated in Software-In-the-Loop (SITL) and Hardware-In-the-Loop (HIL) simulations using a fixed-wing UAV model and in real flight experiments using quadrotors. It is observed that the algorithm enables a UAV to avoid moving obstacles approaching to it with different directions and speeds.
ContributorsLin, Yucong (Author) / Saripalli, Srikanth (Thesis advisor) / Scowen, Paul (Committee member) / Fainekos, Georgios (Committee member) / Thangavelautham, Jekanthan (Committee member) / Youngbull, Cody (Committee member) / Arizona State University (Publisher)
Created2015
Description
There has been exciting progress in the area of Unmanned Aerial Vehicles (UAV) in the last decade, especially for quadrotors due to their nature of easy manipulation and simple structure. A lot of research has been done on achieving autonomous and robust control for quadrotors. Recently researchers have been utilizing linear temporal logic as mission specification language for robot motion planning due to its expressiveness and scalability. Several algorithms have been proposed to achieve autonomous temporal logic planning. Also, several frameworks are designed to compose those discrete planners and continuous controllers to make sure the actual trajectory also satisfies the mission specification. However, most of these works use first-order kinematic models which are not accurate when quadrotors fly at high speed and cannot fully utilize the potential of quadrotors.
This thesis work describes a new design for a hierarchical hybrid controller that is based on a dynamic model and seeks to achieve better performance in terms of speed and accuracy compared with some previous works. Furthermore, the proposed hierarchical controller is making progress towards guaranteed satisfaction of mission specification expressed in Linear Temporal Logic for dynamic systems. An event-driven receding horizon planner is also utilized that aims at distributed and decentralized planning for large-scale navigation scenarios. The benefits of this approach will be demonstrated using simulations results.
This thesis work describes a new design for a hierarchical hybrid controller that is based on a dynamic model and seeks to achieve better performance in terms of speed and accuracy compared with some previous works. Furthermore, the proposed hierarchical controller is making progress towards guaranteed satisfaction of mission specification expressed in Linear Temporal Logic for dynamic systems. An event-driven receding horizon planner is also utilized that aims at distributed and decentralized planning for large-scale navigation scenarios. The benefits of this approach will be demonstrated using simulations results.
ContributorsZhang, Xiaotong (Author) / Fainekos, Georgios (Thesis advisor) / Ben Amor, Heni (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2016
Description
The goal of reinforcement learning is to enable systems to autonomously solve tasks in the real world, even in the absence of prior data. To succeed in such situations, reinforcement learning algorithms collect new experience through interactions with the environment to further the learning process. The behaviour is optimized by maximizing a reward function, which assigns high numerical values to desired behaviours. Especially in robotics, such interactions with the environment are expensive in terms of the required execution time, human involvement, and mechanical degradation of the system itself. Therefore, this thesis aims to introduce sample-efficient reinforcement learning methods which are applicable to real-world settings and control tasks such as bimanual manipulation and locomotion. Sample efficiency is achieved through directed exploration, either by using dimensionality reduction or trajectory optimization methods. Finally, it is demonstrated how data-efficient reinforcement learning methods can be used to optimize the behaviour and morphology of robots at the same time.
ContributorsLuck, Kevin Sebastian (Author) / Ben Amor, Hani (Thesis advisor) / Aukes, Daniel (Committee member) / Fainekos, Georgios (Committee member) / Scholz, Jonathan (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2019
Description
Imitation learning is a promising methodology for teaching robots how to physically interact and collaborate with human partners. However, successful interaction requires complex coordination in time and space, i.e., knowing what to do as well as when to do it. This dissertation introduces Bayesian Interaction Primitives, a probabilistic imitation learning framework which establishes a conceptual and theoretical relationship between human-robot interaction (HRI) and simultaneous localization and mapping. In particular, it is established that HRI can be viewed through the lens of recursive filtering in time and space. In turn, this relationship allows one to leverage techniques from an existing, mature field and develop a powerful new formulation which enables multimodal spatiotemporal inference in collaborative settings involving two or more agents. Through the development of exact and approximate variations of this method, it is shown in this work that it is possible to learn complex real-world interactions in a wide variety of settings, including tasks such as handshaking, cooperative manipulation, catching, hugging, and more.
ContributorsCampbell, Joseph (Author) / Ben Amor, Heni (Thesis advisor) / Fainekos, Georgios (Thesis advisor) / Yamane, Katsu (Committee member) / Kambhampati, Subbarao (Committee member) / Arizona State University (Publisher)
Created2021
Description
Many real-world engineering problems require simulations to evaluate the design objectives and constraints. Often, due to the complexity of the system model, simulations can be prohibitive in terms of computation time. One approach to overcome this issue is to construct a surrogate model, which approximates the original model. The focus of this work is on the data-driven surrogate models, in which empirical approximations of the output are performed given the input parameters. Recently neural networks (NN) have re-emerged as a popular method for constructing data-driven surrogate models. Although, NNs have achieved excellent accuracy and are widely used, they pose their own challenges. This work addresses two common challenges, the need for: (1) hardware acceleration and (2) uncertainty quantification (UQ) in the presence of input variability. The high demand in the inference phase of deep NNs in cloud servers/edge devices calls for the design of low power custom hardware accelerators. The first part of this work describes the design of an energy-efficient long short-term memory (LSTM) accelerator. The overarching goal is to aggressively reduce the power consumption and area of the LSTM components using approximate computing, and then use architectural level techniques to boost the performance. The proposed design is synthesized and placed and routed as an application-specific integrated circuit (ASIC). The results demonstrate that this accelerator is 1.2X and 3.6X more energy-efficient and area-efficient than the baseline LSTM. In the second part of this work, a robust framework is developed based on an alternate data-driven surrogate model referred to as polynomial chaos expansion (PCE) for addressing UQ. In contrast to many existing approaches, no assumptions are made on the elements of the function space and UQ is a function of the expansion coefficients. Moreover, the sensitivity of the output with respect to any subset of the input variables can be computed analytically by post-processing the PCE coefficients. This provides a systematic and incremental method to pruning or changing the order of the model. This framework is evaluated on several real-world applications from different domains and is extended for classification tasks as well.
ContributorsAzari, Elham (Author) / Vrudhula, Sarma (Thesis advisor) / Fainekos, Georgios (Committee member) / Ren, Fengbo (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2021