Search Constraints

Start Over
Filtering by: Creator Hollinger, Geoffrey A. Remove constraint Creator: Hollinger, Geoffrey A. Committee Member Hollinger, Geoff Remove constraint Committee Member: Hollinger, Geoff

Search Results

  • Multi-Reward Learning and Sparse Rewards

    Creator:
    Christopher, Reid M.
    Abstract:
    Reinforcement learning has made impressive strides in solving problems in challenging domains, but problems are increasingly being described with sparse rewards. Sparse rewards directly reduce the rate at which useful feedback is provided to the learner and make it difficult to distinguish between what specific actions led to the reception...
    Resource Type:
    Capstone Project
    Full Text:
    very sparse reward signals. When trying to learn from a sparse reward signal, it greatly reduces the

  • Coordination for Scalable Multiple Robot Planning Under Temporal Uncertainty

    Creator:
    Marcon dos Santos, Gilberto
    Abstract:
    This dissertation incorporates coalition formation and probabilistic planning towards a domain-independent automated planning solution scalable to multiple heterogeneous robots in complex domains. The first research direction investigates the effectiveness of Task Fusion and introduces heuristics that improve task allocation and result in better quality plans, while requiring lower computational cost...
    Resource Type:
    Dissertation
    Full Text:
    writing. I would like to extend my sincere thanks to all my committee members, Drs. Geoffrey Hollinger

  • Human Performance with Multiple UAV Systems: Use Cases and Modeling

    Creator:
    Uriarte, Patrick A.
    Abstract:
    Commercial and public safety usage of Unmanned Aerial Vehicles in the National Airspace is currently restricted by federal regulation. The Federal Aeronautics Association is interested in modifying the restrictions; however, research is needed to study the human factor and required aptitude for a single human operating multiple UAVs. This Master’s...
    Resource Type:
    Capstone Project
    Full Text:
    1.1 Human Performance with Multiple UAV Systems: Use Cases and Modeling by Patrick A

  • Utilization of Robot Ankle Torque to Account for Foot Placement Error

    Creator:
    Bernards, Mitchell F.
    Abstract:
    Modern walking robots have shown that dynamic gaits can be achieved without ankle motors. It seems logical that the additional control authority that they provide can be used to improve the stability of the walking gait against foot placement errors caused by low level control. This thesis develops and compares...
    Resource Type:
    Honors College Thesis
    Full Text:
    by Mitchell F. Bernards A THESIS submitted to Oregon State University Honors College in partial

  • Real-Time Estimation and Prediction of Wave Excitation Forces for Wave Energy Control Applications

    Creator:
    Ling, Bradley A.
    Abstract:
    Wave energy is emerging as a new potential source for renewable energy generation. However, wave energy technology is not currently cost competitive with other more mature renewable energy sources such as wind and solar. One approach that researchers and developers are taking to reduce the cost of wave energy is...
    Resource Type:
    Masters Thesis
    Full Text:
    Forces for Wave Energy Control Applications AN ABSTRACT OF THE THESIS OF Bradley A. Ling for the

  • Artificial Swarm Control Through Learning Based Leadership

    Creator:
    Tuzel, Ovunc
    Abstract:
    Collective migration in animal groups is often guided by distributed leader agents that influence their peers by modulating their motion behaviors. Distributed leadership is a promising navigation strategy for artificial swarms, but designing the leaders’ controllers is difficult due to the swarm’s collective emergent behaviors. The presented research formulates a...
    Resource Type:
    Masters Thesis
    Full Text:
    Based Leadership Abstract approved: Julie A. Adams Collective migration in animal groups is often

  • Q-Network Policy Selection For Multiagent Learning

    Creator:
    Cook, Joshua
    Abstract:
    Controllers for robotic systems can be complex and difficult to write by hand. Learning offers an approach to improve a controller through direct feedback. Learning is not trivial, as the feedback does not tell the agent how to improve, only how well its current actions solve the given task. Learning...
    Resource Type:
    Honors College Thesis
    Full Text:
    systems can be complex and difficult to write by hand. Learning offers an approach to improve a controller

  • Methods for Detection and Recovery of Out-of-Distribution Examples

    Creator:
    Ratzlaff, Neale J.
    Abstract:
    Deep neural networks currently comprise the backbone of many applications where safety is a critical concern, for example: autonomous driving and medical diagnostics. Unfortunately these systems currently fail to detect out-of-distribution (OOD) inputs and can be prone to making dangerous errors when exposed to them. In addition, these same systems...
    Resource Type:
    Masters Thesis
    Full Text:
    currently comprise the backbone of many applications where safety is a critical concern, for example

  • Uncertainty in Deep Learning with Implicit Neural Networks

    Creator:
    Ratzlaff, Neale
    Abstract:
    The ability to extract uncertainties from predictions is crucial for the adoption of deep learning systems to safety-critical applications. Uncertainty estimates can be used as a failure signal, which is necessary for automating complex tasks where safety is a concern. Furthermore, current deep learning systems do not provide uncertainty estimates,...
    Resource Type:
    Dissertation
    Full Text:
    , Geoffrey Hollinger, and Stefano Ermon. Tom and Alan in particu- lar have provided consistent, invaluable

  • Design and Testing of a Tethered, Coaxial Rotor Micro Air Vehicle

    Creator:
    Shryer, Jacob R.
    Abstract:
    Unmanned Aerial System (UAS) technology is a rapidly developing technological marketspace. This thesis focuses on micro, tethered, coaxial UASs and the development of an electrically-tethered observation platform (ETOP). The thesis details the current status of the technology as well as current products on the market. Stability considerations, critical when adding...
    Resource Type:
    Honors College Thesis
    Full Text:
    Design and Testing of a Tethered, Coaxial Rotor Micro Air