Search Constraints

Start Over
Filtering by: Creator Baehr, Matthew M. Remove constraint Creator: Baehr, Matthew M. Committee Member Hollinger, Geoff Remove constraint Committee Member: Hollinger, Geoff

Search Results

  • Unmanned aircraft systems for bridge inspection : testing and developing end-to-end operational workflow

    Creator:
    Gillins, Matthew N.
    Abstract:
    Bridge inspections are vital for monitoring the health and serviceability of transportation infrastructure throughout the world. However, inspections can be logistically-challenging, expensive, and dangerous. For example, inspections may require climbing, as well as the use of scaffolding, ladders, rescue boats, bucket trucks, and/or under-bridge inspection vehicles. Small, multirotor unmanned aircraft...
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Matthew N. Gillins for

  • 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:
    to become a multi-objective MDP with m different rewards. Each reward consist of the sum of the

  • From running birds to walking robots : optimization as a unifying framework for dynamic bipedal locomotion

    Creator:
    Hubicki, Christian M.
    Abstract:
    Bipedal locomotion is a complex phenomenon to understand and control, making it difficult for legged robots to achieve the speed, agility, efficiency, and robustness of their animal counterparts. This thesis argues for the use of numerical optimization to investigate and implement bipedal control as it applies to biology, dynamical models,...
    Resource Type:
    Dissertation
    Full Text:
    Unifying Framework for Dynamic Bipedal Locomotion AN ABSTRACT OF THE THESIS OF Christian M. Hubicki

  • Learning in Complex Domains : Leveraging Multiple Rewards through Alignment

    Creator:
    Klinkhammer, Eric R.
    Abstract:
    In this thesis, we introduce alignment-based algorithms for improving the performance of reinforcement learning solutions for problems where the reward signal cannot be collapsed into a single number. Many real world problems require an agent to balance performance, longevity, and safety, and do so across different timelines. The key to...
    Resource Type:
    Masters Thesis

  • Counterfactual thinking applied to multiagent systems

    Creator:
    Zerbel, Nicholas
    Abstract:
    Multiagent approaches are well suited to designing autonomous solutions for systems that feature complex interactions between many individuals such as in autonomous traffic systems and multi-robot exploration systems. However, creating autonomous agents that function effectively in these systems is a challenging task. In these complex environments, agents need informative reward...
    Resource Type:
    Dissertation

  • Robust Long Term Autonomy Through Local Behaviors

    Creator:
    Yates, Connor L.
    Abstract:
    Multi-robot teams offer promising solutions for many long term deployments in remote and dangerous domains, such as extraterrestrial or underseas exploration. However, long term deployments present many problems preventing robot teams from operating effectively. Learning over long time scales is makes it difficult to assign credit to robots' actions, as...
    Resource Type:
    Dissertation

  • 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

  • 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:
    , Christopher Buss, Lawrence Neal, Matthew Olson, Michael Slater, Robert DeBortoli, Risheek Garrepalli, Saeed

  • Why Use Ankles? An Optimization Approach to Discover Energetic Benefits of Ankles in Steady Locomotion

    Creator:
    Hector, Michael J.
    Abstract:
    Design and control of legged robots is a popular field in the pursuit of building robots that can be as mobile as humans. While much effort is put into understanding how to control the dynamics of these legs, less effort is focused on designing and controlling robot ankles. Ankles on...
    Resource Type:
    Masters Thesis
    Full Text:
    equations of motion, ẍ = xFLeg mr (2.3) ÿ = yFLeg mr − g (2.4) where m is the body mass and g is the

  • Providing Informative Feedback for Learning in Tightly Coupled Multiagent Domains

    Creator:
    Rockefeller, Golden C.
    Abstract:
    Autonomous agents that sense, decide, act, and coordinate effectively with each other are critical in many real-world domains such as autonomous driving, search and rescue missions, air traffic management, and underwater or deep space exploration. All such domains share a key difficulty: though high-level mission goals are clear to system...
    Resource Type:
    Dissertation