Search Constraints

Start Over
Filtering by: Creator Bills, Debra T. Remove constraint Creator: Bills, Debra T. Committee Member Smart, Bill Remove constraint Committee Member: Smart, Bill

Search Results

  • The Assessment of a Robotic Cookstove Feeder to Assist Human Operators in Cookstove Testing

    Creator:
    Jou, Matthew
    Abstract:
    This study aims to explore whether a robotic cookstove feeder can sufficiently reduce variability between tests of a cookstove, produces statistically similar firepower and measured emissions rates, and reduce tester interaction time during standard cookstove testing as compared to a trained human operator. A series of modified ISO/FDIS 19867-1 testing...
    Resource Type:
    Honors College Thesis

  • One Service Robot’s Exploration of Entertainment Methods During COVID-19

    Creator:
    Tsai, Yao-Lin
    Abstract:
    The study focuses on how to use entertainment method approach to prompt people with best practices for COVID safety. During COVID times, there have been many robots deployed in public places such as social distancing enforcer or a robot that provide facial masks, but few investigations have been done to...
    Resource Type:
    Capstone Project
    Full Text:
    Robotics (2020), under preparation. [23] T Umetani, A Nadamoto, and T Kitamura. 2017. Manzai robots

  • 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:
    taking action a while in state s will lead to state s′, T (s, a, s′), and reward function describing

  • On surrogate supervision multi-view learning

    Creator:
    Jin, Gaole
    Abstract:
    Data can be represented in multiple views. Traditional multi-view learning methods (i.e., co-training, multi-task learning) focus on improving learning performance using information from the auxiliary view, although information from the target view is sufficient for learning task. However, this work addresses a semi-supervised case of multi-view learning, the surrogate supervision...
    Resource Type:
    Masters Thesis
    Full Text:
    . Bill Smart for serving as committee members in my defence., and Dr. Yevgeniy Kovchegov for attending

  • Multi-Robot Coordination : Applications in Orchard Bin Management and Informative Path Planning

    Creator:
    Zhang, Yawei
    Abstract:
    Efficient coordination is desired for multi-robot systems in many scenarios. In this research, we first provide a multi-robot system to help human workers during tree fruit harvest. We present an auction-based method to coordinate a team of self-propelled bin carriers to retrieve fruit bins. Second, we propose a more general...
    Resource Type:
    Masters Thesis
    Full Text:
    600 700 800 900 1000 1100 Robots T o ta l F in is h S te p s Baseline Auction

  • Analyzing Human Gaze Patterns During Grasping Tasks To Advance Robotic Grasping

    Creator:
    Allani, Sai Krishna
    Abstract:
    There is a strong interest in the robotics community in learning how humans grasp and manipulate objects, partly because robots need to operate in human environments and partly because humans are currently much better in physical interaction tasks than robots. This thesis seeks to identify the human heuristics for grasping...
    Resource Type:
    Masters Thesis
    Full Text:
    did a two sample T-test at 5% significance level between all the three stage across both condition

  • Grasping complex casting shapes with an underactuated parallel jaw gripper on an industrial robot

    Creator:
    Carpenter, Ryan Joseph
    Abstract:
    Steel foundries are in great need of automation as current operations involve many hazardous manual tasks. Automating foundry operations is very challenging due to the variety of tasks that must be performed on physical objects that vary significantly in size, shape, and weight. This thesis focuses on robotically automating the...
    Resource Type:
    Masters Thesis
    Full Text:
    perturbations to the grasp on a physi- cal robot. *Indicates significant (t-test p value <.05) difference

  • Using RUBI to partition agents in air traffic problems with hard constraints and reward shaping

    Creator:
    Curran, William
    Abstract:
    Air traffic flow management over the U.S. airpsace is a difficult problem. Current management approaches lead to hundreds of thousands of hours of delay, costing billions of dollars annually. Weather and airport conditions may instigate this delay, but routing decisions balancing delay with congestion contribute significantly to the propagation of...
    Resource Type:
    Masters Thesis
    Full Text:
    ← 1 to Episodes do 4: s ← initialize 5: for t ← 1 to T imesteps do 6: a ← argmaxaVt(a) with

  • Robotic Machining Fundamentals for Casting Defect Removal

    Creator:
    Biederman, Moriah
    Abstract:
    In the past half century, industrial robots have developed a strong presence in manufacturing. They now commonly perform tasks such as materials handling, assembly, welding, and painting. Unfortunately robotic machining tasks have seen limited deployments. The majority of machining robots are designed for soft materials like wood or plastic and...
    Resource Type:
    Masters Thesis

  • 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
    Full Text:
    probability that the agent will take a particular action, at a particular time step t ∈ N, in response to