Search Constraints

Start Over
Filtering by: Creator Geier, Joel E. Remove constraint Creator: Geier, Joel E. Degree Field Robotics Remove constraint Degree Field: Robotics

Search Results

  • Learning to coordinate in sparse asymmetric multiagent systems

    Creator:
    Dixit, Gaurav
    Abstract:
    Multiagent learning offers a rich framework to address challenging real-world problems such as remote exploration and healthcare coordination, which require autonomous agents to express elaborate interactions. To be effective in such systems, agents must collectively reason about and pursue high-level, long-term, and possibly nebulous objectives while adapting their strategy to...
    Resource Type:
    Dissertation
    Full Text:
    posterior distribution using Metropolis-Hastings (d). The new approximate posteriors (e), are a better

  • 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:
    rewards are. V (st) = E[ ∞∑ k=0 γkR(st+k)] (1) Q(st, at) = E[ ∞∑ k=0 γkR(st+k, at+k)] (2) Depending

  • Ballistic rebounds for wrapping a target with a casting manipulator

    Creator:
    Hill, Lucas P.
    Abstract:
    Casting manipulation in robotics is the act of launching a tethered projectile and using it to interact with the environment. One such interaction is wrapping a target. In this work, we identify throwing and tether control parameters for successfully wrapping a target with an end-weighted cable, evolving through a set...
    Resource Type:
    Masters Thesis
    Full Text:
    rebound, e = 0 is a perfectly inelas- tic rebound and e = 1 is perfectly elastic

  • Tackling Credit Assignment Using Memory and Multilevel Optimization for Multiagent Reinforcement Learning

    Creator:
    Khadka, Shauharda
    Abstract:
    There is growing commercial interest in the use of multiagent systems in real world applications. Some examples include inventory management in warehouses, smart homes, planetary exploration, search and rescue, air-traffic management and autonomous transportation systems. However, multiagent coordination is an extremely challenging problem. First, information relevant for coordination is often...
    Resource Type:
    Dissertation
    Full Text:
    flow into the network. (e) We add a read gate, which filters the amount of information read from memory

  • The Design Freedoms of a Novel Cable-Driven Manipulator

    Creator:
    Layng, Brian M.
    Abstract:
    Legged locomotion in robotics benefits from engineered hardware dynamics such as configuration-dependent, nonlinear transmissions and compliance. This thesis introduces a novel cable driven leg that allows the design of configuration-dependent transmission ratios while also permitting the addition of compliance in line with the cables to achieve compliant legged locomotion. The...
    Resource Type:
    Masters Thesis
    Full Text:
    20 25 30 35 40 45 50 55 60 65 70 To rq ue R eq ui re d by K ne e M ot or (N m

  • Decentralized Multi-Robot Exploration with Sparse Communication through Deep Imitation Learning

    Creator:
    Senewiratne, Yomal K.
    Abstract:
    We present a method for decentralized, multi-robot exploration in adverse environments where communication is minimal. A key conceptual feature of our method is enabling implicit coordination between robots by training a Convolutional Neural Network (CNN) as a heuristic for planning using Monte Carlo Tree Search (MCTS). Our method consists of...
    Resource Type:
    Masters Thesis
    Full Text:
    environment is represented by a navigation graph G with vertices V and edges E . We assume the vertices V are

  • Robust Reference-Free Sim-to-Real Reinforcement Learning for Bipedal Locomotion

    Creator:
    Siekmann, Jonah A.
    Abstract:
    In recent years, model-free Deep Reinforcement Learning (RL) has become an increasingly popular alternative to more traditional model-based or optimization-based control methods in solving robotic legged locomotion. However, deploying RL in the real world can be a significant undertaking. Constructing reward functions which compel controllers to learn the desired behavior...
    Resource Type:
    Masters Thesis
    Full Text:
    compose the expected penalty, E[ρ(s, φ)]. Terms involving an expectation of a variable Ii(φ) vary over the

  • Geometry of Locomotion

    Creator:
    Ramasamy, Suresh
    Abstract:
    Many animals and robots move through the world by coupling cyclical changes in shape called gaits to an interaction with the environment. Because mobility is an important aspect of such robots, a key metric when evaluating design and performance of mobile robots is the efficiency of their optimal gaits. The...
    Resource Type:
    Dissertation
    Full Text:
    Commutativity Assumption . . . . . . . . . . . . . . . . . . . . 157 E Starting Point Selection Heuristic

  • 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

  • Near-contact Grasping Strategies: Improve Robotic Grasping from Awkward Poses with Deliberate Finger Motion

    Creator:
    Ong, Yi Herng
    Abstract:
    As robots are becoming more relevant to our lives, they are still having hard time accomplishing simple tasks such as picking and lifting. Problems that include environmental constraints, pose uncertainties and hardware noises restrain robots for grasping an object successfully from a perceivable environment. Many have looked into finding best...
    Resource Type:
    Masters Thesis
    Full Text:
    1.666 rad 0 rad 1.066 rad 0.6178 rad 0 rad 0.8792 rad D eg re e 99 deg 45 deg 80 deg D eg re