Sökning: "Danica Kragic"

Visar resultat 1 - 5 av 33 avhandlingar innehållade orden Danica Kragic.

  1. 1. Visual Servoing for Manipulation : Robustness and Integration Issues

    Författare :Danica Kragic; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Computer science; Datalogi;

    Sammanfattning : .... LÄS MER

  2. 2. Intention recognition in human machine collaborative systems

    Författare :Daniel Aarno; Danica Kragic; Darius Burschka; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Robotics; Human-machine collaboration; Virtual fixture; hidden Markov model; Machine learning; Artificial intelligence; Computer science; Datavetenskap;

    Sammanfattning : Robotsystem har använts flitigt under de senaste årtiondena för att skapa automationslösningar i ett flertal områden. De flesta nuvarande automationslösningarna är begränsade av att uppgifterna de kan lösa måste vara repetitiva och förutsägbara. LÄS MER

  3. 3. Data-Driven Methods for Contact-Rich Manipulation: Control Stability and Data-Efficiency

    Författare :Shahbaz Abdul Khader; Danica Kragic; Ludovic Righetti; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Robotic; Skill Learning; Reinforcement Learning; Contact-Rich Manipulation; Computer Science; Datalogi;

    Sammanfattning : Autonomous robots are expected to make a greater presence in the homes and workplaces of human beings. Unlike their industrial counterparts, autonomous robots have to deal with a great deal of uncertainty and lack of structure in their environment. LÄS MER

  4. 4. Transfer-Aware Kernels, Priors and Latent Spaces from Simulation to Real Robots

    Författare :Rika Antonova; Danica Kragic; Jens Kober; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; Computer Science; Datalogi;

    Sammanfattning : Consider challenging sim-to-real cases lacking high-fidelity simulators and allowing only 10-20 hardware trials. This work shows that even imprecise simulation can be beneficial if used to build transfer-aware representations. LÄS MER

  5. 5. Transfer Learning using low-dimensional Representations in Reinforcement Learning

    Författare :Isac Arnekvist; Danica Kragic; Johannes Andreas Stork; Christos Dimitrakakis; KTH; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Computer Science; Datalogi;

    Sammanfattning : Successful learning of behaviors in Reinforcement Learning (RL) are often learned tabula rasa, requiring many observations and interactions in the environment. Performing this outside of a simulator, in the real world, often becomes infeasible due to the large amount of interactions needed. LÄS MER