Avancerad sökning

Visar resultat 1 - 5 av 80 avhandlingar som matchar ovanstående sökkriterier.

1. 1. Flexible Robot to Object Interactions Through Rigid and Deformable Cages

   Författare :Alejandro Marzinotto; Danica Kragic; Henrik Gordon Petersen; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; planning; control; perception; caging; cage; grasping; multi-agent; robot; robotic; knot; knotting; behaviour trees; behavior trees; action scheduling; RRT; Computer Science; Datalogi;

   Sammanfattning : In this thesis we study the problem of robotic interaction with objects from a flexible perspective that complements the rigid force-closure approach. In a flexible interaction the object is not firmly bound to the robot (immobilized), which leads to many interesting scenarios. LÄS MER

3. 2. Interactive Perception : From Scenes to Objects

   Författare :Niklas Bergström; Danica Kragic; Yiannis Aloimonos; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

   Sammanfattning : This thesis builds on the observation that robots, like humans, do not have enough experience to handle all situations from the start. Therefore they need tools to cope with new situations, unknown scenes and unknown objects. In particular, this thesis addresses objects. LÄS MER

4. 3. Towards Automatically Correcting Robot Behavior Using Non-Expert Feedback

   Författare :Sanne van Waveren; Iolanda Leite; Hadas Kress-Gazit; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Non-expert robot correction; robot failure; human-robot interaction; robotics; Datalogi; Computer Science;

   Sammanfattning : Robots that operate in human environments need the capability to adapt their behavior to new situations. Most robots so far rely on pre-programmed behavior or machine learning algorithms trained offline with selected data. LÄS MER

5. 4. Reinforcement Learning for Active Visual Perception

   Författare :Aleksis Pirinen; Mathematical Imaging Group; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; computer vision; reinforcement learning; deep learning; active vision; object detection; human pose estimation; semantic segmentation;

   Sammanfattning : Visual perception refers to automatically recognizing, detecting, or otherwise sensing the content of an image, video or scene. The most common contemporary approach to tackle a visual perception task is by training a deep neural network on a pre-existing dataset which provides examples of task success and failure, respectively. LÄS MER

7. 5. Force-based Perception and Control Strategies for Human-Robot Shared Object Manipulation

   Författare :Ramin Jaberzadeh Ansari; Chalmers tekniska högskola; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; system identification; kinesthetic perception; human-robot interaction control; physical human-robot collaboration;

   Sammanfattning : Physical Human-Robot Interaction (PHRI) is essential for the future integration of robots in human-centered environments. In these settings, robots are expected to share the same workspace, interact physically, and collaborate with humans to achieve a common task. LÄS MER