Sökning: "robotic techniques"
Visar resultat 21 - 25 av 57 uppsatser innehållade orden robotic techniques.
21. Scoring functions evaluation for active learning in humanoid robotics
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Object detection is an essential ability for humanoid robots. State-of-the art deep learning models for object detection reached remarkable results on general-purpose datasets. However, these methods are typically based on the supervised learning framework, requiring large amounts of data and long computational time to be trained. LÄS MER
22. Acoustic-Inertial Forward-Scan Sonar Simultaneous Localization and Mapping
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The increasing accessibility and versatility of forward-scan (FS) imaging sonars (also known as forward looking sonars or FLS) has spurred the interest of the robotics community seeking to solve the difficult problem of robotic perception in low-visibility underwater scenarios. Processing the incoming data from an imaging sonar is challenging, since it captures an acoustic 2D image of the 3D scene instead of providing straightforward range measurements like other sonar technologies do (e. LÄS MER
23. En kvalitativ förstudie kring automatiseringstekniken Robotic Process Automation inom medelstora verksamheter : Utmaningar, möjligheter och rekommendationer vid implementering av Robotic process automation i medelstora verksamheter
Kandidat-uppsats, Högskolan Dalarna/InformatikSammanfattning : Allt fler har fått upp ögonen för olika automatiseringstekniker för att underlätta för kunder, anställda och verksamheten. Robotic Process Automation (RPA) är en snabbt framväxande teknologi som automatiserar repetitiva och monotona arbetsprocesser som kan anses vara tidskrävande för anställda. LÄS MER
24. Reinforcement Learning for Dexterity Transfer Between Manipulators
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Learning complex manipulation skills with robotic arms is a challenging problem in Reinforcement Learning. Training policies from scratch is often timeconsuming and normally infeasible when using real robots. LÄS MER
25. The Co-Strategy Process: introducing technology through interdisciplinary collaboration, so it meets biology in society : A case study regarding the path of Robot-Assisted-Rehabilitation from laboratory to patients in Sweden
Master-uppsats, Uppsala universitet/Institutionen för biologisk grundutbildningSammanfattning : As part of the current fast growing development of digital technologies, collaborations between professions such as neurosciences, robotics, big data processing and artificial intelligence offer new possibilities for healthcare. For these new technologies to reach clinical practice, there is an increasing need for interdisciplinary organizational work to support decision-making over their introduction. LÄS MER
