Cristin-resultat-ID: 1960031
Sist endret: 26. november 2021, 18:44
Resultat
Leder
2021

Guest Editorial: Deep Learning and Robotics

Bidragsytere:
  • Antonios Gasteratos
  • Loukas Bampis
  • Peter Galambos
  • Konstantinos Alexis og
  • Yiannis Aloimonos

Tidsskrift

Electronics Letters
ISSN 0013-5194
e-ISSN 1350-911X
NVI-nivå 1

Om resultatet

Leder
Publiseringsår: 2021
Volum: 57
Hefte: 16
Sider: 603 - 604
Open Access

Beskrivelse Beskrivelse

Tittel

Guest Editorial: Deep Learning and Robotics

Sammendrag

With the ongoing advancements in robotics and autonomous systems, the magnitude of unstructured data has gotten excessively enormous, while conventional data processing procedures lack successful adaptation. Besides, breaking down perplexing, high dimensional, and noisy data is a colossal challenge, emphasising the urgency of creating novel approaches that can produce a justifiable structure. To address these issues, deep learning models have yielded exceptional outcomes in the late decade. Deep learning has transfigured the evolution of robotics by setting new horizons. The capacity of deep neural networks to represent hierarchical features from multimodal sensory data, including image, audio, text, etc., make them ground-breaking in a plethora of related tasks. Meanwhile, under no human supervision, they succeed in carrying out complex, noisy and dynamic tasks, rendering them suitable for intelligent behaviours applicable to autonomous and cognitive robotics. Hence, deep learning has significantly supported a wide variety of robotics domains, including human-computer/robot interaction, by efficiently overcoming existing barriers and announcing further issues and solutions in more advanced challenges. A wide variety of research is being conducted to explore and discover possible challenges and opportunities to exploit deep learning schemes in robotics. The current Special Issue is focused on research ideas, articles and experimental studies related to “Deep Learning and Robotics” for learning, analysing and forecasting the various aspects of deep learning in robotics applications.

Bidragsytere

Antonios Gasteratos

  • Tilknyttet:
    Forfatter
    ved Democritus University of Thrace

Loukas Bampis

  • Tilknyttet:
    Forfatter
    ved Democritus University of Thrace

Peter Galambos

  • Tilknyttet:
    Forfatter
    ved Óbudai Egyetem

Konstantinos Alexis

  • Tilknyttet:
    Forfatter
    ved Institutt for teknisk kybernetikk ved Norges teknisk-naturvitenskapelige universitet

Yiannis Aloimonos

  • Tilknyttet:
    Forfatter
    ved University of Maryland
1 - 5 av 5