Editorial: Robust Artificial Intelligence for Neurorobotics

Joe Hays, Subramanian Ramamoorthy, Christian Tetzlaff

Research output: Contribution to journalEditorialpeer-review

Abstract / Description of output

Neural computing is a powerful paradigm that has revolutionized machine learning. Building from early roots in the study of adaptive behavior and attempts to understand information processing in parallel and distributed neural architectures, modern neural networks have convincingly demonstrated successes in numerous areas—transforming the practice of computer vision, natural language processing, and even computational biology.

Applications in robotics bring stringent constraints on size, weight and power constraints (SWaP), which challenge the developers of these technologies in new ways. Indeed, these requirements take us back to the roots of the field of neural computing, forcing us to ask how it could be that the human brain achieves with as little as 12 watts of power what seems to require entire server farms with state of the art computational and numerical methods. Likewise, even lowly insects demonstrate a degree of adaptivity and resilience that still defy easy explanation or computational replication.

In this Research Topic, we have compiled the latest research addressing several aspects of these broadly defined challenge questions. As illustrated in Figure 1, the articles are organized into four prevailing themes: Sense, Think, Act, and Tools.
Original languageEnglish
Article number809903
Number of pages3
JournalFrontiers in Neurorobotics
Volume15
DOIs
Publication statusPublished - 16 Dec 2021

Keywords / Materials (for Non-textual outputs)

  • robotics
  • adaptation
  • neuromorphic
  • artificial intelligence
  • autonomy

Fingerprint

Dive into the research topics of 'Editorial: Robust Artificial Intelligence for Neurorobotics'. Together they form a unique fingerprint.

Cite this