Emerging Learning Techniques for Robotics

Emerging Learning Techniques for Robotics

Emerging Learning Techniques for Robotics

Learning is a rapidly advancing field in recent years, in terms of both methodological development and practical applications.

In medical robotics, computational models are able to learn with supervision or without supervision to facilitate intricate medical interventions, i.e. cancer detection and autonomous suturing.

It can implicitly capture task principles and repeat it with comparable accuracy, robustness and time-efficiency. Whilst some of the technical challenges are still being addressed, including generative modelling, large-scale parameter optimisation, and handling heterogeneous multi-modal data with varying temporal dependencies and missing samples, its use for medical robotics has reached marked success. Examples include the use of deep learning for tissue characterisation and the use of reinforcement learning for catheter manipulation. Other applications include surgical vision, navigation, learning, adaptation and task automation.

The purpose of this workshop is to report the latest advances in the field of learning for medical robotics, addressing both original algorithmic development and new applications of deep learning.

Topics for this special issue include, but are not limited to:

  • Learning for surgical vision and navigation;
  • Learning for tissue characterisation, optical biopsy and margin assessment;
  • Learning for learning, adaptation and surgical task completion.

Sponsored by: